{"id":"https://openalex.org/W7160851389","doi":"https://doi.org/10.1021/acs.jcim.5c02769","title":"Functional Groups Are All You Need for Chemically Interpretable Molecular Property Prediction","display_name":"Functional Groups Are All You Need for Chemically Interpretable Molecular Property Prediction","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160851389","doi":"https://doi.org/10.1021/acs.jcim.5c02769","pmid":"https://pubmed.ncbi.nlm.nih.gov/42108966"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c02769","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c02769","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/A5129858104","display_name":"Roshan Balaji","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I4210099114","display_name":"Czech Academy of Sciences, Institute of Biotechnology","ror":"https://ror.org/00wzqmx94","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210099114"]},{"id":"https://openalex.org/I4210163794","display_name":"Data Management (Italy)","ror":"https://ror.org/017j5za44","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210163794"]},{"id":"https://openalex.org/I4210167034","display_name":"Millennium Institute for Integrative Biology","ror":"https://ror.org/05xcmte05","country_code":"CL","type":"other","lineage":["https://openalex.org/I4210167034"]}],"countries":["CL","CZ","IN","IT"],"is_corresponding":false,"raw_author_name":"Roshan Balaji","raw_affiliation_strings":["BioSystems Engineering and Control Lab, Department of Biotechnology","Indian Institute of Technology Madras","The Centre for Integrative Biology and Systems Medicine (IBSE)","Wadhwani School of Data Science and AI"],"raw_orcid":"https://orcid.org/0009-0005-1302-1032","affiliations":[{"raw_affiliation_string":"BioSystems Engineering and Control Lab, Department of Biotechnology","institution_ids":["https://openalex.org/I4210099114"]},{"raw_affiliation_string":"Indian Institute of Technology Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"The Centre for Integrative Biology and Systems Medicine (IBSE)","institution_ids":["https://openalex.org/I4210167034"]},{"raw_affiliation_string":"Wadhwani School of Data Science and AI","institution_ids":["https://openalex.org/I4210163794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074634045","display_name":"Joe Bobby","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I4210099114","display_name":"Czech Academy of Sciences, Institute of Biotechnology","ror":"https://ror.org/00wzqmx94","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210099114"]},{"id":"https://openalex.org/I4210163794","display_name":"Data Management (Italy)","ror":"https://ror.org/017j5za44","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210163794"]}],"countries":["CZ","IN","IT"],"is_corresponding":false,"raw_author_name":"Joe Bobby","raw_affiliation_strings":["BioSystems Engineering and Control Lab, Department of Biotechnology","Indian Institute of Technology Madras","Wadhwani School of Data Science and AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioSystems Engineering and Control Lab, Department of Biotechnology","institution_ids":["https://openalex.org/I4210099114"]},{"raw_affiliation_string":"Indian Institute of Technology Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Wadhwani School of Data Science and AI","institution_ids":["https://openalex.org/I4210163794"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135885551","display_name":"Nirav Pravinbhai Bhatt","orcid":"https://orcid.org/0000-0003-0928-6028"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I4210099114","display_name":"Czech Academy of Sciences, Institute of Biotechnology","ror":"https://ror.org/00wzqmx94","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210099114"]},{"id":"https://openalex.org/I4210163794","display_name":"Data Management (Italy)","ror":"https://ror.org/017j5za44","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210163794"]},{"id":"https://openalex.org/I4210167034","display_name":"Millennium Institute for Integrative Biology","ror":"https://ror.org/05xcmte05","country_code":"CL","type":"other","lineage":["https://openalex.org/I4210167034"]}],"countries":["CL","CZ","IN","IT"],"is_corresponding":true,"raw_author_name":"Nirav Pravinbhai Bhatt","raw_affiliation_strings":["BioSystems Engineering and Control Lab, Department of Biotechnology","Indian Institute of Technology Madras","Indian Institute of Technology Madras Zanzibar","The Centre for Integrative Biology and Systems Medicine (IBSE)","Wadhwani School of Data Science and AI"],"raw_orcid":"https://orcid.org/0000-0003-0928-6028","affiliations":[{"raw_affiliation_string":"BioSystems Engineering and Control Lab, Department of Biotechnology","institution_ids":["https://openalex.org/I4210099114"]},{"raw_affiliation_string":"Indian Institute of Technology Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Indian Institute of Technology Madras Zanzibar","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"The Centre for Integrative Biology and Systems Medicine (IBSE)","institution_ids":["https://openalex.org/I4210167034"]},{"raw_affiliation_string":"Wadhwani School of Data Science and AI","institution_ids":["https://openalex.org/I4210163794"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5135885551"],"corresponding_institution_ids":["https://openalex.org/I24676775","https://openalex.org/I4210099114","https://openalex.org/I4210163794","https://openalex.org/I4210167034"],"apc_list":null,"apc_paid":null,"fwci":8.5104,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97813901,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"66","issue":"10","first_page":"5625","last_page":"5640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.6087999939918518,"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":0.6087999939918518,"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":0.36570000648498535,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.007499999832361937,"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/chemical-space","display_name":"Chemical space","score":0.7990000247955322},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.6486999988555908},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6189000010490417},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5503000020980835},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5188000202178955},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.44850000739097595},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4309999942779541},{"id":"https://openalex.org/keywords/quantum-chemical","display_name":"Quantum