Commit message:
planemo upload |
added:
ID_mapping_Uniprot_HomoSapiens_20170809.txt Nextprot_Uniprot_id_mapping_file.txt id_converter.xml id_converter_UniProt.R test-data/UnipIDs.txt test-data/output.txt |
b |
diff -r 000000000000 -r 02c549457875 ID_mapping_Uniprot_HomoSapiens_20170809.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ID_mapping_Uniprot_HomoSapiens_20170809.txt Fri Sep 15 06:02:03 2017 -0400 |
b |
b'@@ -0,0 +1,159553 @@\n+UNIPROT_AC \tUNIPROT_ID\tGeneID_EntrezGene\tRefSeq\tGI_number\tPDB\tGO_ID\tPIR\tOMIM\tUniGene\tEnsembl ENSG\tEnsembl ENST\tEnsembl ENSP \r\n+P31946\t1433B_HUMAN\t7529\t"NP_003395.1; NP_647539.1; XP_016883528.1"\t"4507949; 377656702; 67464628; 1345590; 1034625756; 21328448; 377656701; 67464627; 78101741"\t"2BQ0:A; 2BQ0:B; 2C23:A; 4DNK:A; 4DNK:B"\t"GO:0005737; GO:0030659; GO:0005829; GO:0070062; GO:0005925; GO:0042470; GO:0016020; GO:0005739; GO:0005634; GO:0048471; GO:0043234; GO:0017053; GO:0045296; GO:0019899; GO:0042826; GO:0051219; GO:0050815; GO:0008022; GO:0032403; GO:0019904; GO:0003714; GO:0051220; GO:0035329; GO:0000165; GO:0061024; GO:0045744; GO:0035308; GO:0045892; GO:0043085; GO:1900740; GO:0051291; GO:0006605; GO:0043488; GO:0016032"\tS34755\t601289\tHs.643544\tENSG00000166913\t"ENST00000353703; ENST00000372839"\t"ENSP00000300161; ENSP00000361930"\r\n+P62258\t1433E_HUMAN\t7531\tNP_006752.1\t"374074368; 62131678; 67464424; 194379794; 221045758; 5803225; 374074366; 51702210"\t"2BR9:A; 3UAL:A; 3UBW:A"\t"GO:0030424; GO:0090724; GO:0005737; GO:0030659; GO:0005829; GO:0070062; GO:0005925; GO:0005871; GO:0042470; GO:0016020; GO:0005739; GO:0005634; GO:0045296; GO:0005246; GO:0019899; GO:0042826; GO:0044325; GO:0023026; GO:0051219; GO:0050815; GO:0015459; GO:0019904; GO:0046982; GO:0017112; GO:0003723; GO:0031625; GO:0034605; GO:0021987; GO:0097711; GO:0000086; GO:0035329; GO:0021766; GO:0035556; GO:0000165; GO:0061024; GO:0086013; GO:1905913; GO:1901020; GO:0043154; GO:1902309; GO:0001764; GO:0046827; GO:1900740; GO:0006605; GO:1900034; GO:0051480; GO:0086091; GO:0003064; GO:0060306; GO:1901016; GO:0021762; GO:0016032"\t"A61235; I38947"\t605066\tHs.513851\t"ENSG00000108953; ENSG00000274474"\t"ENST00000264335; ENST00000571732; ENST00000616643; ENST00000627231"\t"ENSP00000264335; ENSP00000461762; ENSP00000481059; ENSP00000487356"\r\n+Q04917\t1433F_HUMAN\t7533\tNP_003396.1\t"4507951; 437363; 83754686; 83754699; 83754700; 1345593; 83754684; 83754685; 28862; 83754683"\t"2C63:A; 2C63:B; 2C63:C; 2C63:D; 2C74:A; 2C74:B"\t"GO:0005737; GO:0030659; GO:0005829; GO:0070062; GO:0014704; GO:0005739; GO:0005886; GO:0003779; GO:0019899; GO:0035259; GO:0005159; GO:0044325; GO:0019904; GO:0046982; GO:0017080; GO:0006713; GO:0042921; GO:0006886; GO:0086010; GO:0061024; GO:0050774; GO:1900740; GO:0045893; GO:0045664; GO:2000649; GO:0002028; GO:0048167; GO:0021762"\t"S34756; S38509; S38532"\t113508\tHs.226755\tENSG00000128245\tENST00000248975\tENSP00000248975\r\n+P61981\t1433G_HUMAN\t7532\tNP_036611.2\t"6016838; 380764684; 635576381; 82407956; 82407958; 550545213; 635576377; 380765197; 82407950; 550545214; 119592210; 1006588564; 1006588561; 635576379; 21464101; 82407952; 48428721; 5726310; 550545212; 635576378; 1006588559; 18088513; 49456805; 1006588565; 550545215; 1006588558; 49456763; 1006588562; 82407948; 82407954; 635576376; 635576380"\t"2B05:A; 2B05:B; 2B05:C; 2B05:D; 2B05:E; 2B05:F; 3UZD:A; 4E2E:A; 4J6S:A; 4J6S:B; 4J6S:C; 4J6S:D; 4O46:A; 4O46:B; 4O46:C; 4O46:D; 4O46:E; 4O46:F; 5D3E:A; 5D3E:B; 5D3E:E; 5D3E:F; 5D3E:I; 5D3E:J"\t"GO:0030659; GO:0005829; GO:0070062; GO:0005925; GO:0016020; GO:0005739; GO:0043209; GO:0005159; GO:0019904; GO:0005080; GO:0008426; GO:0030971; GO:0003723; GO:0032869; GO:0097711; GO:0000086; GO:0061024; GO:0006469; GO:1900740; GO:0006605; GO:0045664; GO:0009966; GO:0048167"\t\t605356\tHs.744840\tENSG00000170027\tENST00000307630\tENSP00000306330\r\n+P31947\t1433S_HUMAN\t2810\tNP_006133.1\t"436408756; 306991738; 