Mercurial > repos > tomnl > sirius_csifingerid
changeset 8:4f7f41ac1623 draft default tip
"planemo upload for repository https://github.com/computational-metabolomics/sirius_csifingerid_galaxy commit 3aeab1e21bcdecb5bbc25474d837ebac5624715a"
| author | tomnl |
|---|---|
| date | Fri, 04 Oct 2019 07:24:44 -0400 |
| parents | 5bfa9dedb0f6 |
| children | |
| files | sirius_csifingerid.py sirius_csifingerid.xml test-data/CCMSLIB00000578155_result.tsv test-data/ML006801.tsv test-data/RP022611_result.tsv test-data/generic.tsv |
| diffstat | 6 files changed, 164 insertions(+), 121 deletions(-) [+] |
line wrap: on
line diff
--- a/sirius_csifingerid.py Thu Aug 01 13:20:41 2019 -0400 +++ b/sirius_csifingerid.py Fri Oct 04 07:24:44 2019 -0400 @@ -1,16 +1,18 @@ from __future__ import absolute_import, print_function + import argparse import csv -import sys -import six -import re +import glob +import multiprocessing import os +import re +import sys import tempfile -import multiprocessing -import glob import uuid from collections import defaultdict +import six + parser = argparse.ArgumentParser() parser.add_argument('--input_pth') parser.add_argument('--result_pth') @@ -50,28 +52,37 @@ # Setup regular expressions for MSP parsing dictionary ###################################################################### regex_msp = {} -regex_msp['name'] = ['^Name(?:=|:)(.*)$'] -regex_msp['polarity'] = ['^ion.*mode(?:=|:)(.*)$', '^ionization.*mode(?:=|:)(.*)$', '^polarity(?:=|:)(.*)$'] -regex_msp['precursor_mz'] = ['^precursor.*m/z(?:=|:)\s*(\d*[.,]?\d*)$', '^precursor.*mz(?:=|:)\s*(\d*[.,]?\d*)$'] -regex_msp['precursor_type'] = ['^precursor.*type(?:=|:)(.*)$', '^adduct(?:=|:)(.*)$', '^ADDUCTIONNAME(?:=|:)(.*)$'] -regex_msp['num_peaks'] = ['^Num.*Peaks(?:=|:)\s*(\d*)$'] -regex_msp['msp'] = ['^Name(?:=|:)(.*)$'] # Flag for standard MSP format +regex_msp['name'] = [r'^Name(?:=|:)(.*)$'] +regex_msp['polarity'] = [r'^ion.*mode(?:=|:)(.*)$', + r'^ionization.*mode(?:=|:)(.*)$', + r'^polarity(?:=|:)(.*)$'] +regex_msp['precursor_mz'] = [r'^precursor.*m/z(?:=|:)\s*(\d*[.,]?\d*)$', + r'^precursor.*mz(?:=|:)\s*(\d*[.,]?\d*)$'] +regex_msp['precursor_type'] = [r'^precursor.*type(?:=|:)(.*)$', + r'^adduct(?:=|:)(.*)$', + r'^ADDUCTIONNAME(?:=|:)(.*)$'] +regex_msp['num_peaks'] = [r'^Num.*Peaks(?:=|:)\s*(\d*)$'] +regex_msp['msp'] = [r'^Name(?:=|:)(.*)$'] # Flag for standard MSP format regex_massbank = {} -regex_massbank['name'] = ['^RECORD_TITLE:(.*)$'] -regex_massbank['polarity'] = ['^AC\$MASS_SPECTROMETRY:\s+ION_MODE\s+(.*)$'] -regex_massbank['precursor_mz'] = ['^MS\$FOCUSED_ION:\s+PRECURSOR_M/Z\s+(\d*[.,]?\d*)$'] -regex_massbank['precursor_type'] = ['^MS\$FOCUSED_ION:\s+PRECURSOR_TYPE\s+(.*)$'] -regex_massbank['num_peaks'] = ['^PK\$NUM_PEAK:\s+(\d*)'] -regex_massbank['cols'] = ['^PK\$PEAK:\s+(.*)'] -regex_massbank['massbank'] = ['^RECORD_TITLE:(.*)$'] # Flag for massbank format +regex_massbank['name'] = [r'^RECORD_TITLE:(.*)$'] +regex_massbank['polarity'] = \ + [r'^AC\$MASS_SPECTROMETRY:\s+ION_MODE\s+(.*)$'] +regex_massbank['precursor_mz'] = \ + [r'^MS\$FOCUSED_ION:\s+PRECURSOR_M/Z\s+(\d*[.,]?\d*)$'] +regex_massbank['precursor_type'] = \ + [r'^MS\$FOCUSED_ION:\s+PRECURSOR_TYPE\s+(.*)$'] +regex_massbank['num_peaks'] = [r'^PK\$NUM_PEAK:\s+(\d*)'] +regex_massbank['cols'] = [r'^PK\$PEAK:\s+(.*)'] +regex_massbank['massbank'] = [r'^RECORD_TITLE:(.*)$'] # Flag for massbank if args.schema == 'msp': meta_regex = regex_msp elif args.schema == 'massbank': meta_regex = regex_massbank elif args.schema == 'auto': - # If auto we just check for all the available paramter names and then determine if Massbank or MSP based on + # If auto we just check for all the available paramter names + # and then determine if Massbank or MSP based on # the name parameter meta_regex = {} meta_regex.update(regex_massbank) @@ -84,14 +95,14 @@ print(meta_regex) - - # this dictionary will store the meta data results form the MSp file meta_info = {} # function to extract the meta data using the regular expressions -def parse_meta(meta_regex, meta_info={}): +def parse_meta(meta_regex, meta_info=None): + if meta_info is None: + meta_info = {} for k, regexes in six.iteritems(meta_regex): for reg in regexes: m = re.search(reg, line, re.IGNORECASE) @@ -120,27 +131,29 @@ return paramd - ###################################################################### # Function