{"id":"https://openalex.org/W7128718261","doi":"https://doi.org/10.1109/tpami.2026.3664098","title":"Explainable Molecular Property Prediction: Aligning Chemical Concepts With Predictions via Language Models","display_name":"Explainable Molecular Property Prediction: Aligning Chemical Concepts With Predictions via Language Models","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7128718261","doi":"https://doi.org/10.1109/tpami.2026.3664098","pmid":"https://pubmed.ncbi.nlm.nih.gov/41678476"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3664098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3664098","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Pattern Analysis and Machine Intelligence","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":"Zhenzhong Wang","orcid":"https://orcid.org/0000-0002-2816-853X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhenzhong Wang","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-2816-853X","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125761481","display_name":"Zehui Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zehui Lin","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0009-0557-3143","affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122310449","display_name":"Wanyu Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wanyu Lin","raw_affiliation_strings":["Department of Computing and Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-7328-8039","affiliations":[{"raw_affiliation_string":"Department of Computing and Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125761517","display_name":"Ming Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ming Yang","raw_affiliation_strings":["Department of Applied Physics, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-0876-1221","affiliations":[{"raw_affiliation_string":"Department of Applied Physics, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060216728","display_name":"Minggang Zeng","orcid":"https://orcid.org/0000-0002-8648-9905"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Minggang Zeng","raw_affiliation_strings":["Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kay Chen Tan","orcid":"https://orcid.org/0000-0002-6802-2463"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kay Chen Tan","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-6802-2463","affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17294842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"6","first_page":"7017","last_page":"7031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9607999920845032,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9607999920845032,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.01590000092983246,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.008299999870359898,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/property","display_name":"Property (philosophy)","score":0.7537000179290771},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5430999994277954},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4765999913215637},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.4352000057697296},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.3521000146865845},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.3418000042438507},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.31310001015663147},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3125}],"concepts":[{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.7537000179290771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371000051498413},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5430999994277954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4853000044822693},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.4352000057697296},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4296000003814697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40299999713897705},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3125},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29910001158714294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29089999198913574},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C165216359","wikidata":"https://www.wikidata.org/wiki/Q670653","display_name":"Marginal distribution","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3664098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3664098","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41678476","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41678476","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 transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1644634136","display_name":null,"funder_award_id":"A0046682","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G428188999","display_name":null,"funder_award_id":"P0057774","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G4875108467","display_name":null,"funder_award_id":"3502Z202571027","funder_id":"https://openalex.org/F4320316884","funder_display_name":"Natural