%% Facts %genome_dir('/mnt/home/knw/Robot_Scientist/KEGG/genomes/'). %sequence_dir('/mnt/home/knw/Robot_Scientist/KEGG/sequences/'). genome_dir('/home/condor/enzyme_files/mnt/home/knw/Robot_Scientist/KEGG/genomes/'). sequence_dir('/home/condor/enzyme_files/mnt/home/knw/Robot_Scientist/KEGG/sequences/'). %% added by maria to output all the likely orfs %output_dir('find_orfs/'). output_dir('/home/condor/enzyme_files/find_orfs/'). match_method(fasta,'fasta34 -q '). match_method(ssearch,'ssearch34 -q '). %% Change by maria to include BLAST %% genes already searched before cluster node crashed on 3/12/2006 done_genes(ThisEnzyme,EList):- (ThisEnzyme == '1.1.1.17', EList=['bab_bbp516','bas_BUsg551','bha_BH3851','bsu_BG11216','buc_BU571','cac_CAC0157','ecc_c4417','ece_Z5024','ecj_JW3574', 'eco_b3600','ecs_ECs4476','efa_EF0413','lla_L33416','lpl_0233','lpl_lp','mmy_0017','mmy_MSC','mpn_MPN652','mpu_7500', 'mpu_MYPU','oih_OB2600','pmu_PM1062','sam_MW2085','sau_SA1963','sav_SAV2159','sfl_SF3634','sfx_S4134','smu_SMU.1182', 'spn_SP0397','spr_spr0359','stm_STM3686','stt_t3833','sty_STY4110','tte_TTE0342','vch_VCA1046','vpa_VP0369','vvu_VV10639', 'vy_VV0504','ype_YPO4067','ypk_y4086'] ; %% node 20 ThisEnzyme == '2.7.7.3', EList=['pai_PAE0887','pfu_PF1084','pab_PAB0944','pho_PH0624','pai_PAE0887','pfu_PF1084','pab_PAB0944','pho_PH0624'] ; %% node 08 ThisEnzyme == '3.1.3.5', EList=['afu_AF0876','mth_MTH1492','dra_DR0505','mpu_MYPU','mpu_0550','afu_AF0876','mth_MTH1492','dra_DR0505','mpu_MYPU','mpu_0550','afu_AF0876','mth_MTH1492','dra_DR0505','mpu_MYPU','mpu_0550','afu_AF0876','mth_MTH1492','dra_DR0505','mpu_MYPU','mpu_0550'] ; %% node 11 ThisEnzyme == '4.1.1.36', EList=['aae_aq','aae_815','dra_DR0579','pgi_PG1851','bth_BT1362','rba_RB7087','fnu_FN0711','mpa_MAP1125','mbo_Mb1426','mtc_MT1436','mtu_Rv1391','oih_OB1504','bca_BCE3912','bce_BC3867','ban_BA4007','bha_BH2510','bsu_BG13388','rpa_RPA0081','bja_bll0759','bms_BRA1064','bme_BMEII0235','atc_AGR','atc_C','atc_552','atu_Atu0316','mlo_mlr3167','gsu_GSU1124','neu_NE1463','bpa_BPP1982','bpe_BP1751','rso_RSc2461','nma_NMA1916','nme_NMB1658','pst_PSPTO0085','ppu_PP5285','pae_PA5320','vpa_VP0181','vvy_VV0283','vvu_VV10828','vch_VC0215','xac_XAC3914','xcc_XCC3859','xft_PD0118','xfa_XF0149','pmu_PM1153','hdu_HD0733','hin_HI0953','wbr_WGLp402','aae_aq','aae_815','dra_DR0579','pgi_PG1851','bth_BT1362','rba_RB7087','fnu_FN0711','mpa_MAP1125','mbo_Mb1426','mtc_MT1436','mtu_Rv1391','oih_OB1504','bca_BCE3912','bce_BC3867','ban_BA4007','bha_BH2510','bsu_BG13388','rpa_RPA0081','bja_bll0759','bms_BRA1064','bme_BMEII0235','atc_AGR','atc_C','atc_552','atu_Atu0316','mlo_mlr3167','gsu_GSU1124','neu_NE1463','bpa_BPP1982','bpe_BP1751','rso_RSc2461','nma_NMA1916','nme_NMB1658','pst_PSPTO0085','ppu_PP5285','pae_PA5320','vpa_VP0181','vvy_VV0283','vvu_VV10828','vch_VC0215','xac_XAC3914','xcc_XCC3859','xft_PD0118','xfa_XF0149','pmu_PM1153','hdu_HD0733','hin_HI0953','wbr_WGLp402','aae_aq','aae_815','dra_DR0579','pgi_PG1851','bth_BT1362','rba_RB7087','fnu_FN0711','mpa_MAP1125','mbo_Mb1426','mtc_MT1436','mtu_Rv1391','oih_OB1504','bca_BCE3912','bce_BC3867','ban_BA4007','bha_BH2510','bsu_BG13388','rpa_RPA0081','bja_bll0759','bms_BRA1064','bme_BMEII0235','atc_AGR','atc_C','atc_552','atu_Atu0316','mlo_mlr3167','gsu_GSU1124','neu_NE1463','bpa_BPP1982','bpe_BP1751','rso_RSc2461','nma_NMA1916','nme_NMB1658','pst_PSPTO0085','ppu_PP5285','pae_PA5320','vpa_VP0181','vvy_VV0283','vvu_VV10828','vch_VC0215','xac_XAC3914','xcc_XCC3859','xft_PD0118','xfa_XF0149','pmu_PM1153','hdu_HD0733','hin_HI0953','wbr_WGLp402'] ; %% node 04 ThisEnzyme == '2.4.2.1', EList=['ape_APE0993','dra_DR2166','pgi_PG0558','bth_BT1881','rba_RB5437','rba_RB6588','fnu_FN0435','ape_APE0993','dra_DR2166','pgi_PG0558','bth_BT1881','rba_RB5437','rba_RB6588','fnu_FN0435'] ; %% node 12 ThisEnzyme == '6.3.2.5', EList=['aae_aq','aae_815','dra_DR0579','pgi_PG1851','bth_BT1362','rba_RB7087','fnu_FN0711','mpa_MAP1125','mbo_Mb1426','mtc_MT1436','mtu_Rv1391','oih_OB1504','bca_BCE3912','bce_BC3867','ban_BA4007','bha_BH2510','bsu_BG13388','rpa_RPA0081','bja_bll0759','bms_BRA1064','bme_BMEII0235','atc_AGR','atc_C','atc_552','atu_Atu0316','mlo_mlr3167','bba_Bd3562','gsu_GSU1124','neu_NE1463','bpa_BPP1982','bpe_BP1751','rso_RSc2461','nma_NMA1916','nme_NMB1658','pst_PSPTO0085','ppu_PP5285','pae_PA5320','vpa_VP0181','vvy_VV0283','vvu_VV10828','vch_VC0215','xac_XAC3914','xcc_XCC3859','xft_PD0118','xfa_XF0149','pmu_PM1153','hdu_HD0733','hin_HI0953','wbr_WGLp402','aae_aq','aae_815','dra_DR0579','pgi_PG1851','bth_BT1362','rba_RB7087','fnu_FN0711','mpa_MAP1125','mbo_Mb1426','mtc_MT1436','mtu_Rv1391','oih_OB1504','bca_BCE3912','bce_BC3867','ban_BA4007','bha_BH2510','bsu_BG13388','rpa_RPA0081','bja_bll0759','bms_BRA1064','bme_BMEII0235','atc_AGR','atc_C','atc_552','atu_Atu0316','mlo_mlr3167','bba_Bd3562','gsu_GSU1124','neu_NE1463','bpa_BPP1982','bpe_