{"id":"https://openalex.org/W4411383955","doi":"https://doi.org/10.1021/acs.jcim.5c00465","title":"Predicting Biological Activity from Biosynthetic Gene Clusters Using Neural Networks","display_name":"Predicting Biological Activity from Biosynthetic Gene Clusters Using Neural Networks","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411383955","doi":"https://doi.org/10.1021/acs.jcim.5c00465","pmid":"https://pubmed.ncbi.nlm.nih.gov/40524326"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c00465","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00465","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099469771","display_name":"Hemant Goyat","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164849","display_name":"National Agri-Food Biotechnology Institute","ror":"https://ror.org/05nnsek89","country_code":"IN","type":"facility","lineage":["https://openalex.org/I4210164849"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant Goyat","raw_affiliation_strings":["Computational Biology Lab, National Agri-Food Biotechnology Institute, Sector 81, SAS Nagar, Punjab 140308, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Lab, National Agri-Food Biotechnology Institute, Sector 81, SAS Nagar, Punjab 140308, India","institution_ids":["https://openalex.org/I4210164849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001119081","display_name":"Dalwinder Singh","orcid":"https://orcid.org/0000-0002-8076-4435"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Dalwinder Singh","raw_affiliation_strings":["Department of Anatomy and Cell Biology","Western University"],"raw_orcid":"https://orcid.org/0000-0002-8076-4435","affiliations":[{"raw_affiliation_string":"Department of Anatomy and Cell Biology","institution_ids":[]},{"raw_affiliation_string":"Western University","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099469772","display_name":"Sunaina Paliyal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164849","display_name":"National Agri-Food Biotechnology Institute","ror":"https://ror.org/05nnsek89","country_code":"IN","type":"facility","lineage":["https://openalex.org/I4210164849"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunaina Paliyal","raw_affiliation_strings":["Computational Biology Lab, National Agri-Food Biotechnology Institute, Sector 81, SAS Nagar, Punjab 140308, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Lab, National Agri-Food Biotechnology Institute, Sector 81, SAS Nagar, Punjab 140308, India","institution_ids":["https://openalex.org/I4210164849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102693577","display_name":"Shrikant Mantri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164849","display_name":"National Agri-Food Biotechnology Institute","ror":"https://ror.org/05nnsek89","country_code":"IN","type":"facility","lineage":["https://openalex.org/I4210164849"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shrikant Mantri","raw_affiliation_strings":["Computational Biology Lab, National Agri-Food Biotechnology Institute, Sector 81, SAS Nagar, Punjab 140308, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Lab, National Agri-Food Biotechnology Institute, Sector 81, SAS Nagar, Punjab 140308, India","institution_ids":["https://openalex.org/I4210164849"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001119081","https://openalex.org/A5102693577"],"corresponding_institution_ids":["https://openalex.org/I125749732","https://openalex.org/I4210164849"],"apc_list":null,"apc_paid":null,"fwci":4.1636,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.93684828,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"65","issue":"13","first_page":"7193","last_page":"7208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.9965999722480774,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9958000183105469,"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/computational-biology","display_name":"Computational biology","score":0.5594983100891113},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5018999576568604},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4937823712825775},{"id":"https://openalex.org/keywords/neural-activity","display_name":"Neural activity","score":0.45897382497787476},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3249642848968506},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.31059250235557556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28605353832244873},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.26775842905044556},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.24923428893089294}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5594983100891113},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5018999576568604},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4937823712825775},{"id":"https://openalex.org/C2984127161","wikidata":"https://www.wikidata.org/wiki/Q969316","display_name":"Neural activity","level":2,"score":0.45897382497787476},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3249642848968506},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.31059250235557556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28605353832244873},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.26775842905044556},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.24923428893089294}],"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":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"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":"D053898","descriptor_name":"Biosynthetic