Previous changeset 1:1db83da40c54 (2020-03-19) Next changeset 3:4cbfd3d0a4c4 (2022-02-02) |
Commit message:
"planemo upload for repository https://github.com/computational-metabolomics/sirius_csifingerid_galaxy commit 3e3dee9a853b6133cf089b3c063f53c52b39463d" |
modified:
sirius_csifingerid.py sirius_csifingerid.xml test-data/CCMSLIB00000578155_result.tsv test-data/ML006801.tsv test-data/RP022611_result.tsv test-data/generic.tsv |
added:
test-data/RP022611_result_all_adducts.tsv |
b |
diff -r 1db83da40c54 -r 856b3761277d sirius_csifingerid.py --- a/sirius_csifingerid.py Thu Mar 19 07:30:54 2020 -0400 +++ b/sirius_csifingerid.py Thu Jul 02 11:01:45 2020 -0400 |
[ |
@@ -25,12 +25,15 @@ parser.add_argument('--out_dir') parser.add_argument('--tool_directory') parser.add_argument('--temp_dir') - parser.add_argument('--meta_select_col', default='all') parser.add_argument('--cores_top_level', default=1) parser.add_argument('--chunks', default=1) parser.add_argument('--minMSMSpeaks', default=1) +parser.add_argument('--rank_filter', default=0) parser.add_argument('--schema', default='msp') +parser.add_argument('-a', '--adducts', action='append', nargs=1, + required=False, default=[], help='Adducts used') + args = parser.parse_args() print(args) if os.stat(args.input_pth).st_size == 0: @@ -48,6 +51,15 @@ wd = os.path.join(td, str(uuid.uuid4())) os.mkdir(wd) +print(args.adducts) +if args.adducts: + adducts_from_cli = [ + a[0].replace('__ob__', '[').replace('__cb__', ']') for a in + args.adducts + ] +else: + adducts_from_cli = [] + ###################################################################### # Setup regular expressions for MSP parsing dictionary ###################################################################### @@ -62,6 +74,12 @@ r'^adduct(?:=|:)(.*)$', r'^ADDUCTIONNAME(?:=|:)(.*)$'] regex_msp['num_peaks'] = [r'^Num.*Peaks(?:=|:)\s*(\d*)$'] +regex_msp['retention_time'] = [r'^RETENTION.*TIME(?:=|:)\s*(.*)$', + r'^rt(?:=|:)\s*(.*)$', + r'^time(?:=|:)\s*(.*)$'] +# From example winter_pos.mspy from kristian +regex_msp['AlignmentID'] = [r'^AlignmentID(?:=|:)\s*(.*)$'] + regex_msp['msp'] = [r'^Name(?:=|:)(.*)$'] # Flag for standard MSP format regex_massbank = {} @@ -73,9 +91,12 @@ regex_massbank['precursor_type'] = \ [r'^MS\$FOCUSED_ION:\s+PRECURSOR_TYPE\s+(.*)$'] regex_massbank['num_peaks'] = [r'^PK\$NUM_PEAK:\s+(\d*)'] +regex_massbank['retention_time'] = [ + r'^AC\$CHROMATOGRAPHY:\s+RETENTION_TIME\s*(\d*\.?\d+).*'] regex_massbank['cols'] = [r'^PK\$PEAK:\s+(.*)'] regex_massbank['massbank'] = [r'^RECORD_TITLE:(.*)$'] # Flag for massbank + if args.schema == 'msp': meta_regex = regex_msp elif args.schema == 'massbank': @@ -141,6 +162,8 @@ # record name (i.e. when using msPurity and we have the columns # coded into the name) or just the spectra index (spectrac) paramd = init_paramd(args) + meta_info = {k: v for k, v in meta_info.items() if k + not in ['msp', 'massbank', 'cols']} if args.meta_select_col == 'name': # have additional column of just the name @@ -177,15 +200,22 @@ # Replace param details with details from MSP if required if 'precursor_type' in meta_info and meta_info['precursor_type']: paramd["cli"]["--ion"] = meta_info['precursor_type'] + adduct = meta_info['precursor_type'] else: if paramd["default_ion"]: paramd["cli"]["--ion"] = paramd["default_ion"] + adduct = paramd["default_ion"] else: paramd["cli"]["--auto-charge"] = '' if 'precursor_mz' in meta_info and meta_info['precursor_mz']: paramd["cli"]["--precursor"] = meta_info['precursor_mz'] + if not ('precursor_type' in paramd['additional_details'] or 'adduct' + in paramd['additional_details']): + # If possible always good to have the adduct in output as a column + paramd['additional_details']['adduct'] = adduct + # ============== Create CLI cmd for metfrag =============================== cmd = "sirius --fingerid" for k, v in six.iteritems(paramd["cli"]): @@ -248,11 +278,23 @@ elif plinesread and plinesread == pnumlines: # ======= Get sample name and additional details for output ======= - spectrac += 1 - paramd, cmd = run_sirius(meta_info, peaklist, args, wd, spectrac) + if adducts_from_cli: + for adduct in adducts_from_cli: + print(adduct) + spectrac += 1 + meta_info['precursor_type'] = adduct + paramd, cmd = run_sirius(meta_info, peaklist, args, wd, + spectrac) - paramds[paramd["SampleName"]] = paramd - cmds.append(cmd) + paramds[paramd["SampleName"]] = paramd + cmds.append(cmd) + else: + spectrac += 1 + paramd, cmd = run_sirius(meta_info, peaklist, args, wd, + spectrac) + + paramds[paramd["SampleName"]] = paramd + cmds.append(cmd) meta_info = {} pnumlines = 0 @@ -262,10 +304,23 @@ # run metfrag on still if plinesread and plinesread == pnumlines: - paramd, cmd = run_sirius(meta_info, peaklist, args, wd, spectrac + 1) + if adducts_from_cli: + for adduct in adducts_from_cli: + print(adduct) + spectrac += 1 + meta_info['precursor_type'] = adduct + paramd, cmd = run_sirius(meta_info, peaklist, args, wd, + spectrac) - paramds[paramd["SampleName"]] = paramd - cmds.append(cmd) + paramds[paramd["SampleName"]] = paramd + cmds.append(cmd) + else: + spectrac += 1 + paramd, cmd = run_sirius(meta_info, peaklist, args, wd, + spectrac) + + paramds[paramd["SampleName"]] = paramd + cmds.append(cmd) # Perform multiprocessing on command line call level if int(args.cores_top_level) > 1: @@ -321,6 +376,10 @@ ad = paramds[fn.split(os.sep)[-3]]['additional_details'] for line in reader: + if 0 < int(args.rank_filter) < int(line['rank']): + # filter out those annotations greater than rank filter + # If rank_filter is zero then skip + continue line.update(ad) # round score to 5 d.p. line['score'] = round(float(line['score']), 5) |