BP1751','rso_RSc2461','nma_NMA1916','nme_NMB1658','pst_PSPTO0085','ppu_PP5285','pae_PA5320','vpa_VP0181','vvy_VV0283','vvu_VV10828','vch_VC0215','xac_XAC3914','xcc_XCC3859','xft_PD0118','xfa_XF0149','pmu_PM1153','hdu_HD0733','hin_HI0953','wbr_WGLp402','aae_aq','aae_815','dra_DR0579','pgi_PG1851','bth_BT1362','rba_RB7087','fnu_FN0711','mpa_MAP1125','mbo_Mb1426','mtc_MT1436','mtu_Rv1391','oih_OB1504','bca_BCE3912','bce_BC3867','ban_BA4007','bha_BH2510','bsu_BG13388','rpa_RPA0081','bja_bll0759','bms_BRA1064','bme_BMEII0235','atc_AGR','atc_C','atc_552','atu_Atu0316','mlo_mlr3167','bba_Bd3562','gsu_GSU1124','neu_NE1463','bpa_BPP1982','bpe_BP1751','rso_RSc2461','nma_NMA1916','nme_NMB1658','pst_PSPTO0085','ppu_PP5285','pae_PA5320','vpa_VP0181','vvy_VV0283','vvu_VV10828','vch_VC0215','xac_XAC3914','xcc_XCC3859','xft_PD0118','xfa_XF0149','pmu_PM1153','hdu_HD0733','hin_HI0953','plu_plu4866','aae_aq','aae_815','dra_DR0579','pgi_PG1851','bth_BT1362','rba_RB7087','fnu_FN0711','mpa_MAP1125','mbo_Mb1426','mtc_MT1436','mtu_Rv1391','oih_OB1504','bca_BCE3912','bce_BC3867','ban_BA4007','bha_BH2510','bsu_BG13388','rpa_RPA0081','bja_bll0759','bms_BRA1064','bme_BMEII0235','atc_AGR','atc_C','atc_552','atu_Atu0316','mlo_mlr3167','bba_Bd3562','gsu_GSU1124','neu_NE1463','bpa_BPP1982','bpe_BP1751','rso_RSc2461','nma_NMA1916','nme_NMB1658','pst_PSPTO0085','ppu_PP5285','pae_PA5320','vpa_VP0181','vvy_VV0283','vvu_VV10828','vch_VC0215','xac_XAC3914','xcc_XCC3859','xft_PD0118','xfa_XF0149','pmu_PM1153','hdu_HD0733','hin_HI0953','wbr_WGLp402'] ; %% node 22 ThisEnzyme == '2.7.1.35', EList=['dra_DRA0184','bth_BT4458','blo_BL0934','poy_PAM434','oih_OB1040','bca_BCE5542','bce_BC5413','ban_BA5663','bsu_BG10598','rpa_RPA2799','bja_blr4233','bms_BR1830','bme_BMEI0221','atc_AGR','atc_C','atc_4518','atu_Atu2487','mlo_mlr4132','bpa_BPP2900','bpe_BP1321','pst_PSPTO5521','ppu_PP5357','pae_PA5516','vpa_VPA1632','vvy_VVA0065','vvu_VV21237','xac_XAC1524','xcc_XCC1476','pmu_PM0290','hin_HI0405','plu_plu2595','ypk_y1967','ype_YPO2368','dra_DRA0184','bth_BT4458','blo_BL0934','poy_PAM434','oih_OB1040','bca_BCE5542','bce_BC5413','ban_BA5663','bsu_BG10598','rpa_RPA2799','bja_blr4233','bms_BR1830','bme_BMEI0221','atc_AGR','atc_C','atc_4518','atu_Atu2487','mlo_mlr4132','bpa_BPP2900','bpe_BP1321','pst_PSPTO5521','ppu_PP5357','pae_PA5516','vpa_VPA1632','vvy_VVA0065','vvu_VV21237','xac_XAC1524','xcc_XCC1476','pmu_PM0290','hin_HI0405','plu_plu2595','ypk_y1967','ype_YPO2368'] ; %% node 05 ThisEnzyme == '2.7.1.56', EList=['dra_DRB0074','fnu_FN1440','mmy_MSC','mmy_0647','mmy_MSC','mmy_0832','mpe_MYPE7750','mpn_MPN079','dra_DRB0074','fnu_FN1440','mmy_MSC','mmy_0647','mmy_MSC','mmy_0832','mpe_MYPE7750','mpn_MPN079'] ; %% node 13 ThisEnzyme == '2.7.7.2', EList=['aae_aq','aae_139','dra_DR1008','pgi_PG0957','bth_BT2543','pmt_PMT0364','pmm_PMM1273','pma_Pro1347','ana_alr4848','gvi_gll0217','fnu_FN0707','blo_BL1619'] ; %% node 17 ThisEnzyme == '2.3.1.51', EList=['pgi_PG1249','bth_BT0243','pmt_PMT1998','pmm_PMM0138','pma_Pro0160','ana_alr0241','gvi_gll3009','blo_BL1424','pgi_PG1249','bth_BT0243','pmt_PMT1998','pmm_PMM0138','pma_Pro0160','ana_alr0241','gvi_gll3009','blo_BL1424'] ; %% node 35 ThisEnzyme == '2.7.1.21', EList=['pai_PAE2453','hal_VNG1515G','dra_DR1984','pgi_PG0925','bth_BT2275','rba_RB8399','poy_PAM104','mmy_MSC','mmy_0149','mga_MGA','mga_0502','mpe_MYPE10320','mpu_MYPU','mpu_1450','mpn_MPN044','pai_PAE2453','hal_VNG1515G','dra_DR1984','pgi_PG0925','bth_BT2275','rba_RB8399','poy_PAM104','mmy_MSC','mmy_0149','mga_MGA','mga_0502','mpe_MYPE10320','mpu_MYPU','mpu_1450','mpn_MPN044','pai_PAE2453','hal_VNG1515G','dra_DR1984','pgi_PG0925','bth_BT2275','rba_RB8399','poy_PAM104','mmy_MSC','mmy_0149','mga_MGA','mga_0502','mpe_MYPE10320','mpu_MYPU','mpu_1450','mpn_MPN044'] ; %% node 21 ThisEnzyme == '6.3.2.12', EList=[] ; %% node 06 ThisEnzyme == '1.17.4.2', EList=[] ; %% node 23 ThisEnzyme == '2.7.4.16', EList=['pai_PAE1022','pai_PAE1024','ape_APE0235','pfu_PF1877','pab_PAB2358','pho_PH1833','pai_PAE1022','pai_PAE1024','ape_APE0235','pfu_PF1877','pab_PAB2358','pho_PH1833','pai_PAE1022','pai_PAE1024','ape_APE0235','pfu_PF1877','pab_PAB2358','pho_PH1833'] ; %% node 19 ThisEnzyme == '2.1.1.13', EList=['dra_DR0966','bth_BT0180','pmt_PMT0729','pmm_PMM0877','pma_Pro0959','ana_alr0308','gvi_gll0477','rba_RB9857','fnu_FN0163','mpa_MAP1859c','mle_ML1307','mbo_Mb2148c','mtc_MT2183','mtu_Rv2124c','bca_BCE4332','bca_BCE4333','bce_BC4250','bce_BC4251','ban_BA4478','ban_BA4479','bha_BH1630','rpa_RPA3702','bja_bll1418','bms_BR0188','bme_BMEI1759','atc_AGR','atc_C','atc_3907','atu_Atu2155','gsu_GSU2921','wsu_WS1234','neu_NE1623','bpa_BPP3983','bpe_BP3594','rso_RSc0294','rso_RSc0295','pst_PSPTO2732','ppu_PP2375','pae_PA1843','vpa_VP2717','vvy_VV2960','vvu_VV11423','vch_VC0390','xac_XAC1559','xac_XAC1560','xcc_XCC1511','xcc_XCC1512','ypk_y0020','ype_YPO3722','ddi_DDB0230138','dra_DR0966','bth_BT0180','pmt_PMT0729','pmm_PMM0877','pma_Pro0959','ana_alr0308','gvi_gll0477','rba_RB9857','fnu_FN0163','mpa_MAP1859c','mle_ML1307','mbo_Mb2148c','mtc_MT2183','mtu_Rv2124c','bca_BCE4332','bca_BCE4333','bce_BC4250','bce_BC4251','ban_BA4478','ban_BA4479','bha_BH1630','rpa_RPA3702','bja_bll1418','bms_BR0188','bme_BMEI1759','atc_AGR','atc_C','atc_3907','atu_Atu2155','gsu_GSU2921','wsu_WS1234','neu_NE1623','bpa_BPP3983','bpe_BP3594','rso_RSc0294','rso_RSc0295','pst_PSPTO2732','ppu_PP2375','pae_PA1843','vpa_VP2717','vvy_VV2960','vvu_VV11423','vch_VC0390','xac_XAC1559','xac_XAC1560','xcc_XCC1511','xcc_XCC1512','ypk_y0020','ype_YPO3722','ddi_DDB0230138'] ; %% node 