{"id":"https://openalex.org/W4407808959","doi":"https://doi.org/10.1021/acs.jcim.4c02161","title":"EC2Vec: A Machine Learning Method to Embed Enzyme Commission (EC) Numbers into Vector Representations","display_name":"EC2Vec: A Machine Learning Method to Embed Enzyme Commission (EC) Numbers into Vector Representations","publication_year":2025,"publication_date":"2025-02-21","ids":{"openalex":"https://openalex.org/W4407808959","doi":"https://doi.org/10.1021/acs.jcim.4c02161","pmid":"https://pubmed.ncbi.nlm.nih.gov/39981640"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c02161","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c02161","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c02161?ref=article_openPDF","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c02161?ref=article_openPDF","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102873593","display_name":"Mengmeng Liu","orcid":"https://orcid.org/0000-0002-8475-2319"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengmeng Liu","raw_affiliation_strings":["Division of Electrical and Computer Engineering","Louisiana State University","Division of Electrical and Computer Engineering, Louisiana State University, Baton Rouge, Louisiana 70803, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Electrical and Computer Engineering","institution_ids":[]},{"raw_affiliation_string":"Louisiana State University","institution_ids":["https://openalex.org/I121820613"]},{"raw_affiliation_string":"Division of Electrical and Computer Engineering, Louisiana State University, Baton Rouge, Louisiana 70803, United States","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059119453","display_name":"Xialong Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xialong Ni","raw_affiliation_strings":["Department of Biological Sciences","Louisiana State University","Department of Biological Sciences, Louisiana State University, Baton Rouge, Louisiana 70803, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences","institution_ids":[]},{"raw_affiliation_string":"Louisiana State University","institution_ids":["https://openalex.org/I121820613"]},{"raw_affiliation_string":"Department of Biological Sciences, Louisiana State University, Baton Rouge, Louisiana 70803, United States","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057117526","display_name":"J. Ramanujam","orcid":"https://orcid.org/0000-0002-4349-1327"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Ramanujam","raw_affiliation_strings":["Center for Computation and Technology","Division of Electrical and Computer Engineering","Louisiana State University","Center for Computation and Technology, Louisiana State University, Baton Rouge, Louisiana 70803, United States","Division of Electrical and Computer Engineering, Louisiana State University, Baton Rouge, Louisiana 70803, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computation and Technology","institution_ids":[]},{"raw_affiliation_string":"Division of Electrical and Computer Engineering","institution_ids":[]},{"raw_affiliation_string":"Louisiana State University","institution_ids":["https://openalex.org/I121820613"]},{"raw_affiliation_string":"Center for Computation and Technology, Louisiana State University, Baton Rouge, Louisiana 70803, United States","institution_ids":["https://openalex.org/I121820613"]},{"raw_affiliation_string":"Division of Electrical and Computer Engineering, Louisiana State University, Baton Rouge, Louisiana 70803, United States","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033579800","display_name":"Micha\u0142 Bryli\u0144ski","orcid":"https://orcid.org/0000-0002-6204-2869"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michal Brylinski","raw_affiliation_strings":["Center for Computation and Technology","Department of Biological Sciences","Louisiana State University","Department of Biological Sciences, Louisiana State University, Baton Rouge, Louisiana 70803, United States","Center for Computation and Technology, Louisiana State University, Baton Rouge, Louisiana 70803, United States"],"raw_orcid":"https://orcid.org/0000-0002-6204-2869","affiliations":[{"raw_affiliation_string":"Center for Computation and Technology","institution_ids":[]},{"raw_affiliation_string":"Department of Biological Sciences","institution_ids":[]},{"raw_affiliation_string":"Louisiana State University","institution_ids":["https://openalex.org/I121820613"]},{"raw_affiliation_string":"Department of Biological Sciences, Louisiana State University, Baton Rouge, Louisiana 70803, United States","institution_ids":["https://openalex.org/I121820613"]},{"raw_affiliation_string":"Center for Computation and Technology, Louisiana State University, Baton Rouge, Louisiana 70803, United States","institution_ids":["https://openalex.org/I121820613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033579800"],"corresponding_institution_ids":["https://openalex.org/I121820613"],"apc_list":null,"apc_paid":null,"fwci":1.1237,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75069942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"65","issue":"5","first_page":"2173","last_page":"2179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.998199999332428,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.998199999332428,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9950000047683716,"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":0.9879999756813049,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/commission","display_name":"Commission","score":0.6664193868637085},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5429506301879883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5195817947387695},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4679144024848938},{"id":"https://openalex.org/keywords/enzyme","display_name":"Enzyme","score":0.4519287943840027