to run sirius when all meta and spectra is obtained ###################################################################### def run_sirius(meta_info, peaklist, args, wd, spectrac): - # Get sample details (if possible to extract) e.g. if created as part of the msPurity pipeline) - # choose between getting additional details to add as columns as either all meta data from msp, just - # details from the record name (i.e. when using msPurity and we have the columns coded into the name) or - # just the spectra index (spectrac) - + # Get sample details (if possible to extract) e.g. if created as part of + # the msPurity pipeline) choose between getting additional details to + # add as columns as either all meta data from msp, just details from the + # 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) if args.meta_select_col == 'name': # have additional column of just the name paramd['additional_details'] = {'name': meta_info['name']} elif args.meta_select_col == 'name_split': - # have additional columns split by "|" and then on ":" e.g. MZ:100.2 | RT:20 | xcms_grp_id:1 - paramd['additional_details'] = {sm.split(":")[0].strip(): sm.split(":")[1].strip() for sm in - meta_info['name'].split("|")} + # have additional columns split by "|" and + # then on ":" e.g. MZ:100.2 | RT:20 | xcms_grp_id:1 + paramd['additional_details'] = { + sm.split(":")[0].strip(): sm.split(":")[1].strip() for sm in + meta_info['name'].split("|")} elif args.meta_select_col == 'all': - # have additional columns based on all the meta information extracted from the MSP + # have additional columns based on all + # the meta information extracted from the MSP paramd['additional_details'] = meta_info else: # Just have and index of the spectra in the MSP file @@ -148,11 +161,12 @@ paramd["SampleName"] = "{}_sirius_result".format(spectrac) - paramd["cli"]["--output"] = os.path.join(wd, "{}_sirius_result".format(spectrac)) + paramd["cli"]["--output"] = \ + os.path.join(wd, "{}_sirius_result".format(spectrac)) # =============== Output peaks to txt file ============================== - numlines = 0 - paramd["cli"]["--ms2"] = os.path.join(wd, "{}_tmpspec.txt".format(spectrac)) + paramd["cli"]["--ms2"] = os.path.join(wd, + "{}_tmpspec.txt".format(spectrac)) # write spec file with open(paramd["cli"]["--ms2"], 'w') as outfile: @@ -172,7 +186,7 @@ if 'precursor_mz' in meta_info and meta_info['precursor_mz']: paramd["cli"]["--precursor"] = meta_info['precursor_mz'] - # =============== Create CLI cmd for metfrag =============================== + # ============== Create CLI cmd for metfrag =============================== cmd = "sirius --fingerid" for k, v in six.iteritems(paramd["cli"]): cmd += " {} {}".format(str(k), str(v)) @@ -187,6 +201,7 @@ return paramd, cmd + def work(cmds): return [os.system(cmd) for cmd in cmds] @@ -212,18 +227,19 @@ if pnumlines == 0: - # =============== Extract metadata from MSP ======================== + # ============== Extract metadata from MSP ======================== meta_info = parse_meta(meta_regex, meta_info) - if ('massbank' in meta_info and 'cols' in meta_info) or ('msp' in meta_info and 'num_peaks' in meta_info): - + if ('massbank' in meta_info and 'cols' in meta_info) or \ + ('msp' in meta_info and 'num_peaks' in meta_info): pnumlines = int(meta_info['num_peaks']) peaklist = [] plinesread = 0 elif plinesread < pnumlines: # =============== Extract peaks from MSP ========================== - line = tuple(line.split()) # .split() will split on any empty space (i.e. tab and space) + # .split() will split on any empty space (i.e. tab and space) + line = tuple(line.split()) # Keep only m/z and intensity, not relative intensity save_line = tuple(line[0].split() + line[1].split()) plinesread += 1 @@ -231,7 +247,7 @@ peaklist.append(save_line) elif plinesread and plinesread == pnumlines: - # =============== Get sample name and additional details for output ======= + # ======= Get sample name and additional details for output ======= spectrac += 1 paramd, cmd = run_sirius(meta_info, peaklist, args, wd, spectrac) @@ -242,8 +258,8 @@ pnumlines = 0 plinesread = 0 - # end of file. Check if there is a MSP spectra to run metfrag on still - + # end of file. Check if there is a MSP spectra to + # run metfrag on still if plinesread and plinesread == pnumlines: paramd, cmd = run_sirius(meta_info, peaklist, args, wd, spectrac + 1) @@ -253,7 +269,8 @@ # Perform multiprocessing on command line call level if int(args.cores_top_level) > 1: - cmds_chunks = [cmds[x:x + int(args.chunks)] for x in list(range(0, len(cmds), int(args.chunks)))] + cmds_chunks = [cmds[x:x + int(args.chunks)] + for x in list(range(0, len(cmds), int(args.chunks)))] pool = multiprocessing.Pool(processes=int(args.cores_top_level)) pool.map(work, cmds_chunks) pool.close() @@ -262,12 +279,15 @@ ###################################################################### # Concatenate and filter the output ###################################################################### -# outputs might have different headers. Need to get a list of all the headers before we start merging the files -# outfiles = [os.path.join(wd, f) for f in glob.glob(os.path.join(wd, "*_metfrag_result.csv"))] +# outputs might have different headers. Need to get a list of all the headers +# before we start merging the files outfiles = [os.path.join(wd, f) for f in +# glob.glob(os.path.join(wd, "*_metfrag_result.csv"))] outfiles = glob.glob(os.path.join(wd, '*', '*', 'summary_csi_fingerid.csv')) # sort files nicely -outfiles.sort(key = lambda s: int(re.match('^.*/(\d+).*/.*/summary_csi_fingerid.csv', s).group(1))) +outfiles.sort(key=lambda s: int(re.match(r'^.*/(' + r'\d+).*/.*/summary_csi_fingerid.csv', + s).group(1))) print(outfiles) if len(outfiles) == 0: @@ -287,9 +307,9 @@ headers = list(paramd['additional_details'].keys()) + headers - with open(args.result_pth, 'a') as merged_outfile: - dwriter = csv.DictWriter(merged_outfile, fieldnames=headers, delimiter='\t') + dwriter = csv.DictWriter(merged_outfile, + fieldnames=headers, delimiter='\t') dwriter.writeheader() for fn in sorted(outfiles): @@ -301,7 +321,8 @@ ad = paramds[fn.split(os.sep)[-3]]['additional_details'] for line in reader: - line.update(ad) + # round score to 5 d.p. + line['score'] = round(float(line['score']), 5) dwriter.writerow(line)
--- a/sirius_csifingerid.xml Thu Aug 01 13:20:41 2019 -0400 +++ b/sirius_csifingerid.xml Fri Oct 04 07:24:44 2019 -0400 @@ -1,15 +1,17 @@ -<tool id="sirius_csifingerid" name="SIRIUS-CSI:FingerID" version="4.0.1+galaxy0.2.6"> - <description> </description> +<tool id="sirius_csifingerid" name="SIRIUS-CSI:FingerID" + version="4.0.1+galaxy1"> + <description>is used to identify metabolites using single and + tandem mass spectrometry</description> <requirements> - <requirement type="package" version="4.0.1">sirius-csifingerid</requirement> + <requirement type="package" version="4.0.1"> + sirius-csifingerid</requirement> </requirements> - <command detect_errors="exit_code" interpreter="python"> + <command detect_errors="exit_code"> <![CDATA[ - - sirius_csifingerid.py - --input_pth "$input" - --database '$database' + python '$__tool_directory__/sirius_csifingerid.py' + --input_pth '$input' + --database $database --profile $profile --candidates $candidates --ppm_max $ppm_max @@ -22,12 +24,12 @@ --schema $schema --temp_dir . - - ]]></command> <inputs> - <param name="input" type="data" format="msp,txt" label="MSP file (Output from Create MSP tool)" argument="--input_pth"/> - <param name="database" type="select" label="Select SIRIUS-CSI:FingerID Database" argument="--database"> + <param name="input" argument="--input_pth" type="data" format="msp" + label="MSP file (output from Create MSP tool)" /> + <param argument="--database" type="select" + label="Select SIRIUS-CSI:FingerID Database" > <option value="PubChem" >PubChem</option> <option selected="true" value="hmdb">HMDB</option> <option value="kegg">KEGG</option> @@ -35,68 +37,78 @@ <option value="biocyc">BioCyc</option> <option value="all">All (see help)</option> </param> - <param name="ppm_max" type="integer" value="10" label="Mass deviation of the fragment peaks in ppm" argument="--ppm_max"/> - <param name="candidates" type="integer" value="5" label="The maximum number of candidates in the output" argument="--candidates"/> - <param name="polarity" type="select" label="Ion Mode" argument="--polarity"> + <param argument="--ppm_max" type="integer" value="10" min="0" + label="Mass deviation of the fragment peaks in ppm" /> + <param argument="--candidates" type="integer" value="5" min="1" + label="Maximum number of candidates in the output" /> + <param argument="--polarity" type="select" label="Ion