28 ThisEnzyme == '2.3.1.30', EList=['hal_VNG1481G','mma_MM2939','mma_MM3269','mac_MA2721','mac_MA3442','pgi_PG0115','bth_BT0607','bth_BT3256','pmt_PMT0117','pmm_PMM1638','pma_Pro1800','ana_all4037','ana_alr1404','gvi_gll1785','gvi_glr2514','rba_RB5098','mpa_MAP2124','mle_ML0838','mbo_Mb2363','mtc_MT2398','mtu_Rv2335','oih_OB0098','bca_BCE0088','bce_BC0109','ban_BA0088','bha_BH0110','bsu_BG10155','rpa_RPA1425','rpa_RPA3429','bja_bll5586','bja_bll7158','bja_blr2371','bms_BR1262','bme_BMEI0734','atc_AGR','atc_C','atc_2895','atu_Atu1571','mlo_mlr0175','bba_Bd3116','gsu_GSU2572','wsu_WS0553','hhe_HH1234','hpj_jhp1133','hpy_HP1210','neu_NE0575','neu_NE1695','bpa_BPP2351','bpe_BP1972','rso_RSc1162','rso_RSp1439','nma_NMA0742','nme_NMB0560','pst_PSPTO1421','pst_PSPTO5178','ppu_PP0228','ppu_PP0840','pae_PA3816','vpa_VP2833','vvy_VV3088','vvu_VV11276','vch_VC2649','pmu_PM1430','hdu_HD0659','hin_HI0606','bfl_Bfl603','bab_bbp051','bas_BUsg051','buc_BU054','plu_plu4837','ypk_y0072','ype_YPO0070','hal_VNG1481G','mma_MM2939','mma_MM3269','mac_MA2721','mac_MA3442','pgi_PG0115','bth_BT0607','bth_BT3256','pmt_PMT0117','pmm_PMM1638','pma_Pro1800','ana_all4037','ana_alr1404','gvi_gll1785','gvi_glr2514','rba_RB5098','mpa_MAP2124','mle_ML0838','mbo_Mb2363','mtc_MT2398','mtu_Rv2335','oih_OB0098','bca_BCE0088','bce_BC0109','ban_BA0088','bha_BH0110','bsu_BG10155','rpa_RPA1425','rpa_RPA3429','bja_bll5586','bja_bll7158','bja_blr2371','bms_BR1262','bme_BMEI0734','atc_AGR','atc_C','atc_2895','atu_Atu1571','mlo_mlr0175','bba_Bd3116','gsu_GSU2572','wsu_WS0553','hhe_HH1234','hpj_jhp1133','hpy_HP1210','neu_NE0575','neu_NE1695','bpa_BPP2351','bpe_BP1972','rso_RSc1162','rso_RSp1439','nma_NMA0742','nme_NMB0560','pst_PSPTO1421','pst_PSPTO5178','ppu_PP0228','ppu_PP0840','pae_PA3816','vpa_VP2833','vvy_VV3088','vvu_VV11276','vch_VC2649','pmu_PM1430','hdu_HD0659','hin_HI0606','bfl_Bfl603','bab_bbp051','bas_BUsg051','buc_BU054','plu_plu4837','ypk_y0072','ype_YPO0070'] ; %% node 39 ThisEnzyme == '3.5.99.6', EList=['dra_DRA0154','pgi_PG0803','pgi_PG1285','bth_BT0258','bth_BT3587','bth_BT4127','pmt_PMT1424','ana_all0727','rba_RB1355','rba_RB2532','rba_RB3340','rba_RB3556','fnu_FN1143','blo_BL1343','mmy_MSC','mmy_0129','mmy_MSC','mmy_0821','mpe_MYPE1760','mpu_MYPU','mpu_3620','oih_OB0611','bca_BCE4121','bce_BC4054','ban_BA4273','bha_BH0420','bsu_BG12631','bsu_BG12746','bms_BRA0912','bme_BMEII0384','atc_AGR','atc_C','atc_4724','atu_Atu2607','mlo_mll4767','pae_PA3759','vpa_VPA0038','vvy_VVA0028','vvu_VV21200','vch_VCA1025','xac_XAC0714','xcc_XCC3411','xft_PD0683','xfa_XF1464','pmu_PM0875','hdu_HD1847','hin_HI0141','bfl_Bfl323','plu_plu1317','ypk_y1202','ype_YPO2627','dra_DRA0154','pgi_PG0803','pgi_PG1285','bth_BT0258','bth_BT3587','bth_BT4127','pmt_PMT1424','ana_all0727','rba_RB1355','rba_RB2532','rba_RB3340','rba_RB3556','fnu_FN1143','blo_BL1343','mmy_MSC','mmy_0129','mmy_MSC','mmy_0821','mpe_MYPE1760','mpu_MYPU','mpu_3620','oih_OB0611','bca_BCE4121','bce_BC4054','ban_BA4273','bha_BH0420','bsu_BG12631','bsu_BG12746','bms_BRA0912','bme_BMEII0384','atc_AGR','atc_C','atc_4724','atu_Atu2607','mlo_mll4767','pae_PA3759','vpa_VPA0038','vvy_VVA0028','vvu_VV21200','vch_VCA1025','xac_XAC0714','xcc_XCC3411','xft_PD0683','xfa_XF1464','pmu_PM0875','hdu_HD1847','hin_HI0141','bfl_Bfl323','plu_plu1317','ypk_y1202','ype_YPO2627'] ). match_method(psiblast,'/usr/local/blast/bin/blastpgp -d "/data/blast/data/nr /data/blast/data/SCE/s.cerevisiae.pep" -e 1 -F F -h 0.002 -t 1 '). %% writelist/2, to be added to utilities.pl writelist(_Stream,[]):-!. writelist(Stream,[H|T]):- write(Stream,H),nl(Stream),!, writelist(Stream,T). % Check if String is an orf_header orf_header(String) :- name(String,[F|_Rest]), name('>',[F]). % find the Orf in the orf_header String correct_orf_field(Orf,String) :- orf_header(String), find_in_string(Orf,String). % If you are at the end of stream and encounter '' do nothing string_from_file(Stream,'',MoreFile) :- at_end_of_stream(Stream), MoreFile = 'false'. % read a line of the sequence from Stream as a string until you reach the end of the stream string_from_file(Stream,String,MoreFile) :- read_line_to_codes(Stream,Codes), name(String,Codes), ( at_end_of_stream(Stream), MoreFile = 'false' ; MoreFile = 'true'). % Get all the string lines into a list of strings (split at ' ') all_words_from_file(_Stream,PrevString,SoFar,Strings,MoreFile) :- MoreFile == 'false', separated_string(' ',PrevString,Chain), chain_list(Chain,Words), conc(SoFar,Words,Strings). all_words_from_file(Stream,PrevString,SoFar,Strings,_MoreFile) :- separated_string(' ',PrevString,Chain), chain_list(Chain,Words), conc(SoFar,Words,NewSoFar), string_from_file(Stream,NewString,NewMoreFile),!, all_words_from_file(Stream,NewString,NewSoFar,Strings,NewMoreFile). % concatenate strings together all_strings_from_file(_Stream,PrevString,SoFar,Strings,MoreFile) :- MoreFile == 'false', conc(SoFar,[PrevString],Strings). all_strings_from_file(Stream,PrevString,SoFar,Strings,_MoreFile) :- string_from_file(Stream,NewString,NewMoreFile),!, all_strings_from_file(Stream,NewString,[PrevString|SoFar],Strings,NewMoreFile). strings_from_file(File,Words) :- open(File,read,Stream), all_strings_from_file(Stream,'',[],Words,'true'), close(Stream). words_from_file(File,Words) :- open(File,read,Stream), all_words_from_file(Stream,'',[],Words,'true'), close(Stream). sequence_information(Organism,File,SFacts) :- strings_from_file(File,Words), words_with_string(Organism,Words,[],Found), reverse(Found,RFound), all_yeast_sequence_info(RFound,[],Information), make_sequence_rankings(1,Information,[],SFacts). %% Maria's version of sequence_information % here sequence_informationm(Enzyme,File) :- %construct Outfile, from File output_dir(OutDir), name(File,FILE), name(OutDir,OUTDIR), append(OUTDIR,MIDDLE,FILE), append(NAME,[46|_],MIDDLE),!, name(Name,NAME), multiple_atom_concat([OutDir,'enz','_',Enzyme,'.txt'],OutFile), open(OutFile,append,Stream), format(Stream,'~q ~n',[Name]), close(Stream), multiple_atom_concat(['grep -E "(sce:|round)" ',File,' >> ', OutFile],Command1), unix(system(Command1)). % read in sceinfo and split the lines into predicates (Round, ORF, E-value) %% Maria's version of sequence_information_from_files sequence_information_from_filesm(_Enz,[]). sequence_information_from_filesm(Enzyme,[F|Files]) :- sequence_informationm(Enzyme,F),!, sequence_information_from_filesm(Enzyme,Files). sequence_information_from_files(_O,[],S,S). sequence_information_from_files(Organism,[F|Files],Done,SFacts) :- sequence_information(Organism,F,Facts), conc(Done,Facts,NewDone),!, sequence_information_from_files(Organism,Files,NewDone,SFacts). process_sequence_info(Rank,String,SFact) :- separated_string(' ',String,SChain), chain_list(SChain,SList), remove_nulls(SList,[],[First|Rest]), last_item(Rest,Last), SFact =..[sequence,First,Last,Rank]. make_sequence_rankings(_I,[],R,R). make_sequence_rankings(I,[S|Strings],Done,Rankings) :- process_sequence_info(I,S,SFact), significant_sequence(SFact,NewSFact), I2 is I + 1,!, make_sequence_rankings(I2,Strings,[NewSFact|Done],Rankings). make_sequence_rankings(I,[_S|Strings],Done,Rankings) :- !,make_sequence_rankings(I,Strings,Done,Rankings). words_with_string(_S,[],RDone,Found) :- reverse(RDone,Found). words_with_string(String,[Word|Words],Done,Found) :- find_in_string(String,Word),!, words_with_string(String,Words,[Word|Done],Found). words_with_string(String,[_Word|Words],Done,Found) :- !,words_with_string(String,Words,Done,Found). all_yeast_sequence_info([S|_Strings],RYInfo,YInfo) :- find_in_string('>>',S), reverse(RYInfo,YInfo). all_yeast_sequence_info([S|Strings],Done,YInfo) :- !,all_yeast_sequence_info(Strings,[S|Done],YInfo). construct_sequence(_Stream,SoFar,Sequence,String,MoreFile) :- join_string(SoFar,String,Sequence), MoreFile == 'false'. construct_sequence(_Stream,Sequence,Sequence,String,_MoreFile) :- orf_header(String). construct_sequence(Stream,SoFar,Sequence,String,_MoreFile) :- join_string(SoFar,String,NewSoFar), string_from_file(Stream,NewString,NewMoreFile),!, construct_sequence(Stream,NewSoFar,Sequence,NewString,NewMoreFile). find_and_construct_sequence(_Stream,_Orf,_Sequence,_String,_Header,MoreFile) :- MoreFile == 'false',!,fail. find_and_construct_sequence(Stream,Orf,Sequence,String,String,_MoreFile) :- correct_orf_field(Orf,String), string_from_file(Stream,NewString,NewMoreFile), construct_sequence(Stream,'',Sequence,NewString,NewMoreFile). find_and_construct_sequence(Stream,Orf,Sequence,_String,Header,_MoreFile) :- string_from_file(Stream,NewString,NewMoreFile),!, find_and_construct_sequence(Stream,Orf,Sequence,NewString,Header,NewMoreFile). sequence_from_file(Orf,File,Header,Sequence) :- open(File,read,Stream), find_and_construct_sequence(Stream,Orf,Sequence,'',Header,'true'),!, close(Stream). sequence_from_file(Orf,_File,_Header,_Sequence) :- write('no sequence found for '),write(Orf),nl,nl. sequence_from_organism(Organism,Orf,FileType,Header,Sequence) :- genome_file_type(Organism,FileType,GFile), genome_dir(Dir), multiple_atom_concat([Dir,GFile],FName), sequence_from_file(Orf,FName,Header,Sequence). get_genome_file_name(Organism,Type,FName) :- genome_file_type(Organism,Type,GFile), genome_dir(Dir), multiple_atom_concat([Dir,GFile],FName). %% Maria's version of create_sequence_file % If the sequence file already exists, don't try writing to it. create_sequence_filem(Organism,Orf,FName,FileType,_Header,_Sequence) :- sequence_dir(Dir), multiple_atom_concat([Dir,Organism,'_',Orf,'.',FileType],FName), exists_file(FName),!. %open(FName,read,Stream),!, %close(Stream). create_sequence_filem(Organism,Orf,FName,FileType,Header,Sequence) :- sequence_dir(Dir), multiple_atom_concat([Dir,Organism,'_',Orf,'.',FileType],FName), open(FName,write,Stream), write(Stream,Header), nl(Stream), write(Stream,Sequence), close(Stream). create_sequence_file(Organism,Orf,FName,FileType,Header,Sequence) :- sequence_dir(Dir), multiple_atom_concat([Dir,Organism,'_',Orf,'.',FileType],FName), open(FName,write,Stream), write(Stream,Header), nl(Stream), write(Stream,Sequence), close(Stream). create_sequence_files_and_commands([],_Type,_Method,_TG,Cmds,Cmds). create_sequence_files_and_commands([GN|GeneNames],Type,Method, TargetGenome,Done,Cmds) :- GN = gene_name(Organism,_EC,Orf,_Gene), sequence_from_organism(Organism,Orf,Type,Header,Sequence), create_sequence_file(Organism,Orf,SFName,Type,Header,Sequence), get_genome_file_name(TargetGenome,Type,TGName), sequence_dir(SDir), match_method(Method,MCString), multiple_atom_concat([SDir,Organism,'_',Orf,'.match'],OutName), multiple_atom_concat([MCString,SFName,' ',TGName,' > ',OutName],Command), write(Command),nl, unix(system(Command)),!, create_sequence_files_and_commands(GeneNames,Type,Method, TargetGenome,[OutName|Done],Cmds). create_sequence_files_and_commands([_GN|GeneNames],Type,Method, TargetGenome,Done,Cmds) :- !,create_sequence_files_and_commands(GeneNames,Type,Method, TargetGenome,Done,Cmds). %% Maria's version of create_sequence_files_and_commands create_sequence_files_and_commandsm([],_Type,_Method,_TG,Cmds,Cmds). create_sequence_files_and_commandsm([GN|GeneNames],Type,Method, TargetGenome,Done,Cmds) :- GN = gene_name(Organism,_EC,Orf,_Gene),%trace, sequence_from_organism(Organism,Orf,Type,Header,Sequence),%trace, create_sequence_filem(Organism,Orf,SFName,Type,Header,Sequence), %get_genome_file_name(TargetGenome,Type,TGName), % we don't need this as psi-blast looks at all organisms output_dir(OutDir), %% here %run_blast(OutDir,Organism,Orf,SFName,Method,[],Outfiles), run_blast_n(20,OutDir,Organism,Orf,SFName,Method,[],Outfiles), % change this from 5 to 20 for the full amount conc(Outfiles,Done,MoreOutfiles),!, create_sequence_files_and_commandsm(GeneNames,Type,Method, TargetGenome,MoreOutfiles,Cmds). % is it necessary to have the Done ones here? create_sequence_files_and_commandsm([_GN|GeneNames],Type,Method, TargetGenome,Done,Cmds) :- !,create_sequence_files_and_commandsm(GeneNames,Type,Method, TargetGenome,Done,Cmds). % Blast command that runs for as many iterations as we set it to run_blast_n(N,OutDir,Organism,Orf,SFName,Method,[],[Outname]):- multiple_atom_concat([OutDir,Organism,'_',Orf],Lemma), multiple_atom_concat([Lemma,'_',N,'.match'],Outname), % '2' in the name of the file here signals the number of iterations match_method(Method,MCString), multiple_atom_concat([Lemma,'_',N,'.check'],OutCheck), multiple_atom_concat([MCString,'-i ',SFName,' -o ',Outname,' -j ',N,' -C ',OutCheck],Command), write(Command),nl, unix(system(Command)), write('done blast'),nl,!. %% Maria's code % run_blast/7 creates the files to be placed as arguments to the blast command and calls run_blast_loop/7. % Orf is the Orf from Organism that codes for the enzyme of interest % run_blast(+SDir,+Organism,+Orf,+SFName,+Method,[],-Outfiles) run_blast(OutDir,Organism,Orf,SFName,Method,[],Outfiles):- multiple_atom_concat([OutDir,Organism,'_',Orf],Lemma), multiple_atom_concat([Lemma,'2.match'],Outname), % '2' in the name of the file here signals the number of iterations run_blast_loop(2,SFName,Outname,Method,Lemma,[],Outfiles). % run_blast_loop/7 % run_blast_loop(+It,+InName,+Outname,+Method,+Lemma,[],-Outfiles) % 1st run of run_blast_loop/7 run_blast_loop(2,InName,Outname,Method,Lemma,[],Outfiles):-!, match_method(Method,MCString), multiple_atom_concat([Lemma,'1.check'],OutCheck), multiple_atom_concat([Lemma,'2.match'],Outname2), multiple_atom_concat([MCString,'-i ',InName,' -o ',Outname,' -j 2',' -C ',OutCheck],Command), write(Command),nl, unix(system(Command)),!, run_blast_loop(3,OutCheck,Outname2,Method,Lemma,[Outname],Outfiles). % last run of run_blast_loop/7 run_blast_loop(20,InName,Outname,Method,_Lemma,Done,[Outname|Done]):-!, match_method(Method,MCString), multiple_atom_concat([MCString,'-R ',InName,' -o ',Outname,' -j 1'],Command), write(Command),nl, unix(system(Command)). % intermediate run of run_blast_loop/7 