b |
diff -r 1db83da40c54 -r 856b3761277d sirius_csifingerid.xml --- a/sirius_csifingerid.xml Thu Mar 19 07:30:54 2020 -0400 +++ b/sirius_csifingerid.xml Thu Jul 02 11:01:45 2020 -0400 |
[ |
@@ -1,5 +1,5 @@ <tool id="sirius_csifingerid" name="SIRIUS-CSI:FingerID" - version="4.0.1+galaxy3" profile="18.01"> + version="4.0.1+galaxy4" profile="18.01"> <description>is used to identify metabolites using single and tandem mass spectrometry</description> <requirements> @@ -24,6 +24,29 @@ --schema $schema --temp_dir . + #if $adducts_cond.adducts_selector == 'select': + #for $a in $adducts_cond.adducts + --adducts $a + #end for + #elif $adducts_cond.adducts_selector == 'all': + #if $polarity == 'positive': + --adducts [M+H]+ + --adducts [M+NH4]+ + --adducts [M+Na]+ + --adducts [M+K]+ + --adducts [M+CH3OH+H]+ + --adducts [M+ACN+H]+ + --adducts [M+ACN+Na]+ + --adducts [M+2ACN+H]+ + #elif $polarity == 'negative': + --adducts [M-H]- + --adducts [M+Cl]- + --adducts [M+HCOO]- + --adducts [M+CH3COO]- + #end if + #end if + + --rank_filter $rank_filter ]]></command> <inputs> <param name="input" argument="--input_pth" type="data" format="msp" @@ -76,6 +99,40 @@ </param> <param argument="--minMSMSpeaks" type="integer" min="0" value="0" label="Minimum number of MS/MS peaks"/> + + <conditional name="adducts_cond"> + <param name="adducts_selector" type="select" label="How to handle adducts" + help="Choose whether to include a suspect list"> + <option value="msp" selected="True">Use adducts defined in MSP file</option> + <option value="select" >Select from list of adducts</option> + <option value="all" >Use pre-selected adducts for either pos or neg ionisation mode</option> + </param> + <when value="msp"> + </when> + <when value="select"> + <param argument="--adducts" label="Select adducts" + type="select" help="" multiple="true" display="checkboxes"> + <option value="[M+H]+" selected="True">[M+H]+ 1.007276</option> + <option value="[M+NH4]+">[M+NH4]+ 18.034374</option> + <option value="[M+Na]+">[M+Na]+ 22.989218</option> + <option value="[M+K]+">[M+K]+ 38.963158</option> + <option value="[M+CH3OH+H]+">[M+CH3OH+H]+ 33.033489</option> + <option value="[M+ACN+H]+">[M+ACN+H]+ 42.033823</option> + <option value="[M+ACN+Na]+">[M+ACN+Na]+ 64.015765</option> + <option value="[M+2ACN+H]+">[M+2ACN+H]+ 83.06037</option> + <option value="[M-H]-" >[M-H]- -1.007276</option> + <option value="[M+Cl]-">[M+Cl]- 34.969402</option> + <option value="[M+HCOO]-">[M+HCOO]- 44.99819</option> + <option value="[M+CH3COO]-">[M+CH3COO]- 59.01385</option> + </param> + </when> + <when value="all"> + </when> + </conditional> + + <param argument="--rank_filter" type="integer" value="0" + label="Only show the top ranked annotations less than or equal + to this value (default to show all annotations)"/> </inputs> <outputs> <data name="results" format="tsv" @@ -109,6 +166,17 @@ <param name="input" value="invalid_adduct.msp" ftype="msp"/> <output name="results" file="invalid_adduct_result.tsv"/> </test> + <test> + <!-- Test all adducts --> + <param name="input" value="RP022611.txt" ftype="msp"/> + <param name="profile" value="qtof"/> + <param name="polarity" value="negative"/> + <conditional name="adducts_cond"> + <param name="adducts_selector" value="all"/> + </conditional> + <output name="results" file="RP022611_result_all_adducts.tsv"/> + + </test> </tests> <help> ---------------- @@ -118,13 +186,13 @@ Description ----------- -| SIRIUS is a java-based software framework for discovering a landscape of -| de-novo identification of metabolites using single and tandem mass -| spectrometry. SIRIUS uses isotope pattern analysis for detecting the -| molecular formula and further analyses the fragmentation pattern of a -| compound using fragmentation trees. Website: -| https://bio.informatik.uni-jena.de/software/sirius/ -| +SIRIUS is a java-based software framework for discovering a landscape of +de-novo identification of metabolites using single and tandem mass +spectrometry. SIRIUS uses isotope pattern analysis for detecting the +molecular formula and further analyses the fragmentation pattern of a +compound using fragmentation trees. Website: +https://bio.informatik.uni-jena.de/software/sirius/ + Parameters ---------- |
b |
diff -r 1db83da40c54 -r 856b3761277d test-data/CCMSLIB00000578155_result.tsv --- a/test-data/CCMSLIB00000578155_result.tsv Thu Mar 19 07:30:54 2020 -0400 +++ b/test-data/CCMSLIB00000578155_result.tsv Thu Jul 02 11:01:45 2020 -0400 |
[ |
