{"id":"https://openalex.org/W4290875097","doi":"https://doi.org/10.1145/3534678.3539368","title":"Unified 2D and 3D Pre-Training of Molecular Representations","display_name":"Unified 2D and 3D Pre-Training of Molecular Representations","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290875097","doi":"https://doi.org/10.1145/3534678.3539368"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539368","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5028284977","display_name":"Jinhua Zhu","orcid":"https://orcid.org/0000-0003-2157-9077"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinhua Zhu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021772140","display_name":"Yingce Xia","orcid":"https://orcid.org/0000-0001-9823-9033"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingce Xia","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102750692","display_name":"Lijun Wu","orcid":"https://orcid.org/0000-0002-3530-590X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Wu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088666942","display_name":"Shufang Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shufang Xie","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020025718","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0002-9095-0776"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101884287","display_name":"Tie\u2010Yan Liu","orcid":"https://orcid.org/0000-0002-0476-8020"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tie-Yan Liu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5028284977"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":33.0398,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.9981385,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2626","last_page":"2636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9955999851226807,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9707000255584717,"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":0.6919465661048889},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6473994851112366},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.602074146270752},{"id":"https://openalex.org/keywords/atom","display_name":"Atom (system on chip)","score":0.5146020650863647},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5105589628219604},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4469706118106842},{"id":"https://openalex.org/keywords/molecular-graph","display_name":"Molecular graph","score":0.4164876639842987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40422356128692627}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6919465661048889},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6473994851112366},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.602074146270752},{"id":"https://openalex.org/C58312451","wikidata":"https://www.wikidata.org/wiki/Q4817200","display_name":"Atom (system on chip)","level":2,"score":0.5146020650863647},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5105589628219604},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4469706118106842},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.4164876639842987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40422356128692627},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539368","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2262853887","display_name":null,"funder_award_id":"61836011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4052041763","display_name":null,"funder_award_id":"2018497","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W2084651007","https://openalex.org/W2200017991","https://openalex.org/W2773405722","https://openalex.org/W2948990653","https://openalex.org/W2962876364","https://openalex.org/W2973114758","https://openalex.org/W3007309629","https://openalex.org/W3012107310","https://openalex.org/W3081528324","https://openalex.org/W3095883070","https://openalex.org/W3112417367","https://openalex.org/W3127113723","https://openalex.org/W3129576130","https://openalex.org/W3166272013","https://openalex.org/W3189770638","https://openalex.org/W3199618438","https://openalex.org/W6600997697","https://openalex.org/W6602311867","https://openalex.org/W6790978476"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W4404792677","https://openalex.org/W2000990799","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W3114989040","https://openalex.org/W3123468858","https://openalex.org/W2013842271","https://openalex.org/W2808877228"],"abstract_inverted_index":{"Molecular":[0],"representation":[1,73],"learning":[2,74],"has":[3],"attracted":[4],"much":[5],"attention":[6],"recently.":[7],"A":[8],"molecule":[9],"can":[10,23],"be":[11,25],"viewed":[12],"as":[13],"a":[14,28,57,71,78],"2D":[15,44,80,119,122,142,149],"graph":[16,98,123],"with":[17,31,94,141,147],"nodes/atoms":[18],"connected":[19],"by":[20,27],"edges/bonds,":[21],"and":[22,45,69,81,86,91,112,121,145,150,161],"also":[24,172],"represented":[26],"3D":[29,46,82,114,127,151,178],"conformation":[30,115,179],"3-dimensional":[32],"coordinates":[33,85],"of":[34,109],"all":[35],"atoms.":[36],"We":[37,129],"note":[38],"that":[39],"most":[40],"previous":[41],"work":[42],"handles":[43],"information":[47,143],"separately,":[48],"while":[49],"jointly":[50],"leveraging":[51],"these":[52],"two":[53,177],"sources":[54],"may":[55],"foster":[56],"more":[58],"informative":[59],"representation.":[60],"In":[61],"this":[62,66],"work,":[63],"we":[64],"explore":[65],"appealing":[67],"idea":[68],"propose":[70],"new":[72],"method":[75,132,154,171],"based":[76],"on":[77,105,118,126,133,158,165,176],"unified":[79],"pre-training.":[83],"Atom":[84],"interatomic":[87],"distances":[88],"are":[89],"encoded":[90],"then":[92],"fused":[93],"atomic":[95],"representations":[96],"through":[97],"neural":[99],"networks.":[100],"The":[101],"model":[102],"is":[103,168],"pre-trained":[104],"three":[106],"tasks:":[107,139],"reconstruction":[108],"masked":[110],"atoms":[111],"coordinates,":[113],"generation":[116,124,180],"conditioned":[117,125],"graph,":[120],"conformation.":[128],"evaluate":[130],"our":[131],"11":[134],"downstream":[135],"molecular":[136],"property":[137],"prediction":[138],"7":[140],"only":[144],"4":[146],"both":[148],"information.":[152],"Our":[153,170],"achieves":[155,173],"state-of-the-art":[156],"results":[157],"10":[159],"tasks,":[160],"the":[162],"average":[163],"improvement":[164,175],"2D-only":[166],"tasks":[167],"8.3%.":[169],"significant":[174],"tasks.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":15}],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}