{"id":"https://openalex.org/W4409057849","doi":"https://doi.org/10.1109/jbhi.2025.3556766","title":"BFGTP: A BERT-Guided Two-Stage Molecular Representation Learning Framework for Toxicity Prediction","display_name":"BFGTP: A BERT-Guided Two-Stage Molecular Representation Learning Framework for Toxicity Prediction","publication_year":2025,"publication_date":"2025-04-01","ids":{"openalex":"https://openalex.org/W4409057849","doi":"https://doi.org/10.1109/jbhi.2025.3556766","pmid":"https://pubmed.ncbi.nlm.nih.gov/40168218"},"language":"en","primary_location":{"id":"doi:10.1109/jbhi.2025.3556766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3556766","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","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":null,"display_name":"Kaimiao Hu","orcid":"https://orcid.org/0009-0004-1537-6614"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaimiao Hu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0004-1537-6614","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101178817","display_name":"Yuan He","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan He","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0006-7862-5424","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027428789","display_name":"Jianguo Wei","orcid":"https://orcid.org/0000-0002-8964-9759"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguo Wei","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8964-9759","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041589060","display_name":"Changming Sun","orcid":"https://orcid.org/0000-0001-5943-1989"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Changming Sun","raw_affiliation_strings":["CSIRO Data61, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5943-1989","affiliations":[{"raw_affiliation_string":"CSIRO Data61, Sydney, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Geng","orcid":"https://orcid.org/0009-0008-3413-9939"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Geng","raw_affiliation_strings":["Department of Cardiology, Chest Hospital, Tianjin University, Tianjin Key Laboratory of Cardiovascular Emergency and Critical Care, Tianjin Municipal Science and Technology Bureau, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0008-3413-9939","affiliations":[{"raw_affiliation_string":"Department of Cardiology, Chest Hospital, Tianjin University, Tianjin Key Laboratory of Cardiovascular Emergency and Critical Care, Tianjin Municipal Science and Technology Bureau, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033232360","display_name":"Leyi Wei","orcid":"https://orcid.org/0000-0003-1444-190X"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Leyi Wei","raw_affiliation_strings":["Centre for Artificial Intelligence driven Drug Discovery, Faculty of Applied Science, Macao Polytechnic University, Macao SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-1444-190X","affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence driven Drug Discovery, Faculty of Applied Science, Macao Polytechnic University, Macao SAR, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044939301","display_name":"Ran Su","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Su","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5922-0364","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8854,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74697121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"29","issue":"10","first_page":"6960","last_page":"6970"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9994999766349792,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9215999841690063,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9036999940872192,"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/computer-science","display_name":"Computer science","score":0.7053404450416565},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6051039695739746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5002901554107666},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.48140907287597656},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3746492564678192},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09859505295753479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7053404450416565},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6051039695739746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5002901554107666},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.48140907287597656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3746492564678192},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09859505295753479},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D064420","descriptor_name":"Drug-Related Side Effects and Adverse Reactions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064420","descriptor_name":"Drug-Related Side Effects and Adverse Reactions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064420","descriptor_name":"Drug-Related Side Effects and Adverse Reactions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064420","descriptor_name":"Drug-Related Side Effects and Adverse Reactions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/jbhi.2025.3556766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3556766","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},{"id":"pmid:40168218","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40168218","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":"IEEE