Rule 179: [hom( A ),keyword( A ,inner_membrane),amino_acid_ratio_rule(l,5),classification( A ,bacteria)] = 0 [hom( A ),e_val_rule( A ,5),amino_acid_ratio_rule(l,5),keyword( A ,plasmid)] = 0 [hom( A ),mol_wt_rule( A ,3),amino_acid_ratio_rule(n,2),species( A ,bacillus_subtilis)] = 0 [hom( A ),mol_wt_rule( A ,4),amino_acid_ratio_rule(h,1),keyword( A ,transmembrane)] = 0 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 0 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(c,1),classification( A ,eukaryota),mol_wt_rule( A ,5)] = 0 [hom( A ),classification( A ,eukaryota),classification( A ,fungi)] = 1 [hom( A ),classification( A ,eukaryota),classification( A ,metazoa),keyword( A ,transmembrane),amino_acid_ratio_rule(g,5)] = 1 amino_acid_pair_ratio_ym <= 3.2 [hom( A ),classification( A ,eukaryota),classification( A ,metazoa),classification( A ,chordata),classification( A ,vertebrata),keyword( A ,repeat),mol_wt_rule( A ,5),classification( A ,mammalia)] = 0 -> class 'function2(Energy Metabolism )' [94.4%] Evaluation on proper test data (811 items): tb148 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb439 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb462 1,2,2,0 Small-molecule metabolism Energy Metabolism Pyruvate dehydrogenase Pyruvate dehydrogenase 'null' "null" tb484 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb561 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb688 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb851 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1144 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1483 - 1,8,1,0 Small-molecule metabolism Lipid Biosynthesis Synthesis of fatty and mycolic acids Synthesis of fatty and mycolic acids 'fabG1' "3-oxoacyl-[ACP] reductase (aka MabA)" tb1552 1,2,6,2 Small-molecule metabolism Energy Metabolism Respiration anaerobic 'frdA' "fumarate reductase flavoprotein subunit" tb1726 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1882 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb2002 - 1,8,1,0 Small-molecule metabolism Lipid Biosynthesis Synthesis of fatty and mycolic acids Synthesis of fatty and mycolic acids 'fabG3' "3-oxoacyl-[ACP] reductase" tb2129 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3049 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3485 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3513 - 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD18' "acyl-CoA synthase" Proper test Accuracy: 14/17 (82.35%) Application to new data (498 items): tb104 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2251 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 2 Evaluation on training data (1060 items): tb63 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb68 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb161 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb303 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb458 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb565 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb575 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb765 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb769 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb794 1,2,3,0 Small-molecule metabolism Energy Metabolism TCA cycle TCA cycle 'lpdB' "dihydrolipoamide dehydrogenase" tb892 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb897 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb945 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1106 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1245 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1257 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1260 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1432 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1774 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1817 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1865 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1941 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb2263 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb2280 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" Training Accuracy: 24/24 (100.00%) Evaluation on test data (531 items): tb3057 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3085 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3107 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3170 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3537 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3784 - 1,3,3,0 Small-molecule metabolism Central intermediary metabolism Sugar nucleotides Sugar nucleotides 'epiB' "probable UDP-galactose 4-epimerase" tb3790 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3791 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" Test Accuracy: 7/8 (87.50%) Application to new data (1023 items): tb1120 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1138 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2054 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2765 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3719 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 5 ------------------ Rule 228: [hom( A ),species( A ,escherichia_coli)] = 1 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 0 [hom( A ),e_val_rule( A ,1),mol_wt_rule( A ,3),classification( A ,eukaryota)] = 1 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 0 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(w,1),classification( A ,bacteria),e_val_rule( A ,1)] = 1 -> class 'function2(Polyketide and non-ribosomal peptide synthesis )' [79.4%] Evaluation on proper test data (811 items): tb35 - 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD34' "acyl-CoA synthase" tb86 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'hycQ' "probable formate hydrogenlyase subunit" tb99 - 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD10' "acyl-CoA synthase" tb1206 - 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD6' "acyl-CoA synthase" tb2245 - 1,8,1,0 Small-molecule metabolism Lipid Biosynthesis Synthesis of fatty and mycolic acids Synthesis of fatty and mycolic acids 'kasA' "beta-ketoacyl-ACP synthase (meromycolate extension)" tb2246 - 1,8,1,0 Small-molecule metabolism Lipid Biosynthesis Synthesis of fatty and mycolic acids Synthesis of fatty and mycolic acids 'kasB' "beta-ketoacyl-ACP synthase (meromycolate extension)" tb2931 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'ppsA' "phenolpthiocerol synthesis (pksB)" tb2932 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'ppsB' "phenolpthiocerol synthesis (pksC)" tb3157 - 1,2,6,1 Small-molecule metabolism Energy Metabolism Respiration aerobic 'nuoM' "NADH dehydrogenase chain M" tb3800 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks13' "polyketide synthase" tb3825 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks2' "polyketide synthase" Proper test Accuracy: 4/11 (36.36%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb405 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks6' "polyketide synthase" tb1180 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks3' "polyketide synthase" tb1527 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks5' "polyketide synthase" tb1664 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks9' "polyketide synthase" tb2048 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks12' "polyketide synthase (erythronolide synthase-like)" tb2384 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'mbtA' "mycobactin/exochelin synthesis (salicylate-AMP ligase)" Training Accuracy: 6/6 (100.00%) Evaluation on test data (531 items): tb2782 - 2,2,3,0 Macromolecule metabolism Degradation of macromolecules Proteins, peptides and glycopeptides Proteins, peptides and glycopeptides 'pepR' "protease/peptidase, M16 family (insulinase)" tb2933 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'ppsC' "phenolpthiocerol synthesis (pksD)" tb2935 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'ppsE' "phenolpthiocerol synthesis (pksF)" tb2940 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'mas' "mycocerosic acid synthase" Test Accuracy: 3/4 (75.00%) Application to new data (1023 items): Total: 0 ------------------ Rule 1: [amino_acid_ratio_rule(h,3)] = 0 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 0 amino_acid_pair_ratio_cw <= 2 [hom( A ),species( A ,escherichia_coli)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),e_val_rule( A ,1),amino_acid_ratio_rule(e,3)] = 0 [hom( A ),mol_wt_rule( A ,4),amino_acid_ratio_rule(l,5),e_val_rule( A ,2)] = 0 [hom( A ),keyword( A ,inner_membrane),amino_acid_ratio_rule(w,1)] = 0 amino_acid_ratio_r <= 10 [hom( A ),mol_wt_rule( A ,2),amino_acid_ratio_rule(y,2),e_val_rule( A ,1)] = 0 amino_acid_pair_ratio_nc <= 0.9 amino_acid_ratio_d <= 8.2 amino_acid_ratio_e <= 7.3 amino_acid_ratio_k <= 5.7 [hom( A ),mol_wt_rule( A ,5),amino_acid_ratio_rule(e,4)] = 0 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(x,1),classification( A ,bacteria)] = 0 [hom( A ),species( A ,homo_sapiens),amino_acid_ratio_rule(e,4)] = 0 [hom( A ),species( A ,homo_sapiens),amino_acid_ratio_rule(r,5)] = 0 [hom( A ),mol_wt_rule( A ,1),amino_acid_ratio_rule(s,3),classification( A ,bacteria)] = 0 [hom( A ),mol_wt_rule( A ,3),amino_acid_ratio_rule(f,3),e_val_rule( A ,5)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,firmicutes),mol_wt_rule( A ,3),amino_acid_ratio_rule(r,4)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),mol_wt_rule( A ,1),amino_acid_ratio_rule(e,3)] = 0 amino_acid_pair_ratio_mc <= 6.3 amino_acid_ratio_m <= 3.9 [hom( A ),mol_wt_rule( A ,3),amino_acid_ratio_rule(x,1)] = 0 [hom( A ),species( A ,saccharomyces_cerevisiae),amino_acid_ratio_rule(d,4)] = 0 [hom( A ),e_val_rule( A ,3),amino_acid_ratio_rule(f,3),classification( A ,eukaryota)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,firmicutes),e_val_rule( A ,5),amino_acid_ratio_rule(n,1)] = 0 [hom( A ),mol_wt_rule( A ,2),amino_acid_ratio_rule(k,2),e_val_rule( A ,3)] = 0 amino_acid_pair_ratio_lr <= 22.3 -> class 'function2(Cell envelope )' [98.1%] Evaluation on proper test data (811 items): tb62 - 2,2,4,0 Macromolecule metabolism Degradation of macromolecules Polysaccharides, lipopolysaccharides and phospholipids Polysaccharides, lipopolysaccharides and phospholipids 'celA' "cellulase/endoglucanase" tb226 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb227 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb361 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb412 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb419 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqM' "possible zinc metallopeptidase " tb451 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpS4' "conserved small membrane protein" tb497 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb541 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb671 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqP' "probable esterase" tb686 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb817 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb852 - 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD16' "acyl-CoA synthase" tb882 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1129 - 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1132 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1159 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1249 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1368 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lprF' "lipoprotein" tb1388 - 2,1,4,0 Macromolecule metabolism Synthesis and modification of macromolecules Nucleoproteins Nucleoproteins 'mIHF' "integration host factor" tb1401 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1587 - 4,2,2,0 Other IS elements, Repeated sequences, and Phage REP13E12 family REP13E12 family 'REP' "null" tb1588 - 4,2,2,0 Other IS elements, Repeated sequences, and Phage REP13E12 family REP13E12 family 'REP' "null" tb1694 - 4,1,0,0 Other Virulence Virulence Virulence 'tlyA' "cytotoxin/hemolysin homologue" tb1733 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1755 - 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'plcD' "partial CDS for phospholipase C" tb1824 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1881 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppE' "lipoprotein" tb1919 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb1977 - 2,2,3,0 Macromolecule metabolism Degradation of macromolecules Proteins, peptides and glycopeptides Proteins, peptides and glycopeptides 'null' "null" tb1984 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb2046 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppI' "probable lipoprotein" tb2080 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppJ' "lipoprotein" tb2138 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppL' "lipoprotein" tb2175 - 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb2341 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppQ' "lipoprotein" tb2351 - 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'plcA' "phospholipase C precursor" tb2429 - 3,6,0,0 Cell Processes Detoxification Detoxification Detoxification 'ahpD' "member of AhpC/TSA family" tb2686 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2755 - 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'hsdS' "type I restriction/modification system specificity determinant" tb2875 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'mpt70' "major secreted immunogenic protein Mpt70 precursor" tb3016 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqA' "lipoprotein" tb3112 - 1,7,4,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Molybdopterin Molybdopterin 'moaD' "molybdopterin converting factor subunit 1" tb3217 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3244 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqB' "lipoprotein" tb3374 - 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA18' "null" tb3593 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqF' "lipoprotein" tb3604 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3724 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb3746 - 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" Proper test Accuracy: 34/50 (68.00%) Application to new data (498 items): tb4 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb7 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb90 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb140 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb199 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb272 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb295 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb325 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb368 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb416 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb459 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb460 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb519 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb598 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb603 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb633 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb664 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb730 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb736 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb745 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb767 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb774 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb811 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb877 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb900 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb961 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb965 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb988 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb990 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1000 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1012 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1048 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1066 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1069 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1100 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1113 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1114 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1134 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1234 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1259 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1291 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1303 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1495 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1591 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1592 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1691 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1727 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1769 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1770 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1805 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1828 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1870 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1873 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1926 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1930 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1951 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1954 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1973 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2000 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2081 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2082 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2114 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2146 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2172 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2197 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2203 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2226 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2297 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2416 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2425 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2451 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2492 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2514 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2525 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2541 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2545 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2569 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2576 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2619 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2680 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2687 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2693 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2698 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2706 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2722 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2728 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2818 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2820 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2953 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2960 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2983 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2998 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3035 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3040 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3168 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3304 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3353 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3395 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3413 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3438 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3453 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3479 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3493 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3528 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3603 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3605 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3632 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3639 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3657 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3690 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3694 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3701 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3705 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3821 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3831 