{"id":"https://openalex.org/W4416775727","doi":"https://doi.org/10.3389/fbinf.2025.1695353","title":"Beyond Tanimoto: a learned bioactivity similarity index enhances ligand discovery","display_name":"Beyond Tanimoto: a learned bioactivity similarity index enhances ligand discovery","publication_year":2025,"publication_date":"2025-11-28","ids":{"openalex":"https://openalex.org/W4416775727","doi":"https://doi.org/10.3389/fbinf.2025.1695353","pmid":"https://pubmed.ncbi.nlm.nih.gov/41393791"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2025.1695353","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1695353","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1695353/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1695353/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072776787","display_name":"Gustavo Schottlender","orcid":null},"institutions":[{"id":"https://openalex.org/I53241121","display_name":"Fundaci\u00f3n Ciencias Exactas y Naturales","ror":"https://ror.org/05rxmkq09","country_code":"AR","type":"nonprofit","lineage":["https://openalex.org/I53241121"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Gustavo Schottlender","raw_affiliation_strings":["Instituto de C\u00e1lculo, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, CONICET, Universidad de Buenos Aires, Buenos Aires, Argentina"],"affiliations":[{"raw_affiliation_string":"Instituto de C\u00e1lculo, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, CONICET, Universidad de Buenos Aires, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I53241121"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063004071","display_name":"Juan Manuel Prieto","orcid":"https://orcid.org/0009-0004-2838-0356"},"institutions":[{"id":"https://openalex.org/I24354313","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]},{"id":"https://openalex.org/I4210145660","display_name":"Bio-Medical Science (South Korea)","ror":"https://ror.org/046p12h21","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210145660"]},{"id":"https://openalex.org/I53241121","display_name":"Fundaci\u00f3n Ciencias Exactas y Naturales","ror":"https://ror.org/05rxmkq09","country_code":"AR","type":"nonprofit","lineage":["https://openalex.org/I53241121"]}],"countries":["AR","KR"],"is_corresponding":false,"raw_author_name":"Juan Manuel Prieto","raw_affiliation_strings":["Departamento de Qu\u00edmica Biol\u00f3gica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires (FCEyN-UBA), Buenos Aires, Argentina","LUCAI BIO, Dover, DE, United States"],"affiliations":[{"raw_affiliation_string":"Departamento de Qu\u00edmica Biol\u00f3gica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires (FCEyN-UBA), Buenos Aires, Argentina","institution_ids":["https://openalex.org/I53241121","https://openalex.org/I24354313"]},{"raw_affiliation_string":"LUCAI BIO, Dover, DE, United States","institution_ids":["https://openalex.org/I4210145660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089022257","display_name":"Marcelo A. Mart\u00ed","orcid":"https://orcid.org/0000-0002-7911-9340"},"institutions":[{"id":"https://openalex.org/I24354313","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]},{"id":"https://openalex.org/I53241121","display_name":"Fundaci\u00f3n Ciencias Exactas y Naturales","ror":"https://ror.org/05rxmkq09","country_code":"AR","type":"nonprofit","lineage":["https://openalex.org/I53241121"]}],"countries":["AR"],"is_corresponding":true,"raw_author_name":"Marcelo A. Marti","raw_affiliation_strings":["Departamento de Qu\u00edmica Biol\u00f3gica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires (FCEyN-UBA), Buenos Aires, Argentina","Instituto de Qu\u00edmica Biol\u00f3gica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN) CONICET, Pabell\u00f3n 2 de Ciudad Universitaria, Buenos Aires, Argentina"],"affiliations":[{"raw_affiliation_string":"Departamento de Qu\u00edmica Biol\u00f3gica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires (FCEyN-UBA), Buenos Aires, Argentina","institution_ids":["https://openalex.org/I53241121","https://openalex.org/I24354313"]},{"raw_affiliation_string":"Instituto de Qu\u00edmica Biol\u00f3gica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN) CONICET, Pabell\u00f3n 2 de Ciudad Universitaria, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I53241121"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090937046","display_name":"Dar\u00edo Fern\u00e1ndez Do Porto","orcid":"https://orcid.org/0000-0002-3622-4052"},"institutions":[{"id":"https://openalex.org/I24354313","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]},{"id":"https://openalex.org/I53241121","display_name":"Fundaci\u00f3n Ciencias Exactas y Naturales","ror":"https://ror.org/05rxmkq09","country_code":"AR","type":"nonprofit","lineage":["https://openalex.org/I53241121"]}],"countries":["AR"],"is_corresponding":true,"raw_author_name":"Dario Fern\u00e1ndez Do Porto","raw_affiliation_strings":["Departamento de Qu\u00edmica Biol\u00f3gica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires (FCEyN-UBA), Buenos Aires, Argentina","Instituto de C\u00e1lculo, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, CONICET, Universidad