mode" > <option value="positive" selected="true">Positive</option> <option value="negative">Negative</option> </param> - <param name="profile" type="select" label="Analysis used" argument="--profile"> + <param argument="--profile" type="select" label="Analysis used" > <option value="orbitrap" selected="true">Orbitrap</option> <option value="qtof">qTOF</option> <option value="fticr">FT-ICR</option> </param> - <param name="schema" type="select" label="Schema" - help="The schema used for the MSP file (auto will try automatically determine the schema)"> + <param argument="--schema" type="select" label="Schema" + help="Schema used for the MSP file (auto will try to + determine the schema automatically)"> <option value="auto" selected="True">Auto</option> <option value="msp" >Generic MSP</option> <option value="massbank">MassBank</option> </param> - <param name="meta_select_col" type="select" label="Choose how additional metadata columns are extracted" - help="The SIRIUS-CSI:Fingerid output can have additional meta data columns added, these can be either extracted - from all MSP parameters or from the 'Name' and 'RECORD_TITLE' MSP parameter. Additionally, columns - can be added from the 'Name' or 'RECORD_TITLE' parameter by splitting on | and : - e.g. 'MZ:100.2 | RT:20 | xcms_grp_id:1' would create MZ,RT and xcms_grp_id columns"> - <option value="name" selected="true">Extra metadata columns from the Name or RECORD_TITLE</option> - <option value="name_split" >Extra metadata columns from the Name or RECORD_TITLE (each column is split on "|" and ":" ) </option> - <option value="all">Extra metadata columns from all MSP parameters</option> + <param argument="--meta_select_col" type="select" + label="Choose how additional metadata columns are extracted" + help="The SIRIUS-CSI:Fingerid output can have additional + metadata columns added; these can be either extracted from all + MSP parameters or from the 'Name' and 'RECORD_TITLE' MSP + parameters. Additionally, columns can be added from the 'Name' + or 'RECORD_TITLE' parameters by splitting on | and : e.g. + 'MZ:100.2 | RT:20 | xcms_grp_id:1' would create MZ,RT and + xcms_grp_id columns"> + <option value="name" selected="true"> + Extra metadata columns from the Name or RECORD_TITLE</option> + <option value="name_split" > + Extra metadata columns from the Name or + RECORD_TITLE (each column is split on "|" and ":" ) </option> + <option value="all"> + Extra metadata columns from all MSP parameters</option> </param> - <param name="minMSMSpeaks" type="integer" label="Minimum number of MS/MS peaks" value="0"/> + <param argument="--minMSMSpeaks" type="integer" min="0" value="0" + label="Minimum number of MS/MS peaks"/> </inputs> <outputs> - <data name="results" format="tsv" label="${tool.name} results of ${input.name}" from_work_dir="sirius_all_summary.tsv" /> + <data name="results" format="tsv" + from_work_dir="sirius_all_summary.tsv"/> </outputs> <tests> - <test> <!-- Test "massbank" style data format --> - <param name="input" value="ML006801.txt"/> + <param name="input" value="ML006801.txt" ftype="msp"/> <output name="results" file="ML006801.tsv"/> </test> <test> <!-- Test "generic format" style data format --> - <param name="input" value="generic.msp"/> + <param name="input" value="generic.msp" ftype="msp"/> <output name="results" file="generic.tsv"/> </test> <test> <!-- Test for glucose (qtof) MassBank data format --> - <param name="input" value="RP022611.txt"/> + <param name="input" value="RP022611.txt" ftype="msp"/> <param name="profile" value="qtof"/> <output name="results" file="RP022611_result.tsv"/> </test> <test> <!-- Test for glucose (q-exactive) GNPS, MoNA data format --> - <param name="input" value="CCMSLIB00000578155.msp"/> + <param name="input" value="CCMSLIB00000578155.msp" ftype="msp"/> <param name="profile" value="orbitrap"/> <output name="results" file="CCMSLIB00000578155_result.tsv"/> </test> - <test> <!