{"id":"https://openalex.org/W4386012079","doi":"https://doi.org/10.1093/bib/bbad296","title":"Self-supervised learning with chemistry-aware fragmentation for effective molecular property prediction","display_name":"Self-supervised learning with chemistry-aware fragmentation for effective molecular property prediction","publication_year":2023,"publication_date":"2023-08-20","ids":{"openalex":"https://openalex.org/W4386012079","doi":"https://doi.org/10.1093/bib/bbad296","pmid":"https://pubmed.ncbi.nlm.nih.gov/37598424"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbad296","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbad296","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","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/A5102751255","display_name":"Ailin Xie","orcid":"https://orcid.org/0009-0000-9001-4681"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ailin Xie","raw_affiliation_strings":["Fudan University , and School of Computer Science, , 200438 Shanghai , China","Shanghai Key Lab of Intelligent Information Processing , and School of Computer Science, , 200438 Shanghai , China","Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science, Fudan University, 200438 Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University , and School of Computer Science, , 200438 Shanghai , China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing , and School of Computer Science, , 200438 Shanghai , China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science, Fudan University, 200438 Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103007849","display_name":"Ziqiao Zhang","orcid":"https://orcid.org/0000-0003-3747-7673"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqiao Zhang","raw_affiliation_strings":["Fudan University , and School of Computer Science, , 200438 Shanghai , China","Shanghai Key Lab of Intelligent Information Processing , and School of Computer Science, , 200438 Shanghai , China","Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science, Fudan University, 200438 Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University , and School of Computer Science, , 200438 Shanghai , China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing , and School of Computer Science, , 200438 Shanghai , China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science, Fudan University, 200438 Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086316879","display_name":"Jihong Guan","orcid":"https://orcid.org/0000-0003-2313-7635"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihong Guan","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University , 201804 Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University , 201804 Shanghai , China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017862559","display_name":"Shuigeng Zhou","orcid":"https://orcid.org/0000-0002-1949-2768"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuigeng Zhou","raw_affiliation_strings":["Fudan University , and School of Computer Science, , 200438 Shanghai , China","Shanghai Key Lab of Intelligent Information Processing , and School of Computer Science, , 200438 Shanghai , China","Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science, Fudan University, 200438 Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University , and School of Computer Science, , 200438 Shanghai , China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing , and School of Computer Science, , 200438 Shanghai , China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science, Fudan University, 200438 Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017862559"],"corresponding_institution_ids":["https://openalex.org/I113940042","https://openalex.org/I24943067"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":2.4209,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.9078064,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"24","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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":0.9991999864578247,"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":0.9689000248908997,"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/computer-science","display_name":"Computer science","score":0.7299425601959229},{"id":"https://openalex.org/keywords/molecular-graph","display_name":"Molecular graph","score":0.6295086145401001},{"id":"https://openalex.org/keywords/fragmentation","display_name":"Fragmentation (computing)","score":0.5769197940826416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.567973792552948},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5527396202087402},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5030893683433533},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4934903383255005},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4596739411354065},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.29375773668289185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7299425601959229},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.6295086145401001},{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.5769197940826416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.567973792552948},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5527396202087402},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5030893683433533},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4934903383255005},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4596739411354065},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29375773668289185},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbad296","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbad296","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:37598424","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37598424","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":"Briefings in bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G1487418658","display_name":"\u5355\u7ec6\u80deRNA\u6d4b\u5e8f\u6570\u636e\u805a\u7c7b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61972100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2062780035","display_name":null,"funder_award_id":"62172300","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1983865998","https://openalex.org/W1985572431","https://openalex.org/W1988037271","https://openalex.org/W1998492578","https://openalex.org/W2002609131","https://openalex.org/W2022476850","https://openalex.org/W2023818227","https://openalex.org/W2031296931","https://openalex.org/W2060531713","https://openalex.org/W2117043211","https://openalex.org/W2187089797","https://openalex.org/W2325811289","https://openalex.org/W2345649508","https://openalex.org/W2412082922","https://openalex.org/W2472085920","https://openalex.org/W2507264141","https://openalex.org/W2560674852","https://openalex.org/W2594183968","https://openalex.org/W2606780347","https://openalex.org/W2913668833","https://openalex.org/W2966357564","https://openalex.org/W2968734407","https://openalex.org/W2973114758","https://openalex.org/W2974690583","https://openalex.org/W2987522751","https://openalex.org/W3005680577","https://openalex.org/W3034516664","https://openalex.org/W3093934881","https://openalex.org/W3095883070","https://openalex.org/W3112376181","https://openalex.org/W3124027051","https://openalex.org/W3131204112","https://openalex.org/W3134210100","https://openalex.org/W3135514413","https://openalex.org/W3137551757","https://openalex.org/W3174831608","https://openalex.org/W3198212015","https://openalex.org/W3205158828","https://openalex.org/W3211394146","https://openalex.org/W3213940558","https://openalex.org/W4200125570","https://openalex.org/W4206816857","https://openalex.org/W4210860176","https://openalex.org/W4213077304","https://openalex.org/W4214868967","https://openalex.org/W4221151574","https://openalex.org/W4225751401","https://openalex.org/W4285307137","https://openalex.org/W4288419263","https://openalex.org/W4296262915","https://openalex.org/W4301372783","https://openalex.org/W6720342652","https://openalex.org/W6760045743","https://openalex.org/W6770257887","https://openalex.org/W6783990618","https://openalex.org/W6784526300","https://openalex.org/W6784614190","https://openalex.org/W6792108999","https://openalex.org/W6801428820","https://openalex.org/W6802320626","https://openalex.org/W6804049574","https://openalex.org/W6804531267","https://openalex.org/W6807990343"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W2013842271","https://openalex.org/W2808877228"],"abstract_inverted_index":{"Molecular":[0],"property":[1],"prediction":[2],"(MPP)":[3],"is":[4,122,143,162],"a":[5,100,116,134,142,159],"crucial":[6],"and":[7,196,233],"fundamental":[8],"task":[9],"for":[10,82,103,153,168],"AI-aided":[11],"drug":[12],"discovery":[13],"(AIDD).":[14],"Recent":[15],"studies":[16],"have":[17,87],"shown":[18],"great":[19],"promise":[20],"of":[21,44,174,192,226,239],"applying":[22],"self-supervised":[23,111,207],"learning":[24,58,113,149],"(SSL)":[25],"to":[26,30,62,66,72,124,150,164,217,230],"producing":[27],"molecular":[28,51,53,119,166,231],"representations":[29,54,152,167,221],"cope":[31],"with":[32,137,204],"the":[33,85,110,126,154,172,183,193,197,224,236],"widely-concerned":[34],"data":[35],"scarcity":[36],"problem":[37,238],"in":[38,49,84,107,156],"AIDD.":[39],"As":[40],"some":[41],"specific":[42],"substructures":[43,68,131],"molecules":[45,219],"play":[46],"important":[47],"roles":[48],"determining":[50],"properties,":[52,232],"learned":[55],"by":[56,147],"deep":[57],"models":[59,81],"are":[60],"expected":[61],"attach":[63],"more":[64],"importance":[65],"such":[67,91],"implicitly":[69,222],"or":[70],"explicitly":[71],"achieve":[73],"better":[74],"predictive":[75],"performance.":[76],"However,":[77],"few":[78],"SSL":[79],"pre-trained":[80,144],"MPP":[83,105,169],"literature":[86],"ever":[88],"focused":[89],"on":[90,145,171,177,190,200],"substructures.":[92],"To":[93],"challenge":[94],"this":[95,97],"situation,":[96],"paper":[98],"presents":[99],"Chemistry-Aware":[101],"Fragmentation":[102],"Effective":[104],"(CAFE-MPP":[106],"short)":[108],"under":[109],"contrastive":[112,148],"framework.":[114],"First,":[115],"novel":[117],"fragment-based":[118],"graph":[120,240],"(FMG)":[121],"designed":[123],"represent":[125],"topological":[127],"relationship":[128],"between":[129],"chemistry-aware":[130],"that":[132,182,213],"constitute":[133],"molecule.":[135],"Then,":[136],"well-designed":[138],"hard":[139],"negative":[140],"pairs,":[141],"fragment-level":[146],"extract":[151],"nodes":[155],"FMGs.":[157],"Finally,":[158],"Graphormer":[160],"model":[161],"leveraged":[163],"produce":[165],"based":[170],"embeddings":[173],"fragments.":[175],"Experiments":[176],"11":[178,194],"benchmark":[179],"datasets":[180,195],"show":[181],"proposed":[184],"CAFE-MPP":[185,214],"method":[186],"achieves":[187],"state-of-the-art":[188],"performance":[189,199],"7":[191],"second-best":[198],"3":[201],"datasets,":[202],"compared":[203],"six":[205],"remarkable":[206],"methods.":[208],"Further":[209],"investigations":[210],"also":[211],"demonstrate":[212],"can":[215,234],"learn":[216],"embed":[218],"into":[220],"containing":[223],"information":[225],"fragments":[227],"highly":[228],"correlated":[229],"alleviate":[235],"over-smoothing":[237],"neural":[241],"networks.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}