b'@@ -1,9 +1,9 @@\n-name\tinchikey2D\tinchi\tmolecularFormula\trank\tscore\tname\tsmiles\txlogp\tpubchemids\tlinks\r\n-D-GLUCOSE-6-PHOSPHATE\tNBSCHQHZLSJFNQ\tInChI=1S/C6H13O9P/c7-3-2(1-14-16(11,12)13)15-6(10)5(9)4(3)8/h2-10H,1H2,(H2,11,12,13)\tC6H13O9P\t1\t-2956.17597\tD-GLUCOSE-6-PHOSPHATE\tC(C1C(C(C(C(O)O1)O)O)O)OP(=O)(O)O\t\t208;5958;65127;439198;439284;439404;439427;440100;447096;449526;4178491;4459709;9817215;9859975;10038266;10332946;10422797;10422798;10848963;11499884;11536233;11651816;11651817;11701643;12314997;12598269;16219407;21604864;21604865;23421197;23421199;23421200;24802166;25200774;25244236;42609823;44589902;44629605;46936284;51351673;51351674;59660207;59660208;66804219;70828590;71048769;72200063;89530481;89533633;90087729;90657928;92043642;92144442;92331699;92450038;100983220;101251820;102072969;124302956;124303605\tHMDB:(3498);KNApSAcK:(7307);Natural Products:(UNPD119019 UNPD208877);CHEBI:(47944 136602 41076 4141 17665 134068 91004 61567 61667 4170 61548 58735 17719 58225 60332 58247 48066);KEGG:(C02962 C03735 C00275 C02965 C01172 C00092 C00668 C01113);Plantcyc:(MANNOSE-6P CPD-15711 CPD-15712 D-HEXOSE-6-PHOSPHATE GLC-6-P ALPHA-GLC-6-P CPD-1241);YMDB:(2311);Biocyc:(CPD-15712 CPD-1241)\r\n-D-GLUCOSE-6-PHOSPHATE\tHXXFSFRBOHSIMQ\tInChI=1S/C6H13O9P/c7-1-2-3(8)4(9)5(10)6(14-2)15-16(11,12)13/h2-10H,1H2,(H2,11,12,13)\tC6H13O9P\t2\t-2968.893\tD-GLUCOSE-6-PHOSPHATE\tC(C1C(C(C(C(O1)OP(=O)(O)O)O)O)O)O\t\t466;65533;122250;123912;439165;439279;439426;439995;644175;1549075;1549076;3034296;3246168;3551220;5702593;6560208;6560209;7091266;7098639;10084035;11108064;11299931;11536234;11557960;11586967;11637475;11701642;12773693;12773694;15720053;20706002;21120286;22298591;23421196;23421198;23724605;23724607;24802153;24802168;25134172;25244208;25245607;26470622;26470623;26470920;26470921;26470922;40467866;40467867;40467868;40473131;40473132;42609824;44224049;45109780;46173227;46173228;46878478;51397481;57349329;57466719;57616986;57616987;58434201;59383287;59973641;59973642;59985133;60023647;67062884;67062905;67062913;67062918;67794900;68298161;68937634;70124502;70837719;71122101;71728461;88462985;90472756;91265893;91658980;101503810;101747832;101747833;121494054;122545953;125293590;125293595;125293596;125293598\tHMDB:(62705);KNApSAcK:(7389);Natural Products:(UNPD85752 UNPD57928 UNPD186485);CHEBI:(16077 17973 75522 24588 53072 58601 57684 60389 58336 60465 53025 16326 80181 58908 18205 16218 58409 57629);KEGG:(C15924 C15926 C01171 C03384 C00636 C00446 C01002 C00103 C00663);Plantcyc:(CPD-9828 GALACTOSE-1P GLC-1-P MANNOSE-1P CPDQT-4 CPD-448 CPD4FS-5);YMDB:(970);Biocyc:(CPD4FS-5)\r\n-D-GLUCOSE-6-PHOSPHATE\tBGWGXPAPYGQALX\tInChI=1S/C6H13O9P/c7-2-6(10)5(9)4(8)3(15-6)1-14-16(11,12)13/h3-5,7-10H,1-2H2,(H2,11,12,13)\tC6H13O9P\t3\t-2996.82333\tD-GLUCOSE-6-PHOSPHATE\tC(C1C(C(C(CO)(O)O1)O)O)OP(=O)(O)O\t\t719;124155;439160;439396;440641;440970;444848;5083448;9543488;15648788;16760431;20843252;21604862;21604863;23421195;24802142;25201714;25245410;42609822;46174048;46878483;52916945;86308139;91746169;92024282;102322321;122174030;124300900;124350439;124524514;124579643\tHMDB:(6873);KNApSAcK:(7305);Natural Products:(UNPD153056);CHEBI:(57634 4251 81499 61553 58695 16084 6307 45804 47946 58926 61527);KEGG:(C06312 C18096 C01097 C05345 C00085);Plantcyc:(TAGATOSE-6-PHOSPHATE FRUCTOSE-6P);Biocyc:(L-TAGATOSE-6-PHOSPHATE)\r\n-D-GLUCOSE-6-PHOSPHATE\tPMTUDJVZIGZBIX\tInChI=1S/C6H13O9P/c7-1-3-4(9)5(10)6(2-8,14-3)15-16(11,12)13/h3-5,7-10H,1-2H2,(H2,11,12,13)\tC6H13O9P\t4\t-2999.57091\tD-GLUCOSE-6-PHOSPHATE\tC(C1C(C(C(CO)(O1)OP(=O)(O)O)O)O)O\t\t193537;5176477;6398638;15703397;16069990;21126112;21126113;57357663;99639213;124202606\tHMDB:(6800);CHEBI:(27884 57267 12350);KEGG:(C03267);YMDB:(878);Biocyc:(FRUCTOSE-2-PHOSPHATE)\r\n-D-GLUCOSE-6-PHOSPHATE\tRHKKZBWRNHGJEZ\tInChI=1S/C6H13O9P/c7-1-3-4(8)5(9)6(10,15-3)2-14-16(11,12)13/h3-5,7-10H,1-2H2,(H2,11,12,13)\tC6H13O9P\t5\t-3000.17545\tD-GLUCOSE-6-PHOSPHATE\tC(C1C(C(C(COP(=O)(O)O)(O)O1)O)O)O\t\t717;439394;10400369;21627880;23421194;25244216;51397484;52916944;90658050;90658051;90659357'..b'918;67794900;68298161;68937634;70124502;70837719;71122101;71728461;88462985;90472756;91265893;91658980;101503810;101747832;101747833;121494054;122545953;125293590;125293595;125293596;125293598\tHMDB:(62705);KNApSAcK:(7389);Natural Products:(UNPD85752 UNPD57928 UNPD186485);CHEBI:(16077 17973 75522 24588 53072 58601 57684 60389 58336 60465 53025 16326 80181 58908 18205 16218 58409 57629);KEGG:(C15924 C15926 C01171 C03384 C00636 C00446 C01002 C00103 C00663);Plantcyc:(CPD-9828 GALACTOSE-1P GLC-1-P MANNOSE-1P CPDQT-4 CPD-448 CPD4FS-5);YMDB:(970);Biocyc:(CPD4FS-5)\r\n+D-GLUCOSE-6-PHOSPHATE\t[M-H]-\tBGWGXPAPYGQALX\tInChI=1S/C6H13O9P/c7-2-6(10)5(9)4(8)3(15-6)1-14-16(11,12)13/h3-5,7-10H,1-2H2,(H2,11,12,13)\tC6H13O9P\t3\t-2996.82333\tD-GLUCOSE-6-PHOSPHATE\tC(C1C(C(C(CO)(O)O1)O)O)OP(=O)(O)O\t\t719;124155;439160;439396;440641;440970;444848;5083448;9543488;15648788;16760431;20843252;21604862;21604863;23421195;24802142;25201714;25245410;42609822;46174048;46878483;52916945;86308139;91746169;92024282;102322321;122174030;124300900;124350439;124524514;124579643\tHMDB:(6873);KNApSAcK:(7305);Natural Products:(UNPD153056);CHEBI:(57634 4251 81499 61553 58695 16084 6307 45804 47946 58926 61527);KEGG:(C06312 C18096 C01097 C05345 C00085);Plantcyc:(TAGATOSE-6-PHOSPHATE FRUCTOSE-6P);Biocyc:(L-TAGATOSE-6-PHOSPHATE)\r\n+D-GLUCOSE-6-PHOSPHATE\t[M-H]-\tPMTUDJVZIGZBIX\tInChI=1S/C6H13O9P/c7-1-3-4(9)5(10)6(2-8,14-3)15-16(11,12)13/h3-5,7-10H,1-2H2,(H2,11,12,13)\tC6H13O9P\t4\t-2999.57091\tD-GLUCOSE-6-PHOSPHATE\tC(C1C(C(C(CO)(O1)OP(=O)(O)O)O)O)O\t\t193537;5176477;6398638;15703397;16069990;21126112;21126113;57357663;99639213;124202606\tHMDB:(6800);CHEBI:(27884 