{"id":"https://openalex.org/W4221151574","doi":"https://doi.org/10.1021/acs.jcim.2c00495","title":"Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast","display_name":"Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast","publication_year":2022,"publication_date":"2022-05-31","ids":{"openalex":"https://openalex.org/W4221151574","doi":"https://doi.org/10.1021/acs.jcim.2c00495","pmid":"https://pubmed.ncbi.nlm.nih.gov/35638560"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.2c00495","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c00495","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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2202.09346","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100409331","display_name":"Yuyang Wang","orcid":"https://orcid.org/0000-0003-0723-6246"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuyang Wang","raw_affiliation_strings":["Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States"],"raw_orcid":"https://orcid.org/0000-0003-0723-6246","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011452751","display_name":"Rishikesh Magar","orcid":"https://orcid.org/0000-0001-6216-0518"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rishikesh Magar","raw_affiliation_strings":["Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101957211","display_name":"Liang Chen","orcid":"https://orcid.org/0000-0002-3149-0239"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Liang","raw_affiliation_strings":["Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008745801","display_name":"Amir Barati Farimani","orcid":"https://orcid.org/0000-0002-2952-8576"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amir Barati Farimani","raw_affiliation_strings":["Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States","Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States"],"raw_orcid":"https://orcid.org/0000-0002-2952-8576","affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5008745801"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":9.5431,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":{"value":0.98682431,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"62","issue":"11","first_page":"2713","last_page":"2725"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9634000062942505,"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/cheminformatics","display_name":"Cheminformatics","score":0.9314324855804443},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.779361367225647},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6646108627319336},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6494689583778381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6459951400756836},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5782586336135864},{"id":"https://openalex.org/keywords/molecular-descriptor","display_name":"Molecular descriptor","score":0.510279655456543},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2640834450721741},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.25093895196914673},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.1790238618850708},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.10216450691223145}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.9314324855804443},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.779361367225647},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6646108627319336},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6494689583778381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6459951400756836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5782586336135864},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.510279655456543},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2640834450721741},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.25093895196914673},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.1790238618850708},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.10216450691223145},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000080486","descriptor_name":"Computational Chemistry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000080486","descriptor_name":"Computational Chemistry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000080486","descriptor_name":"Computational Chemistry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.2c00495","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c00495","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:35638560","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35638560","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":null},{"id":"pmh:oai:arXiv.org:2202.09346","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.09346","pdf_url":"https://arxiv.org/pdf/2202.09346","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2202.09346","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.09346","pdf_url":"https://arxiv.org/pdf/2202.09346","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W1999798000","https://openalex.org/W2019538911","https://openalex.org/W2022476850","https://openalex.org/W2025948031","https://openalex.org/W2076063813","https://openalex.org/W2080635178","https://openalex.org/W2138621090","https://openalex.org/W2151697120","https://openalex.org/W2461620095","https://openalex.org/W2529996553","https://openalex.org/W2558748708","https://openalex.org/W2594183968","https://openalex.org/W2602318385","https://openalex.org/W2606780347","https://openalex.org/W2749279690","https://openalex.org/W2