969812714; 350610438; 350610440; 2702355; 393715161; 453056146; 394985958; 398953; 305677674; 305677670; 350610436; 528082005; 390981001; 1025734704; 187302; 12654345; 61680850; 49456807; 12804273; 12653125; 394985950; 528082006; 16306737; 528082000; 433286579; 390980999; 394985956; 499142131; 23940; 394985954; 528082007; 564730948; 499142129; 528082001; 307776567; 291463695; 62738854; 835018920; 350610430; 969812717; 528082008; 564730947; 491668340; 528082002; 61680851; 984077415; 394985952; 5454052; 350610432; 23270783; 528082003; 973744025; 2702353; 54571'..b'\t\t\r\n+Q3LAC0\tQ3LAC0_HUMAN\t\t\t77019285\t\t"GO:0016021; GO:0042613; GO:0002504; GO:0006955"\t\t\t"Hs.534322; Hs.696211; Hs.736560"\t\t\t\r\n+Q5QCF4\tQ5QCF4_HUMAN\t\t\t56182557\t\t\t\t\tHs.408528\t\t\t\r\n+Q9GIL4\tQ9GIL4_HUMAN\t\t\t11877216\t\t"GO:0042613; GO:0019882; GO:0006955"\t\t\t"Hs.485130; Hs.534322; Hs.696211; Hs.736560"\t\t\t\r\n+Q9TPV3\tQ9TPV3_HUMAN\t\t\t5802635\t\t\t\t\t"Hs.654404; Hs.726974; Hs.77961"\t\t\t\r\n+W0NTP1\tW0NTP1_HUMAN\t\t\t574614416\t\t\t\t\t"Hs.656020; Hs.743218"\t\t\t\r\n+A0A0D9SFF4\tA0A0D9SFF4_HUMAN\t\t\t\t\t\t\t\t\tENSG00000179915\tENST00000628515\tENSP00000486544\r\n+A0A0D9SFR5\tA0A0D9SFR5_HUMAN\t\t\t\t\t\t\t\t\tENSG00000162065\tENST00000630263\tENSP00000486835\r\n+A0A0D9SFZ8\tA0A0D9SFZ8_HUMAN\t\t\t\t\t\t\t\t\tENSG00000128040\tENST00000631082\tENSP00000487028\r\n+A0A0E3DD47\tA0A0E3DD47_HUMAN\t\t\t631900061\t\t"GO:0042613; GO:0019882; GO:0006955"\t\t\t"Hs.409934; Hs.534322"\t\t\t\r\n+A0A0E3JPD9\tA0A0E3JPD9_HUMAN\t\t\t794447125\t\t"GO:0016021; GO:0005743; GO:0045263; GO:0015078; GO:0015986"\t\t\t\t\t\t\r\n+A0A0G2JP19\tA0A0G2JP19_HUMAN\t\t\t\t\tGO:0016021\t\t\t\tENSG00000277221\tENST00000611862\tENSP00000482650\r\n+A0A0G2JQ91\tA0A0G2JQ91_HUMAN\t\t\t\t\tGO:0016020\t\t\t\tENSG00000278608\tENST00000617216\tENSP00000485495\r\n+A0A0G2JQT8\tA0A0G2JQT8_HUMAN\t\t\t\t\t"GO:0016021; GO:0007160"\t\t\t\tENSG00000278468\tENST00000627791\tENSP00000486164\r\n+A0A0G2R1D7\tA0A0G2R1D7_HUMAN\t\t\t"1037404902; 661916902"\t\t\t\t\t"Hs.656020; Hs.743218"\t\t\t\r\n+A0A0G2R1T2\tA0A0G2R1T2_HUMAN\t\t\t661917058\t\t"GO:0042613; GO:0019882; GO:0006955"\t\t\tHs.485130\t\t\t\r\n+A0A0S2Z5J1\tA0A0S2Z5J1_HUMAN\t53947\t"NP_001304967.1; NP_059132.1; XP_005261701.1; XP_005261703.1; XP_005261704.1; XP_005261705.1; XP_006724328.1; XP_006724329.1; XP_011528535.1; XP_016884320.1"\t"60459546; 15523687; 189066521; 957951157; 530420175; 7959011; 16877647; 1034629093; 530420171; 768025131; 578837269; 530420179; 8250233; 966750452; 578837271; 530420177; 8392830; 119593680"\t\t"GO:0016021; GO:0050512; GO:0015643; GO:0001576"\t\t\tHs.105956\t\t\t\r\n+A0A0U4CQG9\tA0A0U4CQG9_HUMAN\t\t\t972988092\t\t"GO:0005524; GO:0004674"\t\t\tHs.631535\t\t\t\r\n+A0A140VKB3\tA0A140VKB3_HUMAN\t594\t"NP_000047.1; NP_898871.1"\t"1480477; 4557353; 158260977; 34101272; 179362; 219493; 54696988; 119569081; 119569082; 25304054; 332368119"\t\t"GO:0005739; GO:0003826"\t\t\tHs.654441\t\t\t\r\n+A0A167HES1\tA0A167HES1_HUMAN\t\t\t1023115953\t\t"GO:0005622; GO:0007417; GO:0035556"\t\t\tHs.292737\t\t\t\r\n+A0A0N7A555\tA0A0N7A555_HUMAN\t\t\t723439294\t\t"GO:0042613; GO:0019882; GO:0006955"\t\t\t\t\t\t\r\n+A0A0S2Z4S0\tA0A0S2Z4S0_HUMAN\t\t\t957950595\t\t"GO:0016021; GO:0006810"\t\t\tHs.445892\t\t\t\r\n+A0A0S2Z5C3\tA0A0S2Z5C3_HUMAN\t55003\tNP_060376.2\t"119575674; 957951237; 55769546"\t\t"GO:0005730; GO:0008283; GO:0060021"\t\t\tHs.310231\t\t\t\r\n+A0A0S2Z643\tA0A0S2Z643_HUMAN\t\t\t957951889\t\t\t\t\tHs.31652\t\t\t\r\n+A0A0U4BH10\tA0A0U4BH10_HUMAN\t\t\t1015635350\t\t"GO:0016020; GO:0047276; GO:0005975"\t\t\tHs.654423\t\t\t\r\n+A0A0J9YVT0\tA0A0J9YVT0_HUMAN\t\t\t"186233; 