57267 12350);KEGG:(C03267);YMDB:(878);Biocyc:(FRUCTOSE-2-PHOSPHATE)\r\n+D-GLUCOSE-6-PHOSPHATE\t[M-H]-\tRHKKZBWRNHGJEZ\tInChI=1S/C6H13O9P/c7-1-3-4(8)5(9)6(10,15-3)2-14-16(11,12)13/h3-5,7-10H,1-2H2,(H2,11,12,13)\tC6H13O9P\t5\t-3000.17545\tD-GLUCOSE-6-PHOSPHATE\tC(C1C(C(C(COP(=O)(O)O)(O)O1)O)O)O\t\t717;439394;10400369;21627880;23421194;25244216;51397484;52916944;90658050;90658051;90659357;90659358;92209483;97041850\tHMDB:(1076);KNApSAcK:(19676);CHEBI:(37515 58674);KEGG:(C01094);Plantcyc:(FRU1P);Biocyc:(CPD-16154 CPD-16158 CPD-16159)\r\n+D-GLUCOSE-6-PHOSPHATE\t[M-H]-\tINAPMGSXUVUWAF\tInChI=1S/C6H13O9P/c7-1-2(8)4(10)6(5(11)3(1)9)15-16(12,13)14/h1-11H,(H2,12,13,14)\tC6H13O9P\t6\t-3061.86763\tD-GLUCOSE-6-PHOSPHATE\tC1(C(C(C(C(C1O)O)OP(=O)(O)O)O)O)O\t\t9;107737;160886;161368;440043;440194;4449629;5288642;5288700;6323385;7098643;10659045;13072112;18654477;25200523;25200860;25203035;35027167;53924828;59824613;59824614;59824615;59824616;101661021;121400595;121403401\tHMDB:(6814);KNApSAcK:(7483);Natural Products:(UNPD107543 UNPD92136 UNPD189294);CHEBI:(58469 18169 62383 37493 18384 58433 18297 64841 58401 64838 84142 84141);KEGG:(C03546 C06155 C01177 C04006);Plantcyc:(1-L-MYO-INOSITOL-1-P D-MYO-INOSITOL-1-MONOPHOSPHATE CPD-6701 CPD-6702 CPD-6746 CPD-9887 D-MYO-INOSITOL-4-PHOSPHATE);YMDB:(2322);Biocyc:(D-MYO-INOSITOL-4-PHOSPHATE CPD-6701 CPD-6702 CPD-6746)\r\n+D-GLUCOSE-6-PHOSPHATE\t[M-H]-\tGSXOAOHZAIYLCY\tInChI=1S/C6H13O9P/c7-1-3(8)5(10)6(11)4(9)2-15-16(12,13)14/h4-7,9-11H,1-2H2,(H2,12,13,14)\tC6H13O9P\t7\t-3108.21629\tD-GLUCOSE-6-PHOSPHATE\tC(C(=O)C(C(C(COP(=O)(O)O)O)O)O)O\t\t603;69507;151197;5459902;5459952;6602428;20111689;20111690;21114947;21872891;23615358;40467872;40467873;46943428;50909805;87615581\tHMDB:(124);KNApSAcK:(19683);Natural Products:(UNPD94448);CHEBI:(57579 61519 134284 15946 15845 61559 47947 134283);Plantcyc:(D-ALLULOSE-6-PHOSPHATE);YMDB:(78);Biocyc:(CPD-15828 CPD-15826 D-ALLULOSE-6-PHOSPHATE)\r\n+D-GLUCOSE-6-PHOSPHATE\t[M-H]-\tZKLLSNQJRLJIGT\tInChI=1S/C6H13O9P/c7-1-3(8)5(10)6(11)4(9)2-15-16(12,13)14/h3,5-8,10-11H,1-2H2,(H2,12,13,14)\tC6H13O9P\t8\t-3116.86489\tD-GLUCOSE-6-PHOSPHATE\tC(C(C(C(C(=O)COP(=O)(O)O)O)O)O)O\t\t481;65246;151033;439837;440076;6101730;11129032;11737049;14844438;20111955;21145035;23615304;54551858;54551860;54551861;54551863;91010818\tHMDB:(60467);KNApSAcK:(19630);CHEBI:(38342 218 18105);KEGG:(C03654 C02888);YMDB:(655);Biocyc:(CPD-15970 CPD0-1116 CPD-531)\r\n' |
b |
diff -r 1db83da40c54 -r 856b3761277d test-data/ML006801.tsv --- a/test-data/ML006801.tsv Thu Mar 19 07:30:54 2020 -0400 +++ b/test-data/ML006801.tsv Thu Jul 02 11:01:45 2020 -0400 |
[ |
@@ -1,2 +1,2 @@ -name inchikey2D inchi molecularFormula rank score name smiles xlogp pubchemids links -L-thialysine; LC-ESI-ITFT; MS2; CE: 50%; R=7500; [M+H]+ GHSJKUNUIHUPDF InChI=1S/C5H12N2O2S/c6-1-2-10-3-4(7)5(8)9/h4H,1-3,6-7H2,(H,8,9) C5H12N2O2S 1 -7.08314 L-thialysine; LC-ESI-ITFT; MS2; CE: 50%; R=7500; [M+H]+ C(CSCC(C(=O)O)N)N 20049;99558;6995002;12898158;25246097;54754416;57517225 HMDB:(33518);Natural Products:(UNPD166389);CHEBI:(497734);Plantcyc:(S-2-AMINOETHYL-L-CYSTEINE);Biocyc:(S-2-AMINOETHYL-L-CYSTEINE THIALYSINE) +name adduct inchikey2D inchi molecularFormula rank score name smiles xlogp pubchemids links +L-thialysine; LC-ESI-ITFT; MS2; CE: 50%; R=7500; [M+H]+ [M+H]+ GHSJKUNUIHUPDF InChI=1S/C5H12N2O2S/c6-1-2-10-3-4(7)5(8)9/h4H,1-3,6-7H2,(H,8,9) C5H12N2O2S 1 -7.08314 L-thialysine; LC-ESI-ITFT; MS2; CE: 50%; R=7500; [M+H]+ C(CSCC(C(=O)O)N)N 20049;99558;6995002;12898158;25246097;54754416;57517225 HMDB:(33518);Natural Products:(UNPD166389);CHEBI:(497734);Plantcyc:(S-2-AMINOETHYL-L-CYSTEINE);Biocyc:(S-2-AMINOETHYL-L-CYSTEINE THIALYSINE) |
b |
diff -r 1db83da40c54 -r 856b3761277d test-data/RP022611_result.tsv --- a/test-data/RP022611_result.tsv Thu Mar 19 07:30:54 2020 -0400 +++ b/test-data/RP022611_result.tsv Thu Jul 02 11:01:45 2020 -0400 |
[ |
b'@@ -1,9 +1,9 @@\n-name\tinchikey2D\tinchi\tmolecularFormula\trank\tscore\tname\tsmiles\txlogp\tpubchemids\tlinks\r\n-D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tWQZGKKKJIJFFOK\tInChI=1S/C6H12O6/c7-1-2-3(8)4(9)5(10)6(11)12-2/h2-11H,1H2\tC6H12O6\t1\t-2990.5565\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tC(C1C(C(C(C(O)O1)O)O)O)O\t\t206;5793;6036;18950;64689;79025;81696;185698;439353;439357;439507;439583;439680;441035;441032;441033;441034;444314;448388;448702;451187;451188;451189;452245;455147;657055;1549080;2724488;3000450;3034742;5104362;5319264;6102790;6321330;6323336;6400264;6560213;6971003;6971007;6971016;6971096;6971097;6971098;6992021;6992084;7018164;7043897;7044038;7098663;7098664;7157007;9794056;9815418;9834129;9899007;10035228;10081060;10103794;10130220;10197954;10219674;10219763;10313382;10329946;10899282;10954241;11019447;11030410;11344362;11367383;11412863;11480819;11492034;11571906;11571917;11600783;11651921;11672764;11959770;11970126;12003287;12193653;12285853;12285856;12285861;12285862;12285863;12285866;12285868;12285869;12285870;12285871;12285873;12285877;12285878;12285879;12285885;12285886;12285889;12285890;12285891;12285892;12285893;12285894;16211