journal of biomedical and health informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[{"id":"https://openalex.org/G1049933001","display_name":null,"funder_award_id":"62222311","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2108975889","display_name":null,"funder_award_id":"22JCZDJC00580","funder_id":"https://openalex.org/F4320336756","funder_display_name":"Tianjin Science and Technology Program"},{"id":"https://openalex.org/G7047309604","display_name":"\u4e2a\u6027\u5316\u6297\u764c\u836f\u7269\u7684\u667a\u80fd\u9009\u62e9\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072329","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336756","display_name":"Tianjin Science and Technology Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W49274203","https://openalex.org/W1564885879","https://openalex.org/W1901616594","https://openalex.org/W2009867031","https://openalex.org/W2010524461","https://openalex.org/W2047131820","https://openalex.org/W2052396986","https://openalex.org/W2065354989","https://openalex.org/W2098506332","https://openalex.org/W2106421086","https://openalex.org/W2146402650","https://openalex.org/W2199498392","https://openalex.org/W2225235469","https://openalex.org/W2289901683","https://openalex.org/W2295598076","https://openalex.org/W2331872634","https://openalex.org/W2576683119","https://openalex.org/W2609731728","https://openalex.org/W2770630458","https://openalex.org/W2887896328","https://openalex.org/W2893455886","https://openalex.org/W2911107164","https://openalex.org/W2962876364","https://openalex.org/W2966357564","https://openalex.org/W2973114758","https://openalex.org/W3039264283","https://openalex.org/W3115434616","https://openalex.org/W3135028703","https://openalex.org/W3166272013","https://openalex.org/W4211219865","https://openalex.org/W4280602833","https://openalex.org/W4298009900","https://openalex.org/W4307468223","https://openalex.org/W4309412288","https://openalex.org/W4311326710","https://openalex.org/W4313530695","https://openalex.org/W4365512576","https://openalex.org/W4376620126","https://openalex.org/W4385245566","https://openalex.org/W4385732850","https://openalex.org/W4386230622","https://openalex.org/W4391136507","https://openalex.org/W4400831251","https://openalex.org/W4406030356","https://openalex.org/W4406321957","https://openalex.org/W4407466332"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Accurate":[0],"prediction":[1],"of":[2,22,114,143,210],"molecular":[3,31,46,51,76,80,99,112,172,219],"toxicity":[4,35,87,104,177],"is":[5,135],"vital":[6],"for":[7,30,49,103,111],"drug":[8],"development.":[9],"Most":[10],"mainstream":[11],"methods":[12],"rely":[13],"on":[14,62,175,188],"fingerprints":[15],"or":[16],"graph-based":[17],"feature":[18],"extraction,":[19],"the":[20,67,118,131,140,152,185,192,208],"emergence":[21],"large":[23],"language":[24],"models":[25],"(LLMs)":[26],"offers":[27],"new":[28],"prospects":[29],"representation":[32,100],"learning":[33,101,147],"in":[34,70,86],"prediction.":[36,88,105],"Although":[37],"several":[38],"studies":[39],"attempt":[40],"to":[41,44,137,148,158,170,216],"leverage":[42],"LLMs":[43],"integrate":[45],"sequence":[47,71],"data":[48,81],"pretraining":[50],"representations,":[52],"certain":[53],"limitations":[54],"remain.":[55],"Current":[56],"LLM-based":[57],"approaches":[58],"usually":[59],"utilize":[60,139],"solely":[61],"class":[63],"embedding":[64],"features,":[65],"overlooking":[66],"rich":[68],"information":[69],"embedding.":[72],"Moreover,":[73],"integrating":[74],"pre-trained":[75],"representations":[77,154,169],"with":[78,121],"multi-modal":[79],"may":[82],"further":[83],"enhance":[84],"performance":[85,195],"To":[89],"address":[90],"these":[91],"challenges,":[92],"we":[93,107],"propose":[94],"BFGTP,":[95],"a":[96],"BERT-guided":[97],"two-stage":[98,132],"framework":[102],"Firstly,":[106],"design":[108],"independent":[109],"encoders":[110],"descriptions":[113],"three":[115],"modalities,":[116],"where":[117],"fingerprint":[119,166],"encoder":[120],"dual":[122],"level":[123],"attention":[124],"mechanisms":[125],"effectively":[126],"integrates":[127],"multi-category":[128],"fingerprints.":[129],"Then,":[130],"guide":[133],"strategy":[134],"introduced":[136],"fully":[138],"prior":[141],"knowledge":[142,156],"LLMs,":[144],"employing":[145],"contrastive":[146],"align":[149,159],"and":[150,155,167,191,204,213],"fuse":[151],"tri-modal":[153],"distillation":[157],"predicted":[160],"value":[161],"distributions.":[162],"BFGTP":[163,181],"ultimately":[164],"combines":[165],"graph":[168],"predict":[171],"toxicity.":[173],"Experiments":[174],"seven":[176],"datasets":[178,190],"show":[179],"that":[180],"outperforms":[182],"baselines,":[183],"achieving":[184],"highest":[186],"AUC":[187],"five":[189,197],"best":[193],"average":[194],"across":[196],"evaluation":[198],"metrics.":[199],"Ablation":[200],"studies,":[201],"t-SNE":[202],"visualization":[203],"case":[205],"study":[206],"confirm":[207],"effectiveness":[209],"BFGTP's":[211],"components":[212],"its":[214],"ability":[215],"capture":[217],"meaningful":[218],"representations.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}