478306641"\t\t\t\t\tHs.720416\tENSG00000282642\tENST00000631807\tENSP00000487655\r\n+A0A0J9YX13\tA0A0J9YX13_HUMAN\t\t\t\t\t"GO:0003824; GO:0050662"\t\t\t\tENSG00000278243\tENST00000632379\tENSP00000488203\r\n+A0A0J9YXT7\tA0A0J9YXT7_HUMAN\t\t\t\t\t"GO:0061617; GO:0042407"\t\t\t\tENSG00000184831\tENST00000633432\tENSP00000488538\r\n+A0A0J9YY02\tA0A0J9YY02_HUMAN\t\t\t\t\t\t\t\t\tENSG00000282092\tENST00000632049\tENSP00000488625\r\n+A0A0N6W203\tA0A0N6W203_HUMAN\t\t\t675585190\t\t"GO:0016021; GO:0005743; GO:0070469; GO:0008137; GO:0042773"\t\t\t\t\t\t\r\n+A0A0N7A6I7\tA0A0N7A6I7_HUMAN\t\t\t723439130\t\t"GO:0042613; GO:0019882; GO:0006955"\t\t\t"Hs.409934; Hs.534322"\t\t\t\r\n+A0A0N7A6W4\tA0A0N7A6W4_HUMAN\t\t\t723439219\t\t"GO:0042613; GO:0019882; GO:0006955"\t\t\tHs.696211\t\t\t\r\n+A0A0N7M1B0\tA0A0N7M1B0_HUMAN\t\t\t939460591\t\t\t\t\t"Hs.656020; Hs.743218"\t\t\t\r\n+A0A0N9M6N1\tA0A0N9M6N1_HUMAN\t\t\t933617972\t\t\t\t\t"Hs.656020; Hs.743218"\t\t\t\r\n+A0A0U5IHY9\tA0A0U5IHY9_HUMAN\t\t\t974569914\t\t"GO:0016021; GO:0042613; GO:0002504; GO:0006955"\t\t\t"Hs.409934; Hs.534322"\t\t\t\r\n+A0A126GVK9\tA0A126GVK9_HUMAN\t390075\tNP_001001922.2\t"84662226; 21697630; 223460928; 187953403; 937627828; 119589168; 284005439"\t\t"GO:0016021; GO:0005886; GO:0004930; GO:0004984"\t\t\tHs.690207\t\t\t\r\n+A0A126GWS3\tA0A126GWS3_HUMAN\t\t\t"157697652; 937628644"\t\t"GO:0016021; GO:0005886; GO:0004930; GO:0004984"\t\t\tHs.446910\t\t\t\r\n' |
b |
diff -r 000000000000 -r 02c549457875 Nextprot_Uniprot_id_mapping_file.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Nextprot_Uniprot_id_mapping_file.txt Fri Sep 15 06:02:03 2017 -0400 |
b |
b'@@ -0,0 +1,20180 @@\n+neXtProt_ID\tUniprot_AC\r\n+NX_A0A075B6H9\tA0A075B6H9\r\n+NX_A0A075B6I0\tA0A075B6I0\r\n+NX_A0A075B6I1\tA0A075B6I1\r\n+NX_A0A075B6I4\tA0A075B6I4\r\n+NX_A0A075B6I9\tA0A075B6I9\r\n+NX_A0A075B6J1\tA0A075B6J1\r\n+NX_A0A075B6J6\tA0A075B6J6\r\n+NX_A0A075B6J9\tA0A075B6J9\r\n+NX_A0A075B6K0\tA0A075B6K0\r\n+NX_A0A075B6K2\tA0A075B6K2\r\n+NX_A0A075B6K4\tA0A075B6K4\r\n+NX_A0A075B6K6\tA0A075B6K6\r\n+NX_A0A075B6P5\tA0A075B6P5\r\n+NX_A0A075B6Q5\tA0A075B6Q5\r\n+NX_A0A075B6R2\tA0A075B6R2\r\n+NX_A0A075B6S2\tA0A075B6S2\r\n+NX_A0A075B6S4\tA0A075B6S4\r\n+NX_A0A075B6S5\tA0A075B6S5\r\n+NX_A0A075B6S6\tA0A075B6S6\r\n+NX_A0A075B759\tA0A075B759\r\n+NX_A0A087WSX0\tA0A087WSX0\r\n+NX_A0A087WSY4\tA0A087WSY4\r\n+NX_A0A087WSY6\tA0A087WSY6\r\n+NX_A0A087WSZ0\tA0A087WSZ0\r\n+NX_A0A087WTH1\tA0A087WTH1\r\n+NX_A0A087WTH5\tA0A087WTH5\r\n+NX_A0A087WUL8\tA0A087WUL8\r\n+NX_A0A087WVF3\tA0A087WVF3\r\n+NX_A0A087WW87\tA0A087WW87\r\n+NX_A0A087WX78\tA0A087WX78\r\n+NX_A0A087WXM9\tA0A087WXM9\r\n+NX_A0A087WXS9\tA0A087WXS9\r\n+NX_A0A087X179\tA0A087X179\r\n+NX_A0A087X1C5\tA0A087X1C5\r\n+NX_A0A087X1G2\tA0A087X1G2\r\n+NX_A0A096LP49\tA0A096LP49\r\n+NX_A0A096LP55\tA0A096LP55\r\n+NX_A0A096LPI5\tA0A096LPI5\r\n+NX_A0A0A0MRZ7\tA0A0A0MRZ7\r\n+NX_A0A0A0MRZ8\tA0A0A0MRZ8\r\n+NX_A0A0A0MRZ9\tA0A0A0MRZ9\r\n+NX_A0A0A0MS14\tA0A0A0MS14\r\n+NX_A0A0A0MS15\tA0A0A0MS15\r\n+NX_A0A0A0MT36\tA0A0A0MT36\r\n+NX_A0A0A0MT76\tA0A0A0MT76\r\n+NX_A0A0A0MT89\tA0A0A0MT89\r\n+NX_A0A0B4J1U3\tA0A0B4J1U3\r\n+NX_A0A0B4J1U7\tA0A0B4J1U7\r\n+NX_A0A0B4J1V0\tA0A0B4J1V0\r\n+NX_A0A0B4J1V1\tA0A0B4J1V1\r\n+NX_A0A0B4J1V2\tA0A0B4J1V2\r\n+NX_A0A0B4J1V6\tA0A0B4J1V6\r\n+NX_A0A0B4J1X5\tA0A0B4J1X5\r\n+NX_A0A0B4J1X8\tA0A0B4J1X8\r\n+NX_A0A0B4J1Y8\tA0A0B4J1Y8\r\n+NX_A0A0B4J1Y9\tA0A0B4J1Y9\r\n+NX_A0A0B4J1Z2\tA0A0B4J1Z2\r\n+NX_A0A0B4J2A2\tA0A0B4J2A2\r\n+NX_A0A0B4J2D9\tA0A0B4J2D9\r\n+NX_A0A0B4J2F0\tA0A0B4J2F0\r\n+NX_A0A0B4J2H0\tA0A0B4J2H0\r\n+NX_A0A0C4DH24\tA0A0C4DH24\r\n+NX_A0A0C4DH25\tA0A0C4DH25\r\n+NX_A0A0C4DH29\tA0A0C4DH29\r\n+NX_A0A0C4DH31\tA0A0C4DH31\r\n+NX_A0A0C4DH32\tA0A0C4DH32\r\n+NX_A0A0C4DH33\tA0A0C4DH33\r\n+NX_A0A0C4DH34\tA0A0C4DH34\r\n+NX_A0A0C4DH38\tA0A0C4DH38\r\n+NX_A0A0C4DH39\tA0A0C4DH39\r\n+NX_A0A0C4DH41\tA0A0C4DH41\r\n+NX_A0A0C4DH42\tA0A0C4DH42\r\n+NX_A0A0C4DH55\tA0A0C4DH55\r\n+NX_A0A0C4DH62\tA0A0C4DH62\r\n+NX_A0A0C4DH67\tA0A0C4DH67\r\n+NX_A0A0C4DH68\tA0A0C4DH68\r\n+NX_A0A0C4DH69\tA0A0C4DH69\r\n+NX_A0A0C4DH72\tA0A0C4DH72\r\n+NX_A0A0C4DH73\tA0A0C4DH73\r\n+NX_A0A0C5B5G6\tA0A0C5B5G6\r\n+NX_A0A0G2JMI3\tA0A0G2JMI3\r\n+NX_A0A0G2JS06\tA0A0G2JS06\r\n+NX_A0A0J9YVY3\tA0A0J9YVY3\r\n+NX_A0A0J9YWL9\tA0A0J9YWL9\r\n+NX_A0A0J9YXX1\tA0A0J9YXX1\r\