{"id":"https://openalex.org/W4392208003","doi":"https://doi.org/10.26599/bdma.2024.9020003","title":"Exploring Fragment Adding Strategies to Enhance Molecule Pretraining in AI-Driven Drug Discovery","display_name":"Exploring Fragment Adding Strategies to Enhance Molecule Pretraining in AI-Driven Drug Discovery","publication_year":2024,"publication_date":"2024-02-27","ids":{"openalex":"https://openalex.org/W4392208003","doi":"https://doi.org/10.26599/bdma.2024.9020003"},"language":"en","primary_location":{"id":"doi:10.26599/bdma.2024.9020003","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2024.9020003","pdf_url":"https://ieeexplore.ieee.org/ielx7/8254253/10452165/10452166.pdf","source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ieeexplore.ieee.org/ielx7/8254253/10452165/10452166.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073704794","display_name":"Zhaoxu Meng","orcid":"https://orcid.org/0000-0003-0686-0231"},"institutions":[{"id":"https://openalex.org/I146773158","display_name":"Qingdao Agricultural University","ror":"https://ror.org/051qwcj72","country_code":"CN","type":"education","lineage":["https://openalex.org/I146773158"]},{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaoxu Meng","raw_affiliation_strings":["School of Life Sciences, Shandong University,Qingdao,China,266237","School of Life Sciences, Shandong University, Qingdao 266237, China"],"affiliations":[{"raw_affiliation_string":"School of Life Sciences, Shandong University,Qingdao,China,266237","institution_ids":["https://openalex.org/I154099455","https://openalex.org/I146773158"]},{"raw_affiliation_string":"School of Life Sciences, Shandong University, Qingdao 266237, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101442772","display_name":"Cheng Chen","orcid":"https://orcid.org/0000-0003-3062-9048"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Chen","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University,Qingdao,China,266237","School of Computer Science and Technology, Shandong University, Qingdao 266237, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University,Qingdao,China,266237","institution_ids":["https://openalex.org/I80143920"]},{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao 266237, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043732387","display_name":"Xuan Zhang","orcid":"https://orcid.org/0000-0001-8214-7265"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University,Qingdao,China,266237","School of Computer Science and Technology, Shandong University, Qingdao 266237, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University,Qingdao,China,266237","institution_ids":["https://openalex.org/I80143920"]},{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao 266237, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434561","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0003-0699-3501"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]},{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["Shandong University,State Key Laboratory of Microbiology Technology,Qingdao,China,266237","State Key Laboratory of Microbiology Technology, Shandong University, Qingdao 266237, China"],"affiliations":[{"raw_affiliation_string":"Shandong University,State Key Laboratory of Microbiology Technology,Qingdao,China,266237","institution_ids":["https://openalex.org/I80143920"]},{"raw_affiliation_string":"State Key Laboratory of Microbiology Technology, Shandong University, Qingdao 266237, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101906222","display_name":"Xuefeng Cui","orcid":"https://orcid.org/0000-0002-8816-3482"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Cui","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University,Qingdao,China,266237","School of Computer Science and Technology, Shandong University, Qingdao 266237, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University,Qingdao,China,266237","institution_ids":["https://openalex.org/I80143920"]},{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao 266237, China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073704794"],"corresponding_institution_ids":["https://openalex.org/I146773158","https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":4.5254,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.95071276,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"7","issue":"3","first_page":"565","last_page":"576"},"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":0.9819999933242798,"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/T11407","display_name":"Innovative Microfluidic and Catalytic Techniques Innovation","score":0.935699999332428,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/fragment","display_name":"Fragment (logic)","score":0.8463184833526611},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.6908838152885437},{"id":"https://openalex.org/keywords/drug","display_name":"Drug","score":0.5848455429077148},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4166716933250427},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.3856419324874878},{"id":"https://openalex.org/keywords/nanotechnology","display_name":"Nanotechnology","score":0.33758074045181274},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3039686679840088},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.2302265763282776},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.2180168628692627},{"id":"https://openalex.org/keywords/pharmacology","display_name":"Pharmacology","score":0.20290827751159668},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15812164545059204},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.1206301748752594},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0664815902709961}],"concepts":[{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