{"id":"https://openalex.org/W4406271402","doi":"https://doi.org/10.1109/bibm62325.2024.10821952","title":"Molecular Graph Representation Learning Integrating Large Language Models with Domain-specific Small Models","display_name":"Molecular Graph Representation Learning Integrating Large Language Models with Domain-specific Small Models","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406271402","doi":"https://doi.org/10.1109/bibm62325.2024.10821952"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10821952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10821952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5100425871","display_name":"Tianyu Zhang","orcid":"https://orcid.org/0000-0003-4281-7417"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyu Zhang","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057157471","display_name":"Yuxiang Ren","orcid":"https://orcid.org/0000-0001-8829-3984"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Ren","raw_affiliation_strings":["Huawei Technologies,China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111208283","display_name":"Chengbin Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengbin Hou","raw_affiliation_strings":["Fuyao University of Science and Technology,School of Computing and Artificial Intelligence,Fuzhou,China"],"affiliations":[{"raw_affiliation_string":"Fuyao University of Science and Technology,School of Computing and Artificial Intelligence,Fuzhou,China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074195858","display_name":"Hairong Lv","orcid":"https://orcid.org/0000-0003-1568-6861"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hairong Lv","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081242795","display_name":"Xuegong Zhang","orcid":"https://orcid.org/0000-0002-9684-5643"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuegong Zhang","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100425871"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3693,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59323273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2928","last_page":"2935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9824000000953674,"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":0.9824000000953674,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9550999999046326,"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"}},{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9401999711990356,"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":0.7442442774772644},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5161808133125305},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5140958428382874},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.44420120120048523},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4349616467952728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42883968353271484},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42294496297836304},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14062634110450745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442442774772644},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5161808133125305},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5140958428382874},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.44420120120048523},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4349616467952728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42883968353271484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42294496297836304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14062634110450745},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10821952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10821952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2594183968","https://openalex.org/W2970641574","https://openalex.org/W3116202926","https://openalex.org/W3128497535","https://openalex.org/W3157265962","https://openalex.org/W3215452784","https://openalex.org/W4214868967","https://openalex.org/W4282017563","https://openalex.org/W4381679608","https://openalex.org/W4391035336","https://openalex.org/W4393147105","https://openalex.org/W4402915290","https://openalex.org/W4404534210","https://openalex.org/W6754929296","https://openalex.org/W6772452955","https://openalex.org/W6784614190","https://openalex.org/W6791353385","https://openalex.org/W6803136014","https://openalex.org/W6803921755","https://openalex.org/W6839226590","https://openalex.org/W6841143912"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W2055929693","https://openalex.org/W4324271173","https://openalex.org/W1967645776","https://openalex.org/W2352227742","https://openalex.org/W4390679071","https://openalex.org/W3006966347"],"abstract_inverted_index":{"Molecular":[0,142],"property":[1,136],"prediction":[2],"is":[3,58],"a":[4,140,160,197],"crucial":[5],"foundation":[6],"for":[7,123,191],"drug":[8],"discovery.":[9],"In":[10],"recent":[11],"years,":[12],"pre-trained":[13],"deep":[14],"learning":[15,145],"models":[16,151,155],"have":[17,36,67],"been":[18],"widely":[19],"applied":[20],"to":[21,108,168,185,201,213],"this":[22],"task.":[23],"Some":[24],"approaches":[25,133],"that":[26,147],"incorporate":[27],"prior":[28],"biological":[29],"domain":[30,55,97],"knowledge":[31,56,98,121,171],"into":[32],"the":[33,118,129,170,176,215,223,226],"pre-training":[34,216],"framework":[35,146],"achieved":[37],"impressive":[38],"results.":[39],"However,":[40,106],"these":[41],"methods":[42],"heavily":[43],"rely":[44],"on":[45],"biochemical":[46],"experts,":[47],"and":[48,50,61,73,83,99,113,152,181,208],"retrieving":[49],"summarizing":[51],"vast":[52],"amounts":[53],"of":[54,120,131,178,217,225],"literature":[57],"both":[59,132],"time-consuming":[60],"expensive.":[62],"Large":[63,149],"Language":[64],"Models":[65,93],"(LLMs)":[66],"demonstrated":[68],"remarkable":[69],"performance":[70],"in":[71,86,134],"understanding":[72],"efficiently":[74],"providing":[75],"general":[76],"knowledge.":[77,89],"Nevertheless,":[78],"they":[79,116],"occasionally":[80],"exhibit":[81],"hallucinations":[82],"lack":[84,117],"precision":[85],"generating":[87],"domain-specific":[88,179],"Conversely,":[90],"Domain-specific":[91,153],"Small":[92],"(DSMs)":[94],"possess":[95],"rich":[96],"can":[100],"accurately":[101],"calculate":[102],"molecular":[103,135,192,206,218],"domain-related":[104],"metrics.":[105],"due":[107],"their":[109,209],"limited":[110],"model":[111],"size":[112],"singular":[114],"functionality,":[115],"breadth":[119],"necessary":[122],"comprehensive":[124],"representation":[125,144],"learning.":[126],"To":[127],"leverage":[128],"advantages":[130],"prediction,":[137],"we":[138,158,195],"propose":[139],"novel":[141],"Graph":[143],"integrates":[148],"language":[150],"small":[154],"(MolGraph-LarDo).":[156],"Technically,":[157],"design":[159],"two-stage":[161],"prompt":[162],"strategy":[163],"where":[164],"DSMs":[165],"are":[166],"introduced":[167],"calibrate":[169],"provided":[172],"by":[173],"LLMs,":[174],"enhancing":[175],"accuracy":[177],"information":[180],"thus":[182],"enabling":[183],"LLMs":[184],"generate":[186],"more":[187],"precise":[188],"textual":[189],"descriptions":[190],"samples.":[193],"Subsequently,":[194],"employ":[196],"multi-modal":[198],"alignment":[199],"method":[200],"coordinate":[202],"various":[203],"modalities,":[204],"including":[205],"graphs":[207],"corresponding":[210],"descriptive":[211],"texts,":[212],"guide":[214],"representations.":[219],"Extensive":[220],"experiments":[221],"demonstrate":[222],"effectiveness":[224],"proposed":[227],"method.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}