run_blast_loop(It,InName,Outname,Method,Lemma,Done,Outfiles):- match_method(Method,MCString), NIt is It+1, multiple_atom_concat([Lemma,It,'.check'],OutCheck), multiple_atom_concat([Lemma,NIt,'.match'],OutnameN), multiple_atom_concat([MCString,'-R ',InName,' -o ',Outname,' -j 1',' -C ',OutCheck],Command), write(Command),nl, unix(system(Command)),!, run_blast_loop(NIt,OutCheck,OutnameN,Method,Lemma,[Outname|Done],Outfiles). genome_files(Files) :- clauses_from_file('/mnt/data/Robot_Scientist/KEGG/genomes/genomes.txt', Files). genome_file_type(FName,Type) :- separated_string('.',FName,CH), chain_list(CH,CHL), last_item(CHL,Type). species_abbreviation(File,ABB) :- open(File,read,Stream), string_from_file(Stream,NewString,_MF), string_fragment(2,4,NewString,ABB), close(Stream). genome_species_abbreviation(File,ABB) :- open(File,read,Stream), string_from_file(Stream,NewString,_MF), string_fragment(5,7,NewString,ABB), close(Stream). get_abbreviation(Type,File,ABB) :- Type == 'pep', species_abbreviation(File,ABB). get_abbreviation(Type,File,ABB) :- Type == 'nuc', species_abbreviation(File,ABB). get_abbreviation(Type,File,ABB) :- Type == 'genome', genome_species_abbreviation(File,ABB). genome_file_information([],I,I). genome_file_information([GF|GFileNames],Done,Info) :- GF = genome_file(GFName), genome_dir(Dir), multiple_atom_concat([Dir,GFName],GFile), genome_file_type(GFName,FType), get_abbreviation(FType,GFile,ABB), FI = genome_file_type(ABB,FType,GFName),!, genome_file_information(GFileNames,[FI|Done],Info). genome_file_information([_GF|GFileNames],Done,Info) :- !,genome_file_information(GFileNames,Done,Info). make_genome_info(GInfo) :- genome_files(GFiles),%trace, genome_file_information(GFiles,[],GInfo), open('genome_file_info.pl',write,Stream), write_file_terms(Stream,GInfo), close(Stream). find_enzyme_orfs(Organism,Enzyme,FileType,Method,LikelyOrfs) :- genes_from_organisms(Organism,Enzyme,GeneNames), writelist(GeneNames), length(GeneNames,LN),write('Other Genes':LN),%get0(10), create_sequence_files_and_commands(GeneNames,FileType,Method,Organism,[],MatchFiles), sequence_information_from_files(Organism,MatchFiles,[],SequenceFacts), length(MatchFiles,NumberTests), create_rankings(NumberTests,SequenceFacts,[],Rankings), mean_rankings(NumberTests,Rankings,[],MeanRankings), quicksort_rankings(MeanRankings,LikelyOrfs). %%% Maria's code %% Find all enzymes with unknown orfs and put them in list. %% there are unknown ORF names not assigned an enzyme class, but a reaction number. %% We should make a link between the reaction number and some enzyme class. enzyme_list(List):- findall(Enzyme,(orf_fact(ORF,Enzyme,_EC,_G,_GD,_R),name(ORF,[H|_]),name('U',[H]),Enzyme \= 'none'),List). for_all_enzymes:- enzyme_list(EzList), open(Stream,write,'enzyme_list.txt'), writelist(Stream,EzList), close(Stream), find_enzyme_orf_loop(EzList,[]). find_enzyme_orf_loop([H|T],Done):- find_enzyme_orfsm(_Org,H,'pep',psiblast),!, find_enzyme_orf_loop(T,[H|Done]). %For each enzyme in the list do the following find_enzyme_orfsm(Organism,Enzyme,FileType,Method):- genes_from_organisms(Organism,Enzyme,AllGeneNames), %% remove from AllGeneNames the ones already in done_genes(List) done_genes(Enzyme,PList), subtract(AllGeneNames,PList,GeneNames), writelist(GeneNames), length(GeneNames,LN),write('Other Genes':LN),%get0(10), create_sequence_files_and_commandsm(GeneNames,FileType,Method,Organism,[],MatchFiles), sequence_information_from_filesm(Enzyme,MatchFiles). %length(MatchFiles,NumberTests). significant_sequence(S,NewS) :- S = sequence(Orf,EScore,Rank), find_in_string('e-',EScore), name(EScore,ECodes), number_codes(ENum,ECodes), NewS = sequence(Orf,ENum,Rank). significant_sequence(S,NewS) :- S = sequence(Orf,EScore,Rank), name(EScore,ECodes), number_codes(ENum,ECodes), ENum < 0.02, NewS = sequence(Orf,ENum,Rank). find_and_update_ranking(_NumberTests,Orf1,E,[R|Rankings],Past,NewRankings) :- R = ranking(Orf2,OldScore,N),%trace, Orf1 == Orf2, % Score is (1/NumberTests) * E, NewScore is OldScore + E, N1 is N + 1, NewR = ranking(Orf1,NewScore,N1), conc(Past,[NewR],PastNew), conc(PastNew,Rankings,NewRankings). find_and_update_ranking(NumberTests,Orf1,E,[R|Rankings],Past,NewRankings) :- !,find_and_update_ranking(NumberTests,Orf1,E,Rankings,[R|Past],NewRankings). mean_rankings(_NumberTests,[],R,R). mean_rankings(NumberTests,[R|Rankings],Done,NewRankings) :- R = ranking(Orf,Total,_N), Mean is Total/NumberTests, NewR = ranking(Orf,Mean),!, mean_rankings(NumberTests,Rankings,[NewR|Done],NewRankings). create_rankings(_NumberTests,[],Rankings,Rankings). create_rankings(NumberTests,[S|Sequences],Done,Rankings) :- S = sequence(Orf,_E,Rank), find_and_update_ranking(NumberTests,Orf,Rank,Done,[],Updated),!, create_rankings(NumberTests,Sequences,Updated,Rankings). create_rankings(NumberTests,[S|Sequences],Done,Rankings) :- S = sequence(Orf,_E,Rank),%trace, % Score is (1/NumberTests) * E, NewR = ranking(Orf,Rank,1),!, create_rankings(NumberTests,Sequences,[NewR|Done],Rankings). quicksort_rankings([],[]). quicksort_rankings([X|Tail],Sorted) :- split_ranking(X,Tail,Small,Big), quicksort_rankings(Small,SortedSmall), quicksort_rankings(Big,SortedBig), append(SortedSmall,[X|SortedBig],Sorted). split_ranking(_,[],[],[]). split_ranking(X,[Y|Tail],[Y|Small],Big) :- X = ranking(_O1,XS), Y = ranking(_O2,YS), XS < YS,!, split_ranking(X,Tail,Small,Big). split_ranking(X,[Y|Tail],Small,[Y|Big]) :- split_ranking(X,Tail,Small,Big). possible_orfs_for_orf_info(NumberFind,Organism,OrfInfo,Type,Method,Conjectures) :- OrfInfo = orf_info(OldOrf,Enzyme,Reaction), find_enzyme_orfs(Organism,Enzyme,Type,Method,SequenceFacts), exp_generator_directory(ExpDir), multiple_atom_concat([ExpDir,Organism,'.',Enzyme,'.result'],OutFile), open(OutFile,write,Stream), write_file_terms(Stream,SequenceFacts), close(Stream), number_from_list(1,NumberFind,SequenceFacts,Found), make_conjectures(Found,OldOrf,Enzyme,Reaction,[],Conjectures). all_possible_orfs_and_conjectures(_N,_O,[],_ED,_T,_M,Conjectures,Conjectures). all_possible_orfs_and_conjectures(NumberFind,Organism,[OI|OrfInfo],EnzymesDone,Type, Method,Done,Conjectures) :- OI = orf_info(_OldOrf,Enzyme,_Reaction), \+member(Enzyme,EnzymesDone), possible_orfs_for_orf_info(NumberFind,Organism,OI,Type,Method,OIConjectures), conc(Done,OIConjectures,NewDone),!, all_possible_orfs_and_conjectures(NumberFind,Organism,OrfInfo,[Enzyme|EnzymesDone],Type, Method,NewDone,Conjectures). all_possible_orfs_and_conjectures(NumberFind,Organism,[OI|OrfInfo],EnzymesDone,Type, Method,Done,Conjectures) :- OI = orf_info(OldOrf,Enzyme,Reaction), exp_generator_directory(ExpDir), multiple_atom_concat([ExpDir,Organism,'.',Enzyme,'.result'],OutFile), clauses_from_file(OutFile,SequenceFacts), number_from_list(1,NumberFind,SequenceFacts,Found), make_conjectures(Found,OldOrf,Enzyme,Reaction,[],OIConjectures), conc(Done,OIConjectures,NewDone),!, all_possible_orfs_and_conjectures(NumberFind,Organism,OrfInfo,EnzymesDone,Type, Method,NewDone,Conjectures). make_wet_conjectures([],Conjectures,Conjectures). make_wet_conjectures([OI|OrfInfo],Done,Conjectures) :- OI = orf_info(Orf,Enzyme,Reaction), Con = conjecture(Orf,Enzyme,Reaction),!, make_wet_conjectures(OrfInfo,[Con|Done],Conjectures). make_conjectures([],_O,_E,_R,RDone,Conjectures) :- reverse(RDone,Conjectures). make_conjectures([R|Rankings],OldOrf,Enzyme,Reaction,Done,Conjectures) :- R = ranking(OrfInfo,Rank), separated_string(':',OrfInfo,Chain), chain_list(Chain,[_Org,Orf]), Conjecture = conjecture(OldOrf,Orf,Enzyme,Reaction,Rank),!, make_conjectures(Rankings,OldOrf,Enzyme,Reaction,[Conjecture|Done],Conjectures). find_possible_orfs(_NF,_O,_T,_M,[],_CJF,_ExpF). find_possible_orfs(NumberFind,Organism,Type,Method,[UK|UKGenes],CJFile,ExpFile) :- make_outer_recovery_point([UK|UKGenes]), conjectures_and_experiments(NumberFind,Organism,UK,Type,Method, CJFile,ExpFile),!, find_possible_orfs(NumberFind,Organism,Type,Method,UKGenes, CJFile,ExpFile). %% find wet evidence biology find_wet_conjectures_and_experiments([],_S1,_S2). find_wet_conjectures_and_experiments([KG|KnownGenes],Stream1,Stream2) :- make_wet_outer_recovery_point([KG|KnownGenes]), wet_conjectures_and_experiments(KG,Stream1,Stream2),!, find_wet_conjectures_and_experiments(KnownGenes,Stream1,Stream2). make_outer_recovery_point([R|Reactions]) :- exp_generator_directory(ExpDir), multiple_atom_concat([ExpDir,'outer_recovery_point.pl'],ORPFile), ORP = outer_recovery_point(R,Reactions), open(ORPFile,write,Stream), write_file_terms(Stream,[ORP]), close(Stream). %% outer recovery point for wet evidence genes make_wet_outer_recovery_point([KG|KnownGenes]) :- exp_generator_directory(ExpDir), multiple_atom_concat([ExpDir,'wet_outer_recovery_point.pl'],ORPFile), ORP = outer_recovery_point(KG,KnownGenes), open(ORPFile,write,Stream), write_file_terms(Stream,[ORP]), close(Stream). make_static_recovery_point(NumberFind,Organism,Type,Method) :- exp_generator_directory(ExpDir), multiple_atom_concat([ExpDir,'static_recovery_point.pl'],SRPFile), \+exists_file(SRPFile), SRP = static_recovery_point(NumberFind,Organism,Type,Method), open(SRPFile,write,Stream), write_file_terms(Stream,[SRP]), close(Stream). execute_recovery(CJFile,ExpFile) :- exp_generator_directory(ExpDir), multiple_atom_concat([ExpDir,'static_recovery_point.pl'],SRPFile), multiple_atom_concat([ExpDir,'outer_recovery_point.pl'],ORPFile), multiple_atom_concat([ExpDir,'inner_recovery_point.pl'],IRPFile), clauses_from_file(SRPFile,[SRP]), clauses_from_file(ORPFile,[ORP]), clauses_from_file(IRPFile,[IRP]), SRP = static_recovery_point(NumberFind,Organism,Type,Method), ORP = outer_recovery_point(UK,UKGenesLeft), IRP = inner_recovery_point(Met,MetabolitesLeft), multiple_atom_concat([ExpDir,UK,'_recovered_growth.pl'],OutFile), write('recovered: about to start recovered_growths'),nl,nl,%trace, %open(OutFile,append,Stream), find_recovered_growths(1,OutFile,UK,[Met|MetabolitesLeft]), %close(Stream), clauses_from_file(OutFile,Recovered), load_full_metabolite_graph,%trace, all_orf_info(UK,OrfInfo), knocked_out_orf_info(OrfInfo,_Reactions,[],KOOrfInfo), all_possible_orfs_and_conjectures(NumberFind,Organism,KOOrfInfo,[],Type,Method,[],Conjectures), write('passed possible orfs'),nl,nl, construct_experiments(Conjectures,Recovered,[],AllExperiments), real_conjectures(Conjectures,[],AllRealConjectures), make_set(AllExperiments,[],Experiments), make_set(AllRealConjectures,[],RealConjectures), writelist(RealConjectures),nl,nl, writelist(Experiments),nl,nl, open(CJFile,append,Stream1), open(ExpFile,append,Stream2), write_file_terms(Stream1,RealConjectures), write_file_terms(Stream2,Experiments), close(Stream1), close(Stream2), find_possible_orfs(NumberFind,Organism,Type,Method, UKGenesLeft,CJFile,ExpFile). execute_wet_recovery(CJFile,ExpFile) :- exp_generator_directory(ExpDir), multiple_atom_concat([ExpDir,'wet_outer_recovery_point.pl'],ORPFile), multiple_atom_concat([ExpDir,'wet_inner_recovery_point.pl'],IRPFile), clauses_from_file(ORPFile,[ORP]), clauses_from_file(IRPFile,[IRP]), ORP = outer_recovery_point(Gene,GenesLeft), IRP = inner_recovery_point(Met,MetabolitesLeft), multiple_atom_concat([ExpDir,Gene,'_recovered_growth.pl'],OutFile), write('recovered: about to start recovered_growths'),nl,nl,%trace, %open(OutFile,append,Stream), findall_wet_recovered_growths(Gene,[Met|MetabolitesLeft],OutFile), %close(Stream), clauses_from_file(OutFile,Recovered), load_full_metabolite_graph,%trace, all_orf_info(Gene,OrfInfo), find_knocked_out_reactions_and_enzymes(Gene,Reactions,_Enzymes), knocked_out_orf_info(OrfInfo,Reactions,[],KOOrfInfo), write('passed possible orfs'),nl,nl, make_wet_conjectures(KOOrfInfo,[],Conjectures), construct_wet_experiments(Conjectures,Recovered,[],AllExperiments),%trace, make_set(AllExperiments,[],Experiments), writelist(Conjectures),nl,nl, writelist(Experiments),nl,nl, open(CJFile,append,Stream1), open(ExpFile,append,Stream2), write_file_terms(Stream1,Conjectures), write_file_terms(Stream2,Experiments), close(Stream1), close(Stream2), find_wet_conjectures_and_experiments(GenesLeft,CJFile,ExpFile). %% parameters are usually ... %% all_conjectures_and_experiments(3,sce,pep,fasta). all_conjectures_and_experiments(NumberFind,Organism,Type,Method) :- interesting_unknown_genes(UKGenes), wild_type_reactions(WildReactions), all_compounds_from_reaction_set(WildReactions,Compounds), CR = compounds_from_reactions(Compounds), exp_generator_directory(ExpDir), multiple_atom_concat([ExpDir,'compounds_from_reactions.pl'],CompFile), open(CompFile,write,CRStream), write_file_terms(CRStream,[CR]), close(CRStream), single_lists(Compounds,CompoundLists), CL = single_compound_lists(CompoundLists), multiple_atom_concat([ExpDir,'single_compound_lists.pl'],SLFile), open(SLFile,write,SLStream), write_file_terms(SLStream,[CL]), close(SLStream), multiple_atom_concat([ExpDir,'conjectures.pl'],CJFile), multiple_atom_concat([ExpDir,'experiments.pl'],ExpFile), ( make_static_recovery_point(NumberFind,Organism,Type,Method), find_possible_orfs(NumberFind,Organism,Type,Method,UKGenes,CJFile,ExpFile) ; execute_recovery(CJFile,ExpFile)). %% alternative_version for no wet evidence genes all_wet_conjectures_and_experiments :- interesting_known_genes(KnownGenes), wild_type_reactions(WildReactions), all_compounds_from_reaction_set(WildReactions,Compounds), CR = compounds_from_reactions(Compounds), exp_generator_directory(ExpDir), multiple_atom_concat([ExpDir,'compounds_from_reactions.pl'],CompFile), open(CompFile,write,CRStream), write_file_terms(CRStream,[CR]), close(CRStream), single_lists(Compounds,CompoundLists), CL = single_compound_lists(CompoundLists), multiple_atom_concat([ExpDir,'single_compound_lists.pl'],SLFile), open(SLFile,write,SLStream), write_file_terms(SLStream,[CL]), close(SLStream), multiple_atom_concat([ExpDir,'wet_conjectures.pl'],CJFile), multiple_atom_concat([ExpDir,'wet_experiments.pl'],ExpFile), multiple_atom_concat([ExpDir,'wet_outer_recovery_point.pl'],ORPFile), ( \+exists_file(ORPFile), find_wet_conjectures_and_experiments(KnownGenes,CJFile,ExpFile) ; execute_wet_recovery(CJFile,ExpFile)). interesting_reactions([412]). %interesting_reactions([226,227,228,229,230,231,251,412]). orf_name_and_rank(_I,_Max,_OldOrf,_E,[],Done,Ranks) :- reverse(Done,Ranks). orf_name_and_rank(I,Max,_OldOrf,_E,_Rankings,Done,Ranks) :- I > Max, reverse(Done,Ranks). orf_name_and_rank(I,Max,OldOrf,Enzyme,[Ranking|Rankings],Done,Ranks) :- Ranking = ranking(Orf,_Score), separated_string(':',Orf,Chain), chain_list(Chain,[_Org,NewOrf]), NewRanking = match(OldOrf,NewOrf,Enzyme,I), I2 is I + 1,!, orf_name_and_rank(I2,Max,OldOrf,Enzyme,Rankings,[NewRanking|Done],Ranks).