{"id":"https://openalex.org/W7133215200","doi":"https://doi.org/10.1186/s13321-026-01170-0","title":"Collision-free morgan fingerprints: a principled approach to enhance machine learning performance and interpretability in chemistry","display_name":"Collision-free morgan fingerprints: a principled approach to enhance machine learning performance and interpretability in chemistry","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133215200","doi":"https://doi.org/10.1186/s13321-026-01170-0","pmid":"https://pubmed.ncbi.nlm.nih.gov/41772717"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-026-01170-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01170-0","pdf_url":null,"source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13321-026-01170-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100775347","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-4366-7724"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jibai Li","raw_affiliation_strings":["Department of Environmental Science, School of Ecological and Environmental Sciences, East China Normal University, Shanghai, 200241, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Environmental Science, School of Ecological and Environmental Sciences, East China Normal University, Shanghai, 200241, People's Republic of China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127840143","display_name":"Xintong Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xintong Qu","raw_affiliation_strings":["Department of Environmental Science, School of Ecological and Environmental Sciences, East China Normal University, Shanghai, 200241, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Environmental Science, School of Ecological and Environmental Sciences, East China Normal University, Shanghai, 200241, People's Republic of China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453343","display_name":"Wenlong Zhang","orcid":"https://orcid.org/0000-0001-8368-3465"},"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"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenlong Zhang","raw_affiliation_strings":["Geogia Tech Shenzhen Institute, Tianjin University, Shenzhen, 518055, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Geogia Tech Shenzhen Institute, Tianjin University, Shenzhen, 518055, China","institution_ids":["https://openalex.org/I162868743","https://openalex.org/I4210152380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070370992","display_name":"Shifa Zhong","orcid":"https://orcid.org/0000-0002-5822-0837"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shifa Zhong","raw_affiliation_strings":["Department of Environmental Science, School of Ecological and Environmental Sciences, East China Normal University, Shanghai, 200241, People's Republic of China. sfzhong@des.ecnu.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Environmental Science, School of Ecological and Environmental Sciences, East China Normal University, Shanghai, 200241, People's Republic of China. sfzhong@des.ecnu.edu.cn","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070370992"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":2.8082,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87175348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"18","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.8273000121116638,"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":0.8273000121116638,"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":0.16140000522136688,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0010000000474974513,"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/interpretability","display_name":"Interpretability","score":0.9083999991416931},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5335999727249146},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.4697999954223633},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4596000015735626},{"id":"https://openalex.org/keywords/applicability-domain","display_name":"Applicability domain","score":0.3799000084400177},{"id":"https://openalex.org/keywords/workaround","display_name":"Workaround","score":0.3763999938964844},{"id":"https://openalex.org/keywords/credibility","display_name":"Credibility","score":0.3571999967098236},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.34450000524520874}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9083999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728000283241272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7368999719619751},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7095999717712402},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.4697999954223633},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C107908354","wikidata":"https://www.wikidata.org/wiki/Q4781456","display_name":"Applicability domain","level":3,"score":0.3799000084400177},{"id":"https://openalex.org/C194541083","wikidata":"https://www.wikidata.org/wiki/Q457174","display_name":"Workaround","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C50292564","wikidata":"https://www.wikidata.org/wiki/Q2462783","display_name":"Computational learning theory","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-026-01170-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01170-0","pdf_url":null,"source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:41772717","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41772717","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 cheminformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:1849975cf420432d8f34aaa5a9a241e7","is_oa":true,"landing_page_url":"https://doaj.org/article/1849975cf420432d8f34aaa5a9a241e7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 18, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13097559","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13097559/","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-026-01170-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01170-0","pdf_url":null,"source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1266421222","display_name":null,"funder_award_id":"22476052","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1988037271","https://openalex.org/W2064911970","https://openalex.org/W2151697120","https://openalex.org/W2594183968","https://openalex.org/W2744167442","https://openalex.org/W2763694886","https://openalex.org/W2784006847","https://openalex.org/W2800748443","https://openalex.org/W2883583109","https://openalex.org/W2901434355","https://openalex.org/W2905012389","https://openalex.org/W2999615587","https://openalex.org/W3004731690","https://openalex.org/W3011286504","https://openalex.org/W3048453687","https://openalex.org/W3087318293","https://openalex.org/W3094083226","https://openalex.org/W3101477379","https://openalex.org/W3136198265","https://openalex.org/W3137928831","https://openalex.org/W3158878314","https://openalex.org/W3173289526","https://openalex.org/W3185391990","https://openalex.org/W3196726907","https://openalex.org/W4200509818","https://openalex.org/W4221001963","https://openalex.org/W4224245099","https://openalex.org/W4224982784","https://openalex.org/W4225966185","https://openalex.org/W4226054611","https://openalex.org/W4317952015","https://openalex.org/W4378070318","https://openalex.org/W4380244113","https://openalex.org/W4381679608","https://openalex.org/W4382536268","https://openalex.org/W4383216745","https://openalex.org/W4385476898","https://openalex.org/W4387032960","https://openalex.org/W4387033339","https://openalex.org/W4387999175","https://openalex.org/W4388409550","https://openalex.org/W4393152099","https://openalex.org/W4395072098","https://openalex.org/W4396887243","https://openalex.org/W4398223058","https://openalex.org/W4399684922","https://openalex.org/W4399797001","https://openalex.org/W4400362104","https://openalex.org/W4402623547","https://openalex.org/W4403483599","https://openalex.org/W4406028047","https://openalex.org/W4409360886","https://openalex.org/W4414127859"],"related_works":[],"abstract_inverted_index":{"The":[0],"success":[1],"of":[2,14,71,139,191],"machine":[3,93,234],"learning":[4,94,183,235],"in":[5,111,117,215,299],"chemistry":[6],"is":[7,225],"fundamentally":[8,129],"underpinned":[9],"by":[10,121,126,141],"the":[11,69,135,187,226,264],"information":[12,73,164],"fidelity":[13,165],"molecular":[15,173,246,271],"representations.":[16,174],"Despite":[17],"their":[18,231],"widespread":[19],"adoption":[20],"for":[21,171,203,221,269],"efficiency":[22],"and":[23,30,49,91,102,113,133,154,189,200,209,237],"interpretability,":[24],"Morgan":[25,61,216],"fingerprints":[26,217],"harbor":[27],"a":[28,64,81,147,167,197,239,250,266,289],"long-overlooked":[29],"fundamental":[31,168],"flaw:":[32],"bit":[33,213],"collisions.":[34],"This":[35,194],"phenomenon":[36],"erroneously":[37],"maps":[38],"distinct":[39],"chemical":[40,131],"substructures":[41],"to":[42,107,228,244,260,295],"identical":[43],"positions,":[44],"systematically":[45,229],"corrupting":[46],"structure-property":[47],"relationships":[48],"severely":[50],"compromising":[51],"model":[52],"interpretability.":[53],"To":[54],"address":[55],"this":[56,223],"challenge,":[57],"we":[58,96],"introduce":[59],"Collision-Free":[60],"Fingerprints":[62],"(CF-MF),":[63],"principled":[65],"framework":[66,253],"that":[67,98,254,281],"guarantees":[68],"integrity":[70],"substructure":[72],"through":[74],"an":[75],"adaptive,":[76],"data-driven":[77],"sizing":[78],"mechanism.":[79],"Through":[80],"comprehensive":[82],"evaluation":[83],"across":[84],"25":[85],"diverse":[86],"datasets":[87],"(>":[88],"50,000":[89],"molecules)":[90],"multiple":[92],"paradigms,":[95],"demonstrate":[97],"CF-MF":[99,128],"delivers":[100],"consistent":[101],"significant":[103],"performance":[104,155,178,236,275],"gains":[105],"up":[106],"16.81%":[108],"RMSE":[109],"reduction":[110],"regression":[112],"11.1%":[114],"accuracy":[115],"increase":[116],"classification.":[118],"More":[119],"critically,":[120],"eliminating":[122,282],"attribution":[123],"errors":[124],"caused":[125],"collisions,":[127],"restores":[130,284],"interpretability":[132],"expands":[134],"reliable":[136,199],"prediction":[137],"domains":[138],"models":[140,184],"60-100%.":[142],"Our":[143],"information-theoretic":[144,252],"analysis":[145],"reveals":[146],"strong":[148],"correlation":[149],"between":[150],"collision-induced":[151,257],"entropy":[152,258],"loss":[153,259],"degradation":[156],"(R2":[157],"=":[158],"0.854,":[159],"p":[160],"<":[161],"0.001),":[162],"establishing":[163],"as":[166],"design":[169],"principle":[170],"next-generation":[172],"It":[175],"also":[176],"achieves":[177],"competitive":[179],"with":[180],"state-of-the-art":[181],"deep":[182],"while":[185],"retaining":[186],"simplicity":[188],"intuitiveness":[190],"traditional":[192],"fingerprints.":[193],"work":[195,278],"provides":[196],"more":[198],"trustworthy":[201,296],"foundation":[202],"AI-driven":[204],"drug":[205],"discovery,":[206],"materials":[207],"science,":[208],"environmental":[210],"assessment.Scientific":[211],"contributionWhile":[212],"collisions":[214,283],"have":[218],"been":[219],"acknowledged":[220],"decades,":[222],"study":[224],"first":[227],"quantify":[230],"impact":[232],"on":[233],"provide":[238],"principled,":[240],"reproducible":[241],"solution":[242],"applicable":[243],"any":[245],"dataset.":[247],"We":[248],"establish":[249],"novel":[251],"directly":[255],"links":[256],"predictive":[261],"degradation,":[262],"offering":[263],"field":[265],"quantitative":[267],"criterion":[268],"evaluating":[270],"representation":[272],"fidelity.":[273],"Beyond":[274],"gains,":[276],"our":[277],"uniquely":[279],"demonstrates":[280],"chemically":[285],"valid":[286],"SHAP":[287],"attributions-addressing":[288],"critical":[290],"but":[291],"previously":[292],"unrecognized":[293],"barrier":[294],"AI":[297],"interpretation":[298],"chemistry.":[300]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-03-03T00:00:00"}