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3863 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3882 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3890 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3895 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3898 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3909 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 121 Evaluation on training data (1060 items): tb51 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb102 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb179 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lprO' "lipoprotein" tb204 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb236 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb291 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb292 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb314 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb344 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqJ' "lipoprotein" tb345 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb383 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb401 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb431 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb461 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb477 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb479 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb506 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpS2' "conserved small membrane protein" tb513 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb531 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb537 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb544 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb556 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb559 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb583 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqN' "equivalent to MKU20446_1 MK35 " tb604 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqO' "lipoprotein" tb615 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb621 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb622 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb713 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb738 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb806 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'cpsY' "probable UDP-glucose-4-epimerase" tb835 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqQ' "lipoprotein" tb838 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqR' "lipoprotein" tb867 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1002 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1016 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqT' "similar to M. kansasii Q49597" tb1064 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqV' "lipoprotein" tb1097 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1228 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqX' "lipoprotein" tb1230 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1252 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lprE' "lipoprotein" tb1270 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lprA' "lipoprotein" tb1274 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lprB' "lipoprotein" tb1275 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lprC' "lipoprotein" tb1411 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lprG' "lipoprotein" tb1418 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lprH' "lipoprotein" tb1424 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1456 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1508 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1541 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lprI' "lipoprotein" tb1610 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1635 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1671 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1678 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1779 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1799 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppT' "probable lipoprotein" tb1899 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppD' "lipoprotein" tb1920 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1980 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'mpt64' "secreted immunogenic protein Mpb64/Mpt64" tb1987 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb2113 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2116 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppK' "lipoprotein" tb2144 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2171 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppM' "probable lipoprotein" tb2174 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2199 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2270 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppN' "possible lipoprotein" tb2301 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb2473 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2507 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2536 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2543 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppA' "lipoprotein" tb2544 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppB' "lipoprotein" tb2560 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Training Accuracy: 74/74 (100.00%) Evaluation on test data (531 items): tb2652 - 4,2,3,0 Other IS elements, Repeated sequences, and Phage Phage-related functions Phage-related functions 'null' "null" tb2654 - 4,2,3,0 Other IS elements, Repeated sequences, and Phage Phage-related functions Phage-related functions 'null' "null" tb2673 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2810 - 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1555' "null" tb2945 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppX' "lipoprotein" tb2968 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3036 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb3078 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3162 - 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'null' "null" tb3310 - 4,9,0,0 Other Miscellaneous phosphatases, lyases, and hydrolases Miscellaneous phosphatases, lyases, and hydrolases Miscellaneous phosphatases, lyases, and hydrolases 'null' "null" tb3317 - 1,2,3,0 Small-molecule metabolism Energy Metabolism TCA cycle TCA cycle 'sdhD' "succinate dehydrogenase D subunit" tb3450 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3451 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb3452 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb3466 - 4,2,2,0 Other IS elements, Repeated sequences, and Phage REP13E12 family REP13E12 family 'REP' "null" tb3481 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3524 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3584 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqE' "lipoprotein" tb3629 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3635 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3704 - 1,4,1,0 Small-molecule metabolism Amino acid biosynthesis Glutamate family Glutamate family 'gshA' "possible gamma-glutamylcysteine synthase" tb3763 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqH' "19 kDKD " tb3779 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3792 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3793 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'embC' "involved in arabinogalactan synthesis" tb3794 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'embA' "involved in arabinogalactan synthesis" tb3805 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3840 - 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3843 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3883 - 2,2,3,0 Macromolecule metabolism Degradation of macromolecules Proteins, peptides and glycopeptides Proteins, peptides and glycopeptides 'null' "null" tb3901 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Test Accuracy: 21/31 (67.74%) Application to new data (1023 items): tb26 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb28 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb98 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb108 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb121 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb127 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb175 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb184 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb185 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb193 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb203 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb207 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb209 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb210 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb219 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb240 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb259 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb266 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb276 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb283 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb289 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb307 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb309 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb320 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb326 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb340 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb358 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb360 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb365 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb381 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb396 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb398 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb428 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb455 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb463 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb499 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb540 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb571 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb577 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb584 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb597 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb614 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb665 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb669 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb760 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb762 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb776 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb779 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb787 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb801 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb804 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb807 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb813 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb819 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb831 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb862 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb883 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb895 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb912 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb926 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb941 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1006 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1009 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1025 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1045 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1060 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1075 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1081 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1083 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1102 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1103 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1109 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1125 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1154 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1158 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1171 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1174 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1184 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1209 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1233 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1271 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1335 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1343 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1356 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1376 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1378 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1382 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1434 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1435 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1455 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1476 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1489 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1499 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1517 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1531 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1546 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1597 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1615 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1632 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1670 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1697 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1698 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1735 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1778 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1780 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1783 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1794 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1830 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1836 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1845 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1874 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1884 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1888 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1891 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1952 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1961 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1962 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1974 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1975 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2008 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2023 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2033 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2044 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2050 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2074 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2102 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2111 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2120 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2125 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2132 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2134 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2137 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2143 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2160 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2170 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2219 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2227 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2235 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2237 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2240 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2253 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2274 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2292 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2348 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2365 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2376 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2387 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2389 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2390 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2413 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2422 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2446 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2450 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2452 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2468 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2472 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2516 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2571 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2575 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2598 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2600 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2616 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2617 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2620 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2645 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2660 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2661 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2665 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2668 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2694 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2695 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2696 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2712 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2719 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2721 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2740 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2743 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2759 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2760 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2762 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2774 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2798 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2799 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2823 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2824 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2827 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2840 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2867 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2980 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3008 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3013 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3015 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3067 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3074 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3081 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3165 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3166 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3180 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3182 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3190 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3195 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3205 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3207 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3210 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3212 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3258 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3267 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3268 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3277 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3289 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3320 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3337 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3346 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3351 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3355 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3364 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3369 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3510 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3531 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3572 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3577 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3587 