884;16211941;16211984;16211986;16212959;16212960;16212966;16213546;16213640;16213872;16217112;16219580;21355827;22825318;22836365;22836366;23424086;24802149;24802163;24802281;24892722;42626680;44328781;44328785;46188479;46780441;46897877;50939543;51340651;54445181;54445182;56845432;56845995;57197748;57288387;57483528;57691826;57973135;58070804;58265153;58265160;58265166;58265178;58265190;58265196;58300638;58595959;58594768;58618581;58969552;59034276;59036328;59040622;59083882;59105109;59125088;59146659;59383280;59445439;59503407;59503411;59886072;59965103;60052896;60078648;66629908;67518639;67615000;67615455;67641738;67938791;67944215;67944290;67950444;68167579;68324677;68334110;69528681;70443535;70543261;71309028;71309128;71309129;71309140;71309397;71309503;71309513;71309514;71309671;71309852;71309905;71309908;71309927;71317094;71317095;71317096;71317097;71317182;71777654;75357255;76973265;86278404;87297824;87929779;87931119;88255060;88547603;88974141;89000581;89200515;89332529;89374440;89424182;89742272;89855666;90057933;90159939;90346255;90470917;90472751;90472752;90472753;90472761;90472762;90472770;90473076;90781811;90895196;91057721;92043367;92043446;101015849;101033892;101254308;101254309;101254310;101254311;101254312;101254313;101254314;101254315;101469918;101513786;101718250;101718251;101796201;102089288;102447462;102447463;102601142;102601177;102601371;102601743;102601816;117064633;117064644;117065485;117633116;117768413;117938207;118797420;118797610;118797621;118797622;118855887;118855889;118855904;118855910;118855920;118855925;118924468;121494058;121494046;122360911;122522140;125280077;125280078;125280079;125280080;125309563;125309564;125353406;125363512;125363513;125363514;125363515;126704391\tHMDB:(62202);KNApSAcK:(1126);Natural Products:(UNPD148053 UNPD72621 UNPD116684 UNPD119270 UNPD130932 UNPD158921 UNPD83717 UNPD175249 UNPD175204 UNPD191130 UNPD20367 UNPD175399);CHEBI:(37692 37671 37693 63421 37630 27667 72452 4191 4093 37619 15903 80962 37631 17925 37677 15444 37679 27380 4208 18246 16362 28729 37680 18269 4167 37740 59573 59552 27517 28100 37706 83029 28563 28102 37620 37686 37741 86059 4139 37744 68462 37627 28061 37704);KEGG:(C21032 C00221 C00031 C21050 C02209 C01825 C15923 C00936 C00738 C00737 C06465 C06466 C06464 C00984 C00962 C00159 C06467 C01487 C00267 C00124);Plantcyc:(ALPHA-GLUCOSE L-GALACTOSE ALPHA-D-GALACTOSE CPD-12601 CPD-13559 GALACTOSE CPD-15761 CPD-3607 CPD-15762 510-methenyl-thf GLC);YMDB:(894);Biocyc:(CPD-11613 CPD-13428 CPD-11611 CPD-13559 CPD-12844 CPD-15758 CPD-15627 CPD-15759 Alpha-D-Talose CPD-15628 L-SORBOSONE CPD-18461 CPD-15622 CPD-15624 CPD-15625 CPD-15757 CPD-15761 CPD-3607 CPD-15762 CPD-15621)\r\n-D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tRFSUNEUAIZKAJO\tInChI=1S/C6H12O6/c7-1-3-4(9)5(10)6(11,2-8)12-3/h3-5,7-11H,1-2H2\tC6H12O6\t2\t-2992'..b'CPD-10726);YMDB:(204);Biocyc:(CPD-15986 CPD-10728 CPD-15987 CPD-10726 CPD-10727 CPD-10725)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M-H]-\tBJHIKXHVCXFQLS\tInChI=1S/C6H12O6/c7-1-3(9)5(11)6(12)4(10)2-8/h3,5-9,11-12H,1-2H2\tC6H12O6\t4\t-3015.06916\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tC(C(C(C(C(=O)CO)O)O)O)O\t\t1101;5984;6904;90008;92092;107428;5460024;10965117;11458041;11961810;15559364;15559365;15559366;15559367;15975980;56846514;71310259;87203108;87883498;88364517;89357936;90194848;90471261;100938761;100938762;100938763;100938764;100938765;101274261;102026061;102525471;126737088\tHMDB:(62538);KNApSAcK:(33848);Natural Products:(UNPD157348 UNPD11673 UNPD28362 UNPD42482);CHEBI:(13172 13022 134275 47693 27605 37724 27922);HSDB:(87-79-6);KEGG:(C21523 C10906 C01452);Plantcyc:(CPD-9570 CPD-15616 PSICOSE CPD-15382 TAGATOSE);YMDB:(657);Biocyc:(CPD-15825 PSICOSE)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M-H]-\tGZCGUPFRVQAUEE\tInChI=1S/C6H12O6/c7-1-3(9)5(11)6(12)4(10)2-8/h1,3-6,8-12H,2H2\tC6H12O6\t5\t-3017.53465\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tC(=O)C(C(C(C(CO)O)O)O)O\t\t24749;64731;80127;82308;84996;90173;94780;99459;102190;102288;107526;111112;111123;111317;134512;161658;165139;165171;165863;166991;167792;168037;169509;187891;3037556;3086538;5460248;6451569;10910141;10954115;11229130;11355844;11745248;11805319;12305796;12305797;12305799;12305800;12305811;15977259;16057040;21183545;45109778;53462839;53462852;53462878;56846079;56846519;56846584;57449163;57557846;58654615;58654624;60078498;60101813;66509130;71309394;71309492;71309493;71310055;71310073;71434190;71777455;76973373;87109007;87228435;87228929;87229000;87355288;88034483;88353328;89242343;89317890;89327884;89327885;89472723;89623639;90132269;90273086;90472355;90472363;92023398;92043770;92044000;100917967;101117002;101117003;101129024;101129025;101129026;101129027;101248541;101261456;101265967;101446815;101719777;101728293;101728294;102505103;102601198;102601265;102601267;102601589;102601778;102602086;119077284;119078796;126664755\tHMDB:(62473);Natural Products:(UNPD142849 UNPD3363 UNPD7578 UNPD95755 UNPD35192 UNPD45514);CHEBI:(37681 37695 28385 37617 28014 37675 33917 86058 37701 37746 17118 37626 68461);HSDB:(50-99-7);KEGG:(C01582);Plantcyc:(CPD-15373 CPD-15374 CPD-15590);YMDB:(789);Biocyc:(CPD-7409 CPD-15626 CPD-7408 CPD-9728 UDP-GLACTOSE