},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.41076481342315674},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.3394436836242676},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32114434242248535},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.27522069215774536},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.10586574673652649}],"concepts":[{"id":"https://openalex.org/C2776034101","wikidata":"https://www.wikidata.org/wiki/Q1509347","display_name":"Commission","level":2,"score":0.6664193868637085},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5429506301879883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5195817947387695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4679144024848938},{"id":"https://openalex.org/C181199279","wikidata":"https://www.wikidata.org/wiki/Q8047","display_name":"Enzyme","level":2,"score":0.4519287943840027},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.41076481342315674},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3394436836242676},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32114434242248535},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.27522069215774536},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.10586574673652649},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1021/acs.jcim.4c02161","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c02161","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c02161?ref=article_openPDF","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:39981640","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39981640","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":"Journal of chemical information and modeling","raw_type":null},{"id":"pmh:oai:repository.lsu.edu:eecs_pubs-3842","is_oa":true,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/2839","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:11898066","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11898066","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Chem Inf Model","raw_type":"Text"},{"id":"pmh:oai:repository.lsu.edu:biosci_pubs-5834","is_oa":true,"landing_page_url":"https://repository.lsu.edu/biosci_pubs/4828","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.4c02161","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c02161","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c02161?ref=article_openPDF","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","score":0.4099999964237213,"display_name":"Zero hunger"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310395","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407808959.pdf","grobid_xml":"https://content.openalex.org/works/W4407808959.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1974525959","https://openalex.org/W1975147762","https://openalex.org/W1991262449","https://openalex.org/W2109553965","https://openalex.org/W2111973517","https://openalex.org/W2158698691","https://openalex.org/W2777416523","https://openalex.org/W2895484279","https://openalex.org/W3021030593","https://openalex.org/W3089837105","https://openalex.org/W3105895642","https://openalex.org/W3212063608","https://openalex.org/W4243150065","https://openalex.org/W4254094513","https://openalex.org/W4309506674","https://openalex.org/W4327849160","https://openalex.org/W4391544240"],"related_works":["https://openalex.org/W2083674464","https://openalex.org/W4285379861","https://openalex.org/W2322850402","https://openalex.org/W2146489267","https://openalex.org/W2394108515","https://openalex.org/W2437262919","https://openalex.org/W3125791156","https://openalex.org/W4241219018","https://openalex.org/W1599375153","https://openalex.org/W2380483444"],"abstract_inverted_index":{"Enzyme":[0],"commission":[1],"(EC)":[2],"numbers":[3,25,68,115,145],"play":[4],"a":[5,58,90,99,110],"vital":[6],"role":[7],"in":[8,15,75,161],"classifying":[9],"enzymes":[10],"and":[11,20,48,69,78,93,170,175],"understanding":[12],"their":[13,71,105],"functions":[14],"enzyme-related":[16,173],"research.":[17],"Although":[18],"accurate":[19],"informative":[21,79],"encoding":[22,38,121,159],"of":[23,32,66,85,113,126,142],"EC":[24,37,67,87,114,144,158],"is":[26,146],"essential":[27],"for":[28,172],"enhancing":[29],"the":[30,63,86,139,143,162],"effectiveness":[31],"machine":[33,151],"learning":[34,152],"applications,":[35,153],"simple":[36,120],"approaches":[39],"suffer":[40],"from":[41],"limitations":[42],"such":[43],"as":[44,89],"false":[45],"numerical":[46],"order":[47],"high":[49],"sparsity.":[50],"To":[51],"address":[52],"these":[53,96],"issues,":[54],"we":[55],"developed":[56],"EC2Vec,":[57],"multimodal":[59],"autoencoder":[60],"that":[61,117,138],"preserves":[62],"categorical":[64,91],"nature":[65],"leverages":[70],"hierarchical":[72,140],"relationships,":[73],"resulting":[74],"more":[76],"meaningful":[77],"representations.":[80],"EC2Vec":[81,118,127,154],"encodes":[82],"each":[83],"digit":[84],"number":[88],"token":[92],"then":[94],"processes":[95],"embeddings":[97,128,155],"through":[98],"1D":[100],"convolutional":[101],"layer":[102],"to":[103,133],"capture":[104],"relationships.":[106],"Comprehensive":[107],"benchmarking":[108],"against":[109],"large":[111],"collection":[112],"indicates":[116],"outperforms":[119],"methods.":[122],"The":[123],"t-SNE":[124],"visualization":[125],"revealed":[129],"distinct":[130],"clusters":[131],"corresponding":[132],"different":[134],"enzyme":[135],"classes,":[136],"demonstrating":[137],"structure":[141],"effectively":[147],"captured.":[148],"In":[149],"downstream":[150],"outperformed":[156],"other":[157],"methods":[160],"reaction-EC":[163],"pair":[164],"classification":[165],"task,":[166],"underscoring":[167],"its":[168],"robustness":[169],"utility":[171],"research":[174],"bioinformatics":[176],"applications.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}