.8463184833526611},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.6908838152885437},{"id":"https://openalex.org/C2780035454","wikidata":"https://www.wikidata.org/wiki/Q8386","display_name":"Drug","level":2,"score":0.5848455429077148},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4166716933250427},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3856419324874878},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.33758074045181274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3039686679840088},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.2302265763282776},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2180168628692627},{"id":"https://openalex.org/C98274493","wikidata":"https://www.wikidata.org/wiki/Q128406","display_name":"Pharmacology","level":1,"score":0.20290827751159668},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15812164545059204},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.1206301748752594},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0664815902709961}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26599/bdma.2024.9020003","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2024.9020003","pdf_url":"https://ieeexplore.ieee.org/ielx7/8254253/10452165/10452166.pdf","source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:75dbf0c867db4ba6bab24df45ec47c91","is_oa":true,"landing_page_url":"https://doaj.org/article/75dbf0c867db4ba6bab24df45ec47c91","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data Mining and Analytics, Vol 7, Iss 3, Pp 565-576 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.26599/bdma.2024.9020003","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2024.9020003","pdf_url":"https://ieeexplore.ieee.org/ielx7/8254253/10452165/10452166.pdf","source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G43230537","display_name":null,"funder_award_id":"2019YFA0905700,2021YFC2101500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6051875761","display_name":null,"funder_award_id":"2019YFA0905700","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7587655767","display_name":null,"funder_award_id":"62072283","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392208003.pdf","grobid_xml":"https://content.openalex.org/works/W4392208003.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1989297989","https://openalex.org/W2022476850","https://openalex.org/W2134967712","https://openalex.org/W2157444450","https://openalex.org/W2169678694","https://openalex.org/W2461470610","https://openalex.org/W2461620095","https://openalex.org/W2594183968","https://openalex.org/W2962711740","https://openalex.org/W2998702515","https://openalex.org/W3005552578","https://openalex.org/W3008588639","https://openalex.org/W3035581796","https://openalex.org/W3042826782","https://openalex.org/W3087326809","https://openalex.org/W3160838384","https://openalex.org/W3187980261","https://openalex.org/W3207924272","https://openalex.org/W3209017840","https://openalex.org/W3215142809","https://openalex.org/W4200233821","https://openalex.org/W4205948945","https://openalex.org/W4206367183","https://openalex.org/W4206488367","https://openalex.org/W4210617107","https://openalex.org/W4213250811","https://openalex.org/W4214868967","https://openalex.org/W4283689358","https://openalex.org/W4294558607","https://openalex.org/W4313525610","https://openalex.org/W4313527263","https://openalex.org/W6683161245","https://openalex.org/W6690815549","https://openalex.org/W6738964360","https://openalex.org/W6754929296","https://openalex.org/W6755573351","https://openalex.org/W6772452955","https://openalex.org/W6784614190"],"related_works":["https://openalex.org/W1973480752","https://openalex.org/W2805502594","https://openalex.org/W3132641048","https://openalex.org/W4403688099","https://openalex.org/W2090936831","https://openalex.org/W2013003323","https://openalex.org/W1981076832","https://openalex.org/W2024773645","https://openalex.org/W2001717001","https://openalex.org/W2043147644"],"abstract_inverted_index":{"The":[0],"effectiveness":[1],"of":[2,38,67,74,117],"AI-driven":[3],"drug":[4,139],"discovery":[5,140],"can":[6,128],"be":[7,129],"enhanced":[8],"by":[9],"pretraining":[10,20,27],"on":[11,97,103],"small":[12],"molecules.":[13,39,120],"However,":[14],"the":[15,30,35,58,65,72,114,118,125,138],"conventional":[16],"masked":[17],"language":[18],"model":[19],"techniques":[21],"are":[22],"not":[23],"suitable":[24],"for":[25,64,82],"molecule":[26],"due":[28],"to":[29,57,135],"limited":[31],"vocabulary":[32],"size":[33],"and":[34,71],"non-sequential":[36],"structure":[37],"To":[40],"overcome":[41],"these":[42],"challenges,":[43],"we":[44,88,122],"propose":[45],"FragAdd,":[46],"a":[47,52,75,91,104,110],"strategy":[48,127],"that":[49,95,124],"involves":[50],"adding":[51],"chemically":[53],"implausible":[54],"molecular":[55],"fragment":[56],"input":[59],"molecule.":[60],"This":[61],"approach":[62],"allows":[63],"incorporation":[66],"rich":[68],"local":[69],"information":[70],"generation":[73],"high-quality":[76],"graph":[77],"representation,":[78],"which":[79],"is":[80],"advantageous":[81],"tasks":[83],"like":[84],"virtual":[85,92],"screening.":[86],"Consequently,":[87],"have":[89],"developed":[90],"screening":[93],"protocol":[94],"focuses":[96],"identifying":[98],"estrogen":[99],"receptor":[100],"alpha":[101],"binders":[102],"nucleus":[105],"receptor.":[106],"Our":[107],"results":[108],"demonstrate":[109,123],"significant":[111],"improvement":[112],"in":[113],"binding":[115],"capacity":[116],"retrieved":[119],"Additionally,":[121],"FragAdd":[126],"combined":[130],"with":[131],"other":[132],"self-supervised":[133],"methods":[134],"further":[136],"expedite":[137],"process.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