-- Test invalid adduct --> - <param name="input" value="invalid_adduct.msp"/> + <param name="input" value="invalid_adduct.msp" ftype="msp"/> <output name="results" file="invalid_adduct_result.tsv"/> </test> - </tests> <help> ---------------- @@ -106,9 +118,12 @@ 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 @@ -122,25 +137,27 @@ The following databases are available: -* PubChem ( +* PubChem + +* HMDB -* hmdb +* KEGG -* kegg +* KNApSAcK -* knapsack +* BioCyc -* biocyc +* All (SIRIUS will consider all m/z possible molecular formulas) -* all (SIRIUS will consider all m/z possible molecular formulas) +**\3. Mass deviation of the fragment peaks in ppm** -**\3. Allowed mass deviation of the fragment peaks in ppm** +Allowed mass deviation of the fragment peaks. **\4. The maximum number of candidates in the output** Set the top X candidates to return. -**\5. Ion Mode** +**\5. Ion mode** * Positive @@ -154,7 +171,11 @@ * FT-ICR -If you want to analyze spectra measured with Orbitrap or FT-ICR, you should specify the appropriate analysis profile. A profile is a set of configuration options and scoring functions SIRIUS 3 will use for its analysis. For example, the Orbitrap and FT-ICR profiles having tighter constraints for the allowed mass deviation but do not rely so much on the intensity of isotope peaks. +If you want to analyze spectra measured with Orbitrap or FT-ICR, you should +specify the appropriate analysis profile. A profile is a set of configuration +options and scoring functions SIRIUS 3 will use for its analysis. For example, +the Orbitrap and FT-ICR profiles have tighter constraints for the allowed mass +deviation but do not rely so much on the intensity of isotope peaks. Developers and contributors @@ -162,6 +183,7 @@ - **Jordi Capellades (j.capellades.to@gmail.com) - Universitat Rovira i Virgili (SP)** - **Thomas N Lawson (t.n.lawson@bham.ac.uk) - University of Birmingham (UK)** +- **Simon Bray (sbray@informatik.uni-freiburg.de) - University of Freiburg (Germany)** - **Ralf Weber (r.j.weber@bham.ac.uk) - University of Birmingham (UK)** </help>
--- a/test-data/CCMSLIB00000578155_result.tsv Thu Aug 01 13:20:41 2019 -0400 +++ b/test-data/CCMSLIB00000578155_result.tsv Fri Oct 04 07:24:44 2019 -0400 @@ -1,9 +1,9 @@ name inchikey2D inchi molecularFormula rank score name smiles xlogp pubchemids links -D-GLUCOSE-6-PHOSPHATE NBSCHQHZLSJFNQ InChI=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) C6H13O9P 1 -2956.1759660162393 D-GLUCOSE-6-PHOSPHATE C(C1C(C(C(C(O)O1)O)O)O)OP(=O)(O)O 208;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 HMDB:(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) -D-GLUCOSE-6-PHOSPHATE HXXFSFRBOHSIMQ InChI=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) C6H13O9P 2 -2968.8930033087277 D-GLUCOSE-6-PHOSPHATE C(C1C(C(C(C(O1)OP(=O)(O)O)O)O)O)O 466;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 HMDB:(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) -D-GLUCOSE-6-PHOSPHATE BGWGXPAPYGQALX InChI=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) C6H13O9P 3 -2996.823329466129 D-GLUCOSE-6-PHOSPHATE C(C1C(C(C(CO)(O)O1)O)O)OP(=O)(O)O 719;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 HMDB:(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) -D-GLUCOSE-6-PHOSPHATE PMTUDJVZIGZBIX InChI=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) C6H13O9P 4 -2999.570906011912 D-GLUCOSE-6-PHOSPHATE C(C1C(C(C(CO)(O1)OP(=O)(O)O)O)O)O 193537;5176477;6398638;15703397;16069990;21126112;21126113;57357663;99639213;124202606 HMDB:(6800);CHEBI:(27884 57267 12350);KEGG:(C03267);YMDB:(878);Biocyc:(FRUCTOSE-2-PHOSPHATE) -D-GLUCOSE-6-PHOSPHATE RHKKZBWRNHGJEZ InChI=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) C6H13O9P 5 -3000.1754484579087 D-GLUCOSE-6-PHOSPHATE C(C1C(C(C(COP(=O)(O)O)(O)O1)O)O)O 717;439394;10400369;21627880;23421194;25244216;51397484;52916944;90658050;90658051;90659357;90659358;92209483;97041850 HMDB:(1076);KNApSAcK:(19676);CHEBI:(37515 58674);KEGG:(C01094);Plantcyc:(FRU1P);Biocyc:(CPD-16154 CPD-16158 CPD-16159) -D-GLUCOSE-6-PHOSPHATE INAPMGSXUVUWAF InChI=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) C6H13O9P 6 -3061.8676349144794 D-GLUCOSE-6-PHOSPHATE C1(C(C(C(C(C1O)O)OP(=O)(O)O)O)O)O 9;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 HMDB:(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) -D-GLUCOSE-6-PHOSPHATE GSXOAOHZAIYLCY InChI=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) C6H13O9P 7 -3108.216292205978 D-GLUCOSE-6-PHOSPHATE C(C(=O)C(C(C(COP(=O)(O)O)O)O)O)O 603;69507;151197;5459902;5459952;6602428;20111689;20111690;21114947;21872891;23615358;40467872;40467873;46943428;50909805;87615581 HMDB:(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) -D-GLUCOSE-6-PHOSPHATE ZKLLSNQJRLJIGT