n+NX_A0A0U1RRE5\tA0A0U1RRE5\r\n+NX_A0A183\tA0A183\r\n+NX_A0A1B0GVQ0\tA0A1B0GVQ0\r\n+NX_A0A5B9\tA0A5B9\r\n+NX_A0AUZ9\tA0AUZ9\r\n+NX_A0AV02\tA0AV02\r\n+NX_A0AV96\tA0AV96\r\n+NX_A0AVF1\tA0AVF1\r\n+NX_A0AVI2\tA0AVI2\r\n+NX_A0AVI4\tA0AVI4\r\n+NX_A0AVK6\tA0AVK6\r\n+NX_A0AVT1\tA0AVT1\r\n+NX_A0FGR8\tA0FGR8\r\n+NX_A0FGR9\tA0FGR9\r\n+NX_A0JLT2\tA0JLT2\r\n+NX_A0JNW5\tA0JNW5\r\n+NX_A0JP26\tA0JP26\r\n+NX_A0M8Q6\tA0M8Q6\r\n+NX_A0MZ66\tA0MZ66\r\n+NX_A0PG75\tA0PG75\r\n+NX_A0PJE2\tA0PJE2\r\n+NX_A0PJK1\tA0PJK1\r\n+NX_A0PJW6\tA0PJW6\r\n+NX_A0PJW8\tA0PJW8\r\n+NX_A0PJX0\tA0PJX0\r\n+NX_A0PJX2\tA0PJX2\r\n+NX_A0PJX4\tA0PJX4\r\n+NX_A0PJX8\tA0PJX8\r\n+NX_A0PJY2\tA0PJY2\r\n+NX_A0PJZ0\tA0PJZ0\r\n+NX_A0PJZ3\tA0PJZ3\r\n+NX_A0PK00\tA0PK00\r\n+NX_A0PK05\tA0PK05\r\n+NX_A0PK11\tA0PK11\r\n+NX_A0ZSE6\tA0ZSE6\r\n+NX_A1A4F0\tA1A4F0\r\n+NX_A1A4G5\tA1A4G5\r\n+NX_A1A4S6\tA1A4S6\r\n+NX_A1A4V9\tA1A4V9\r\n+NX_A1A4Y4\tA1A4Y4\r\n+NX_A1A519\tA1A519\r\n+NX_A1A580\tA1A580\r\n+NX_A1A5B4\tA1A5B4\r\n+NX_A1A5C7\tA1A5C7\r\n+NX_A1A5D9\tA1A5D9\r\n+NX_A1E959\tA1E959\r\n+NX_A1IGU5\tA1IGU5\r\n+NX_A1KXE4\tA1KXE4\r\n+NX_A1KZ92\tA1KZ92\r\n+NX_A1L020\tA1L020\r\n+NX_A1L0T0\tA1L0T0\r\n+NX_A1L157\tA1L157\r\n+NX_A1L162\tA1L162\r\n+NX_A1L167\tA1L167\r\n+NX_A1L168\tA1L168\r\n+NX_A1L170\tA1L170\r\n+NX_A1L188\tA1L188\r\n+NX_A1L190\tA1L190\r\n+NX_A1L1A6\tA1L1A6\r\n+NX_A1L390\tA1L390\r\n+NX_A1L3X0\tA1L3X0\r\n+NX_A1L3X4\tA1L3X4\r\n+NX_A1L429\tA1L429\r\n+NX_A1L443\tA1L443\r\n+NX_A1L453\tA1L453\r\n+NX_A1L4H1\tA1L4H1\r\n+NX_A1L4K1\tA1L4K1\r\n+NX_A1L4L8\tA1L4L8\r\n+NX_A1L4Q6\tA1L4Q6\r\n+NX_A1X283\tA1X283\r\n+NX_A1XBS5\tA1XBS5\r\n+NX_A1YPR0\tA1YPR0\r\n+NX_A1Z1Q3\tA1Z1Q3\r\n+NX_A2A288\tA2A288\r\n+NX_A2A2V5\tA2A2V5\r\n+NX_A2A2Y4\tA2A2Y4\r\n+NX_A2A2Z9\tA2A2Z9\r\n+NX_A2A368\tA2A368\r\n+NX_A2A3K4\tA2A3K4\r\n+NX_A2A3L6\tA2A3L6\r\n+NX_A2A3N6\tA2A3N6\r\n+NX_A2AJT9\tA2AJT9\r\n+NX_A2CJ06\tA2CJ06\r\n+NX_A2IDD5\tA2IDD5\r\n+NX_A2NJV5\tA2NJV5\r\n+NX_A2PYH4\tA2PYH4\r\n+NX_A2RRD'..b'\tQ9Y5M8\r\n+NX_Q9Y5N1\tQ9Y5N1\r\n+NX_Q9Y5N5\tQ9Y5N5\r\n+NX_Q9Y5N6\tQ9Y5N6\r\n+NX_Q9Y5P0\tQ9Y5P0\r\n+NX_Q9Y5P1\tQ9Y5P1\r\n+NX_Q9Y5P2\tQ9Y5P2\r\n+NX_Q9Y5P3\tQ9Y5P3\r\n+NX_Q9Y5P4\tQ9Y5P4\r\n+NX_Q9Y5P6\tQ9Y5P6\r\n+NX_Q9Y5P8\tQ9Y5P8\r\n+NX_Q9Y5Q0\tQ9Y5Q0\r\n+NX_Q9Y5Q3\tQ9Y5Q3\r\n+NX_Q9Y5Q5\tQ9Y5Q5\r\n+NX_Q9Y5Q6\tQ9Y5Q6\r\n+NX_Q9Y5Q8\tQ9Y5Q8\r\n+NX_Q9Y5Q9\tQ9Y5Q9\r\n+NX_Q9Y5R2\tQ9Y5R2\r\n+NX_Q9Y5R4\tQ9Y5R4\r\n+NX_Q9Y5R5\tQ9Y5R5\r\n+NX_Q9Y5R6\tQ9Y5R6\r\n+NX_Q9Y5R8\tQ9Y5R8\r\n+NX_Q9Y5S1\tQ9Y5S1\r\n+NX_Q9Y5S2\tQ9Y5S2\r\n+NX_Q9Y5S8\tQ9Y5S8\r\n+NX_Q9Y5S9\tQ9Y5S9\r\n+NX_Q9Y5T4\tQ9Y5T4\r\n+NX_Q9Y5T5\tQ9Y5T5\r\n+NX_Q9Y5U2\tQ9Y5U2\r\n+NX_Q9Y5U4\tQ9Y5U4\r\n+NX_Q9Y5U5\tQ9Y5U5\r\n+NX_Q9Y5U8\tQ9Y5U8\r\n+NX_Q9Y5U9\tQ9Y5U9\r\n+NX_Q9Y5V0\tQ9Y5V0\r\n+NX_Q9Y5V3\tQ9Y5V3\r\n+NX_Q9Y5W3\tQ9Y5W3\r\n+NX_Q9Y5W5\tQ9Y5W5\r\n+NX_Q9Y5W7\tQ9Y5W7\r\n+NX_Q9Y5W8\tQ9Y5W8\r\n+NX_Q9Y5W9\tQ9Y5W9\r\n+NX_Q9Y5X0\tQ9Y5X0\r\n+NX_Q9Y5X1\tQ9Y5X1\r\n+NX_Q9Y5X2\tQ9Y5X2\r\n+NX_Q9Y5X3\tQ9Y5X3\r\n+NX_Q9Y5X4\tQ9Y5X4\r\n+NX_Q9Y5X5\tQ9Y5X5\r\n+NX_Q9Y5X9\tQ9Y5X9\r\n+NX_Q9Y5Y0\tQ9Y5Y0\r\n+NX_Q9Y5Y2\tQ9Y5Y2\r\n+NX_Q9Y5Y3\tQ9Y5Y3\r\n+NX_Q9Y5Y4\tQ9Y5Y4\r\n+NX_Q9Y5Y5\tQ9Y5Y5\r\n+NX_Q9Y5Y6\tQ9Y5Y6\r\n+NX_Q9Y5Y7\tQ9Y5Y7\r\n+NX_Q9Y5Y9\tQ9Y5Y9\r\n+NX_Q9Y5Z0\tQ9Y5Z0\r\n+NX_Q9Y5Z4\tQ9Y5Z4\r\n+NX_Q9Y5Z6\tQ9Y5Z6\r\n+NX_Q9Y5Z7\tQ9Y5Z7\r\n+NX_Q9Y5Z9\tQ9Y5Z9\r\n+NX_Q9Y600\tQ9Y600\r\n+NX_Q9Y603\tQ9Y603\r\n+NX_Q9Y605\tQ9Y605\r\n+NX_Q9Y606\tQ9Y606\r\n+NX_Q9Y608\tQ9Y608\r\n+NX_Q9Y613\tQ9Y613\r\n+NX_Q9Y614\tQ9Y614\r\n+NX_Q9Y615\tQ9Y615\r\n+NX_Q9Y616\tQ9Y616\r\n+NX_Q9Y617\tQ9Y617\r\n+NX_Q9Y618\tQ9Y618\r\n+NX_Q9Y619\tQ9Y619\r\n+NX_Q9Y620\tQ9Y620\r\n+NX_Q9Y623\tQ9Y623\r\n+NX_Q9Y624\tQ9Y624\r\n+NX_Q9Y625\tQ9Y625\r\n+NX_Q9Y639\tQ9Y639\r\n+NX_Q9Y644\tQ9Y644\r\n+NX_Q9Y646\tQ9Y646\r\n+NX_Q9Y651\tQ9Y651\r\n+NX_Q9Y653\tQ9Y653\r\n+NX_Q9Y657\tQ9Y657\r\n+NX_Q9Y661\tQ9Y661\r\n+NX_Q9Y662\tQ9Y662\r\n+NX_Q9Y663\tQ9Y663\r\n+NX_Q9Y664\tQ9Y664\r\n+NX_Q9Y666\tQ9Y666\r\n+NX_Q9Y672\tQ9Y672\r\n+NX_Q9Y673\tQ9Y673\r\n+NX_Q9Y675\tQ9Y675\r\n+NX_Q9Y676\tQ9Y676\r\n+NX_Q9Y678\tQ9Y678\r\n+