778051509","https://openalex.org/W2884430236","https://openalex.org/W2896457183","https://openalex.org/W2899070097","https://openalex.org/W2907492528","https://openalex.org/W2919115771","https://openalex.org/W2937307539","https://openalex.org/W2962824366","https://openalex.org/W2962876364","https://openalex.org/W2963263347","https://openalex.org/W2964015378","https://openalex.org/W2964113829","https://openalex.org/W2966357564","https://openalex.org/W2968734407","https://openalex.org/W2973114758","https://openalex.org/W2987522751","https://openalex.org/W3005552578","https://openalex.org/W3005680577","https://openalex.org/W3035524453","https://openalex.org/W3036224891","https://openalex.org/W3045928028","https://openalex.org/W3081836708","https://openalex.org/W3093934881","https://openalex.org/W3095602948","https://openalex.org/W3095883070","https://openalex.org/W3098269892","https://openalex.org/W3104644561","https://openalex.org/W3106743555","https://openalex.org/W3109892317","https://openalex.org/W3116202926","https://openalex.org/W3125600935","https://openalex.org/W3134146005","https://openalex.org/W3134652006","https://openalex.org/W3166272013","https://openalex.org/W3171007011","https://openalex.org/W3171707284","https://openalex.org/W3173985861","https://openalex.org/W3176707157","https://openalex.org/W3176905117","https://openalex.org/W3190580390","https://openalex.org/W3201866154","https://openalex.org/W3206711231","https://openalex.org/W3213940558","https://openalex.org/W3214987860","https://openalex.org/W4200629501","https://openalex.org/W4214868967","https://openalex.org/W4241119204","https://openalex.org/W4281619372","https://openalex.org/W4286907726","https://openalex.org/W4287592659","https://openalex.org/W4287828570","https://openalex.org/W4288419263","https://openalex.org/W4297808394","https://openalex.org/W4301372783","https://openalex.org/W4304697394","https://openalex.org/W4308260849","https://openalex.org/W4312039930","https://openalex.org/W4313485929","https://openalex.org/W4385245566","https://openalex.org/W6600388300","https://openalex.org/W6601048975","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W4382246684","https://openalex.org/W4387845407","https://openalex.org/W2902857455","https://openalex.org/W4207004502","https://openalex.org/W4212982662","https://openalex.org/W2160244398","https://openalex.org/W2907885506","https://openalex.org/W2022444336","https://openalex.org/W2601867172","https://openalex.org/W3042998478"],"abstract_inverted_index":{"Deep":[0],"learning":[1,18,22,80,210],"has":[2,24],"been":[3],"a":[4],"prevalence":[5],"in":[6,12,117],"computational":[7],"chemistry":[8],"and":[9,64,90,133,139,184,215,229],"widely":[10],"implemented":[11],"molecular":[13,33,59,71,88,162],"property":[14,60,163],"predictions.":[15,164],"Recently,":[16],"self-supervised":[17],"(SSL),":[19],"especially":[20],"contrastive":[21,124],"(CL),":[23],"gathered":[25],"growing":[26],"attention":[27],"for":[28],"the":[29,38,55,75,78,84,149,154,168,190,199],"potential":[30],"to":[31,37,57,167],"learn":[32],"representations":[34,222],"that":[35,148,221,232],"generalize":[36],"gigantic":[39],"chemical":[40],"space.":[41],"Unlike":[42],"supervised":[43,209],"learning,":[44],"SSL":[45,72],"can":[46,233],"directly":[47],"leverage":[48],"large":[49],"unlabeled":[50],"data,":[51],"which":[52],"greatly":[53],"reduces":[54],"effort":[56],"acquire":[58],"labels":[61],"through":[62,224],"costly":[63],"time-consuming":[65],"simulations":[66],"or":[67,206],"experiments.":[68],"However,":[69],"most":[70,197],"methods":[73],"borrow":[74],"insights":[76],"from":[77,143],"machine":[79],"community":[81],"but":[82],"neglect":[83],"unique":[85],"cheminformatics":[86,128],"(e.g.,":[87,94],"fingerprints)":[89],"multilevel":[91],"graphical":[92],"structures":[93],"functional":[95,230],"groups)":[96],"of":[97,106,110,156,178,189],"molecules.":[98,144],"In":[99,165],"this":[100],"work,":[101],"we":[102],"propose":[103],"iMolCLR,":[104],"improvement":[105,177],"Molecular":[107],"Contrastive":[108],"Learning":[109],"Representations":[111],"with":[112,212],"graph":[113],"neural":[114],"networks":[115],"(GNNs)":[116],"two":[118],"aspects:":[119],"(1)":[120],"mitigating":[121],"faulty":[122],"negative":[123],"instances":[125],"via":[126],"considering":[127],"similarities":[129],"between":[130,137],"molecule":[131,235],"pairs":[132],"(2)":[134],"fragment-level":[135],"contrasting":[136],"intramolecule":[138],"intermolecule":[140],"substructures":[141],"decomposed":[142],"Experiments":[145],"have":[146],"shown":[147],"proposed":[150],"strategies":[151],"significantly":[152],"improve":[153],"performance":[155],"GNN":[157,201],"models":[158,211],"on":[159,180,192],"various":[160],"challenging":[161],"comparison":[166],"previous":[169],"CL":[170],"framework,":[171],"iMolCLR":[172,204,225],"demonstrates":[173],"an":[174,185],"averaged":[175,186],"1.2%":[176],"ROC-AUC":[179],"eight":[181],"classification":[182],"benchmarks":[183],"10.1%":[187],"decrease":[188],"error":[191],"six":[193],"regression":[194],"benchmarks.":[195],"On":[196],"benchmarks,":[198],"generic":[200],"pretrained":[202],"by":[203],"rivals":[205],"even":[207],"surpasses":[208],"sophisticated":[213],"architectures":[214],"engineered":[216],"features.":[217],"Further":[218],"investigations":[219],"demonstrate":[220],"learned":[223],"intrinsically":[226],"embed":[227],"scaffolds":[228],"groups":[231],"reason":[234],"similarities.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}