InChI=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) C6H13O9P 8 -3116.8648927434215 D-GLUCOSE-6-PHOSPHATE C(C(C(C(C(=O)COP(=O)(O)O)O)O)O)O 481;65246;151033;439837;440076;6101730;11129032;11737049;14844438;20111955;21145035;23615304;54551858;54551860;54551861;54551863;91010818 HMDB:(60467);KNApSAcK:(19630);CHEBI:(38342 218 18105);KEGG:(C03654 C02888);YMDB:(655);Biocyc:(CPD-15970 CPD0-1116 CPD-531) +D-GLUCOSE-6-PHOSPHATE NBSCHQHZLSJFNQ InChI=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) C6H13O9P 1 -2956.17597 D-GLUCOSE-6-PHOSPHATE C(C1C(C(C(C(O)O1)O)O)O)OP(=O)(O)O 208;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 HMDB:(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) +D-GLUCOSE-6-PHOSPHATE HXXFSFRBOHSIMQ InChI=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) C6H13O9P 2 -2968.893 D-GLUCOSE-6-PHOSPHATE C(C1C(C(C(C(O1)OP(=O)(O)O)O)O)O)O 466;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 HMDB:(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) +D-GLUCOSE-6-PHOSPHATE BGWGXPAPYGQALX InChI=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) C6H13O9P 3 -2996.82333 D-GLUCOSE-6-PHOSPHATE C(C1C(C(C(CO)(O)O1)O)O)OP(=O)(O)O 719;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 HMDB:(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) +D-GLUCOSE-6-PHOSPHATE PMTUDJVZIGZBIX InChI=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) C6H13O9P 4 -2999.57091 D-GLUCOSE-6-PHOSPHATE C(C1C(C(C(CO)(O1)OP(=O)(O)O)O)O)O 193537;5176477;6398638;15703397;16069990;21126112;21126113;57357663;99639213;124202606 HMDB:(6800);CHEBI:(27884 57267 12350);KEGG:(C03267);YMDB:(878);Biocyc:(FRUCTOSE-2-PHOSPHATE) +D-GLUCOSE-6-PHOSPHATE RHKKZBWRNHGJEZ InChI=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) C6H13O9P 5 -3000.17545 D-GLUCOSE-6-PHOSPHATE C(C1C(C(C(COP(=O)(O)O)(O)O1)O)O)O 717;439394;10400369;21627880;23421194;25244216;51397484;52916944;90658050;90658051;90659357;90659358;92209483;97041850 HMDB:(1076);KNApSAcK:(19676);CHEBI:(37515 58674);KEGG:(C01094);Plantcyc:(FRU1P);Biocyc:(CPD-16154 CPD-16158 CPD-16159) +D-GLUCOSE-6-PHOSPHATE INAPMGSXUVUWAF InChI=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) C6H13O9P 6 -3061.86763 D-GLUCOSE-6-PHOSPHATE C1(C(C(C(C(C1O)O)OP(=O)(O)O)O)O)O 9;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 HMDB:(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) +D-GLUCOSE-6-PHOSPHATE GSXOAOHZAIYLCY InChI=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) C6H13O9P 7 -3108.21629 D-GLUCOSE-6-PHOSPHATE C(C(=O)C(C(C(COP(=O)(O)O)O)O)O)O 603;69507;151197;5459902;5459952;6602428;20111689;20111690;21114947;21872891;23615358;40467872;40467873;46943428;50909805;87615581 HMDB:(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) +D-GLUCOSE-6-PHOSPHATE ZKLLSNQJRLJIGT InChI=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) C6H13O9P 8 -3116.86489 D-GLUCOSE-6-PHOSPHATE C(C(C(C(C(=O)COP(=O)(O)O)O)O)O)O 481;65246;151033;439837;440076;6101730;11129032;11737049;14844438;20111955;21145035;23615304;54551858;54551860;54551861;54551863;91010818 HMDB:(60467);KNApSAcK:(19630);CHEBI:(38342 218 18105);KEGG:(C03654 C02888);YMDB:(655);Biocyc:(CPD-15970 CPD0-1116 CPD-531)
--- a/test-data/ML006801.tsv Thu Aug 01 13:20:41 2019 -0400 +++ b/test-data/ML006801.tsv Fri Oct 04 07:24:44 2019 -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 -7.0831442988613125 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) +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)
--- a/test-data/RP022611_result.tsv Thu Aug 01 13:20:41 2019 -0400 +++ b/test-data/RP022611_result.tsv Fri Oct 04 07:24:44 2019 -0400 @@ -1,9 +1,9 @@ name inchikey2D inchi molecularFormula rank score name smiles xlogp pubchemids links -D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- WQZGKKKJIJFFOK InChI=1S/C6H12O6/c7-1-2-3(8)4(9)5(10)6(11)12-2/h2-11H,1H2 C6H12O6 1 -2990.5564974625718 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C(C1C(C(C(C(O)O1)O)O)O)O 206;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 HMDB:(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) -D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- RFSUNEUAIZKAJO InChI=1S/C6H12O6/c7-1-3-4(9)5(10)6(11,2-8)12-3/h3-5,7-11H,1-2H2 C6H12O6 2 -2992.8106788278706 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C(C1C(C(C(CO)(O)O1)O)O)O 