Pathways","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D053898","descriptor_name":"Biosynthetic Pathways","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c00465","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00465","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:40524326","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40524326","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}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335730","display_name":"National Agri-Food Biotechnology Institute","ror":"https://ror.org/05nnsek89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W37070282","https://openalex.org/W1907426501","https://openalex.org/W1987370810","https://openalex.org/W2010806506","https://openalex.org/W2017337590","https://openalex.org/W2048194168","https://openalex.org/W2084169317","https://openalex.org/W2099835394","https://openalex.org/W2116607382","https://openalex.org/W2187341651","https://openalex.org/W2256742438","https://openalex.org/W2312696342","https://openalex.org/W2328922111","https://openalex.org/W2571489439","https://openalex.org/W2593189583","https://openalex.org/W2608736608","https://openalex.org/W2613440185","https://openalex.org/W2756935148","https://openalex.org/W2803753687","https://openalex.org/W2899058127","https://openalex.org/W2899663614","https://openalex.org/W2940010972","https://openalex.org/W2942056403","https://openalex.org/W2942829220","https://openalex.org/W2945020349","https://openalex.org/W2967688728","https://openalex.org/W2972473680","https://openalex.org/W2982531601","https://openalex.org/W2997918501","https://openalex.org/W3081735746","https://openalex.org/W3091334475","https://openalex.org/W3093920803","https://openalex.org/W3107629351","https://openalex.org/W3127138831","https://openalex.org/W3164648732","https://openalex.org/W3186053381","https://openalex.org/W3194905210","https://openalex.org/W3208188934","https://openalex.org/W3210852361","https://openalex.org/W3216660278","https://openalex.org/W4297240357","https://openalex.org/W4309305948","https://openalex.org/W4309908754","https://openalex.org/W4321207605","https://openalex.org/W4366364289","https://openalex.org/W4368358469","https://openalex.org/W4382490702","https://openalex.org/W4382776738","https://openalex.org/W4383709986","https://openalex.org/W4386607677","https://openalex.org/W4387173328","https://openalex.org/W4389965872","https://openalex.org/W4390783150","https://openalex.org/W4404821554"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2082860237","https://openalex.org/W2119695867","https://openalex.org/W2130076355","https://openalex.org/W1990804418","https://openalex.org/W1993764875","https://openalex.org/W2046158694","https://openalex.org/W2788277189","https://openalex.org/W2013243191","https://openalex.org/W1971568933"],"abstract_inverted_index":{"Microorganisms":[0],"such":[1],"as":[2,62],"bacteria":[3],"and":[4,41,66,102,118,136,145,162,201],"fungi":[5],"have":[6,69],"been":[7,70,120],"used":[8,158,171],"for":[9],"natural":[10,27,64],"products":[11],"that":[12,58,113],"translate":[13],"to":[14,24,34,51,72,85,143,159,172,197],"drugs.":[15],"However,":[16,79],"assessing":[17],"the":[18,35,133,147,151,174,183,190],"bioactivity":[19],"of":[20,38,47,98],"extract":[21],"from":[22],"culture":[23],"identify":[25,52],"novel":[26],"molecules":[28],"remains":[29],"a":[30,86,109,128,137],"strenuous":[31],"process":[32],"due":[33,84],"cumbersome":[36],"order":[37],"production,":[39],"purification,":[40],"assaying.":[42],"Thus,":[43],"extensive":[44],"genome":[45,94,154],"mining":[46,95,142,155],"microbiomes":[48],"is":[49],"underway":[50],"biosynthetic":[53],"gene":[54],"clusters":[55],"or":[56],"BGCs":[57,161],"can":[59,114],"be":[60],"profiled":[61],"particular":[63],"products,":[65],"computational":[67],"methods":[68],"developed":[71],"address":[73],"this":[74],"problem":[75],"using":[76,132],"machine":[77],"learning.":[78],"existing":[80,195],"tools":[81],"are":[82,170],"ineffective":[83],"small":[87],"training":[88,130],"data":[89],"set,":[90],"dependence":[91],"on":[92],"old":[93],"tools,":[96],"lack":[97],"relevant":[99],"genomic":[100],"descriptors,":[101],"prevalent":[103],"class":[104,179,184],"imbalance.":[105],"This":[106],"work":[107],"presents":[108],"new":[110,164],"tool,":[111],"NPBdetect,":[112],"detect":[115],"multiple":[116],"bioactivities":[117,207],"has":[119],"designed":[121],"through":[122,140,182],"rigorous":[123],"experiments.":[124],"First,":[125],"we":[126,188],"composed":[127],"larger":[129],"set":[131,139],"MIBiG":[134],"database":[135],"test":[138],"literature":[141],"build":[144,173],"assess":[146],"model,":[148],"respectively.":[149],"Second,":[150],"latest":[152],"antiSMASH":[153],"tool":[156,192,196],"was":[157],"obtain":[160],"introduced":[163],"sequence-based":[165],"descriptors.":[166],"Third,":[167],"neural":[168],"networks":[169],"model":[175],"by":[176],"dealing":[177],"with":[178,193,208],"imbalance":[180],"issues":[181],"weighting":[185],"technique.":[186],"Finally,":[187],"compared":[189],"NPBdetect":[191],"an":[194],"show":[198],"its":[199],"efficacy":[200],"real-world":[202],"utility":[203],"in":[204],"detecting":[205],"several":[206],"high":[209],"confidence.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-10T14:10:52.464848","created_date":"2025-10-10T00:00:00"}