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3626 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3647 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3651 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3654 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3655 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3669 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3687 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3689 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3703 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3707 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3745 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3747 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3755 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3766 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3770 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3771 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3785 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3802 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3822 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3847 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3849 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3864 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3865 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3866 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3878 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3885 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3889 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3899 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3900 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3902 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3905 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3906 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3916 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 255 ------------------ Rule 226: [hom( A ),keyword( A ,plasmid),e_val_rule( A ,1)] = 1 [hom( A ),e_val_rule( A ,1),mol_wt_rule( A ,3),classification( A ,eukaryota)] = 0 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 0 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(w,1),classification( A ,bacteria),e_val_rule( A ,1)] = 1 -> class 'function2(Transport/binding proteins )' [85.7%] Evaluation on proper test data (811 items): tb92 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpA' "cation-transporting ATPase" tb969 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpV' "cation transport ATPase" tb1469 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpD' "probable cadmium-transporting ATPase" tb1997 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpF' "probable cation transport ATPase " tb2723 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'null' "null" tb3743 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'null' "null" Proper test Accuracy: 6/6 (100.00%) Application to new data (498 items): tb1357 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 1 Evaluation on training data (1060 items): tb103 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpB' "cation transport ATPase" tb107 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpI' "probable magnesium transport ATPase" tb425 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpH' "C-terminal region putative cation-transporting ATPase" tb849 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb908 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpE' "probable cation transport ATPase" tb1030 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'kdpB' "potassium-transporting ATPase B chain" tb1607 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'chaA' "putative calcium/proton antiporter" tb1992 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpG' "probable cation transport ATPase" tb2443 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'dctA' "C4-dicarboxylate transport protein" Training Accuracy: 9/9 (100.00%) Evaluation on test data (531 items): tb3270 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpC' "cation transport ATPase" tb3578 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'arsB2' "probable arsenical pump" Test Accuracy: 2/2 (100.00%) Application to new data (1023 items): Total: 0 ------------------ Rule 30: [hom( A ),species( A ,escherichia_coli)] = 0 [hom( A ),species( A ,saccharomyces_cerevisiae),amino_acid_ratio_rule(r,5)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),amino_acid_ratio_rule(r,5)] = 1 [hom( A ),e_val_rule( A ,3),amino_acid_ratio_rule(f,3),classification( A ,eukaryota)] = 0 [hom( A ),e_val_rule( A ,5),amino_acid_ratio_rule(w,1),species( A ,bacillus_subtilis)] = 0 [hom( A ),e_val_rule( A ,1),amino_acid_ratio_rule(l,5),classification( A ,bacteria),mol_wt_rule( A ,2)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),classification( A ,gamma_subdivision),amino_acid_ratio_rule(y,3)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),e_val_rule( A ,2),amino_acid_ratio_rule(t,3),classification( A ,gamma_subdivision)] = 0 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(v,5),classification( A ,bacteria),mol_wt_rule( A ,2),classification( A ,proteobacteria)] = 0 -> class 'function2(IS elements_ Repeated sequences_ and Phage )' [91.2%] Evaluation on proper test data (811 items): tb606 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1536' "transposase" tb771 - 2,2,6,0 Macromolecule metabolism Degradation of macromolecules Aromatic hydrocarbons Aromatic hydrocarbons 'null' "null" tb922 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1535' "transposase" tb1001 - 1,1,2,0 Small-molecule metabolism Degradation Amino acids and amines Amino acids and amines 'arcA' "arginine deiminase" tb1041 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS-like' "null" tb1370 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb1757 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb1763 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb1851 - 1,1,2,0 Small-molecule metabolism Degradation Amino acids and amines Amino acids and amines 'ureF' "urease accessory protein" tb2062 - 1,7,13,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Cobalamin Cobalamin 'cobN' "cobalt insertion " tb2072 - 1,7,13,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Cobalamin Cobalamin 'cobL' "probable methyltransferase" tb2105 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2177 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1558' "null" tb2268 - 4,6,0,0 Other Cytochrome P450 enzymes Cytochrome P450 enzymes Cytochrome P450 enzymes 'null' "null" tb2278 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2648 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2815 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3186 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3254 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3381 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3713 - 1,7,13,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Cobalamin Cobalamin 'cobQ2' "possible cobyric acid synthase" Proper test Accuracy: 13/21 (61.90%) Application to new data (498 items): tb434 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb574 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb627 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb811 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1314 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2910 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2961 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 7 Evaluation on training data (1060 items): tb795 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb797 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1547' "null" tb1034 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1560' "null" tb1042 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS-like' "null" tb1055 4,2,3,0 Other IS elements, Repeated sequences, and Phage Phage-related functions Phage-related functions 'null' "null" tb1149 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS-like' "null" tb1150 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS-like' "null" tb1313 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1557' "transposase" tb2013 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1607' "transposase" tb2014 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1607' "transposase" tb2085 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1556' "putative transposase" tb2168 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2354 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2424 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1558' "null" tb2480 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" Training Accuracy: 15/15 (100.00%) Evaluation on test data (531 items): tb2666 4,2,1,2 Other IS elements, Repeated sequences, and Phage IS elements IS1081 'IS1081' "null" tb2791 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1602' "transposase" tb2813 - 3,4,0,0 Cell Processes Protein and peptide secretion Protein and peptide secretion Protein and peptide secretion 'null' "null" tb2885 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1539' "transposase" tb2978 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1538' "transposase" tb3184 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3317 - 1,2,3,0 Small-molecule metabolism Energy Metabolism TCA cycle TCA cycle 'sdhD' "succinate dehydrogenase D subunit" tb3325 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3386 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1560' "null" tb3387 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1560' "null" tb3431 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1552' "null" tb3474 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3518 - 4,6,0,0 Other Cytochrome P450 enzymes Cytochrome P450 enzymes Cytochrome P450 enzymes 'null' "null" tb3566 - 1,3,1,0 Small-molecule metabolism Central intermediary metabolism General General 'nhoA' "N-hydroxyarylamine o-acetyltransferase" tb3782 - 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'rfbE' "similar to rhamnosyl transferase" tb3798 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1557' "transposase" tb3827 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1537' "transposase" Test Accuracy: 12/17 (70.59%) Application to new data (1023 items): tb595 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb597 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb825 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb919 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1024 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1378 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1953 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2008 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2042 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2311 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2478 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2742 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2955 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3179 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3860 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 15 ------------------ Rule 200: amino_acid_pair_ratio_sd > 0.7 [hom( A ),species( A ,homo_sapiens),mol_wt_rule( A ,5),keyword( A ,alternative_splicing)] = 1 [hom( A ),e_val_rule( A ,5),amino_acid_ratio_rule(q,2),species( A ,bacillus_subtilis)] = 0 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(c,1),classification( A ,eukaryota),mol_wt_rule( A ,5)] = 0 [hom( A ),keyword( A ,alternative_splicing),amino_acid_ratio_rule(x,5),classification( A ,eukaryota),mol_wt_rule( A ,5),classification( A ,metazoa)] = 0 [hom( A ),classification( A ,eukaryota),classification( A ,metazoa),classification( A ,chordata),classification( A ,vertebrata),keyword( A ,repeat),mol_wt_rule( A ,5),classification( A ,mammalia)] = 0 -> class 'function2(Degradation )' [89.9%] Evaluation on proper test data (811 items): tb5 - 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'gyrB' "DNA gyrase subunit B" tb6 - 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'gyrA' "DNA gyrase subunit A" tb50 - 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'ponA1' "penicillin-bonding protein" tb131 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE1' "acyl-CoA dehydrogenase " tb215 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE3' "acyl-CoA dehydrogenase " tb244 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE5' "acyl-CoA dehydrogenase " tb271 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE6' "acyl-CoA dehydrogenase " tb400 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE7' "acyl-CoA dehydrogenase " tb672 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE8' "acyl-CoA dehydrogenase (aka aidB)" tb803 - 1,6,1,0 Small-molecule metabolism Purines, pyrimidines, nucleosides and nucleotides Purine ribonucleotide biosynthesis Purine ribonucleotide biosynthesis 'purL' "phosphoribosylformylglycinamidine synthase II" tb891 - 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb974 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'accD2' "acetyl/propionyl-CoA carboxylase, beta subunit" tb1933 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE18' "acyl-CoA dehydrogenase " tb2724 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE20' "acyl-CoA dehydrogenase " tb3139 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE24' "acyl-CoA dehydrogenase " tb3140 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE23' "acyl-CoA dehydrogenase " tb3285 - 1,8,1,0 Small-molecule metabolism Lipid Biosynthesis Synthesis of fatty and mycolic acids Synthesis of fatty and mycolic acids 'accA3' "acetyl/propionyl CoA carboxylase alpha subunit" tb3573 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE34' "acyl-CoA dehydrogenase " tb3797 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE35' "acyl-CoA dehydrogenase " tb3799 - 1,8,1,0 Small-molecule metabolism Lipid Biosynthesis Synthesis of fatty and mycolic acids Synthesis of fatty and mycolic acids 'accD4' "acetyl/propionyl CoA carboxylase beta subunit" Proper test Accuracy: 13/20 (65.00%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb154 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE2' "acyl-CoA dehydrogenase " tb231 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE4' "acyl-CoA dehydrogenase " tb727 1,1,1,0 Small-molecule metabolism Degradation Carbon compounds Carbon compounds 'fucA' "L-fuculose phosphate aldolase" tb752 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE9' "acyl-CoA dehydrogenase" tb873 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE10' "acyl-CoA dehydrogenase " tb972 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE12' "acyl-CoA dehydrogenase " tb975 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE13' "acyl-CoA dehydrogenase" tb1346 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE14' "acyl-CoA dehydrogenase " tb1467 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE15' "acyl-CoA dehydrogenase " tb1934 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE17' "acyl-CoA dehydrogenase" tb2500 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE19' "acyl-CoA dehydrogenase (aka mmgC)" tb2501 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'accA1' "acetyl/propionyl-CoA carboxylase, alpha subunit" tb2502 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'accD1' "acetyl/propionyl-CoA carboxylase, beta subunit" Training Accuracy: 13/13 (100.00%) Evaluation on test data (531 items): tb2789 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE21' "acyl-CoA dehydrogenase" tb3061 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE22' "acyl-CoA dehydrogenase " tb3274 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE25' "acyl-CoA dehydrogenase " tb3313 - 1,6,4,0 Small-molecule metabolism Purines, pyrimidines, nucleosides and nucleotides Salvage of nucleosides and nucleotides Salvage of nucleosides and nucleotides 'add' "probable adenosine deaminase" tb3504 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE26' "acyl-CoA dehydrogenase " tb3560 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE30' "acyl-CoA dehydrogenase " tb3562 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE31' "acyl-CoA dehydrogenase " Test Accuracy: 6/7 (85.71%) Application to new data (1023 items): Total: 0 ------------------ Rule 235: [hom( A ),e_val_rule( A ,5),amino_acid_ratio_rule(m,1)] = 0 [hom( A ),species( A ,bacillus_subtilis),mol_wt_rule( A ,5)] = 1 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 0 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 1 -> class 'function2(Degradation )' [85.2%] Evaluation on proper test data (811 items): tb101 - 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'nrp' "unknown non-ribosomal peptide synthase" tb1013 - 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks16' "polyketide synthase " tb1521 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD25' "acyl-CoA synthase" tb1550 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD11' "acyl-CoA synthase, N-term" tb2187 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD15' "acyl-CoA synthase" tb2379 - 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'mbtF' "mycobactin/exochelin synthesis (lysine ligation)" tb2383 - 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'mbtB' "mycobactin/exochelin synthesis (serine/threonine ligation)" tb2590 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD9' "acyl-CoA synthase" tb2610 - 4,8,0,0 Other Miscellaneous transferases Miscellaneous transferases Miscellaneous transferases 'null' "null" tb2930 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD26' "acyl-CoA synthase" Proper test Accuracy: 5/10 (50.00%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb119 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD7' "acyl-CoA synthase" tb166 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD5' "acyl-CoA synthase" tb214 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD4' "acyl-CoA synthase" tb270 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD2' "acyl-CoA synthase" tb404 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD30' "acyl-CoA synthase" tb551 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD8' "acyl-CoA synthase" tb1058 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD14' "acyl-CoA synthase" tb1185 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD21' "acyl-CoA synthase" tb1193 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD36' "acyl-CoA synthase" tb1345 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD33' "acyl-CoA synthase" tb1427 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD12' "acyl-CoA synthase" tb1529 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD24' "acyl-CoA synthase" tb1683 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'null' "null" tb1750 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD1' "acyl-CoA synthase" tb1925 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD31' "acyl-CoA synthase" tb2380 - 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'mbtE' "mycobactin/exochelin synthesis (lysine ligation)" tb2505 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD35' "acyl-CoA synthase" Training Accuracy: 16/17 (94.12%) Evaluation on test data (531 items): tb2941 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD28' "acyl-CoA synthase" tb2948 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD22' "acyl-CoA synthase" tb2950 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD29' "acyl-CoA synthase" tb3089 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD13' "acyl-CoA synthase" tb3506 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD17' "acyl-CoA synthase" tb3515 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD19' "acyl-CoA synthase" tb3561 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD3' "acyl-CoA synthase" tb3667 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'acs' "acetyl-CoA synthase" tb3801 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD32' "acyl-CoA synthase" tb3826 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD23' "acyl-CoA synthase" Test Accuracy: 10/10 (100.00%) Application to new data (1023 items): tb557 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2188 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3032 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 3 ------------------ Rule 1: (16, lift 14.5) [hom( A ),species( A ,saccharomyces_cerevisiae),e_val_rule( A ,2)] = 1 [hom( A ),species( A ,bacillus_subtilis),mol_wt_rule( A ,5)] = 1 [hom( A ),e_val_rule( A ,5),amino_acid_ratio_rule(s,3),species( A ,bacillus_subtilis)] = 0 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 1 -> class 'function2(Degradation )' [0.944] Evaluation