716;439163;439553;439709;11008518;11105942;11378852;11769129;12306006;12306007;12306010;12306011;12306012;12306013;12306014;12306016;15942891;21581131;24755524;24755531;50990586;58798223;59105060;59642118;59748470;60078501;60109622;66809988;68009591;68015592;69261724;69261935;69261937;71310006;71310036;71529761;89810242;89810768;90159920;90346952;90347094;102193695;117935612 HMDB:(660);KNApSAcK:(1117);Natural Products:(UNPD19574 UNPD185250 UNPD163774 UNPD109385);CHEBI:(48648 48647 48646 28645 37727 49090 48673 37720 37721 48672 49089 49088 48670 37725 29084);KEGG:(C02336 C00095 C01719);Plantcyc:(BETA-D-FRUCTOSE);Biocyc:(CPD-10723 CPD-10729 CPD-15988 CPD-15989 CPD-10730) -D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- LKDRXBCSQODPBY InChI=1S/C6H12O6/c7-2-6(11)5(10)4(9)3(8)1-12-6/h3-5,7-11H,1-2H2 C6H12O6 3 -3006.7125378812325 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C1C(C(C(C(CO)(O)O1)O)O)O 3426;24310;439192;439304;439312;440545;441036;441484;2723872;2724552;5317407;6432703;6915737;6971020;6971021;6971099;6992107;10130221;10130228;10154314;10176372;11355843;14408225;15559359;16212688;16213406;16213544;16213545;22814148;24802515;45039313;51340644;51340682;52916942;52916943;57745769;59575442;59875236;71308848;71309127;71309810;71309883;71751872;71752285;89015893;89174364;89333506;89345843;89360325;89360759;89363316;89810855;90472720;90472721;90472746;91329420;91654167;101763542;101763543;102602138;118797422;118797598;118855901;118855902;118855927;119077570;121494037;121494038;121494039;121494041;121494042;125300503;125300504;125300505;125300506;125322958;125322959;125322960;125356688;129275707 HMDB:(1266);Natural Products:(UNPD1409 UNPD51200 UNPD43618 UNPD196486 UNPD14140 UNPD69968);CHEBI:(48645 48678 48677 10295 37728 37729 49092 37719 49091 48674 4249 37714 37715);HSDB:(7660-25-5);KEGG:(C08356 C05003 C00764 C00247 C06468 C00795);Plantcyc:(CPD-10726);YMDB:(204);Biocyc:(CPD-15986 CPD-10728 CPD-15987 CPD-10726 CPD-10727 CPD-10725) -D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- BJHIKXHVCXFQLS InChI=1S/C6H12O6/c7-1-3(9)5(11)6(12)4(10)2-8/h3,5-9,11-12H,1-2H2 C6H12O6 4 -3015.0691577392213 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C(C(C(C(C(=O)CO)O)O)O)O 1101;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 HMDB:(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) -D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- GZCGUPFRVQAUEE InChI=1S/C6H12O6/c7-1-3(9)5(11)6(12)4(10)2-8/h1,3-6,8-12H,2H2 C6H12O6 5 -3017.5346505581906 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C(=O)C(C(C(C(CO)O)O)O)O 24749;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 HMDB:(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) -D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- CDAISMWEOUEBRE InChI=1S/C6H12O6/c7-1-2(8)4(10)6(12)5(11)3(1)9/h1-12H C6H12O6 6 -3046.13843778621 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C1(C(C(C(C(C1O)O)O)O)O)O 892;11973225;12302985;53714837;68591801;90768658;91019724;100996307;100996308 HMDB:(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) -D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- KEQUNHIAUQQPAC InChI=1S/C6H12O6/c7-1-5(9)3-12-6(10,2-8)4-11-5/h7-10H,1-4H2 C6H12O6 7 -3051.2416634815486 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C(C1(COC(CO)(CO1)O)O)O 2723627;4180364;13560352;40503129;124202832 HMDB:(32222) -D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- YGMNHEPVTNXLLS InChI=1S/C6H12O6/c7-2-5(10)3(8)1-4(9)6(11)12/h3-5,7-10H,1-2H2,(H,11,12) C6H12O6 8 -3052.678076852649 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C(C(C(CO)O)O)C(C(=O)O)O 10350;152990;5289313;14122626;15560246;21596764;21596765;21596766;21596767;21596768;21596769;21596770;58966097;88049798;89007240;89391706;101963537;101963539 HMDB:(346) +D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- WQZGKKKJIJFFOK InChI=1S/C6H12O6/c7-1-2-3(8)4(9)5(10)6(11)12-2/h2-11H,1H2 C6H12O6 1 -2990.5565 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C(C1C(C(C(C(O)O1)O)O)O)O 206;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 HMDB:(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) +D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- RFSUNEUAIZKAJO InChI=1S/C6H12O6/c7-1-3-4(9)5(10)6(11,2-8)12-3/h3-5,7-11H,1-2H2 C6H12O6 2 -2992.81068 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C(C1C(C(C(CO)(O)O1)O)O)O 