{"id":"https://openalex.org/W7119141242","doi":"https://doi.org/10.1186/s12859-025-06358-z","title":"Predicting the pathway involvement of metabolites annotated in the MetaCyc knowledgebase","display_name":"Predicting the pathway involvement of metabolites annotated in the MetaCyc knowledgebase","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7119141242","doi":"https://doi.org/10.1186/s12859-025-06358-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/41495634"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-025-06358-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06358-z","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12859-025-06358-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011261274","display_name":"Erik D. Huckvale","orcid":"https://orcid.org/0000-0002-6994-8831"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]},{"id":"https://openalex.org/I2802239656","display_name":"Markey Cancer Center","ror":"https://ror.org/01dhvva97","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1285210727","https://openalex.org/I2802239656"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Erik D. Huckvale","raw_affiliation_strings":["Markey Cancer Center, University of Kentucky, Lexington, KY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Markey Cancer Center, University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I2802239656","https://openalex.org/I143302722"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122285242","display_name":"Hunter N. B. Moseley","orcid":null},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]},{"id":"https://openalex.org/I2802239656","display_name":"Markey Cancer Center","ror":"https://ror.org/01dhvva97","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1285210727","https://openalex.org/I2802239656"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hunter N. B. Moseley","raw_affiliation_strings":["Department of Molecular and Cellular Biochemistry, University of Kentucky, Lexington, KY, USA. hunter.moseley@uky.edu","Department of Toxicology and Cancer Biology, University of Kentucky, Lexington, KY, USA. hunter.moseley@uky.edu","Institute for Biomedical Informatics, University of Kentucky, Lexington, KY, USA. hunter.moseley@uky.edu","Markey Cancer Center, University of Kentucky, Lexington, KY, USA. hunter.moseley@uky.edu","Superfund Research Center, University of Kentucky, Lexington, KY, USA. hunter.moseley@uky.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Molecular and Cellular Biochemistry, University of Kentucky, Lexington, KY, USA. hunter.moseley@uky.edu","institution_ids":["https://openalex.org/I143302722"]},{"raw_affiliation_string":"Department of Toxicology and Cancer Biology, University of Kentucky, Lexington, KY, USA. hunter.moseley@uky.edu","institution_ids":["https://openalex.org/I2802239656","https://openalex.org/I143302722"]},{"raw_affiliation_string":"Institute for Biomedical Informatics, University of Kentucky, Lexington, KY, USA. hunter.moseley@uky.edu","institution_ids":["https://openalex.org/I143302722"]},{"raw_affiliation_string":"Markey Cancer Center, University of Kentucky, Lexington, KY, USA. hunter.moseley@uky.edu","institution_ids":["https://openalex.org/I2802239656"]},{"raw_affiliation_string":"Superfund Research Center, University of Kentucky, Lexington, KY, USA. hunter.moseley@uky.edu","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011261274"],"corresponding_institution_ids":["https://openalex.org/I143302722","https://openalex.org/I2802239656"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04056811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","first_page":"36","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.7261999845504761,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.7261999845504761,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.08070000261068344,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.07840000092983246,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5630999803543091},{"id":"https://openalex.org/keywords/microarray","display_name":"Microarray","score":0.41370001435279846},{"id":"https://openalex.org/keywords/proteomics","display_name":"Proteomics","score":0.31040000915527344},{"id":"https://openalex.org/keywords/microarray-analysis-techniques","display_name":"Microarray analysis techniques","score":0.30239999294281006},{"id":"https://openalex.org/keywords/transcriptome","display_name":"Transcriptome","score":0.2782000005245209},{"id":"https://openalex.org/keywords/biological-pathway","display_name":"Biological pathway","score":0.26440000534057617}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6065000295639038},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5630999803543091},{"id":"https://openalex.org/C186836561","wikidata":"https://www.wikidata.org/wiki/Q1931516","display_name":"Microarray","level":4,"score":0.41370001435279846},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4088999927043915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3946000039577484},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3377000093460083},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C8415881","wikidata":"https://www.wikidata.org/wiki/Q6839217","display_name":"Microarray analysis techniques","level":4,"score":0.30239999294281006},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.2782000005245209},{"id":"https://openalex.org/C9927688","wikidata":"https://www.wikidata.org/wiki/Q4915012","display_name":"Biological