chemical","score":0.428600013256073}],"concepts":[{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.7990000247955322},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.6486999988555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6341000199317932},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6189000010490417},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5503000020980835},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46639999747276306},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C2991951333","wikidata":"https://www.wikidata.org/wiki/Q188403","display_name":"Quantum chemical","level":3,"score":0.428600013256073},{"id":"https://openalex.org/C2777332933","wikidata":"https://www.wikidata.org/wiki/Q170409","display_name":"Functional group","level":3,"score":0.38839998841285706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3880000114440918},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3783000111579895},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3596999943256378},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.31690001487731934},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2671000063419342}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","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},{"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.5c02769","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c02769","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:42108966","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42108966","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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5237036943435669}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322211","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1780364926","https://openalex.org/W1849277567","https://openalex.org/W1964513093","https://openalex.org/W1968466100","https://openalex.org/W1975147762","https://openalex.org/W1980260989","https://openalex.org/W1981708439","https://openalex.org/W1982350795","https://openalex.org/W1982597534","https://openalex.org/W1988037271","https://openalex.org/W1995336204","https://openalex.org/W2008505552","https://openalex.org/W2060531713","https://openalex.org/W2076498053","https://openalex.org/W2076658253","https://openalex.org/W2080635178","https://openalex.org/W2096541451","https://openalex.org/W2100495367","https://openalex.org/W2112431023","https://openalex.org/W2145578524","https://openalex.org/W2153693853","https://openalex.org/W2155653793","https://openalex.org/W2164914937","https://openalex.org/W2177317049","https://openalex.org/W2179551254","https://openalex.org/W2200017991","https://openalex.org/W2342247785","https://openalex.org/W2345189907","https://openalex.org/W2406943157","https://openalex.org/W2461470610","https://openalex.org/W2461620095","https://openalex.org/W2473190403","https://openalex.org/W2748957644","https://openalex.org/W2803587386","https://openalex.org/W2804952889","https://openalex.org/W2911107164","https://openalex.org/W2945976633","https://openalex.org/W2953265656","https://openalex.org/W2963351448","https://openalex.org/W2966357564","https://openalex.org/W2968734407","https://openalex.org/W2978444138","https://openalex.org/W2997021962","https://openalex.org/W3007309629","https://openalex.org/W3009321976","https://openalex.org/W3034516664","https://openalex.org/W3038823641","https://openalex.org/W3092125766","https://openalex.org/W3113447514","https://openalex.org/W3124165020","https://openalex.org/W3134146005","https://openalex.org/W3216175560","https://openalex.org/W4213077304","https://openalex.org/W4213269078","https://openalex.org/W4214868967","https://openalex.org/W4225314242","https://openalex.org/W4226159083","https://openalex.org/W4281783323","https://openalex.org/W4283266241","https://openalex.org/W4308683713","https://openalex.org/W4313485929","https://openalex.org/W4377047094","https://openalex.org/W4379184641","https://openalex.org/W4381679608","https://openalex.org/W4387302789","https://openalex.org/W4396623857","https://openalex.org/W4396759674"],"related_works":[],"abstract_inverted_index":{"Molecular":[0],"property":[1,194],"prediction":[2],"using":[3,33,86],"deep":[4],"learning":[5],"(DL)":[6],"models":[7,18,192],"has":[8],"accelerated":[9],"drug":[10],"and":[11,42,78,141,169,189],"materials":[12],"discovery,":[13],"but":[14],"the":[15,34,44,117,148,180],"resulting":[16,92],"DL":[17,191],"often":[19],"lack":[20],"interpretability,":[21],"hindering":[22],"their":[23,58],"adoption":[24],"by":[25,102],"chemists.":[26],"This":[27,176],"work":[28,177],"proposes":[29],"developing":[30],"molecule":[31],"representations":[32,150],"concept":[35],"of":[36,68,110,128,182],"functional":[37,45,69,166],"groups":[38,167],"(FG)":[39,77],"in":[40],"chemistry":[41,183],"introduces":[43],"group":[46],"representation":[47],"(FGR)":[48],"framework,":[49],"a":[50,82,98,106,125],"novel":[51,171],"approach":[52],"to":[53,160,164,186],"encoding":[54],"molecules":[55,96],"based":[56],"on":[57,105,124],"fundamental":[59],"chemical":[60,75,145,156],"substructures.":[61],"The":[62,91],"proposed":[63],"framework":[64,94,120],"integrates":[65],"two":[66],"types":[67],"groups:":[70],"those":[71,79],"curated":[72],"from":[73,81],"established":[74,155],"knowledge":[76,184],"mined":[80],"large":[83,107],"molecular":[84],"corpus":[85],"sequential":[87],"pattern":[88],"mining":[89],"(MFG).":[90],"FGR":[93,119],"encodes":[95],"into":[97,173],"lower-dimensional":[99],"latent":[100],"space":[101],"leveraging":[103],"pretraining":[104],"data":[108,131],"set":[109],"unlabeled":[111],"molecules.":[112],"It":[113],"is":[114],"shown":[115],"that":[116,179],"chemistry-inspired,":[118],"achieves":[121],"state-of-the-art":[122],"performance":[123],"diverse":[126],"range":[127],"33":[129],"benchmark":[130],"sets":[132],"spanning":[133],"physical":[134],"chemistry,":[135],"biophysics,":[136],"quantum":[137],"mechanics,":[138],"biological":[139],"activity,":[140],"pharmacokinetics":[142],"while":[143],"enabling":[144,158],"interpretability.":[146],"Importantly,":[147],"FGR-based":[149],"are":[151],"intrinsically":[152],"aligned":[153],"with":[154],"principles,":[157],"chemists":[159],"link":[161],"predicted":[162],"properties":[163],"specific":[165],"directly":[168],"facilitating":[170],"insights":[172],"structure-property":[174],"relationships.":[175],"demonstrates":[178],"incorporation":[181],"leads":[185],"chemically":[187],"interpretable":[188],"high-performing":[190],"for":[193],"predictions.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-05-12T00:00:00"}