de Buenos Aires, Buenos Aires, Argentina"],"affiliations":[{"raw_affiliation_string":"Departamento de Qu\u00edmica Biol\u00f3gica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires (FCEyN-UBA), Buenos Aires, Argentina","institution_ids":["https://openalex.org/I53241121","https://openalex.org/I24354313"]},{"raw_affiliation_string":"Instituto de C\u00e1lculo, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, CONICET, Universidad de Buenos Aires, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I53241121"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089022257","https://openalex.org/A5090937046"],"corresponding_institution_ids":["https://openalex.org/I24354313","https://openalex.org/I53241121"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":1.348,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87385344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"1695353","last_page":"1695353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9376999735832214,"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":0.9376999735832214,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.016300000250339508,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/chembl","display_name":"chEMBL","score":0.928600013256073},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7196999788284302},{"id":"https://openalex.org/keywords/virtual-screening","display_name":"Virtual screening","score":0.5823000073432922},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5640000104904175},{"id":"https://openalex.org/keywords/chemotype","display_name":"Chemotype","score":0.51910001039505},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5116000175476074},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.49239999055862427},{"id":"https://openalex.org/keywords/structural-similarity","display_name":"Structural similarity","score":0.39719998836517334}],"concepts":[{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.928600013256073},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7196999788284302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6049000024795532},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.5823000073432922},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5640000104904175},{"id":"https://openalex.org/C153784791","wikidata":"https://www.wikidata.org/wiki/Q2212766","display_name":"Chemotype","level":3,"score":0.51910001039505},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022000074386597},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.49239999055862427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44769999384880066},{"id":"https://openalex.org/C139489369","wikidata":"https://www.wikidata.org/wiki/Q770846","display_name":"Structural similarity","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.3901999890804291},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.36910000443458557},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C116569031","wikidata":"https://www.wikidata.org/wiki/Q899107","display_name":"Ligand (biochemistry)","level":3,"score":0.30410000681877136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C24259465","wikidata":"https://www.wikidata.org/wiki/Q2272153","display_name":"Chemical similarity","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26330000162124634},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fbinf.2025.1695353","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1695353","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1695353/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41393791","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41393791","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":"Frontiers in bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:a145e89c2a434ca7bf665cddfbbed726","is_oa":true,"landing_page_url":"https://doaj.org/article/a145e89c2a434ca7bf665cddfbbed726","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Bioinformatics, Vol 5 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12698616","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12698616/","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":"Front Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2025.1695353","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1695353","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1695353/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321594","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416775727.pdf"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W1816679421","https://openalex.org/W1930021478","https://openalex.org/W1955852547","https://openalex.org/W1968319881","https://openalex.org/W1975875968","https://openalex.org/W1981066521","https://openalex.org/W1984994707","https://openalex.org/W1988037271","https://openalex.org/W1993492933","https://openalex.org/W2029667189","https://openalex.org/W2044834685","https://openalex.org/W2050081822","https://openalex.org/W2060531713","https://openalex.org/W2062459137","https://openalex.org/W2105668062","https://openalex.org/W2110400862","https://openalex.org/W2151697120","https://openalex.org/W2156077095","https://openalex.org/W2169678694","https://openalex.org/W2178618822","https://openalex.org/W2200017991","https://openalex.org/W2213443318","https://openalex.org/W2412446857","https://openalex.org/W2558057290","https://openalex.org/W2734479124","https://openalex.org/W2740946158","https://openalex.org/W2765905551","https://openalex.org/W2795688948","https://openalex.org/W2805375306","https://openalex.org/W2811031415","https://openalex.org/W2895884529","https://openalex.org/W2951804018","https://openalex.org/W3025774909","https://openalex.org/W3029832490","https://openalex.org/W3034021666","https://openalex.org/W3036600937","https://openalex.org/W3042826782","https://openalex.org/W3045085645","https://openalex.org/W3112567989","https://openalex.org/W3113447514","https://openalex.org/W3120361527","https://openalex.org/W3138593412","https://openalex.org/W3156894194","https://openalex.org/W3165697851","https://openalex.org/W3166067616","https://openalex.org/W3184138602","https://openalex.org/W3197516020","https://openalex.org/W3198168376","https://openalex.org/W3204764757","https://openalex.org/W4210482071","https://openalex.org/W4213070269","https://openalex.org/W4220851662","https://openalex.org/W4220980941","https://openalex.org/W4221090435","https://openalex.org/W4224867167","https://openalex.org/W4281960442","https://openalex.org/W4295312788","https://openalex.org/W4306867651","https://openalex.org/W4313296448","https://openalex.org/W4376601927","https://openalex.org/W4388455891","https://openalex.org/W4388852108","https://openalex.org/W4391610189","https://openalex.org/W4393991916","https://openalex.org/W4396721167","https://openalex.org/W4399165032","https://openalex.org/W4404343451","https://openalex.org/W4404458588","https://openalex.org/W4406404705","https://openalex.org/W4408557607","https://openalex.org/W4409334630","https://openalex.org/W4410997516"],"related_works":[],"abstract_inverted_index":{"Structural":[0],"similarity":[1,58,67,225],"metrics":[2],"such":[3],"as":[4],"the":[5,21,47,65,76,82,174,188,192,196],"Tanimoto":[6],"coefficient":[7],"(TC)":[8,206],"miss":[9],"many":[10],"functionally":[11,53,240],"related":[12,85],"compounds-indeed,":[13],"60%":[14],"of":[15,49,195],"similarly":[16],"bioactive":[17],"ligand":[18],"pairs":[19],"in":[20],"ChEMBL":[22,157],"database":[23],"show":[24],"TC":[25,103],"<":[26],"0.30,":[27],"revealing":[28],"a":[29,70,126,182,200],"major":[30],"blind":[31,43],"spot":[32,44],"that":[33,56,74,78,235],"constrains":[34],"ligand-based":[35],"discovery.":[36],"Our":[37],"motivation":[38],"is":[39,244],"to":[40,60,207,232],"overcome":[41],"this":[42],"and":[45,112,138,177,214,226],"enable":[46],"recovery":[48],"structurally":[50,237],"different":[51],"yet":[52,239],"equivalent":[54],"chemotypes":[55,234],"structure-based":[57,224],"fails":[59],"detect.":[61],"Here,":[62],"we":[63],"introduce":[64],"bioactivity":[66],"index":[68],"(BSI),":[69,209],"machine":[71],"learning":[72],"model":[73,128],"estimates":[75],"probability":[77],"two":[79],"molecules":[80],"bind":[81],"same":[83],"or":[84],"protein":[86,94,121],"receptors.":[87],"Trained":[88],"under":[89],"leave-one-protein-out":[90],"(LOPO)":[91],"across":[92,120],"Pfam-defined":[93],"groups":[95],"on":[96,155],"dissimilar":[97,238],"pairs,":[98],"BSI":[99,160,219],"not":[100],"only":[101],"outperforms":[102],"but":[104],"also":[105],"surpasses":[106],"modern":[107],"molecular":[108],"embedding":[109],"baselines":[110],"(ChemBERTa":[111],"contrastive":[113],"language-molecule":[114],"pre-training":[115],"(CLAMP),":[116],"using":[117],"cosine":[118],"similarity)":[119],"families.":[122],"We":[123],"further":[124],"develop":[125],"cross-family":[127],"(BSI-Large)":[129],"that,":[130],"while":[131],"slightly":[132],"below":[133],"group-specific":[134,171],"models,":[135],"generalizes":[136],"better":[137],"can":[139],"be":[140],"fine-tuned":[141],"with":[142,170,210],"less":[143],"data,":[144,159],"consistently":[145],"improving":[146],"over":[147],"models":[148,172],"trained":[149],"from":[150,204],"scratch.":[151],"In":[152,181],"retrospective":[153],"validation":[154],"new":[156],"v35":[158],"achieves":[161],"strong":[162],"early-retrieval":[163],"performance":[164],"(top":[165],"2%":[166],"enrichment":[167],"factor,":[168],"EF<sub>2%</sub>),":[169],"delivering":[173],"best":[175],"enrichment,":[176],"BSI-Large":[178],"remaining":[179],"competitive.":[180],"realistic":[183],"virtual":[184],"screening-like":[185],"scenario":[186],"against":[187],"target":[189],"gene":[190],"ADRA2B,":[191],"mean":[193],"rank":[194],"next":[197],"active,":[198,202],"given":[199],"known":[201],"improves":[203],"45.2":[205],"3.9":[208],"54.9":[211],"for":[212,216],"ChemBERTa":[213],"28.6":[215],"CLAMP.":[217],"Altogether,":[218],"complements,":[220],"rather":[221],"than":[222],"replaces,":[223],"embedding-based":[227],"comparisons,":[228],"extending":[229],"hit":[230],"finding":[231],"remote":[233],"are":[236],"equivalent.":[241],"The":[242],"code":[243],"available":[245],"at":[246],"https://github.com/gschottlender/bioactivity-similarity-index.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-11-28T00:00:00"}