Science Foundation of Xiamen City"},{"id":"https://openalex.org/G506647137","display_name":null,"funder_award_id":"20720250164","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320316884","display_name":"Natural Science Foundation of Xiamen City","ror":null},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W2027482274","https://openalex.org/W2056562706","https://openalex.org/W2083360085","https://openalex.org/W2097851570","https://openalex.org/W2121406124","https://openalex.org/W2295107390","https://openalex.org/W2616247523","https://openalex.org/W2788919350","https://openalex.org/W2896457183","https://openalex.org/W2945976633","https://openalex.org/W2950768109","https://openalex.org/W2968734407","https://openalex.org/W2970726176","https://openalex.org/W2973114758","https://openalex.org/W2984234582","https://openalex.org/W3034917890","https://openalex.org/W3035422918","https://openalex.org/W3135021825","https://openalex.org/W4213070269","https://openalex.org/W4213077304","https://openalex.org/W4220737975","https://openalex.org/W4292883990","https://openalex.org/W4312645761","https://openalex.org/W4313485929","https://openalex.org/W4360992523","https://openalex.org/W4361989906","https://openalex.org/W4375859821","https://openalex.org/W4385800564","https://openalex.org/W4387617009","https://openalex.org/W4388042006","https://openalex.org/W4389538269","https://openalex.org/W4389888290","https://openalex.org/W4393160837","https://openalex.org/W4402696779","https://openalex.org/W4403891981","https://openalex.org/W4413336491","https://openalex.org/W7114785843","https://openalex.org/W7133193712","https://openalex.org/W7133232090"],"related_works":[],"abstract_inverted_index":{"Providing":[0],"explainable":[1,52,206],"molecular":[2,28,41,53,73,207,238],"property":[3,29,54,208],"predictions":[4],"is":[5],"critical":[6],"for":[7,51,109,237,254],"many":[8],"scientific":[9],"domains,":[10],"such":[11],"as":[12,61,79,88,250],"drug":[13],"discovery":[14],"and":[15,84,107,193],"material":[16],"science.":[17],"Though":[18],"transformer-based":[19],"language":[20,58],"models":[21],"have":[22],"shown":[23],"great":[24],"potential":[25],"in":[26,205],"accurate":[27],"prediction,":[30],"they":[31],"neither":[32],"provide":[33,65],"chemically":[34,91,114],"meaningful":[35,92,115],"explanations":[36,125,143,168,218],"nor":[37],"faithfully":[38],"reveal":[39],"the":[40,96,119,124,129,142,147,152,156,163,167,170,174,195,203,213,217,224],"structure-property":[42,130],"relationships.":[43],"In":[44],"this":[45],"work,":[46],"we":[47,101,132,222],"develop":[48],"a":[49,71,136,251],"framework":[50,225],"prediction":[55,191],"based":[56],"on":[57,118],"models,":[59],"dubbed":[60],"Lamole,":[62,87,100,221],"which":[63],"can":[64,165,188],"chemical":[66],"concepts-aligned":[67],"explanations.":[68,180],"We":[69,150],"take":[70],"string-based":[72],"representation":[74],"-":[75,78],"Group":[76],"SELFIES":[77],"input":[80],"tokens":[81],"to":[82,128,139,144,160,178,200],"pre-train":[83],"fine-tune":[85],"our":[86],"it":[89],"provides":[90],"semantics.":[93],"By":[94],"disentangling":[95],"information":[97],"flows":[98],"of":[99,112,173,216],"propose":[102],"considering":[103],"both":[104],"self-attention":[105],"weights":[106],"gradients":[108],"better":[110],"quantification":[111],"each":[113],"substructure's":[116],"impact":[117],"model's":[120],"output.":[121],"To":[122,210],"make":[123],"more":[126],"faithful":[127],"relationship,":[131],"then":[133],"carefully":[134],"craft":[135],"marginal":[137,158],"loss":[138,159,164],"explicitly":[140],"optimize":[141],"align":[145,166],"with":[146,155,169,226],"chemists'":[148],"annotations.":[149],"bridge":[151],"manifold":[153],"hypothesis":[154],"elaborated":[157],"prove":[161],"that":[162,241],"tangent":[171],"space":[172],"data":[175],"manifold,":[176],"leading":[177],"concept-aligned":[179],"Experimental":[181],"results":[182],"over":[183],"eight":[184],"datasets":[185],"demonstrate":[186],"Lamole":[187,242],"achieve":[189],"comparable":[190],"accuracy":[192,197],"boost":[194],"explanation":[196],"by":[198],"up":[199],"14.3%,":[201],"being":[202],"state-of-the-art":[204],"prediction.":[209],"further":[211],"illustrate":[212],"actionable":[214],"utility":[215],"derived":[219],"from":[220],"integrated":[223],"an":[227,233],"evolutionary":[228],"algorithm.":[229],"This":[230],"integration":[231],"established":[232],"interpretable":[234],"optimization":[235],"pipeline":[236],"editing,":[239],"demonstrating":[240],"functions":[243],"beyond":[244],"simple":[245],"post-hoc":[246],"analysis":[247],"but":[248],"serves":[249],"practical":[252],"guide":[253],"molecule":[255],"discovery.":[256]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-13T00:00:00"}