716;439163;439553;439709;11008518;11105942;11378852;11769129;12306006;12306007;12306010;12306011;12306012;12306013;12306014;12306016;15942891;21581131;24755524;24755531;50990586;58798223;59105060;59642118;59748470;60078501;60109622;66809988;68009591;68015592;69261724;69261935;69261937;71310006;71310036;71529761;89810242;89810768;90159920;90346952;90347094;102193695;117935612 HMDB:(660);KNApSAcK:(1117);Natural Products:(UNPD19574 UNPD185250 UNPD163774 UNPD109385);CHEBI:(48648 48647 48646 28645 37727 49090 48673 37720 37721 48672 49089 49088 48670 37725 29084);KEGG:(C02336 C00095 C01719);Plantcyc:(BETA-D-FRUCTOSE);Biocyc:(CPD-10723 CPD-10729 CPD-15988 CPD-15989 CPD-10730) +D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- LKDRXBCSQODPBY InChI=1S/C6H12O6/c7-2-6(11)5(10)4(9)3(8)1-12-6/h3-5,7-11H,1-2H2 C6H12O6 3 -3006.71254 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C1C(C(C(C(CO)(O)O1)O)O)O 3426;24310;439192;439304;439312;440545;441036;441484;2723872;2724552;5317407;6432703;6915737;6971020;6971021;6971099;6992107;10130221;10130228;10154314;10176372;11355843;14408225;15559359;16212688;16213406;16213544;16213545;22814148;24802515;45039313;51340644;51340682;52916942;52916943;57745769;59575442;59875236;71308848;71309127;71309810;71309883;71751872;71752285;89015893;89174364;89333506;89345843;89360325;89360759;89363316;89810855;90472720;90472721;90472746;91329420;91654167;101763542;101763543;102602138;118797422;118797598;118855901;118855902;118855927;119077570;121494037;121494038;121494039;121494041;121494042;125300503;125300504;125300505;125300506;125322958;125322959;125322960;125356688;129275707 HMDB:(1266);Natural Products:(UNPD1409 UNPD51200 UNPD43618 UNPD196486 UNPD14140 UNPD69968);CHEBI:(48645 48678 48677 10295 37728 37729 49092 37719 49091 48674 4249 37714 37715);HSDB:(7660-25-5);KEGG:(C08356 C05003 C00764 C00247 C06468 C00795);Plantcyc:(CPD-10726);YMDB:(204);Biocyc:(CPD-15986 CPD-10728 CPD-15987 CPD-10726 CPD-10727 CPD-10725) +D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- BJHIKXHVCXFQLS InChI=1S/C6H12O6/c7-1-3(9)5(11)6(12)4(10)2-8/h3,5-9,11-12H,1-2H2 C6H12O6 4 -3015.06916 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C(C(C(C(C(=O)CO)O)O)O)O 1101;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 HMDB:(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) +D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- GZCGUPFRVQAUEE InChI=1S/C6H12O6/c7-1-3(9)5(11)6(12)4(10)2-8/h1,3-6,8-12H,2H2 C6H12O6 5 -3017.53465 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C(=O)C(C(C(C(CO)O)O)O)O 24749;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 HMDB:(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) +D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- CDAISMWEOUEBRE InChI=1S/C6H12O6/c7-1-2(8)4(10)6(12)5(11)3(1)9/h1-12H C6H12O6 6 -3046.13844 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C1(C(C(C(C(C1O)O)O)O)O)O 892;11973225;12302985;53714837;68591801;90768658;91019724;100996307;100996308 HMDB:(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) +D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- KEQUNHIAUQQPAC InChI=1S/C6H12O6/c7-1-5(9)3-12-6(10,2-8)4-11-5/h7-10H,1-4H2 C6H12O6 7 -3051.24166 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C(C1(COC(CO)(CO1)O)O)O 2723627;4180364;13560352;40503129;124202832 HMDB:(32222) +D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- YGMNHEPVTNXLLS InChI=1S/C6H12O6/c7-2-5(10)3(8)1-4(9)6(11)12/h3-5,7-10H,1-2H2,(H,11,12) C6H12O6 8 -3052.67808 D-Glucose; LC-ESI-QTOF; MS2; CE: 10; R=; [M-H]- C(C(C(CO)O)O)C(C(=O)O)O 10350;152990;5289313;14122626;15560246;21596764;21596765;21596766;21596767;21596768;21596769;21596770;58966097;88049798;89007240;89391706;101963537;101963539 HMDB:(346)
--- a/test-data/generic.tsv Thu Aug 01 13:20:41 2019 -0400 +++ b/test-data/generic.tsv Fri Oct 04 07:24:44 2019 -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 -149.09880138892078 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 -169.83338864057723 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 -136.14546214244544 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 -75.82312484178658 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 -86.79174845072117 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 -75.67854201438384 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) +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)