CPD1G-120 CPD-15629 CPD1G-2 CPD-9327 4-AMINO-BUTYRALDEHYDE CPD-7420 CPD-15590 CPD1F-130 CHOLESTEROL_ESTER CPD-15756 4-TOLUENESULFONATE CPD1F-98 DEMETHYLMENAQUINONE UBIQUINONE-9 CPD-7419 ACETONE CPD1F-129 PARATHION CPD-15383 IRON-CHELATE CPD-15760 CPD-15620 VITAMIN_K_2)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M-H]-\tCDAISMWEOUEBRE\tInChI=1S/C6H12O6/c7-1-2(8)4(10)6(12)5(11)3(1)9/h1-12H\tC6H12O6\t6\t-3046.13844\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tC1(C(C(C(C(C1O)O)O)O)O)O\t\t892;11973225;12302985;53714837;68591801;90768658;91019724;100996307;100996308\tHMDB:(34220);KNApSAcK:(1164);Natural Products:(UNPD40912 UNPD103126 UNPD106247 UNPD16776 UNPD54610 UNPD50920 UNPD136396 UNPD185125 UNPD191761);CHEBI:(27374 17268 27372 24848 25492 23927 27987 23311 10642 22357);KEGG:(C19891 C06153 C00137 C06151 C06152);Plantcyc:(MYO-INOSITOL CPD-8052 CPD-8059 CPD-8050);YMDB:(173);Biocyc:(CPD-8055 CPD-8054 CPD-8053 CPD-8059 CPD-8061 CPD-8060)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M-H]-\tKEQUNHIAUQQPAC\tInChI=1S/C6H12O6/c7-1-5(9)3-12-6(10,2-8)4-11-5/h7-10H,1-4H2\tC6H12O6\t7\t-3051.24166\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tC(C1(COC(CO)(CO1)O)O)O\t\t2723627;4180364;13560352;40503129;124202832\tHMDB:(32222)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M-H]-\tYGMNHEPVTNXLLS\tInChI=1S/C6H12O6/c7-2-5(10)3(8)1-4(9)6(11)12/h3-5,7-10H,1-2H2,(H,11,12)\tC6H12O6\t8\t-3052.67808\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tC(C(C(CO)O)O)C(C(=O)O)O\t\t10350;152990;5289313;14122626;15560246;21596764;21596765;21596766;21596767;21596768;21596769;21596770;58966097;88049798;89007240;89391706;101963537;101963539\tHMDB:(346)\r\n' |
b |
diff -r 1db83da40c54 -r 856b3761277d test-data/RP022611_result_all_adducts.tsv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/RP022611_result_all_adducts.tsv Thu Jul 02 11:01:45 2020 -0400 |
[ |
b'@@ -0,0 +1,21 @@\n+name\tadduct\tinchikey2D\tinchi\tmolecularFormula\trank\tscore\tname\tsmiles\txlogp\tpubchemids\tlinks\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M-H]-\tWQZGKKKJIJFFOK\tInChI=1S/C6H12O6/c7-1-2-3(8)4(9)5(10)6(11)12-2/h2-11H,1H2\tC6H12O6\t1\t-2990.5565\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tC(C1C(C(C(C(O)O1)O)O)O)O\t\t206;5793;6036;18950;64689;79025;81696;185698;439353;439357;439507;439583;439680;441035;441032;441033;441034;444314;448388;448702;451187;451188;451189;452245;455147;657055;1549080;2724488;3000450;3034742;5104362;5319264;6102790;6321330;6323336;6400264;6560213;6971003;6971007;6971016;6971096;6971097;6971098;6992021;6992084;7018164;7043897;7044038;7098663;7098664;7157007;9794056;9815418;9834129;9899007;10035228;10081060;10103794;10130220;10197954;10219674;10219763;10313382;10329946;10899282;10954241;11019447;11030410;11344362;11367383;11412863;11480819;11492034;11571906;11571917;11600783;11651921;11672764;11959770;11970126;12003287;12193653;12285853;12285856;12285861;12285862;12285863;12285866;12285868;12285869;12285870;12285871;12285873;12285877;12285878;12285879;12285885;12285886;12285889;12285890;12285891;12285892;12285893;12285894;16211884;16211941;16211984;16211986;16212959;16212960;16212966;16213546;16213640;16213872;16217112;16219580;21355827;22825318;22836365;22836366;23424086;24802149;24802163;24802281;24892722;42626680;44328781;44328785;46188479;46780441;46897877;50939543;51340651;54445181;54445182;56845432;56845995;57197748;57288387;57483528;57691826;57973135;58070804;58265153;58265160;58265166;58265178;58265190;58265196;58300638;58595959;58594768;58618581;58969552;59034276;59036328;59040622;59083882;59105109;59125088;59146659;59383280;59445439;59503407;59503411;59886072;59965103;60052896;60078648;66629908;67518639;67615000;67615455;67641738;67938791;67944215;67944290;67950444;68167579;68324677;68334110;69528681;70443535;70543261;71309028;71309128;71309129;71309140;71309397;71309503;71309513;71309514;71309671;71309852;71309905;71309908;71309927;71317094;71317095;71317096;71317097;71317182;71777654;75357255;76973265;86278404;87297824;87929779;87931119;88255060;88547603;88974141;89000581;89200515;89332529;89374440;89424182;89742272;89855666;90057933;90159939;90346255;90470917;90472751;90472752;90472753;90472761;90472762;90472770;90473076;90781811;90895196;91057721;92043367;92043446;101015849;101033892;101254308;101254309;101254310;101254311;101254312;101254313;101254314;101254315;101469918;101513786;101718250;101718251;101796201;102089288;102447462;102447463;102601142;102601177;102601371;102601743;102601816;117064633;117064644;117065485;117633116;117768413;117938207;118797420;118797610;118797621;118797622;118855887;118855889;118855904;118855910;118855920;118855925;118924468;121494058;121494046;122360911;122522140;125280077;125280078;125280079;125280080;125309563;125309564;125353406;125363512;125363513;125363514;125363515;126704391\tHMDB:(62202);KNApSAcK:(1126);Natural Products:(UNPD148053 UNPD72621 UNPD116684 UNPD119270 UNPD130932 UNPD158921 UNPD83717 UNPD175249 UNPD175204 UNPD191130 UNPD20367 UNPD175399);CHEBI:(37692 37671 37693 63421 37630 27667 72452 4191 4093 37619 15903 80962 37631 17925 37677 15444 37679 27380 4208 18246 16362 28729 37680 18269 4167 37740 59573 59552 27517 28100 37706 83029 28563 28102 37620 37686 37741 