on proper test data (811 items): tb101 - 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'nrp' "unknown non-ribosomal peptide synthase" tb1013 - 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks16' "polyketide synthase " tb1521 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD25' "acyl-CoA synthase" tb2187 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD15' "acyl-CoA synthase" tb2379 - 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'mbtF' "mycobactin/exochelin synthesis (lysine ligation)" tb2383 - 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'mbtB' "mycobactin/exochelin synthesis (serine/threonine ligation)" tb2590 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD9' "acyl-CoA synthase" tb2610 - 4,8,0,0 Other Miscellaneous transferases Miscellaneous transferases Miscellaneous transferases 'null' "null" tb2930 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD26' "acyl-CoA synthase" Proper test Accuracy: 4/9 (44.44%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb119 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD7' "acyl-CoA synthase" tb166 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD5' "acyl-CoA synthase" tb214 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD4' "acyl-CoA synthase" tb270 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD2' "acyl-CoA synthase" tb404 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD30' "acyl-CoA synthase" tb551 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD8' "acyl-CoA synthase" tb1058 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD14' "acyl-CoA synthase" tb1185 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD21' "acyl-CoA synthase" tb1193 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD36' "acyl-CoA synthase" tb1345 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD33' "acyl-CoA synthase" tb1427 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD12' "acyl-CoA synthase" tb1529 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD24' "acyl-CoA synthase" tb1683 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'null' "null" tb1750 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD1' "acyl-CoA synthase" tb1925 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD31' "acyl-CoA synthase" tb2505 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD35' "acyl-CoA synthase" Training Accuracy: 16/16 (100.00%) Evaluation on test data (531 items): tb2941 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD28' "acyl-CoA synthase" tb2950 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD29' "acyl-CoA synthase" tb3089 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD13' "acyl-CoA synthase" tb3506 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD17' "acyl-CoA synthase" tb3515 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD19' "acyl-CoA synthase" tb3561 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD3' "acyl-CoA synthase" tb3667 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'acs' "acetyl-CoA synthase" tb3801 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD32' "acyl-CoA synthase" tb3826 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD23' "acyl-CoA synthase" Test Accuracy: 9/9 (100.00%) Application to new data (1023 items): tb3032 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 1 ------------------ Rule 2: (14/1, lift 13.4) amino_acid_pair_ratio_ym <= 3.2 [hom( A ),species( A ,escherichia_coli)] = 1 [hom( A ),e_val_rule( A ,3),mol_wt_rule( A ,2)] = 0 [hom( A ),species( A ,saccharomyces_cerevisiae),mol_wt_rule( A ,3)] = 0 [hom( A ),species( A ,homo_sapiens),mol_wt_rule( A ,5),keyword( A ,alternative_splicing)] = 1 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 0 [hom( A ),keyword( A ,alternative_splicing),amino_acid_ratio_rule(x,5),classification( A ,eukaryota),mol_wt_rule( A ,5),classification( A ,metazoa)] = 0 [hom( A ),classification( A ,eukaryota),classification( A ,metazoa),classification( A ,chordata),classification( A ,vertebrata),keyword( A ,repeat),mol_wt_rule( A ,5),classification( A ,mammalia)] = 0 -> class 'function2(Degradation )' [0.875] Evaluation on proper test data (811 items): tb5 - 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'gyrB' "DNA gyrase subunit B" tb50 - 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'ponA1' "penicillin-bonding protein" tb131 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE1' "acyl-CoA dehydrogenase " tb215 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE3' "acyl-CoA dehydrogenase " tb244 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE5' "acyl-CoA dehydrogenase " tb271 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE6' "acyl-CoA dehydrogenase " tb400 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE7' "acyl-CoA dehydrogenase " tb672 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE8' "acyl-CoA dehydrogenase (aka aidB)" tb1679 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE16' "acyl-CoA dehydrogenase " tb1933 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE18' "acyl-CoA dehydrogenase " tb2724 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE20' "acyl-CoA dehydrogenase " tb3139 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE24' "acyl-CoA dehydrogenase " tb3140 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE23' "acyl-CoA dehydrogenase " tb3543 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE29' "acyl-CoA dehydrogenase " tb3573 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE34' "acyl-CoA dehydrogenase " tb3797 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE35' "acyl-CoA dehydrogenase " Proper test Accuracy: 14/16 (87.50%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb154 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE2' "acyl-CoA dehydrogenase " tb231 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE4' "acyl-CoA dehydrogenase " tb727 1,1,1,0 Small-molecule metabolism Degradation Carbon compounds Carbon compounds 'fucA' "L-fuculose phosphate aldolase" tb752 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE9' "acyl-CoA dehydrogenase" tb873 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE10' "acyl-CoA dehydrogenase " tb904 - 1,8,1,0 Small-molecule metabolism Lipid Biosynthesis Synthesis of fatty and mycolic acids Synthesis of fatty and mycolic acids 'accD3' "acetyl/propionyl CoA carboxylase beta subunit" tb972 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE12' "acyl-CoA dehydrogenase " tb975 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE13' "acyl-CoA dehydrogenase" tb1346 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE14' "acyl-CoA dehydrogenase " tb1467 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE15' "acyl-CoA dehydrogenase " tb1934 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE17' "acyl-CoA dehydrogenase" tb2500 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE19' "acyl-CoA dehydrogenase (aka mmgC)" tb2501 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'accA1' "acetyl/propionyl-CoA carboxylase, alpha subunit" tb2502 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'accD1' "acetyl/propionyl-CoA carboxylase, beta subunit" Training Accuracy: 13/14 (92.86%) Evaluation on test data (531 items): tb2789 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE21' "acyl-CoA dehydrogenase" tb3061 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE22' "acyl-CoA dehydrogenase " tb3274 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE25' "acyl-CoA dehydrogenase " tb3313 - 1,6,4,0 Small-molecule metabolism Purines, pyrimidines, nucleosides and nucleotides Salvage of nucleosides and nucleotides Salvage of nucleosides and nucleotides 'add' "probable adenosine deaminase" tb3504 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE26' "acyl-CoA dehydrogenase " tb3505 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE27' "acyl-CoA dehydrogenase" tb3560 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE30' "acyl-CoA dehydrogenase " tb3562 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE31' "acyl-CoA dehydrogenase " Test Accuracy: 7/8 (87.50%) Application to new data (1023 items): tb648 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 1 ------------------ Rule 3: (14/1, lift 13.4) amino_acid_pair_ratio_cp <= 1.8 amino_acid_pair_ratio_cs <= 1.1 [hom( A ),classification( A ,eukaryota),classification( A ,fungi)] = 1 [hom( A ),keyword( A ,transmembrane),mol_wt_rule( A ,3),classification( A ,bacteria)] = 0 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 0 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(w,1),classification( A ,bacteria),e_val_rule( A ,1)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,firmicutes),keyword( A ,transmembrane),amino_acid_ratio_rule(h,1)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 1 [hom( A ),keyword( A ,alternative_splicing),amino_acid_ratio_rule(x,5),classification( A ,eukaryota),mol_wt_rule( A ,5),classification( A ,metazoa)] = 0 -> class 'function2(Degradation )' [0.875] Evaluation on proper test data (811 items): tb673 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA4' "enoyl-CoA hydratase/isomerase superfamily " tb860 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadB' "beta oxidation complex, alpha subunit (multiple activities)" tb971 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA7' "enoyl-CoA hydratase/isomerase superfamily " tb1626 - 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb2338 - 1,7,4,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Molybdopterin Molybdopterin 'moeW' "molybdopterin biosynthesis" tb2486 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA14' "enoyl-CoA hydratase/isomerase superfamily " tb2679 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA15' "enoyl-CoA hydratase/isomerase superfamily " tb2831 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA16' "enoyl-CoA hydratase/isomerase superfamily " tb3116 - 1,7,4,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Molybdopterin Molybdopterin 'moeB' "molybdopterin biosynthesis" tb3373 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA18' "enoyl-CoA hydratase/isomerase superfamily, N-term" tb3513 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD18' "acyl-CoA synthase" tb3516 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA19' "enoyl-CoA hydratase/isomerase superfamily " tb3671 - 2,2,3,0 Macromolecule metabolism Degradation of macromolecules Proteins, peptides and glycopeptides Proteins, peptides and glycopeptides 'null' "null" Proper test Accuracy: 9/13 (69.23%) Application to new data (498 items): tb3404 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" Total: 1 Evaluation on training data (1060 items): tb195 - 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb222 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA1' "enoyl-CoA hydratase/isomerase superfamily " tb456 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA2' "enoyl-CoA hydratase/isomerase superfamily " tb632 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA3' "enoyl-CoA hydratase/isomerase superfamily " tb675 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA5' "enoyl-CoA hydratase/isomerase superfamily " tb905 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA6' "enoyl-CoA hydratase/isomerase superfamily (aka eccH)" tb1070 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA8' "enoyl-CoA hydratase/isomerase superfamily " tb1071 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA9' "enoyl-CoA hydratase/isomerase superfamily " tb1141 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA11' "enoyl-CoA hydratase/isomerase superfamily" tb1142 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA10' "enoyl-CoA hydratase/isomerase superfamily" tb1175 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadH' "2,4-Dienoyl-CoA Reductase" tb1472 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA12' "enoyl-CoA hydratase/isomerase superfamily" tb1549 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD11' "null" tb1935 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA13' "enoyl-CoA hydratase/isomerase superfamily " Training Accuracy: 13/14 (92.86%) Evaluation on test data (531 items): tb3039 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA17' "enoyl-CoA hydratase/isomerase superfamily" tb3043 - 1,2,6,1 Small-molecule metabolism Energy Metabolism Respiration aerobic 'ctaD' "cytochrome c oxidase polypeptide I" tb3550 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA20' "enoyl-CoA hydratase/isomerase superfamily" tb3774 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'echA21' "enoyl-CoA hydratase/isomerase superfamily" Test Accuracy: 3/4 (75.00%) Application to new data (1023 items): tb1043 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" Total: 1 ------------------ Rule 5: (7/1, lift 11.9) amino_acid_pair_ratio_yf <= 1 [hom( A ),species( A ,escherichia_coli)] = 1 [hom( A ),classification( A ,eukaryota),classification( A ,fungi)] = 0 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(w,1),classification( A ,bacteria),e_val_rule( A ,1)] = 0 [hom( A ),classification( A ,eukaryota),classification( A ,metazoa),e_val_rule( A ,1),amino_acid_ratio_rule(g,5),classification( A ,chordata)] = 1 -> class 'function2(Degradation )' [0.778] Evaluation on proper test data (811 items): tb2504 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'scoA' "3-oxo acid:CoA transferase, alpha subunit" tb3544 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE28' "acyl-CoA dehydrogenase " Proper test Accuracy: 2/2 (100.00%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb782 - 2,2,3,0 Macromolecule metabolism Degradation of macromolecules Proteins, peptides and glycopeptides Proteins, peptides and glycopeptides 'ptrBa' "protease II, alpha subunit" tb855 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'far' "fatty acyl-CoA racemase" tb1143 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'mcr' "alpha-methyl acyl-CoA racemase" tb1492 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'mutA' "methylmalonyl-CoA mutase, beta subunit" tb1493 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'mutB' "methylmalonyl-CoA mutase, alpha subunit" tb1715 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadB3' "3-hydroxyacyl-CoA dehydrogenase" tb2503 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'scoB' "3-oxo acid:CoA transferase, beta subunit" Training Accuracy: 6/7 (85.71%) Evaluation on test data (531 items): tb3563 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadE32' "acyl-CoA dehydrogenase " Test Accuracy: 1/1 (100.00%) Application to new data (1023 items): Total: 0 ------------------ Rule 17: (6, lift 54.6) [hom( A ),keyword( A ,membrane)] = 1 [hom( A ),keyword( A ,plasmid),e_val_rule( A ,1)] = 1 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 0 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(w,1),classification( A ,bacteria),e_val_rule( A ,1)] = 1 -> class 'function2(Polyketide and non-ribosomal peptide synthesis )' [0.875] Evaluation on proper test data (811 items): tb99 - 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD10' "acyl-CoA synthase" tb1206 - 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadD6' "acyl-CoA synthase" tb2245 - 1,8,1,0 Small-molecule metabolism Lipid Biosynthesis Synthesis of fatty and mycolic acids Synthesis of fatty and mycolic acids 'kasA' "beta-ketoacyl-ACP synthase (meromycolate extension)" tb2246 - 1,8,1,0 Small-molecule metabolism Lipid Biosynthesis Synthesis of fatty and mycolic acids Synthesis of fatty and mycolic acids 'kasB' "beta-ketoacyl-ACP synthase (meromycolate extension)" tb2931 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'ppsA' "phenolpthiocerol synthesis (pksB)" tb2932 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'ppsB' "phenolpthiocerol synthesis (pksC)" tb3800 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks13' "polyketide synthase" tb3825 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks2' "polyketide synthase" Proper test Accuracy: 4/8 (50.00%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb405 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks6' "polyketide synthase" tb1180 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks3' "polyketide synthase" tb1527 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks5' "polyketide synthase" tb1664 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks9' "polyketide synthase" tb2048 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'pks12' "polyketide synthase (erythronolide synthase-like)" tb2384 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'mbtA' "mycobactin/exochelin synthesis (salicylate-AMP ligase)" Training Accuracy: 6/6 (100.00%) Evaluation on test data (531 items): tb2933 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'ppsC' "phenolpthiocerol synthesis (pksD)" tb2935 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'ppsE' "phenolpthiocerol synthesis (pksF)" tb2940 1,9,0,0 Small-molecule metabolism Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis Polyketide and non-ribosomal peptide synthesis 'mas' "mycocerosic acid synthase" Test Accuracy: 3/3 (100.00%) Application to new data (1023 items): Total: 0 ------------------ Rule 18: (53/3, lift 11.6) amino_acid_pair_ratio_ak <= 10.5 amino_acid_pair_ratio_am <= 10.6 amino_acid_pair_ratio_ig <= 14.3 amino_acid_pair_ratio_mc <= 3.3 amino_acid_pair_ratio_nn <= 5.1 amino_acid_ratio_q > 0.6 [amino_acid_ratio_rule(r,3)] = 0 [hom( A ),species( A ,escherichia_coli)] = 1 [hom( A ),e_val_rule( A ,3),amino_acid_ratio_rule(y,3)] = 0 [hom( A ),e_val_rule( A ,3),amino_acid_ratio_rule(l,4)] = 0 [hom( A ),e_val_rule( A ,1),amino_acid_ratio_rule(y,3)] = 0 [hom( A ),keyword( A ,membrane),amino_acid_ratio_rule(c,1)] = 0 [hom( A ),keyword( A ,transmembrane),e_val_rule( A ,2)] = 0 [hom( A ),classification( A ,eukaryota),classification( A ,fungi)] = 0 [hom( A ),classification( A ,eukaryota),amino_acid_ratio_rule(h,3)] = 0 [hom( A ),classification( A ,eukaryota),classification( A ,metazoa),amino_acid_ratio_rule(m,1)] = 0 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 0 [hom( A ),e_val_rule( A ,1),amino_acid_ratio_rule(c,1),species( A ,haemophilus_influenzae)] = 0 [hom( A ),e_val_rule( A ,4),amino_acid_ratio_rule(l,4),classification( A ,bacteria)] = 0 [hom( A ),e_val_rule( A ,5),amino_acid_ratio_rule(h,1),classification( A ,eukaryota)] = 0 [hom( A ),mol_wt_rule( A ,2),amino_acid_ratio_rule(s,3),e_val_rule( A ,1)] = 0 [hom( A ),mol_wt_rule( A ,3),amino_acid_ratio_rule(r,4),e_val_rule( A ,2)] = 0 [hom( A ),mol_wt_rule( A ,3),amino_acid_ratio_rule(p,4),classification( A ,eukaryota)] = 0 [hom( A ),mol_wt_rule( A ,3),amino_acid_ratio_rule(s,3),e_val_rule( A ,1)] = 0 [hom( A ),mol_wt_rule( A ,3),amino_acid_ratio_rule(f,2),species( A ,haemophilus_influenzae)] = 0 [hom( A ),mol_wt_rule( A ,5),amino_acid_ratio_rule(t,3),classification( A ,eukaryota)] = 0 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(w,1),classification( A ,bacteria),e_val_rule( A ,1)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,firmicutes),e_val_rule( A ,3),amino_acid_ratio_rule(w,2)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),e_val_rule( A ,2),mol_wt_rule( A ,4)] = 0 [hom( A ),classification( A ,eukaryota),classification( A ,metazoa),e_val_rule( A ,1),amino_acid_ratio_rule(g,5),classification( A ,chordata)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,firmicutes),classification( A ,bacillus),classification( A ,bacillaceae),mol_wt_rule( A ,5),amino_acid_ratio_rule(w,1)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,firmicutes),classification( A ,bacillus),classification( A ,bacillaceae),mol_wt_rule( A ,4),amino_acid_ratio_rule(n,2)] = 0 -> class 'function2(Broad regulatory functions )' [0.927] Evaluation on proper test data (811 items): tb135 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb158 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb322 - 1,3,3,0 Small-molecule metabolism Central intermediary metabolism Sugar nucleotides Sugar nucleotides 'udgA' "UDP-glucose dehydrogenase/GDP-mannose 6-dehydrogenase" tb328 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb353 - 3,2,0,0 Cell Processes Chaperones/Heat shock Chaperones/Heat shock Chaperones/Heat shock 'hspR' "heat shock regulator" tb370 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb377 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb468 - 1,1,3,0 Small-molecule metabolism Degradation Fatty acids Fatty acids 'fadB2' "3-hydroxyacyl-CoA dehydrogenase" tb509 - 1,7,12,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Heme and porphyrin Heme and porphyrin 'hemA' "glutamyl-tRNA reductase" tb576 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb586 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb589 - 4,1,0,0 Other Virulence Virulence Virulence 'mce2' "cell invasion protein" tb653 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb757 