pathway","level":4,"score":0.26440000534057617},{"id":"https://openalex.org/C18431079","wikidata":"https://www.wikidata.org/wiki/Q1502169","display_name":"Gene expression profiling","level":4,"score":0.26249998807907104},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C195814341","wikidata":"https://www.wikidata.org/wiki/Q494918","display_name":"Protein microarray","level":5,"score":0.25279998779296875},{"id":"https://openalex.org/C192989942","wikidata":"https://www.wikidata.org/wiki/Q68685","display_name":"Metabolic pathway","level":3,"score":0.2522999942302704}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D053858","descriptor_name":"Metabolic Networks and Pathways","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D053858","descriptor_name":"Metabolic Networks and Pathways","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D053858","descriptor_name":"Metabolic Networks and Pathways","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D053858","descriptor_name":"Metabolic Networks and Pathways","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D053858","descriptor_name":"Metabolic Networks and Pathways","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-025-06358-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06358-z","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41495634","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41495634","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:7214a72843e14135a3d0ffc4b5d49e89","is_oa":true,"landing_page_url":"https://doaj.org/article/7214a72843e14135a3d0ffc4b5d49e89","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1, Pp 1-18 (2026)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11678710","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12870939","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-025-06358-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06358-z","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7059854399","display_name":null,"funder_award_id":"P42 ES007380","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2011301426","https://openalex.org/W2768490449","https://openalex.org/W2781939187","https://openalex.org/W2949054050","https://openalex.org/W2949676527","https://openalex.org/W2977870980","https://openalex.org/W3035965352","https://openalex.org/W3084923451","https://openalex.org/W3139397034","https://openalex.org/W3150635270","https://openalex.org/W3175749050","https://openalex.org/W3176437359","https://openalex.org/W4251404875","https://openalex.org/W4294216483","https://openalex.org/W4312197939","https://openalex.org/W4388140995","https://openalex.org/W4389894348","https://openalex.org/W4396574955","https://openalex.org/W4396693180","https://openalex.org/W4402761624","https://openalex.org/W4403810263","https://openalex.org/W4409260305"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1],"associations":[2],"of":[3,56,68,128,139,156,164],"metabolites":[4],"with":[5,130,141,166],"biochemical":[6],"pathways":[7,172,204],"are":[8,26,173,193],"highly":[9],"useful":[10],"information":[11],"for":[12,35,51,78,145],"interpreting":[13],"molecular":[14,30],"datasets":[15],"generated":[16],"in":[17,28,184,199],"biological":[18],"and":[19,60,70,86,99,107],"biomedical":[20],"research.":[21],"However,":[22,149],"such":[23],"pathway":[24,36,54,87,108,153,186],"annotations":[25,109],"sparse":[27],"most":[29],"datasets,":[31],"limiting":[32],"their":[33],"utility":[34],"level":[37],"interpretation.":[38],"To":[39],"address":[40],"these":[41],"shortcomings,":[42],"several":[43],"past":[44],"publications":[45],"have":[46,160],"presented":[47],"machine":[48],"learning":[49],"models":[50,103,115],"predicting":[52],"the":[53,65,114,146,176,195,201,210],"association":[55],"small":[57],"biomolecule":[58],"(metabolite":[59],"xenobiotic)":[61],"using":[62],"data":[63],"from":[64,111],"Kyoto":[66],"Encyclopedia":[67],"Genes":[69],"Genomes":[71],"(KEGG).":[72],"But":[73],"other":[74],"similar":[75],"knowledgebases":[76],"exist,":[77],"example":[79],"MetaCyc,":[80],"which":[81],"has":[82],"more":[83],"compound":[84,105],"entries":[85,106],"definitions":[88],"than":[89],"KEGG.":[90],"RESULTS:":[91],"As":[92],"a":[93,122,136,161,181],"logical":[94],"next":[95],"step,":[96],"we":[97,120],"trained":[98,116],"evaluated":[100],"multilayer":[101],"perceptron":[102],"on":[104,117],"obtained":[110],"MetaCyc.":[112],"From":[113],"this":[118],"dataset,":[119],"observed":[121],"mean":[123,137,162],"Matthews":[124],"correlation":[125],"coefficient":[126],"(MCC)":[127],"0.845":[129],"0.0101":[131],"standard":[132,143,168],"deviation,":[133],"compared":[134],"to":[135],"MCC":[138,163],"0.847":[140],"0.0098":[142],"deviation":[144],"KEGG":[147],"dataset.":[148],"KEGG's":[150],"184":[151],"metabolic-only":[152],"predictions":[154],"(out":[155],"502":[157],"total":[158],"pathways)":[159],"0.800":[165],"0.021":[167],"deviation.":[169],"Since":[170],"MetaCyc":[171,177,203],"metabolic":[174,185],"focused,":[175],"results":[178,192],"represent":[179],"over":[180],"5.6%":[182],"improvement":[183],"prediction":[187],"performance.":[188],"CONCLUSIONS:":[189],"These":[190],"performance":[191,213],"pragmatically":[194],"same,":[196],"demonstrating":[197],"that":[198],"aggregate,":[200],"4055":[202],"can":[205],"be":[206],"effectively":[207],"predicted":[208],"at":[209],"current":[211],"state-of-the-art":[212],"level.":[214]},"counts_by_year":[],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2026-01-08T00:00:00"}