86059 4139 37744 68462 37627 28061 37704);KEGG:(C21032 C00221 C00031 C21050 C02209 C01825 C15923 C00936 C00738 C00737 C06465 C06466 C06464 C00984 C00962 C00159 C06467 C01487 C00267 C00124);Plantcyc:(ALPHA-GLUCOSE L-GALACTOSE ALPHA-D-GALACTOSE CPD-12601 CPD-13559 GALACTOSE CPD-15761 CPD-3607 CPD-15762 510-methenyl-thf GLC);YMDB:(894);Biocyc:(CPD-11613 CPD-13428 CPD-11611 CPD-13559 CPD-12844 CPD-15758 CPD-15627 CPD-15759 Alpha-D-Talose CPD-15628 L-SORBOSONE CPD-18461 CPD-15622 CPD-15624 CPD-15625 CPD-15757 CPD-15761 CPD-3607 CPD-15762 CPD-15621)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M-H]-\tRFSUNEUAIZKAJO\tInChI=1S/C6H12O6/c7-1-3-4(9)5(10)6(11,2-8)12-3/h3-5,7-11H'..b';126611603\tHMDB:(1292)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M+HCOO]-\tCJXCLBPFKGZXJP\tInChI=1S/C5H10O4/c1-2-3(6)4(7)5(8)9/h3-4,6-7H,2H2,1H3,(H,8,9)/p-1\tC5H10O4\t2\t-3023.85117\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tCCC(C(C(=O)O)O)O\t\t20848965;20848966;55300746;55303824;88626871;92436357\tHMDB:(421)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M+HCOO]-\tPDWIQYODPROSQH\tInChI=1S/C5H10O4/c6-2-4-3(7)1-5(8)9-4/h3-8H,1-2H2\tC5H10O4\t3\t-3025.24996\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tC1C(C(CO)OC1O)O\t\t345751;439576;9828112;9855484;10975537;11367008;11658300;11908474;22833604;25796535;45038839;58618535;59016537;59620653;68004209;68034341;68045634;68253592;70679306;89218301;91205052;119077186;124356137\tHMDB:(3224);CHEBI:(90761);KEGG:(C01801)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M+HCOO]-\tKMZHZAAOEWVPSE\tInChI=1S/C5H10O4/c1-4(7)9-3-5(8)2-6/h5-6,8H,2-3H2,1H3\tC5H10O4\t4\t-3063.70008\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tCC(=O)OCC(CO)O\t\t33510;6993818;6999061\tHMDB:(12485);Natural Products:(UNPD115118);HSDB:(26446-35-5)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M+HCOO]-\tAOWPAWLEXIYETE\tInChI=1S/C5H10O4/c1-3(6)5(2,9)4(7)8/h3,6,9H,1-2H3,(H,7,8)\tC5H10O4\t5\t-3075.29598\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tCC(C(C)(C(=O)O)O)O\t\t301941;10986275;12600066;71695576;71695577\tHMDB:(29576);Natural Products:(UNPD143821 UNPD15807 UNPD95601 UNPD85304)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M+HCOO]-\tJTEYKUFKXGDTEU\tInChI=1S/C5H10O4/c1-5(2,9)3(6)4(7)8/h3,6,9H,1-2H3,(H,7,8)\tC5H10O4\t6\t-3081.55551\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tCC(C)(C(C(=O)O)O)O\t\t677;440279;21933884;23615351;53973411;53973412;89565436\tHMDB:(12141);KNApSAcK:(19678);Natural Products:(UNPD3564);CHEBI:(15689 49072 15684 11424);KEGG:(C04039 C04272);Plantcyc:(CPD-13357);YMDB:(1070);Biocyc:(CPD-13357)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M+CH3COO]-\tUFYGCFHQAXXBCF\tInChI=1S/C4H8O4/c5-2-1-3(6)4(7)8/h3,5-6H,1-2H2,(H,7,8)\tC4H8O4\t1\t-2999.8103\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tC(CO)C(C(=O)O)O\t\t192742;7019449;7019450;9898817;21868134\tHMDB:(360);CHEBI:(86348)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M+CH3COO]-\tUQPHVQVXLPRNCX\tInChI=1S/C4H8O4/c5-1-3(7)4(8)2-6/h3,5-7H,1-2H2\tC4H8O4\t2\t-3004.20308\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tC(C(C(=O)CO)O)O\t\t162406;5460032;5460177\tHMDB:(6293);Natural Products:(UNPD106799 UNPD27359);CHEBI:(27913 16023 23958);KEGG:(C02045 C02022);Plantcyc:(D-ERYTHRULOSE ERYTHRULOSE);Biocyc:(D-ERYTHRULOSE ERYTHRULOSE)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M+CH3COO]-\tLOUGYXZSURQALL\tInChI=1S/C4H8O4/c1-2(5)3(6)4(7)8/h2-3,5-6H,1H3,(H,7,8)\tC4H8O4\t3\t-3006.4083\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tCC(C(C(=O)O)O)O\t\t250402;10964471;13120899;13120900;13120901;19827131;20848986;20849185;20849186;57690457;57690460;88626574;88627063\tHMDB:(2453);CHEBI:(86347 86391)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M+CH3COO]-\tDZAIOXUZHHTJKN\tInChI=1S/C4H8O4/c5-2-3(6)1-4(7)8/h3,5-6H,1-2H2,(H,7,8)\tC4H8O4\t4\t-3008.82318\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tC(C(CO)O)C(=O)O\t\t150929;10920498;11400753;22320917;22842605;58067869\tHMDB:(337);Natural Products:(UNPD130472);CHEBI:(86371);Biocyc:(CPD-16714)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M+CH3COO]-\tFMAORJIQYMIRHF\tInChI=1S/C4H8O4/c5-2-1-8-4(7)3(2)6/h2-7H,1H2\tC4H8O4\t5\t-3052.47373\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tC1C(C(C(O)O1)O)O\t\t101562;439574;441031;4475714;10219421;10464337;12308911;20055052;20056706;21581149;21581150;24802123;36688093;89467333;89810651;90472722;90478203;91746266;118855922;122359830;125365294;125365295\tHMDB:(2649);CHEBI:(132185);KEGG:(C01796 C06463)\r\n+D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\t[M+CH3COO]-\tDGADNPLBVRLJGD\tInChI=1S/C4H8O4/c1-4(8,2-5)3(6)7/h5,8H,2H2,1H3,(H,6,7)\tC4H8O4\t6\t-3072.91165\tD-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]-\tCC(CO)(C(=O)O)O\t\t560781;9543155;53758262;55300053;86306358;86306359\tHMDB:(2601);CHEBI:(36532 19315)\r\n' |
b |
diff -r 1db83da40c54 -r 856b3761277d test-data/generic.tsv --- a/test-data/generic.tsv Thu Mar 19 07:30:54 2020 -0400 +++ b/test-data/generic.tsv Thu Jul 02 11:01:45 2020 -0400 |
[ |