NX_Q9Y679\tQ9Y679\r\n+NX_Q9Y680\tQ9Y680\r\n+NX_Q9Y689\tQ9Y689\r\n+NX_Q9Y691\tQ9Y691\r\n+NX_Q9Y692\tQ9Y692\r\n+NX_Q9Y693\tQ9Y693\r\n+NX_Q9Y694\tQ9Y694\r\n+NX_Q9Y696\tQ9Y696\r\n+NX_Q9Y697\tQ9Y697\r\n+NX_Q9Y698\tQ9Y698\r\n+NX_Q9Y6A1\tQ9Y6A1\r\n+NX_Q9Y6A2\tQ9Y6A2\r\n+NX_Q9Y6A4\tQ9Y6A4\r\n+NX_Q9Y6A5\tQ9Y6A5\r\n+NX_Q9Y6A9\tQ9Y6A9\r\n+NX_Q9Y6B2\tQ9Y6B2\r\n+NX_Q9Y6B6\tQ9Y6B6\r\n+NX_Q9Y6B7\tQ9Y6B7\r\n+NX_Q9Y6C2\tQ9Y6C2\r\n+NX_Q9Y6C5\tQ9Y6C5\r\n+NX_Q9Y6C7\tQ9Y6C7\r\n+NX_Q9Y6C9\tQ9Y6C9\r\n+NX_Q9Y6D0\tQ9Y6D0\r\n+NX_Q9Y6D5\tQ9Y6D5\r\n+NX_Q9Y6D6\tQ9Y6D6\r\n+NX_Q9Y6D9\tQ9Y6D9\r\n+NX_Q9Y6E0\tQ9Y6E0\r\n+NX_Q9Y6E2\tQ9Y6E2\r\n+NX_Q9Y6E7\tQ9Y6E7\r\n+NX_Q9Y6F1\tQ9Y6F1\r\n+NX_Q9Y6F6\tQ9Y6F6\r\n+NX_Q9Y6F7\tQ9Y6F7\r\n+NX_Q9Y6F8\tQ9Y6F8\r\n+NX_Q9Y6F9\tQ9Y6F9\r\n+NX_Q9Y6G1\tQ9Y6G1\r\n+NX_Q9Y6G3\tQ9Y6G3\r\n+NX_Q9Y6G5\tQ9Y6G5\r\n+NX_Q9Y6G9\tQ9Y6G9\r\n+NX_Q9Y6H1\tQ9Y6H1\r\n+NX_Q9Y6H3\tQ9Y6H3\r\n+NX_Q9Y6H5\tQ9Y6H5\r\n+NX_Q9Y6H6\tQ9Y6H6\r\n+NX_Q9Y6H8\tQ9Y6H8\r\n+NX_Q9Y6I0\tQ9Y6I0\r\n+NX_Q9Y6I3\tQ9Y6I3\r\n+NX_Q9Y6I4\tQ9Y6I4\r\n+NX_Q9Y6I7\tQ9Y6I7\r\n+NX_Q9Y6I8\tQ9Y6I8\r\n+NX_Q9Y6I9\tQ9Y6I9\r\n+NX_Q9Y6J0\tQ9Y6J0\r\n+NX_Q9Y6J3\tQ9Y6J3\r\n+NX_Q9Y6J6\tQ9Y6J6\r\n+NX_Q9Y6J8\tQ9Y6J8\r\n+NX_Q9Y6J9\tQ9Y6J9\r\n+NX_Q9Y6K0\tQ9Y6K0\r\n+NX_Q9Y6K1\tQ9Y6K1\r\n+NX_Q9Y6K5\tQ9Y6K5\r\n+NX_Q9Y6K8\tQ9Y6K8\r\n+NX_Q9Y6K9\tQ9Y6K9\r\n+NX_Q9Y6L6\tQ9Y6L6\r\n+NX_Q9Y6L7\tQ9Y6L7\r\n+NX_Q9Y6M0\tQ9Y6M0\r\n+NX_Q9Y6M1\tQ9Y6M1\r\n+NX_Q9Y6M4\tQ9Y6M4\r\n+NX_Q9Y6M5\tQ9Y6M5\r\n+NX_Q9Y6M7\tQ9Y6M7\r\n+NX_Q9Y6M9\tQ9Y6M9\r\n+NX_Q9Y6N1\tQ9Y6N1\r\n+NX_Q9Y6N3\tQ9Y6N3\r\n+NX_Q9Y6N5\tQ9Y6N5\r\n+NX_Q9Y6N6\tQ9Y6N6\r\n+NX_Q9Y6N7\tQ9Y6N7\r\n+NX_Q9Y6N8\tQ9Y6N8\r\n+NX_Q9Y6N9\tQ9Y6N9\r\n+NX_Q9Y6P5\tQ9Y6P5\r\n+NX_Q9Y6Q1\tQ9Y6Q1\r\n+NX_Q9Y6Q2\tQ9Y6Q2\r\n+NX_Q9Y6Q3\tQ9Y6Q3\r\n+NX_Q9Y6Q5\tQ9Y6Q5\r\n+NX_Q9Y6Q6\tQ9Y6Q6\r\n+NX_Q9Y6Q9\tQ9Y6Q9\r\n+NX_Q9Y6R0\tQ9Y6R0\r\n+NX_Q9Y6R1\tQ9Y6R1\r\n+NX_Q9Y6R4\tQ9Y6R4\r\n+NX_Q9Y6R6\tQ9Y6R6\r\n+NX_Q9Y6R7\tQ9Y6R7\r\n+NX_Q9Y6R9\tQ9Y6R9\r\n+NX_Q9Y6S9\tQ9Y6S9\r\n+NX_Q9Y6T7\tQ9Y6T7\r\n+NX_Q9Y6U3\tQ9Y6U3\r\n+NX_Q9Y6U7\tQ9Y6U7\r\n+NX_Q9Y6V0\tQ9Y6V0\r\n+NX_Q9Y6V7\tQ9Y6V7\r\n+NX_Q9Y6W3\tQ9Y6W3\r\n+NX_Q9Y6W5\tQ9Y6W5\r\n+NX_Q9Y6W6\tQ9Y6W6\r\n+NX_Q9Y6W8\tQ9Y6W8\r\n+NX_Q9Y6X0\tQ9Y6X0\r\n+NX_Q9Y6X1\tQ9Y6X1\r\n+NX_Q9Y6X2\tQ9Y6X2\r\n+NX_Q9Y6X3\tQ9Y6X3\r\n+NX_Q9Y6X4\tQ9Y6X4\r\n+NX_Q9Y6X5\tQ9Y6X5\r\n+NX_Q9Y6X6\tQ9Y6X6\r\n+NX_Q9Y6X8\tQ9Y6X8\r\n+NX_Q9Y6X9\tQ9Y6X9\r\n+NX_Q9Y6Y0\tQ9Y6Y0\r\n+NX_Q9Y6Y1\tQ9Y6Y1\r\n+NX_Q9Y6Y8\tQ9Y6Y8\r\n+NX_Q9Y6Y9\tQ9Y6Y9\r\n+NX_Q9Y6Z2\tQ9Y6Z2\r\n+NX_Q9Y6Z4\tQ9Y6Z4\r\n+NX_Q9Y6Z5\tQ9Y6Z5\r\n+NX_Q9Y6Z7\tQ9Y6Z7\r\n+NX_Q9YNA8\tQ9YNA8\r\n+NX_S4R3P1\tS4R3P1\r\n+NX_S4R3Y5\tS4R3Y5\r\n+NX_U3KPV4\tU3KPV4\r\n+NX_W5XKT8\tW5XKT8\r\n' |
b |
diff -r 000000000000 -r 02c549457875 id_converter.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/id_converter.xml Fri Sep 15 06:02:03 2017 -0400 |
[ |
@@ -0,0 +1,189 @@ +<tool id="IDconverter" name="ID Converter" version="0.1.0"> + <description>converts identifiers which are of a different type/source to another type of identifiers and create the identifier lists. + </description> + <requirements> + </requirements> + <stdio> + <exit_code range="1:" /> + </stdio> + <command interpreter="Rscript"> + id_converter_UniProt.R + "$idti.idtypein" + #if $input.ids == "text" + "$input.txt" + "list" + #else + "$input.file,$input.ncol,$input.header" + "file" + #end if + "$idto.idtypeout" + "$output" + $__tool_directory__/ID_mapping_Uniprot_HomoSapiens_20170809.txt + $__tool_directory__/Nextprot_Uniprot_id_mapping_file.txt + + </command> + <inputs> + <conditional name="input" > + <param name="ids" type="select" label="Provide your identifiers" help="Copy/paste or ID list from a file (e.g. table)" > + <option value="text">Copy/paste your identifiers</option> + <option value="file">Input file containing your identifiers</option> + </param> + <when value="text" > + <param name="txt" type="text" label="Copy/paste your identifiers" help='IDs must be separated by spaces into the form field, for example: P31946 P62258' > + <sanitizer> + <valid initial="string.printable"> + <remove value="'"/> + </valid> + <mapping initial="none"> + <add source="'" target="__sq__"/> + </mapping> + </sanitizer> + </param> + </when> + <when value="file" > + <param name="file" type="data" format="txt,tabular" label="Choose a file that contains your list of IDs" help="" /> + <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does your input file contain header?" /> + <param name="ncol" type="text" label="The column number of IDs to map" help='For example, fill in "c1" if it is the first column, "c2" if it is the second column and so on' /> + </when> + </conditional> + <conditional name="idti" > + <param name="idtypein" type="select" label="Select type/source of identifier of your list" > + <option value="neXtProt_ID" >neXtProt ID</option> + <option value="UNIPROT_AC" >Uniprot accession number</option> + <option value="UNIPROT_ID" >Uniprot ID</option> + <option value="GeneID_EntrezGene" >Entrez gene ID</option> + <option value="RefSeq" >RefSeq (NCBI) protein</option> + <option value="GI_number" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI</option> + <option value="PDB" >Protein DataBank ID</option> + <option value="GO_ID" >GOterms (Gene Ontology) ID</option> + <option value="PIR" >Protein Information Resource ID</option> + <option value="OMIM" >OMIM (Online Mendelian Inheritance in Man database) ID</option> + <option value="UniGene" >Unigene ID</option> + <option value="Ensembl.ENSG" >Ensembl gene ID</option> + <option value="Ensembl.ENST" >Ensembl transcript ID</option> + <option value="Ensembl.ENSP" >Ensembl protein ID</option> + </param> + <when value="neXtProt_ID" > + </when> + <when value="UNIPROT_AC" > + </when> + <when value="UNIPROT_ID" > + </when> + <when value="GeneID_EntrezGene" > + </when> + <when value="RefSeq" > + </when> + <when value="GI_number" > + </when> + <when value="PDB" > + </when> + <when value="GO_ID" > + </when> + <when value="PIR" > + </when> + <when value="OMIM" > + </when> + <when value="UniGene" > + </when> + <when value="Ensembl.ENSG" > + </when> + <when value="Ensembl.ENST" > + </when> + <when value="Ensembl.ENSP" > + </when> + </conditional> + <section name="idto" title="Target type of IDs" expanded="True" > + <param name="idtypeout" type="select" label="Target type of IDs you would like to map to" display="checkboxes" multiple="True" > + <option value="neXtProt_ID" >neXtProt ID</option> + <option value="UNIPROT_AC" >Uniprot accession number</option> + <option value="UNIPROT_ID" >Uniprot ID</option> + <option value="GeneID_EntrezGene" >Entrez gene ID</option> + <option value="RefSeq" >RefSeq (NCBI) protein</option> + <option value="GI_number" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI</option> + <option value="PDB" >Protein DataBank ID</option> + <option value="GO_ID" >GOterms (Gene Ontology) ID</option> + <option value="PIR" >Protein Information Resource ID</option> + <option value="OMIM" >OMIM (Online Mendelian Inheritance in Man database) ID</option> + <option value="UniGene" >Unigene ID</option> + <option value="Ensembl.ENSG" >Ensembl gene ID</option> + <option value="Ensembl.ENST" >Ensembl transcript ID</option> + <option value="Ensembl.ENSP" >Ensembl protein ID</option> + </param> + </section> + </inputs> + <outputs> + <data name="output" format="tabular" /> + </outputs> + <tests> + <test> + <conditional name="input"> + <param name="ids" value="file" /> + <param name="file" value="UnipIDs.txt" /> + <param name="header" value="false" /> + <param name="ncol" value="c1" /> + </conditional> + <conditional name="idti"> + <param name="idtypein" value="UNIPROT_AC" /> + </conditional> + <section name="idto"> + <param name="idtypeout" value="Ensembl.ENSP,Ensembl.ENSG,neXtProt_ID" /> + </section> + <output name="output" file="output.txt" /> + </test> + </tests> + <help><![CDATA[ +This tool converts a list of IDs to another identifier