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'phoP' "two-component response regulator" tb792 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb906 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb984 - 1,7,4,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Molybdopterin Molybdopterin 'moaB2' "molybdenum cofactor biosynthesis, protein B" tb1015 - 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplY' "50S ribosomal protein L25" tb1049 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1095 - 1,1,4,0 Small-molecule metabolism Degradation Phosphorous compounds Phosphorous compounds 'phoH2' "PhoH-like protein" tb1170 - 4,4,0,0 Other Antibiotic production and resistance Antibiotic production and resistance Antibiotic production and resistance 'null' "null" tb1189 - 2,1,7,0 Macromolecule metabolism Synthesis and modification of macromolecules RNA synthesis, RNA modification and DNA transcription RNA synthesis, RNA modification and DNA transcription 'sigI' "ECF family sigma factor" tb1210 - 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'tagA' "DNA-3-methyladenine glycosidase I" tb1244 - 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqZ' "lipoprotein" tb1855 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1909 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'furA' "ferric uptake regulatory protein" tb1931 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1971 - 4,1,0,0 Other Virulence Virulence Virulence 'null' "null" tb2017 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb2069 - 2,1,7,0 Macromolecule metabolism Synthesis and modification of macromolecules RNA synthesis, RNA modification and DNA transcription RNA synthesis, RNA modification and DNA transcription 'sigC' "ECF subfamily sigma subunit" tb2181 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2261 - 1,8,3,0 Small-molecule metabolism Lipid Biosynthesis Acyltransferases, Mycoloyltransferases, and phospholipid synthesis Acyltransferases, Mycoloyltransferases, and phospholipid synthesis 'null' "null" tb2412 - 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsT' "30S ribosomal protein S20" tb2455 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb2464 - 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'null' "null" tb2849 - 1,7,13,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Cobalamin Cobalamin 'cobA' "cob(I)alamin adenosyltransferase" tb2919 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'glnB' "nitrogen regulatory protein" tb3167 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3173 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3208 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3249 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3291 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3297 - 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'nei' "probable endonuclease VIII" tb3366 - 2,1,7,0 Macromolecule metabolism Synthesis and modification of macromolecules RNA synthesis, RNA modification and DNA transcription RNA synthesis, RNA modification and DNA transcription 'spoU' "probable rRNA methylase" tb3427 - 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1532' "null" tb3461 - 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpmJ' "50S ribosomal protein L36" tb3623 - 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqG' "similar OMP28" tb3765 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb3919 - 3,3,0,0 Cell Processes Cell division Cell division Cell division 'gid' "glucose inhibited division protein B" Proper test Accuracy: 20/49 (40.82%) Application to new data (498 items): tb181 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb208 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb372 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb880 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1140 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1194 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1203 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1375 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1487 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1725 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1991 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2370 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2966 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3113 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3228 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3361 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3486 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3871 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 18 Evaluation on training data (1060 items): tb23 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb43 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb67 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb78 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb81 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb144 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb212 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'nadR' "similar to E.coli NadR" tb232 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb238 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb260 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb302 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb472 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb485 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb491 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'regX3' "two-component response regulator" tb494 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb602 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'tcrA' "two-component response regulator" tb681 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb691 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb737 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb818 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb844 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'narL' "two-component response regulator" tb890 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb903 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb981 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb1019 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1027 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'kdpE' "two-component response regulator" tb1152 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1163 - 1,2,6,2 Small-molecule metabolism Energy Metabolism Respiration anaerobic 'narJ' "nitrate reductase delta chain" tb1167 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1219 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1353 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1358 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1404 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1474 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1534 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1539 - 3,4,0,0 Cell Processes Protein and peptide secretion Protein and peptide secretion Protein and peptide secretion 'lspA' "lipoprotein signal peptidase" tb1556 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1657 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'argR' "arginine repressor" tb1719 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1773 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1776 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1816 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1963 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb1994 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb2034 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb2250 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb2262 - 1,8,3,0 Small-molecule metabolism Lipid Biosynthesis Acyltransferases, Mycoloyltransferases, and phospholipid synthesis Acyltransferases, Mycoloyltransferases, and phospholipid synthesis 'null' "null" tb2282 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb2324 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb2358 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb2359 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'furB' "ferric uptake regulatory protein" tb2506 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb2642 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" Training Accuracy: 50/53 (94.34%) Evaluation on test data (531 items): tb2720 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'lexA' "LexA, SOS repressor protein" tb2887 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb2893 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb2907 - 2,1,2,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosome modification and maturation Ribosome modification and maturation 'rimM' "16S rRNA processing protein" tb2912 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb2989 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3002 - 1,4,7,0 Small-molecule metabolism Amino acid biosynthesis Branched amino acid family Branched amino acid family 'ilvN' "acetolactate synthase I small subunit" tb3055 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3060 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3066 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3095 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3100 - 4,1,0,0 Other Virulence Virulence Virulence 'smpB' "probable small protein b" tb3191 - 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1603' "null" tb3204 - 4,8,0,0 Other Miscellaneous transferases Miscellaneous transferases Miscellaneous transferases 'null' "null" tb3246 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'mtrA' "two-component response regulator" tb3327 - 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1547' "null" tb3328 - 2,1,7,0 Macromolecule metabolism Synthesis and modification of macromolecules RNA synthesis, RNA modification and DNA transcription RNA synthesis, RNA modification and DNA transcription 'sigJ' "similar to SigI, ECF family" tb3334 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3405 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3414 - 2,1,7,0 Macromolecule metabolism Synthesis and modification of macromolecules RNA synthesis, RNA modification and DNA transcription RNA synthesis, RNA modification and DNA transcription 'sigD' "ECF subfamily sigma subunit" tb3638 - 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1534' "null" tb3744 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3817 - 4,4,0,0 Other Antibiotic production and resistance Antibiotic production and resistance Antibiotic production and resistance 'null' "null" tb3830 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3855 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3922 - 4,1,0,0 Other Virulence Virulence Virulence 'null' "null" Test Accuracy: 14/26 (53.85%) Application to new data (1023 items): tb38 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb42 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb47 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb91 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb142 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb190 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb330 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb376 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb546 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb775 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb793 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb967 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1099 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1287 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1453 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1515 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1685 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1847 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2149 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'yfiH' "YFIH_STRGR P45496" tb2327 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2362 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2453 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2510 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2553 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2761 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2842 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2852 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3073 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3134 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3282 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3357 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3394 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb3488 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3788 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" Total: 34 ------------------ Rule 19: (7, lift 11.1) [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 1 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),keyword( A ,plasmid),mol_wt_rule( A ,4)] = 1 -> class 'function2(Broad regulatory functions )' [0.889] Evaluation on proper test data (811 items): tb125 - 2,2,3,0 Macromolecule metabolism Degradation of macromolecules Proteins, peptides and glycopeptides Proteins, peptides and glycopeptides 'pepA' "probable serine protease" tb600 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb1032 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb1858 - 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'modB' "transport system permease, molybdate uptake" tb3276 - 1,6,1,0 Small-molecule metabolism Purines, pyrimidines, nucleosides and nucleotides Purine ribonucleotide biosynthesis Purine ribonucleotide biosynthesis 'purK' "phosphoribosylaminoimidazole carboxylase ATPase subunit" Proper test Accuracy: 2/5 (40.00%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb490 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'senX3' "sensor histidine kinase" tb601 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb758 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'phoR' "sensor histidine kinase" tb902 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb982 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb1028 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'kdpD' "sensor histidine kinase" tb2027 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" Training Accuracy: 7/7 (100.00%) Evaluation on test data (531 items): tb3132 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb3220 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb3245 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'mtrB' "sensor histidine kinase" tb3764 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" Test Accuracy: 4/4 (100.00%) Application to new data (1023 items): tb1488 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 1 ------------------ Rule 21: (45/2, lift 10.9) amino_acid_pair_ratio_cn <= 1.6 amino_acid_pair_ratio_fm <= 2 amino_acid_pair_ratio_fy <= 4.7 amino_acid_pair_ratio_hh <= 3 amino_acid_pair_ratio_lg <= 18 amino_acid_pair_ratio_nh <= 3.8 [hom( A ),species( A ,bacillus_subtilis)] = 1 [hom( A ),classification( A ,eukaryota),classification( A ,fungi)] = 1 [hom( A ),classification( A ,bacteria),classification( A ,firmicutes),classification( A ,actinobacteria)] = 1 [hom( A ),keyword( A ,transmembrane),mol_wt_rule( A ,3),classification( A ,bacteria)] = 0 [hom( A ),species( A ,homo_sapiens),mol_wt_rule( A ,5),keyword( A ,alternative_splicing)] = 0 [hom( A ),mol_wt_rule( A ,3),amino_acid_ratio_rule(d,3),classification( A ,bacteria)] = 0 [hom( A ),mol_wt_rule( A ,3),amino_acid_ratio_rule(k,1),e_val_rule( A ,2)] = 0 [hom( A ),mol_wt_rule( A ,3),amino_acid_ratio_rule(h,1),e_val_rule( A ,4)] = 0 [hom( A ),mol_wt_rule( A ,4),amino_acid_ratio_rule(m,1),species( A ,homo_sapiens)] = 0 [hom( A ),mol_wt_rule( A ,4),amino_acid_ratio_rule(k,1),e_val_rule( A ,2)] = 0 [hom( A ),e_val_rule( A ,5),amino_acid_ratio_rule(g,5),classification( A ,bacteria),mol_wt_rule( A ,3)] = 0 [hom( A ),classification( A ,eukaryota),classification( A ,metazoa),mol_wt_rule( A ,3),amino_acid_ratio_rule(y,1)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,firmicutes),keyword( A ,transmembrane),amino_acid_ratio_rule(h,1)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),keyword( A ,plasmid),amino_acid_ratio_rule(g,5)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),classification( A ,gamma_subdivision),classification( A ,enterobacteriaceae)] = 1 [hom( A ),classification( A ,bacteria),classification( A ,firmicutes),e_val_rule( A ,2),amino_acid_ratio_rule(k,1),classification( A ,actinobacteria)] = 0 [hom( A ),e_val_rule( A ,4),amino_acid_ratio_rule(w,1),classification( A ,bacteria),mol_wt_rule( A ,2),classification( A ,firmicutes)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),classification( A ,gamma_subdivision),classification( A ,enterobacteriaceae),mol_wt_rule( A ,1),amino_acid_ratio_rule(k,2)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,firmicutes),classification( A ,bacillus),classification( A ,bacillaceae),e_val_rule( A ,5),mol_wt_rule( A ,1),classification( A ,bacillus1)] = 0 [hom( A ),classification( A ,eukaryota),classification( A ,metazoa),classification( A ,chordata),classification( A ,vertebrata),keyword( A ,repeat),mol_wt_rule( A ,5),classification( A ,mammalia)] = 0 -> class 'function2(Synthesis and modification of macromolecules )' [0.936] Evaluation on proper test data (811 items): tb467 - 1,2,4,0 Small-molecule metabolism Energy Metabolism Glyoxylate bypass Glyoxylate bypass 'aceA' "isocitrate lyase" tb651 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplJ' "50S ribosomal protein L10" tb682 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsL' "30S ribosomal protein S12" tb683 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsG' "30S ribosomal protein S7" tb684 2,1,6,0 Macromolecule metabolism Synthesis and modification of macromolecules Protein translation and modification Protein translation and modification 'fusA' "elongation factor G" tb702 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplD' "50S ribosomal protein L4" tb715 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplX' "50S ribosomal protein L24" tb716 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplE' "50S ribosomal protein L5" tb721 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsE' "30S ribosomal protein S5" tb846 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1286 - 1,3,5,0 Small-molecule metabolism Central intermediary metabolism Sulphur metabolism Sulphur metabolism 'cysN' "ATP:sulphurylase subunit 1" tb1294 - 1,4,2,0 Small-molecule metabolism Amino acid biosynthesis Aspartate family Aspartate family 'thrA' "homoserine dehydrogenase" tb1329 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'dinG' "probable ATP-dependent helicase" tb1536 2,1,3,0 Macromolecule metabolism Synthesis and modification of macromolecules Aminoacyl tRNA synthases and their modification Aminoacyl tRNA synthases and their modification 'ileS' "isoleucyl-tRNA synthase" tb1552 - 1,2,6,2 Small-molecule metabolism Energy Metabolism Respiration anaerobic 'frdA' "fumarate reductase flavoprotein subunit" tb1617 - 1,2,1,0 Small-molecule metabolism Energy Metabolism Glycolysis Glycolysis 'pykA' "pyruvate kinase" tb1630 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsA' "30S ribosomal protein S1" tb2540 - 1,4,4,0 Small-molecule metabolism Amino acid biosynthesis Aromatic amino acid family Aromatic amino acid family 'aroF' "chorismate synthase" tb3001 - 1,4,7,0 Small-molecule metabolism Amino acid biosynthesis Branched amino acid family Branched amino acid family 'ilvC' "ketol-acid reductoisomerase" tb3215 - 1,7,14,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Iron utilisation Iron utilisation 'entC' "probable isochorismate synthase" tb3442 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsI' "30S ribosomal protein S9" tb3522 - 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb3602 - 1,7,5,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Pantothenate Pantothenate 'panC' "pantoate-beta-alanine ligase" Proper test Accuracy: 12/23 (52.17%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb1 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'dnaA' "chromosomal replication initiator protein" tb3 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'recF' "DNA replication and SOS induction" tb41 2,1,3,0 Macromolecule metabolism Synthesis and modification of macromolecules Aminoacyl tRNA synthases and their modification Aminoacyl tRNA synthases and their modification 'leuS' "leucyl-tRNA synthase" tb55 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsR' "30S ribosomal protein S18" tb120 2,1,6,0 Macromolecule metabolism Synthesis and modification of