@@ -1,7 +1,7 @@ -name inchikey2D inchi molecularFormula rank score name smiles xlogp pubchemids links -MZ:86.0606 | RT:1498 | XCMS_group:19 | file:1 | scan:NA HNJBEVLQSNELDL InChI=1S/C4H7NO/c6-4-2-1-3-5-4/h1-3H2,(H,5,6) C4H7NO 1 -149.0988 MZ:86.0606 | RT:1498 | XCMS_group:19 | file:1 | scan:NA C1CC(=NC1)O 12025;3956071;10419134;12197590;12197592;18999930;20030003;20589568;58329813;90472990;91343693;101225382;101796586;123509162 HMDB:(2039);KNApSAcK:(38233);Natural Products:(UNPD211738);CHEBI:(36592);HSDB:(616-45-5);Plantcyc:(CPD-19607) -MZ:86.0606 | RT:1498 | XCMS_group:19 | file:1 | scan:NA MWFMGBPGAXYFAR InChI=1S/C4H7NO/c1-4(2,6)3-5/h6H,1-2H3 C4H7NO 2 -169.83339 MZ:86.0606 | RT:1498 | XCMS_group:19 | file:1 | scan:NA CC(C)(C#N)O 6406;10486800;91131204 HMDB:(60427);Natural Products:(UNPD47968);CHEBI:(15348);HSDB:(75-86-5);KEGG:(C02659);Plantcyc:(2-HYDROXY-2-METHYLPROPANENITRILE) -MZ:72.0815 | RT:1823 | XCMS_group:2 | file:1 | scan:NA RWRDLPDLKQPQOW InChI=1S/C4H9N/c1-2-4-5-3-1/h5H,1-4H2 C4H9N 1 -136.14546 MZ:72.0815 | RT:1823 | XCMS_group:2 | file:1 | scan:NA C1CCNC1 31268;3613359;11062297;12196044;12196046;12196049;12196050;18440991;20463768;53660610;57608708;57608709;57608710;57750053;60135501;90927493;91312985 HMDB:(31641);Natural Products:(UNPD154562);CHEBI:(33135 52145);HSDB:(123-75-1);Plantcyc:(PYRROLIDINE);Biocyc:(PYRROLIDINE) -MZ:79.0219 | RT:177 | XCMS_group:9 | file:1 | scan:NA IAZDPXIOMUYVGZ InChI=1S/C2H6OS/c1-4(2)3/h1-2H3 C2H6OS 1 -75.82312 MZ:79.0219 | RT:177 | XCMS_group:9 | file:1 | scan:NA CS(=O)C 679;75151;10103116;12206145;12264368;18594457;20151975;21022526;22345572;57247813;71309204;76973052;90811807;90817578 HMDB:(2151);Natural Products:(UNPD148866);CHEBI:(28262);Maconda:(CON00016);HSDB:(67-68-5);KEGG:(C11143);Plantcyc:(DMSO);Biocyc:(DOH-ISO-VAL DMSO) -MZ:79.0219 | RT:184 | XCMS_group:9 | file:1 | scan:NA IAZDPXIOMUYVGZ InChI=1S/C2H6OS/c1-4(2)3/h1-2H3 C2H6OS 1 -86.79175 MZ:79.0219 | RT:184 | XCMS_group:9 | file:1 | scan:NA CS(=O)C 679;75151;10103116;12206145;12264368;18594457;20151975;21022526;22345572;57247813;71309204;76973052;90811807;90817578 HMDB:(2151);Natural Products:(UNPD148866);CHEBI:(28262);Maconda:(CON00016);HSDB:(67-68-5);KEGG:(C11143);Plantcyc:(DMSO);Biocyc:(DOH-ISO-VAL DMSO) -MZ:79.0219 | RT:212 | XCMS_group:9 | file:1 | scan:NA IAZDPXIOMUYVGZ InChI=1S/C2H6OS/c1-4(2)3/h1-2H3 C2H6OS 1 -75.67854 MZ:79.0219 | RT:212 | XCMS_group:9 | file:1 | scan:NA CS(=O)C 679;75151;10103116;12206145;12264368;18594457;20151975;21022526;22345572;57247813;71309204;76973052;90811807;90817578 HMDB:(2151);Natural Products:(UNPD148866);CHEBI:(28262);Maconda:(CON00016);HSDB:(67-68-5);KEGG:(C11143);Plantcyc:(DMSO);Biocyc:(DOH-ISO-VAL DMSO) +name adduct inchikey2D inchi molecularFormula rank score name smiles xlogp pubchemids links +MZ:86.0606 | RT:1498 | XCMS_group:19 | file:1 | scan:NA [M+H]+ HNJBEVLQSNELDL InChI=1S/C4H7NO/c6-4-2-1-3-5-4/h1-3H2,(H,5,6) C4H7NO 1 -149.0988 MZ:86.0606 | RT:1498 | XCMS_group:19 | file:1 | scan:NA C1CC(=NC1)O 12025;3956071;10419134;12197590;12197592;18999930;20030003;20589568;58329813;90472990;91343693;101225382;101796586;123509162 HMDB:(2039);KNApSAcK:(38233);Natural Products:(UNPD211738);CHEBI:(36592);HSDB:(616-45-5);Plantcyc:(CPD-19607) +MZ:86.0606 | RT:1498 | XCMS_group:19 | file:1 | scan:NA [M+H]+ MWFMGBPGAXYFAR InChI=1S/C4H7NO/c1-4(2,6)3-5/h6H,1-2H3 C4H7NO 2 -169.83339 MZ:86.0606 | RT:1498 | XCMS_group:19 | file:1 | scan:NA CC(C)(C#N)O 6406;10486800;91131204 HMDB:(60427);Natural Products:(UNPD47968);CHEBI:(15348);HSDB:(75-86-5);KEGG:(C02659);Plantcyc:(2-HYDROXY-2-METHYLPROPANENITRILE) +MZ:72.0815 | RT:1823 | XCMS_group:2 | file:1 | scan:NA [M+H]+ RWRDLPDLKQPQOW InChI=1S/C4H9N/c1-2-4-5-3-1/h5H,1-4H2 C4H9N 1 -136.14546 MZ:72.0815 | RT:1823 | XCMS_group:2 | file:1 | scan:NA C1CCNC1 31268;3613359;11062297;12196044;12196046;12196049;12196050;18440991;20463768;53660610;57608708;57608709;57608710;57750053;60135501;90927493;91312985 HMDB:(31641);Natural Products:(UNPD154562);CHEBI:(33135 52145);HSDB:(123-75-1);Plantcyc:(PYRROLIDINE);Biocyc:(PYRROLIDINE) +MZ:79.0219 | RT:177 | XCMS_group:9 | file:1 | scan:NA [M+H]+ IAZDPXIOMUYVGZ InChI=1S/C2H6OS/c1-4(2)3/h1-2H3 C2H6OS 1 -75.82312 MZ:79.0219 | RT:177 | XCMS_group:9 | file:1 | scan:NA CS(=O)C 679;75151;10103116;12206145;12264368;18594457;20151975;21022526;22345572;57247813;71309204;76973052;90811807;90817578 HMDB:(2151);Natural Products:(UNPD148866);CHEBI:(28262);Maconda:(CON00016);HSDB:(67-68-5);KEGG:(C11143);Plantcyc:(DMSO);Biocyc:(DOH-ISO-VAL DMSO) +MZ:79.0219 | RT:184 | XCMS_group:9 | file:1 | scan:NA [M+H]+ IAZDPXIOMUYVGZ InChI=1S/C2H6OS/c1-4(2)3/h1-2H3 C2H6OS 1 -86.79175 MZ:79.0219 | RT:184 | XCMS_group:9 | file:1 | scan:NA CS(=O)C 679;75151;10103116;12206145;12264368;18594457;20151975;21022526;22345572;57247813;71309204;76973052;90811807;90817578 HMDB:(2151);Natural Products:(UNPD148866);CHEBI:(28262);Maconda:(CON00016);HSDB:(67-68-5);KEGG:(C11143);Plantcyc:(DMSO);Biocyc:(DOH-ISO-VAL DMSO) +MZ:79.0219 | RT:212 | XCMS_group:9 | file:1 | scan:NA [M+H]+ IAZDPXIOMUYVGZ InChI=1S/C2H6OS/c1-4(2)3/h1-2H3 C2H6OS 1 -75.67854 MZ:79.0219 | RT:212 | XCMS_group:9 | file:1 | scan:NA CS(=O)C 679;75151;10103116;12206145;12264368;18594457;20151975;21022526;22345572;57247813;71309204;76973052;90811807;90817578 HMDB:(2151);Natural Products:(UNPD148866);CHEBI:(28262);Maconda:(CON00016);HSDB:(67-68-5);KEGG:(C11143);Plantcyc:(DMSO);Biocyc:(DOH-ISO-VAL DMSO) |