type, select the source and target type from the dropdown menus above (see below supported source and target types). + +After choosing the type of input IDs, you can choose one or more types of IDs you would like to map to. + +If your input is a list of IDs or a single-column file, the tool will return a file containing the mapped IDs. + +If your input is a multiple-column file, the mapped IDs column(s) will be added at the end of the input file. + +**Available databases** + +* neXtProt ID + +* Uniprot accession number + +* Uniprot ID + +* Entrez gene ID + +* RefSeq (NCBI) protein + +* GI (NCBI GI number) ID assigned to each sequence record processed by NCBI + +* Protein DataBank ID + +* GOterms (Gene Ontology) ID + +* Protein Information Resource ID + +* OMIM (Online Mendelian Inheritance in Man database) ID + +* Unigene ID + +* Ensembl gene ID + +* Ensembl transcript ID + +* Ensembl protein ID + +----- + +.. class:: infomark + +**Authors** + +T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR +Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform + +This work has been partially funded through the French National Agency for Research (ANR) IFB project. + +Contact support@proteore.org for any questions or concerns about the Galaxy implementation of this tool. + + ]]></help> + <citations> + </citations> +</tool> |
b |
diff -r 000000000000 -r 02c549457875 id_converter_UniProt.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/id_converter_UniProt.R Fri Sep 15 06:02:03 2017 -0400 |
[ |
@@ -0,0 +1,115 @@ +# Read file and return file content as data.frame +readfile = function(filename, header) { + if (header == "true") { + # Read only first line of the file as header: + headers <- read.table(filename, nrows = 1, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE) + #Read the data of the files (skipping the first row) + file <- read.table(filename, skip = 1, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE) + #And assign the header to the data + names(file) <- headers + } + else { + file <- read.table(filename, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE) + } + return(file) +} + +# Mapping IDs using file built from Uniprot file source (ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/taxonomic_divisions/uniprot_sprot_human.dat.gz) +# Available databases: +# UNIPROT_AC: Uniprot accession number (e.g. P31946) +# UNIPROT_ID: Uniprot identifiers (e.g 1433B_HUMAN) +# GeneID_EntrezGene: Entrez gene ID (serie of digit) (e.g. 7529) +# RefSeq: RefSeq (NCBI) protein (e.g. NP_003395.1; NP_647539.1; XP_016883528.1) +# GI_number: GI (NCBI GI number) ID (serie of digits) assigned to each sequence record processed by NCBI (e.g; 21328448; 377656701; 67464627; 78101741) +# PDB: Protein DataBank Identifiers (e.g. 2BR9:A; 3UAL:A; 3UBW:A) +# GO_ID: GOterms (Gene Ontology) Identifiers (e.g. GO:0070062; GO:0005925; GO:0042470; GO:0016020; GO:0005739; GO:0005634) +# PIR: Protein Information Resource ID (e.g. S34755) +# OMIM: OMIM (Online Mendelian Inheritance in Man database) ID (serie of digits) (e.g: 601289) +# UniGene: Unigene Identifier (e.g. Hs.643544) +# Ensembl_ENSG: Ensembl gene identifiers (e.g. ENSG00000166913) +# Ensembl_ENST: Ensembl transcript identifiers (e.g. ENST00000353703; ENST00000372839) +# Ensembl_ENSP: Ensembl protein identifiers (e.g. ENSP00000300161; ENSP00000361930) + +mapping = function() { + # Extract arguments + args = commandArgs(trailingOnly = TRUE) + #print(args) + if (length(args) != 7) { + stop("Not enough/Too many arguments", call. = FALSE) + } + else { + input_id_type = args[1] + list_id = args[2] + list_id_input_type = args[3] + options = strsplit(args[4], ",")[[1]] + output = args[5] + uniprot_map_file = args[6] + np_uniprot_file = args[7] + + # Extract ID maps + uniprot_map = read.table(uniprot_map_file, header = TRUE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE) + np_uniprot = read.table(np_uniprot_file, header = TRUE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE) + + # Extract input IDs + if (list_id_input_type == "list") { + list_id = strsplit(args[2], " ")[[1]] + } + else if (list_id_input_type == "file") { + filename = as.character(strsplit(list_id, ",")[[1]][1]) + column_number = as.numeric(gsub("c", "" ,strsplit(list_id, ",")[[1]][2])) + header = strsplit(list_id, ",")[[1]][3] + file_all = readfile(filename, header) + list_id = c() + list_id = sapply(strsplit(file_all[,column_number], ";"), "[", 1) + } + names = c() + + # Map IDs + res = matrix(nrow=length(list_id), ncol=0) + + for (opt in options) { + names = c(names, opt) + # Map to neXtProt ID + if (opt == "neXtProt_ID") { + if (input_id_type == "UNIPROT_AC") { + mapped = sapply(strsplit(np_uniprot[match(list_id, np_uniprot$Uniprot_AC),]$neXtProt_ID, ";"), "[", 1) + } + else if (input_id_type == "neXtProt_ID") { + mapped = matrix(list_id) + } + else { + uniprot = sapply(strsplit(uniprot_map[match(list_id, uniprot_map[input_id_type][,]),]$UNIPROT_AC, ";"), "[", 1) + mapped = sapply(strsplit(np_uniprot[match(uniprot, np_uniprot$Uniprot_AC),]$neXtProt_ID, ";"), "[", 1) + } + } + # Map to other ID types + else { + if (input_id_type == "neXtProt_ID") { + uniprot = sapply(strsplit(np_uniprot[match(list_id, np_uniprot$neXtProt_ID),]$Uniprot_AC, ";"), "[", 1) + mapped = sapply(strsplit(uniprot_map[match(uniprot, uniprot_map$UNIPROT_AC),][opt][,], ";"), "[", 1) + } + else { + mapped = sapply(strsplit(uniprot_map[match(list_id, uniprot_map[input_id_type][,]),][opt][,], ";"), "[", 1) + } + } + res = cbind(res, matrix(mapped)) + } + + # Write output + if (list_id_input_type == "list") { + res = cbind(as.matrix(list_id), res) + names = c(input_id_type, names) + colnames(res) = names + write.table(res, output, row.names = FALSE, sep = "\t", quote = FALSE) + } + else if (list_id_input_type == "file") { + names(res) = options + names = c(names(file_all), names) + output_content = cbind(file_all, res) + colnames(output_content) = names + write.table(output_content, output, row.names = FALSE, sep = "\t", quote = FALSE) + } + } +} + +mapping() |
b |
diff -r 000000000000 -r 02c549457875 test-data/UnipIDs.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/UnipIDs.txt Fri Sep 15 06:02:03 2017 -0400 |
b |
@@ -0,0 +1,25 @@ +P04637 +P08246 +P63244 +P10275 +P00533 +Q14524 +P05067 +P35555 +P35222 +O95273 +P00451 +P38398 +Q05086 +Q12802 +P68871 +P04585 +Q96EB6 +Q9NYL2 +P31749 +P01137 +Q5S007 +Q08379 +P02649 +P35498 +P12931 |
b |
diff -r 000000000000 -r 02c549457875 test-data/output.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/output.txt Fri Sep 15 06:02:03 2017 -0400 |
b |
@@ -0,0 +1,26 @@ +V1 Ensembl.ENSP Ensembl.ENSG neXtProt_ID +P04637 ENSP00000269305 ENSG00000141510 NX_P04637 +P08246 ENSP00000263621 ENSG00000197561 NX_P08246 +P63244 ENSP00000426909 ENSG00000204628 NX_P63244 +P10275 ENSP00000363822 ENSG00000169083 NX_P10275 +P00533 ENSP00000275493 ENSG00000146648 NX_P00533 +Q14524 ENSP00000328968 ENSG00000183873 NX_Q14524 +P05067 ENSP00000284981 ENSG00000142192 NX_P05067 +P35555 ENSP00000325527 ENSG00000166147 NX_P35555 +P35222 ENSP00000344456 ENSG00000168036 NX_P35222 +O95273 ENSP00000300213 ENSG00000166946 NX_O95273 +P00451 ENSP00000327895 ENSG00000185010 NX_P00451 +P38398 ENSP00000312236 ENSG00000012048 NX_P38398 +Q05086 ENSP00000232165 ENSG00000114062 NX_Q05086 +Q12802 ENSP00000354718 ENSG00000170776 NX_Q12802 +P68871 ENSP00000333994 ENSG00000244734 NX_P68871 +P04585 NA NA NA +Q96EB6 ENSP00000212015 ENSG00000096717 NX_Q96EB6 +Q9NYL2 ENSP00000340257 ENSG00000091436 NX_Q9NYL2 +P31749 ENSP00000270202 ENSG00000142208 NX_P31749 +P01137 ENSP00000221930 ENSG00000105329 NX_P01137 +Q5S007 ENSP00000298910 ENSG00000188906 NX_Q5S007 +Q08379 ENSP00000416097 ENSG00000167110 NX_Q08379 +P02649 ENSP00000252486 ENSG00000130203 NX_P02649 +P35498 ENSP00000303540 ENSG00000144285 NX_P35498 +P12931 ENSP00000350941 ENSG00000197122 NX_P12931 |