macromolecules Protein translation and modification Protein translation and modification 'fusA2' "elongation factor G " tb351 - 3,2,0,0 Cell Processes Chaperones/Heat shock Chaperones/Heat shock Chaperones/Heat shock 'grpE' "stimulates DnaK ATPase activity" tb629 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'recD' "exodeoxyribonuclease V" tb640 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplK' "50S ribosomal protein L11" tb641 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplA' "50S ribosomal protein L1" tb652 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplL' "50S ribosomal protein L7/L12" tb667 2,1,7,0 Macromolecule metabolism Synthesis and modification of macromolecules RNA synthesis, RNA modification and DNA transcription RNA synthesis, RNA modification and DNA transcription 'rpoB' "beta subunit of RNA polymerase" tb685 2,1,6,0 Macromolecule metabolism Synthesis and modification of macromolecules Protein translation and modification Protein translation and modification 'tuf' "elongation factor EF-Tu" tb700 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsJ' "30S ribosomal protein S10" tb701 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplC' "50S ribosomal protein L3" tb703 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplW' "50S ribosomal protein L23" tb704 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplB' "50S ribosomal protein L2" tb705 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsS' "30S ribosomal protein S19" tb707 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsC' "30S ribosomal protein S3" tb710 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsQ' "30S ribosomal protein S17" tb717 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsN' "30S ribosomal protein S14" tb718 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsH' "30S ribosomal protein S8" tb719 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplF' "50S ribosomal protein L6" tb722 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpmD' "50S ribosomal protein L30" tb723 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplO' "50S ribosomal protein L15" tb949 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'uvrD' "DNA-dependent ATPase I and helicase II " tb1007 2,1,3,0 Macromolecule metabolism Synthesis and modification of macromolecules Aminoacyl tRNA synthases and their modification Aminoacyl tRNA synthases and their modification 'metS' "methionyl-tRNA synthase" tb1010 2,1,2,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosome modification and maturation Ribosome modification and maturation 'ksgA' "16S rRNA dimethyltransferase" tb1020 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'mfd' "transcription-repair coupling factor" tb1253 2,1,7,0 Macromolecule metabolism Synthesis and modification of macromolecules RNA synthesis, RNA modification and DNA transcription RNA synthesis, RNA modification and DNA transcription 'deaD' "ATP-dependent DNA/RNA helicase" tb1292 2,1,3,0 Macromolecule metabolism Synthesis and modification of macromolecules Aminoacyl tRNA synthases and their modification Aminoacyl tRNA synthases and their modification 'argS' "arginyl-tRNA synthase" tb1297 2,1,7,0 Macromolecule metabolism Synthesis and modification of macromolecules RNA synthesis, RNA modification and DNA transcription RNA synthesis, RNA modification and DNA transcription 'rho' "transcription termination factor rho" tb1317 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'alkA' "DNA-3-methyladenine glycosidase II" tb1328 2,1,8,0 Macromolecule metabolism Synthesis and modification of macromolecules Polysaccharides Polysaccharides 'glgP' "probable glycogen phosphorylase" tb1629 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'polA' "DNA polymerase I" tb1633 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'uvrB' "excinuclease ABC subunit B" tb1644 2,1,7,0 Macromolecule metabolism Synthesis and modification of macromolecules RNA synthesis, RNA modification and DNA transcription RNA synthesis, RNA modification and DNA transcription 'tsnR' "putative 23S rRNA methyltransferase" tb1650 2,1,3,0 Macromolecule metabolism Synthesis and modification of macromolecules Aminoacyl tRNA synthases and their modification Aminoacyl tRNA synthases and their modification 'pheT' "phenylalanyl-tRNA synthase beta subunit" tb1689 2,1,3,0 Macromolecule metabolism Synthesis and modification of macromolecules Aminoacyl tRNA synthases and their modification Aminoacyl tRNA synthases and their modification 'tyrS' "tyrosyl-tRNA synthase" tb2055 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsR2' "30S ribosomal protein S18" tb2056 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsN2' "30S ribosomal protein S14" tb2058 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpmB2' "50S ribosomal protein L28" tb2130 2,1,3,0 Macromolecule metabolism Synthesis and modification of macromolecules Aminoacyl tRNA synthases and their modification Aminoacyl tRNA synthases and their modification 'cysS2' "cysteinyl-tRNA synthase" tb2404 - 1,6,5,0 Small-molecule metabolism Purines, pyrimidines, nucleosides and nucleotides Miscellaneous nucleoside/nucleotide reactions Miscellaneous nucleoside/nucleotide reactions 'lepA' "GTP-binding protein LepA" tb2441 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpmA' "50S ribosomal protein L27" tb2448 2,1,3,0 Macromolecule metabolism Synthesis and modification of macromolecules Aminoacyl tRNA synthases and their modification Aminoacyl tRNA synthases and their modification 'valS' "valyl-tRNA synthase" Training Accuracy: 43/45 (95.56%) Evaluation on test data (531 items): tb2667 - 2,2,3,0 Macromolecule metabolism Degradation of macromolecules Proteins, peptides and glycopeptides Proteins, peptides and glycopeptides 'clpX' "null" tb2793 2,1,7,0 Macromolecule metabolism Synthesis and modification of macromolecules RNA synthesis, RNA modification and DNA transcription RNA synthesis, RNA modification and DNA transcription 'truB' "tRNA pseudouridine 55 synthase" tb2882 2,1,6,0 Macromolecule metabolism Synthesis and modification of macromolecules Protein translation and modification Protein translation and modification 'frr' "ribosome recycling factor" tb2909 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsP' "30S ribosomal protein S16" tb3010 - 1,2,1,0 Small-molecule metabolism Energy Metabolism Glycolysis Glycolysis 'pfkA' "phosphofructokinase I" tb3201 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'null' "null" tb3290 - 4,4,0,0 Other Antibiotic production and resistance Antibiotic production and resistance Antibiotic production and resistance 'lat' "lysine-epsilon aminotransferase" tb3302 - 1,2,6,1 Small-molecule metabolism Energy Metabolism Respiration aerobic 'glpD2' "glycerol-3-phosphate dehydrogenase" tb3318 - 1,2,3,0 Small-molecule metabolism Energy Metabolism TCA cycle TCA cycle 'sdhA' "succinate dehydrogenase A" tb3319 - 1,2,3,0 Small-molecule metabolism Energy Metabolism TCA cycle TCA cycle 'sdhB' "succinate dehydrogenase B" tb3340 - 1,4,2,0 Small-molecule metabolism Amino acid biosynthesis Aspartate family Aspartate family 'metC' "cystathionine beta-lyase" tb3418 - 3,2,0,0 Cell Processes Chaperones/Heat shock Chaperones/Heat shock Chaperones/Heat shock 'groES' "10 kD chaperone" tb3443 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplM' "50S ribosomal protein L13" tb3459 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsK' "30S ribosomal protein S11" tb3460 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rpsM' "30S ribosomal protein S13" tb3646 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'topA' "DNA topoisomerase" Test Accuracy: 8/16 (50.00%) Application to new data (1023 items): tb839 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1422 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3401 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3421 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 4 ------------------ Rule 25: (11/1, lift 24.9) [hom( A ),keyword( A ,membrane)] = 1 [hom( A ),species( A ,bacillus_subtilis)] = 1 [hom( A ),mol_wt_rule( A ,1),amino_acid_ratio_rule(e,4),e_val_rule( A ,3)] = 0 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 0 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(x,5),classification( A ,bacteria),mol_wt_rule( A ,3),classification( A ,firmicutes)] = 0 [hom( A ),classification( A ,eukaryota),classification( A ,metazoa),classification( A ,chordata),classification( A ,vertebrata),keyword( A ,repeat),mol_wt_rule( A ,5),classification( A ,mammalia)] = 1 -> class 'function2(Degradation of macromolecules )' [0.846] Evaluation on proper test data (811 items): tb217 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipW' "probable esterase" tb220 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipC' "probable esterase" tb706 - 2,1,1,0 Macromolecule metabolism Synthesis and modification of macromolecules Ribosomal protein synthesis and modification Ribosomal protein synthesis and modification 'rplV' "50S ribosomal protein L22" tb1399 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipH' "probable lipase" tb1426 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipO' "probable esterase" tb1566 - 4,1,0,0 Other Virulence Virulence Virulence 'null' "null" tb2485 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipQ' "probable carboxlyesterase" tb3682 - 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'ponA2' "class A penicillin binding protein" Proper test Accuracy: 5/8 (62.50%) Application to new data (498 items): tb996 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" Total: 1 Evaluation on training data (1060 items): tb384 - 3,2,0,0 Cell Processes Chaperones/Heat shock Chaperones/Heat shock Chaperones/Heat shock 'clpB' "heat shock protein" tb983 2,2,3,0 Macromolecule metabolism Degradation of macromolecules Proteins, peptides and glycopeptides Proteins, peptides and glycopeptides 'null' "null" tb1076 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipU' "probable esterase" tb1104 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'null' "null" tb1105 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'null' "null" tb1400 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipI' "probable lipase" tb2045 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipT' "probable carboxylesterase" tb2284 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipM' "probable esterase" tb2385 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipK' "probable acetyl-hydrolase" tb2444 2,2,1,0 Macromolecule metabolism Degradation of macromolecules RNA RNA 'rne' "similar at C-term to ribonuclease E" tb2457 2,2,3,0 Macromolecule metabolism Degradation of macromolecules Proteins, peptides and glycopeptides Proteins, peptides and glycopeptides 'clpX' "ATP-dependent Clp protease ATP-binding subunit ClpX" Training Accuracy: 10/11 (90.91%) Evaluation on test data (531 items): tb2916 - 3,4,0,0 Cell Processes Protein and peptide secretion Protein and peptide secretion Protein and peptide secretion 'ffh' "signal recognition particle protein" tb2970 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipN' "probable lipase/esterase" tb2986 - 2,1,4,0 Macromolecule metabolism Synthesis and modification of macromolecules Nucleoproteins Nucleoproteins 'hupB' "DNA-binding protein II " tb3084 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipR' "probable acetyl-hydrolase" tb3487 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipF' "probable esterase" tb3596 2,2,3,0 Macromolecule metabolism Degradation of macromolecules Proteins, peptides and glycopeptides Proteins, peptides and glycopeptides 'clpC' "ATP-dependent Clp protease" tb3627 - 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'null' "null" Test Accuracy: 4/7 (57.14%) Application to new data (1023 items): tb530 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb991 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" Total: 2 ------------------ Rule 29: (18, lift 5.5) [hom( A ),e_val_rule( A ,1),amino_acid_ratio_rule(r,4)] = 1 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 1 [hom( A ),e_val_rule( A ,4),amino_acid_ratio_rule(n,2),species( A ,bacillus_subtilis)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),keyword( A ,plasmid),mol_wt_rule( A ,4)] = 0 -> class 'function2(Cell envelope )' [0.950] Evaluation on proper test data (811 items): tb402 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL1' "conserved large membrane protein" tb507 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL2' "conserved large membrane protein" tb842 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb924 - 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'nramp' "transmembrane protein belonging to Nramp family" tb1183 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL10' "conserved large membrane protein" tb1258 - 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb1302 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'rfe' "undecaprenyl-phosphate alpha-N-acetylglucosaminyltransferase" tb1979 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2195 - 1,2,6,1 Small-molecule metabolism Energy Metabolism Respiration aerobic 'qcrA' "Rieske iron-sulphur component of ubiQ-cytB reductase" tb2200 - 1,2,6,1 Small-molecule metabolism Energy Metabolism Respiration aerobic 'ctaC' "cytochrome c oxidase chain II" tb2339 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL9' "conserved large membrane protein" tb2586 - 3,4,0,0 Cell Processes Protein and peptide secretion Protein and peptide secretion Protein and peptide secretion 'secF' "protein-export membrane protein" tb3411 - 1,6,1,0 Small-molecule metabolism Purines, pyrimidines, nucleosides and nucleotides Purine ribonucleotide biosynthesis Purine ribonucleotide biosynthesis 'guaB2' "inosine-5-monophosphate dehydrogenase" tb3448 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Proper test Accuracy: 8/14 (57.14%) Application to new data (498 items): tb20 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb874 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2075 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" Total: 3 Evaluation on training data (1060 items): tb17 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'rodA' "FtsW/RodA/SpovE family" tb37 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb72 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb191 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb202 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL11' "conserved large membrane protein" tb206 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL3' "conserved large membrane protein" tb246 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb450 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL4' "conserved large membrane protein" tb987 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1490 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1510 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1522 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL12' "conserved large membrane protein" tb1557 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL6' "conserved large membrane protein" tb1841 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1842 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2265 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2518 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppS' "lipoprotein" tb2563 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Training Accuracy: 18/18 (100.00%) Evaluation on test data (531 items): tb2942 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL7' "conserved large membrane protein" tb3253 - 3,1,1,0 Cell Processes Transport/binding proteins Amino acids Amino acids 'null' "null" tb3737 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3823 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL8' "conserved large membrane protein" Test Accuracy: 3/4 (75.00%) Application to new data (1023 items): tb2205 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2625 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 2 ------------------ Rule 30: (10, lift 5.3) amino_acid_pair_ratio_aa <= 21.8 amino_acid_pair_ratio_kh <= 1.3 [hom( A ),species( A ,escherichia_coli)] = 1 [hom( A ),mol_wt_rule( A ,1),amino_acid_ratio_rule(p,3)] = 0 [hom( A ),keyword( A ,plasmid),e_val_rule( A ,1)] = 0 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 0 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(w,1),classification( A ,bacteria),e_val_rule( A ,1)] = 1 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(x,5),classification( A ,bacteria),mol_wt_rule( A ,3),classification( A ,firmicutes)] = 0 -> class 'function2(Cell envelope )' [0.917] Evaluation on proper test data (811 items): tb50 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'ponA1' "penicillin-bonding protein" tb86 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'hycQ' "probable formate hydrogenlyase subunit" tb899 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'ompA' "member of OmpA family" tb1302 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'rfe' "undecaprenyl-phosphate alpha-N-acetylglucosaminyltransferase" tb1730 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'null' "null" tb2339 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL9' "conserved large membrane protein" tb3447 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3682 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'ponA2' "class A penicillin binding protein" Proper test Accuracy: 7/8 (87.50%) Application to new data (498 items): tb284 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 1 Evaluation on training data (1060 items): tb16 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'pbpA' "penicillin-binding protein" tb180 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb907 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'null' "null" tb1481 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1518 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb2037 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2163 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'pbpB' "penicillin-binding protein 2" tb2223 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb2224 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb2395 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Training Accuracy: 10/10 (100.00%) Evaluation on test data (531 items): tb2672 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'null' "null" tb2748 - 3,3,0,0 Cell Processes Cell division Cell division Cell division 'ftsK' "chromosome partitioning" tb2874 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3092 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Test Accuracy: 3/4 (75.00%) Application to new data (1023 items): tb3870 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 1 ------------------ Rule 31: (15/1, lift 5.1) [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,4)] = 0 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 1 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(l,5),classification( A ,eukaryota)] = 0 [hom( A ),e_val_rule( A ,4),amino_acid_ratio_rule(n,2),species( A ,bacillus_subtilis)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),keyword( A ,plasmid),mol_wt_rule( A ,4)] = 0 -> class 'function2(Cell envelope )' [0.882] Evaluation on proper test data (811 items): tb845 - 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb955 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1145 - 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb1217 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1258 - 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb1302 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'rfe' "undecaprenyl-phosphate alpha-N-acetylglucosaminyltransferase" tb1999 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2195 - 1,2,6,1 Small-molecule metabolism Energy Metabolism Respiration aerobic 'qcrA' "Rieske iron-sulphur component of ubiQ-cytB reductase" tb2200 - 1,2,6,1 Small-molecule metabolism Energy Metabolism Respiration aerobic 'ctaC' "cytochrome c oxidase chain II" Proper test Accuracy: 4/9 (44.44%) Application to new data (498 items): tb874 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2075 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2414 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3877 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 4 Evaluation on training data (1060 items): tb72 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb191 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb290 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb585 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb885 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb888 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb987 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1146 - 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb1433 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1490 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1510 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1795 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2156 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'murX' "phospho-N-acetylmuramoyl-pentapeptide transferase" tb2518 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppS' "lipoprotein" tb2563 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Training Accuracy: 14/15 (93.33%) Evaluation on test data (531 items): tb2942 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL7' "conserved large membrane protein" tb3630 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3737 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Test Accuracy: 3/3 (100.00%) Application to new data (1023 items): tb116 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb192 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb483 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb628 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 4 ------------------ Rule 32: (6, lift 5.1) amino_acid_pair_ratio_ey <= 1.8 amino_acid_pair_ratio_ha > 2.2 [hom( A ),keyword( A ,membrane),amino_acid_ratio_rule(c,1)] = 1 [hom( A ),classification( A ,eukaryota),classification( A ,fungi)] = 0 [hom( A ),classification( A ,eukaryota),classification( A ,metazoa),e_val_rule( A ,1)] = 0 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 0 [hom( A ),e_val_rule( A ,5),amino_acid_ratio_rule(f,3),classification( A ,eukaryota)] = 0 [hom( A ),mol_wt_rule( A ,2),amino_acid_ratio_rule(x,5),keyword( A ,transmembrane)] = 0 -> class 'function2(Cell envelope )' [0.875] Evaluation on proper test data (811 items): tb24 - 4,1,0,0 Other Virulence Virulence Virulence 'null' "null" tb1235 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqY' "possible role in sugar transport" tb2290 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lppO' "probable lipoprotein" tb2583 - 1,6,5,0 Small-molecule metabolism Purines, pyrimidines, nucleosides and nucleotides Miscellaneous nucleoside/nucleotide reactions Miscellaneous nucleoside/nucleotide reactions 'relA' "(p)ppGpp synthase I" tb2936 - 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'drrA' "similar daunorubicin resistance ABC-transporter " tb2984 - 1,1,4,0 Small-molecule metabolism Degradation Phosphorous compounds Phosphorous compounds 'ppk' "polyphosphate kinase" tb3717 - 2,2,4,0 Macromolecule metabolism Degradation of macromolecules Polysaccharides, lipopolysaccharides and phospholipids Polysaccharides, lipopolysaccharides and phospholipids 'null' "null" Proper test Accuracy: 2/7 (28.57%) Application to new data (498 items): tb2059 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 1 Evaluation on training data (1060 items): tb399 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqK' "possible PBP" tb655 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1218 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1367 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'null' "null" tb1456 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2153 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'murG' "transferase in peptidoglycan synthesis" Training Accuracy: 6/6 (100.00%) Evaluation on test data (531 items): tb2864 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'null' "null" tb2911 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'dacB' "penicillin binding protein" tb3044 - 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'fecB' "putative FeIII-dicitrate transporter" tb3265 - 1,3,3,0 Small-molecule metabolism Central intermediary metabolism Sugar nucleotides Sugar nucleotides 'wbbL' "dTDP-rhamnosyl transferase" Test Accuracy: 2/4 (50.00%) Application to new data (1023 items): tb230 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb339 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 2 ------------------ Rule 34: (13/1, lift 5.0) amino_acid_pair_ratio_yi <= 4.3 [hom( A ),species( A ,escherichia_coli)] = 1 [hom( A ),species( A ,bacillus_subtilis),mol_wt_rule( A ,5)] = 0 [hom( A ),keyword( A ,transmembrane),mol_wt_rule( A ,3),classification( A ,bacteria)] = 0 [hom( A ),mol_wt_rule( A ,2),amino_acid_ratio_rule(a,5),e_val_rule( A ,1)] = 0 [hom( A ),mol_wt_rule( A ,4),amino_acid_ratio_rule(t,3),classification( A ,eukaryota)] = 0 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 1 -> class 'function2(Cell envelope )' [0.867] Evaluation on proper test data (811 items): tb32 - 1,7,1,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Biotin Biotin 'bioF2' "C-terminal similar to B. subtilis BioF" tb194 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1751 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3041 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3102 - 3,3,0,0 Cell Processes Cell division Cell division Cell division 'ftsE' "membrane protein" tb3854 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" Proper test Accuracy: 2/6 (33.33%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb110 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb986 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1166 2,3,1,0 Macromolecule metabolism Cell envelope Lipoproteins Lipoproteins 'lpqW' "lipoprotein" tb1272 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1273 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1348 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1349 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1393 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb1458 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1463 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1747 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2025 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2326 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Training Accuracy: 12/13 (92.31%) Evaluation on test data (531 items): tb3806 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3829 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" Test Accuracy: 1/2 (50.00%) Application to new data (1023 items): Total: 0 ------------------ Rule 36: (4, lift 4.9) amino_acid_pair_ratio_ct > 2.2 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 1 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),keyword( A ,plasmid),mol_wt_rule( A ,4)] = 0 -> class 'function2(Cell envelope )' [0.833] Evaluation on proper test data (811 items): tb842 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb845 - 1,10,2,0 Small-molecule metabolism Broad regulatory functions Two component systems Two component systems 'null' "null" tb1258 - 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" Proper test Accuracy: 1/3 (33.33%) Application to new data (498 items): tb874 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 1 Evaluation on training data (1060 items): tb876 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb888 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1004 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1490 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Training Accuracy: 4/4 (100.00%) Evaluation on test data (531 items): tb2994 - 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb3737 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Test Accuracy: 1/2 (50.00%) Application to new data (1023 items): tb1744 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2205 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2406 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 3 ------------------ Rule 39: (15, lift 17.5) [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(l,5),classification( A ,eukaryota)] = 1 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 0 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(x,5),classification( A ,bacteria),mol_wt_rule( A ,3),classification( A ,firmicutes)] = 1 -> class 'function2(Transport/binding proteins )' [0.941] Evaluation on proper test data (811 items): tb930 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'pstA1' "PstA component of phosphate uptake" tb1101 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1250 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb1672 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb1686 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2287 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'yjcE' "probable Na+/H+ exchanger" tb2508 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2684 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'arsA' "probable arsenical pump" tb2881 - 1,8,3,0 Small-molecule metabolism Lipid Biosynthesis Acyltransferases, Mycoloyltransferases, and phospholipid synthesis Acyltransferases, Mycoloyltransferases, and phospholipid synthesis 'cdsA' "phosphatidate cytidylyltransferase " tb3665 3,1,1,0 Cell Processes Transport/binding proteins Amino acids Amino acids 'dppB' "probable peptide transport system permease" tb3728 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Proper test Accuracy: 5/11 (45.45%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb362 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'mgtE' "putative magnesium ion transporter" tb935 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'pstC' "PstC component of phosphate uptake" tb936 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'pstA2' "PstA component of phosphate uptake" tb1236 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'sugA' "membrane protein probably involved in sugar transport" tb1282 3,1,1,0 Cell Processes Transport/binding proteins Amino acids Amino acids 'oppC' "oligopeptide transport system permease" tb1283 3,1,1,0 Cell Processes Transport/binding proteins Amino acids Amino acids 'oppB' "oligopeptide transport protein" tb1410 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb1707 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'null' "null" tb1739 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'null' "null" tb2040 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'null' "null" tb2316 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'uspA' "sugar transport protein" tb2329 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'narK1' "probable nitrite extrusion protein" tb2333 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb2443 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'dctA' "C4-dicarboxylate transport protein" tb2459 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" Training Accuracy: 15/15 (100.00%) Evaluation on test data (531 items): tb2685 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'arsB' "probable arsenical pump" tb2836 - 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'dinF' "DNA-damage-inducible protein F" tb2846 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'efpA' "putative efflux protein" tb3236 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'kefB' "probable glutathione-regulated potassium-efflux protein" tb3239 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3273 - 4,9,0,0 Other Miscellaneous phosphatases, lyases, and hydrolases Miscellaneous phosphatases, lyases, and hydrolases Miscellaneous phosphatases, lyases, and hydrolases 'null' "null" tb3331 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'sugI' "probable sugar transport protein" tb3664 3,1,1,0 Cell Processes Transport/binding proteins Amino acids Amino acids 'dppC' "probable peptide transport system permease" tb3756 - 3,5,0,0 Cell Processes Adaptations and atypical conditions Adaptations and atypical conditions Adaptations and atypical conditions 'proZ' "transport system permease" tb3757 - 3,5,0,0 Cell Processes Adaptations and atypical conditions Adaptations and atypical conditions Adaptations and atypical conditions 'proW' "transport system permease" Test Accuracy: 5/10 (50.00%) Application to new data (1023 items): tb2060 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 1 ------------------ Rule 40: (12, lift 17.3) amino_acid_pair_ratio_yi <= 4.3 [hom( A ),keyword( A ,transmembrane),mol_wt_rule( A ,3),classification( A ,bacteria)] = 1 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 0 [hom( A ),e_val_rule( A ,5),amino_acid_ratio_rule(s,3),species( A ,bacillus_subtilis)] = 0 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 1 -> class 'function2(Transport/binding proteins )' [0.929] Evaluation on proper test data (811 items): tb929 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'pstC2' "membrane-bound component of phosphate transport system" tb1250 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb1625 - 4,10,0,0 Other Cyclases Cyclases Cyclases 'null' "null" tb1672 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2281 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'pitB' "phosphate permease" tb3476 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'kgtP' "sugar transport protein" tb3665 3,1,1,0 Cell Processes Transport/binding proteins Amino acids Amino acids 'dppB' "probable peptide transport system permease" tb3728 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3775 - 2,2,5,0 Macromolecule metabolism Degradation of macromolecules Esterases and lipases Esterases and lipases 'lipE' "probable hydrolase" tb3921 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Proper test Accuracy: 5/10 (50.00%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb545 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'pitA' "low-affinity inorganic phosphate transporter" tb783 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb936 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'pstA2' "PstA component of phosphate uptake" tb1200 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'null' "null" tb1236 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'sugA' "membrane protein probably involved in sugar transport" tb1410 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb1819 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb1902 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'nanT' "probable sialic acid transporter " tb2040 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'null' "null" tb2333 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb2398 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'cysW' "sulphate transport system permease protein" tb2459 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" Training Accuracy: 12/12 (100.00%) Evaluation on test data (531 items): tb2685 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'arsB' "probable arsenical pump" tb2846 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'efpA' "putative efflux protein" tb3239 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3331 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'sugI' "probable sugar transport protein" Test Accuracy: 3/4 (75.00%) Application to new data (1023 items): tb2435 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" Total: 1 ------------------ Rule 42: (9, lift 16.9) [hom( A ),keyword( A ,membrane)] = 0 [hom( A ),keyword( A ,plasmid),e_val_rule( A ,1)] = 1 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(c,1),keyword( A ,transmembrane),mol_wt_rule( A ,4)] = 0 [hom( A ),keyword( A ,transmembrane),amino_acid_ratio_rule(w,1),classification( A ,bacteria),e_val_rule( A ,1)] = 1 -> class 'function2(Transport/binding proteins )' [0.909] Evaluation on proper test data (811 items): tb92 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpA' "cation-transporting ATPase" tb969 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpV' "cation transport ATPase" tb1469 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpD' "probable cadmium-transporting ATPase" tb1997 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpF' "probable cation transport ATPase " tb2723 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'null' "null" tb3743 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'null' "null" Proper test Accuracy: 6/6 (100.00%) Application to new data (498 items): tb1357 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 1 Evaluation on training data (1060 items): tb103 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpB' "cation transport ATPase" tb107 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpI' "probable magnesium transport ATPase" tb425 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpH' "C-terminal region putative cation-transporting ATPase" tb849 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb908 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpE' "probable cation transport ATPase" tb1030 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'kdpB' "potassium-transporting ATPase B chain" tb1607 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'chaA' "putative calcium/proton antiporter" tb1992 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpG' "probable cation transport ATPase" tb2443 3,1,3,0 Cell Processes Transport/binding proteins Carbohydrates, organic acids and alcohols Carbohydrates, organic acids and alcohols 'dctA' "C4-dicarboxylate transport protein" Training Accuracy: 9/9 (100.00%) Evaluation on test data (531 items): tb2782 - 2,2,3,0 Macromolecule metabolism Degradation of macromolecules Proteins, peptides and glycopeptides Proteins, peptides and glycopeptides 'pepR' "protease/peptidase, M16 family (insulinase)" tb3270 3,1,2,0 Cell Processes Transport/binding proteins Cations Cations 'ctpC' "cation transport ATPase" tb3578 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'arsB2' "probable arsenical pump" Test Accuracy: 2/3 (66.67%) Application to new data (1023 items): Total: 0 ------------------ Rule 43: (4, lift 15.5) [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 1 [hom( A ),e_val_rule( A ,4),amino_acid_ratio_rule(n,2),species( A ,bacillus_subtilis)] = 1 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),keyword( A ,plasmid),mol_wt_rule( A ,4)] = 0 -> class 'function2(Transport/binding proteins )' [0.833] Evaluation on proper test data (811 items): tb261 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'narK3' "nitrite extrusion protein1 " tb522 3,1,1,0 Cell Processes Transport/binding proteins Amino acids Amino acids 'gabP' "probable 4-amino butyrate transporter" tb1704 3,1,1,0 Cell Processes Transport/binding proteins Amino acids Amino acids 'cycA' "transport of D-alanine, D-serine and glycine" tb2127 3,1,1,0 Cell Processes Transport/binding proteins Amino acids Amino acids 'ansP' "L-asparagine permease" tb2320 3,1,1,0 Cell Processes Transport/binding proteins Amino acids Amino acids 'rocE' "arginine/ornithine transporter" tb2456 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" Proper test Accuracy: 5/6 (83.33%) Application to new data (498 items): tb2626 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 1 Evaluation on training data (1060 items): tb267 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'narU' "similar to nitrite extrusion protein 2" tb346 3,1,1,0 Cell Processes Transport/binding proteins Amino acids Amino acids 'aroP2' "probable aromatic amino acid permease" tb849 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" tb1737 3,1,4,0 Cell Processes Transport/binding proteins Anions Anions 'narK2' "nitrite extrusion protein " Training Accuracy: 4/4 (100.00%) Evaluation on test data (531 items): tb2690 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb2994 3,1,6,0 Cell Processes Transport/binding proteins Efflux proteins Efflux proteins 'null' "null" Test Accuracy: 1/2 (50.00%) Application to new data (1023 items): tb2406 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3365 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 2 ------------------ Rule 48: (15, lift 19.2) [hom( A ),species( A ,escherichia_coli)] = 0 [hom( A ),classification( A ,eukaryota),amino_acid_ratio_rule(x,1)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),amino_acid_ratio_rule(r,5)] = 1 [hom( A ),e_val_rule( A ,5),amino_acid_ratio_rule(w,1),species( A ,bacillus_subtilis)] = 0 [hom( A ),mol_wt_rule( A ,4),amino_acid_ratio_rule(l,5),e_val_rule( A ,2)] = 0 [hom( A ),e_val_rule( A ,1),amino_acid_ratio_rule(l,5),classification( A ,bacteria),mol_wt_rule( A ,2)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),classification( A ,gamma_subdivision),amino_acid_ratio_rule(y,3)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),e_val_rule( A ,2),amino_acid_ratio_rule(t,3),classification( A ,gamma_subdivision)] = 0 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(v,5),classification( A ,bacteria),mol_wt_rule( A ,2),classification( A ,proteobacteria)] = 0 -> class 'function2(IS elements_ Repeated sequences_ and Phage )' [0.941] Evaluation on proper test data (811 items): tb606 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1536' "transposase" tb771 - 2,2,6,0 Macromolecule metabolism Degradation of macromolecules Aromatic hydrocarbons Aromatic hydrocarbons 'null' "null" tb922 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1535' "transposase" tb1001 - 1,1,2,0 Small-molecule metabolism Degradation Amino acids and amines Amino acids and amines 'arcA' "arginine deiminase" tb1041 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS-like' "null" tb1370 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb1757 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb1763 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb1851 - 1,1,2,0 Small-molecule metabolism Degradation Amino acids and amines Amino acids and amines 'ureF' "urease accessory protein" tb2062 - 1,7,13,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Cobalamin Cobalamin 'cobN' "cobalt insertion " tb2072 - 1,7,13,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Cobalamin Cobalamin 'cobL' "probable methyltransferase" tb2105 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2177 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1558' "null" tb2266 - 4,6,0,0 Other Cytochrome P450 enzymes Cytochrome P450 enzymes Cytochrome P450 enzymes 'null' "null" tb2278 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2648 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2815 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3186 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3254 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3381 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3713 - 1,7,13,0 Small-molecule metabolism Biosynthesis of cofactors, prosthetic groups and carriers Cobalamin Cobalamin 'cobQ2' "possible cobyric acid synthase" Proper test Accuracy: 13/21 (61.90%) Application to new data (498 items): tb434 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb574 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb627 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb811 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1314 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1647 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2910 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2961 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 8 Evaluation on training data (1060 items): tb795 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb797 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1547' "null" tb1034 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1560' "null" tb1042 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS-like' "null" tb1055 4,2,3,0 Other IS elements, Repeated sequences, and Phage Phage-related functions Phage-related functions 'null' "null" tb1149 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS-like' "null" tb1150 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS-like' "null" tb1313 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1557' "transposase" tb2013 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1607' "transposase" tb2014 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1607' "transposase" tb2085 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1556' "putative transposase" tb2168 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2354 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2424 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1558' "null" tb2480 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" Training Accuracy: 15/15 (100.00%) Evaluation on test data (531 items): tb2666 4,2,1,2 Other IS elements, Repeated sequences, and Phage IS elements IS1081 'IS1081' "null" tb2791 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1602' "transposase" tb2813 - 3,4,0,0 Cell Processes Protein and peptide secretion Protein and peptide secretion Protein and peptide secretion 'null' "null" tb2885 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1539' "transposase" tb2978 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1538' "transposase" tb3184 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3317 - 1,2,3,0 Small-molecule metabolism Energy Metabolism TCA cycle TCA cycle 'sdhD' "succinate dehydrogenase D subunit" tb3325 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3386 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1560' "null" tb3387 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1560' "null" tb3431 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1552' "null" tb3474 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3566 - 1,3,1,0 Small-molecule metabolism Central intermediary metabolism General General 'nhoA' "N-hydroxyarylamine o-acetyltransferase" tb3782 - 2,3,2,0 Macromolecule metabolism Cell envelope Surface polysaccharides, lipopolysaccharides, proteins and antigens Surface polysaccharides, lipopolysaccharides, proteins and antigens 'rfbE' "similar to rhamnosyl transferase" tb3798 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1557' "transposase" tb3827 4,2,1,3 Other IS elements, Repeated sequences, and Phage IS elements Others 'IS1537' "transposase" Test Accuracy: 12/16 (75.00%) Application to new data (1023 items): tb595 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb597 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb825 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb919 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1024 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb1378 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb1953 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2008 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2042 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2311 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2478 - 6,0,0,0 Unknowns Unknowns Unknowns Unknowns 'null' "null" tb2742 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2955 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3179 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3860 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 15 ------------------ Rule 49: (6, lift 17.8) amino_acid_pair_ratio_hs <= 0 [hom( A ),species( A ,escherichia_coli)] = 1 [hom( A ),classification( A ,eukaryota),classification( A ,fungi)] = 0 [hom( A ),e_val_rule( A ,4),amino_acid_ratio_rule(g,5),species( A ,homo_sapiens)] = 1 -> class 'function2(IS elements_ Repeated sequences_ and Phage )' [0.875] Evaluation on proper test data (811 items): tb50 - 2,3,3,0 Macromolecule metabolism Cell envelope Murein sacculus and peptidoglycan Murein sacculus and peptidoglycan 'ponA1' "penicillin-bonding protein" tb2167 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3570 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" Proper test Accuracy: 1/3 (33.33%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb796 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2106 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2279 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2355 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2479 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb2649 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" Training Accuracy: 6/6 (100.00%) Evaluation on test data (531 items): tb2814 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3185 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3187 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3326 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" tb3475 4,2,1,1 Other IS elements, Repeated sequences, and Phage IS elements IS6110 'IS6110' "null" Test Accuracy: 5/5 (100.00%) Application to new data (1023 items): Total: 0 ------------------ Rule 51: (3, lift 16.3) [hom( A ),species( A ,escherichia_coli)] = 1 [hom( A ),classification( A ,eukaryota),classification( A ,fungi)] = 0 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 0 [hom( A ),mol_wt_rule( A ,5),amino_acid_ratio_rule(w,1),e_val_rule( A ,1)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,firmicutes),classification( A ,bacillus),classification( A ,bacillaceae),mol_wt_rule( A ,5),amino_acid_ratio_rule(w,1)] = 1 -> class 'function2(IS elements_ Repeated sequences_ and Phage )' [0.800] Evaluation on proper test data (811 items): Proper test Accuracy: 0/0 (0.00%) Application to new data (498 items): Total: 0 Evaluation on training data (1060 items): tb1701 4,2,3,0 Other IS elements, Repeated sequences, and Phage Phage-related functions Phage-related functions 'xerD' "integrase/recombinase" tb2309 4,2,3,0 Other IS elements, Repeated sequences, and Phage Phage-related functions Phage-related functions 'null' "null" tb2646 4,2,3,0 Other IS elements, Repeated sequences, and Phage Phage-related functions Phage-related functions 'null' "null" Training Accuracy: 3/3 (100.00%) Evaluation on test data (531 items): tb2894 4,2,3,0 Other IS elements, Repeated sequences, and Phage Phage-related functions Phage-related functions 'xerC' "integrase/recombinase" tb3535 - 1,2,7,0 Small-molecule metabolism Energy Metabolism Miscellaneous oxidoreductases and oxygenases; Miscellaneous oxidoreductases and oxygenases; 'null' "null" tb3711 - 2,1,5,0 Macromolecule metabolism Synthesis and modification of macromolecules DNA replication, repair, recombination and restriction/modification DNA replication, repair, recombination and restriction/modification 'dnaQ' "DNA polymerase III epsilon chain" tb3751 4,2,3,0 Other IS elements, Repeated sequences, and Phage Phage-related functions Phage-related functions 'null' "null" Test Accuracy: 2/4 (50.00%) Application to new data (1023 items): tb343 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3856 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 2 ------------------ Rule 55: (72/1, lift 14.5) amino_acid_pair_ratio_ct <= 2.2 [hom( A ),e_val_rule( A ,1),amino_acid_ratio_rule(r,4)] = 0 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,4)] = 1 [hom( A ),species( A ,mycobacterium_tuberculosis),mol_wt_rule( A ,3),keyword( A ,transmembrane)] = 1 [hom( A ),e_val_rule( A ,2),amino_acid_ratio_rule(l,5),classification( A ,eukaryota)] = 0 [hom( A ),classification( A ,bacteria),classification( A ,proteobacteria),keyword( A ,plasmid),mol_wt_rule( A ,4)] = 0 -> class 'function2(PE and PPE families )' [0.973] Evaluation on proper test data (811 items): tb109 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb152 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb278 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb286 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb304 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb305 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb354 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb650 - 1,10,1,0 Small-molecule metabolism Broad regulatory functions Repressors/activators Repressors/activators 'null' "null" tb742 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb754 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb755 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb872 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb916 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1039 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1088 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1196 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1214 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1361 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1386 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1387 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1396 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1548 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1705 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1787 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1788 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1790 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1791 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1800 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1803 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1808 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1809 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1918 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1983 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb2107 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb2123 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb2154 - 3,3,0,0 Cell Processes Cell division Cell division Cell division 'ftsW' "membrane protein (shape determination)" tb2162 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb2328 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb2371 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb2408 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb2487 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb2519 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb2591 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb2615 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb2634 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3018 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3344 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3350 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3388 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3426 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3477 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb3514 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3595 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3650 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb3652 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3738 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3739 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3812 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" Proper test Accuracy: 56/58 (96.55%) Application to new data (498 items): tb387 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2366 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2626 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 3 Evaluation on training data (1060 items): tb96 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb124 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb151 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb159 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb160 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb256 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb279 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb280 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb285 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb297 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb335 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb355 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb388 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb442 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb453 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb532 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb578 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb676 - 2,3,4,0 Macromolecule metabolism Cell envelope Conserved membrane proteins Conserved membrane proteins 'mmpL5' "conserved large membrane protein" tb746 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb747 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb832 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb833 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb834 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb878 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb915 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb977 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb978 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb980 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1040 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1067 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1068 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1087 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1089 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1091 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1135 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1168 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1169 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1172 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1195 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1243 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1325 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1430 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1441 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1450 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1452 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1468 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1646 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1651 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1706 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1753 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1759 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "wag22, member of the PGRS" tb1768 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1789 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1801 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1802 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1806 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb1807 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb1818 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb1840 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb2098 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb2099 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb2108 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb2126 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb2340 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb2352 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb2353 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb2356 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb2396 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb2430 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb2431 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb2490 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb2608 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" Training Accuracy: 71/72 (98.61%) Evaluation on test data (531 items): tb2741 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb2768 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb2769 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb2770 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb2853 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb2892 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3021 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3022 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3097 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb3135 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3136 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3144 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3159 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3343 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3345 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3347 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3367 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3425 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3429 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3478 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3507 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3508 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3511 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3512 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3532 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3533 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3539 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb3558 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3590 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3621 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3622 4,3,1,1 Other PE and PPE families PE family PE subfamily 'PE' "null" tb3653 4,3,1,2 Other PE and PPE families PE family PE_PGRS subfamily 'PE_PGRS' "null" tb3873 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" tb3887 - 2,3,5,0 Macromolecule metabolism Cell envelope Other membrane proteins Other membrane proteins 'null' "null" tb3892 4,3,2,0 Other PE and PPE families PPE family PPE family 'PPE' "null" Test Accuracy: 34/35 (97.14%) Application to new data (1023 items): tb341 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb378 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb2083 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3616 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" tb3881 - 5,0,0,0 Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals Conserved hypotheticals 'null' "null" Total: 5 ---------------