{"id":"https://openalex.org/W7152551975","doi":"https://doi.org/10.1093/bioinformatics/btag164","title":"NumMolFormer: an explicit functional group number-guided framework for structure-based drug design","display_name":"NumMolFormer: an explicit functional group number-guided framework for structure-based drug design","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7152551975","doi":"https://doi.org/10.1093/bioinformatics/btag164","pmid":"https://pubmed.ncbi.nlm.nih.gov/41955426"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag164","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag164","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btag164","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124165259","display_name":"Zhicun Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicun Zeng","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University , Changsha, Hunan 410083,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University , Changsha, Hunan 410083,","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114948870","display_name":"Yifan Wu","orcid":"https://orcid.org/0009-0005-3029-2408"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Wu","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University , Changsha, Hunan 410083,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University , Changsha, Hunan 410083,","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081430592","display_name":"Zhangli Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangli Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University , Changsha, Hunan 410083,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University , Changsha, Hunan 410083,","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133299494","display_name":"Min Li","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Li","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University , Changsha, Hunan 410083,"],"raw_orcid":"https://orcid.org/0000-0002-0188-1394","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University , Changsha, Hunan 410083,","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5133299494"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45824314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"4","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":0.8519999980926514,"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":0.8519999980926514,"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":0.052000001072883606,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.027300000190734863,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6492999792098999},{"id":"https://openalex.org/keywords/functional-group","display_name":"Functional group","score":0.5325999855995178},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4404999911785126},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4221999943256378},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.4162999987602234},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40299999713897705},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3846000134944916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6509000062942505},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6492999792098999},{"id":"https://openalex.org/C2777332933","wikidata":"https://www.wikidata.org/wiki/Q170409","display_name":"Functional group","level":3,"score":0.5325999855995178},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4205000102519989},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40299999713897705},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3693000078201294},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3474999964237213},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C21951064","wikidata":"https://www.wikidata.org/wiki/Q899212","display_name":"Combinatorial chemistry","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C2780035454","wikidata":"https://www.wikidata.org/wiki/Q8386","display_name":"Drug","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25429999828338623},{"id":"https://openalex.org/C42383842","wikidata":"https://www.wikidata.org/wiki/Q193076","display_name":"Functional programming","level":2,"score":0.2531999945640564}],"mesh":[{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btag164","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag164","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41955426","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41955426","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13107960","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13107960/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag164","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag164","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2614071909","display_name":"\u591a\u7ec4\u5b66\u6570\u636e\u9a71\u52a8\u7684\u836f\u7269\u667a\u80fd\u5316\u53d1\u73b0\u65b9\u6cd5\u7814\u7a76","funder_award_id":"2025JJ30025","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G8663586063","display_name":null,"funder_award_id":"62225209","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"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1653739410","https://openalex.org/W2034549041","https://openalex.org/W2047710091","https://openalex.org/W2153246785","https://openalex.org/W2160592148","https://openalex.org/W2176516200","https://openalex.org/W2236963384","https://openalex.org/W2587598315","https://openalex.org/W2604527271","https://openalex.org/W2767812299","https://openalex.org/W3042595256","https://openalex.org/W3047285698","https://openalex.org/W3082411326","https://openalex.org/W4248107770","https://openalex.org/W4387401786","https://openalex.org/W4408293149","https://openalex.org/W4414156393"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Rational":[1],"molecule":[2],"generation":[3],"that":[4,149],"balances":[5],"binding":[6,37,161],"affinity":[7],"with":[8,75,121,159],"favorable":[9],"physicochemical":[10,32],"properties":[11],"remains":[12],"a":[13,26,58,70,76,81,114,134],"formidable":[14],"challenge":[15],"in":[16,44,106],"structure-based":[17],"drug":[18],"design.":[19],"The":[20,146,174],"number":[21],"of":[22,103,117,136],"functional":[23,65,90,122,153],"groups":[24],"is":[25],"key":[27],"determinant,":[28],"as":[29],"over-functionalization":[30],"compromises":[31],"properties,":[33],"whereas":[34],"under-functionalization":[35],"reduces":[36],"affinity.":[38],"However,":[39],"current":[40],"methods":[41],"are":[42,179],"limited":[43],"their":[45],"capacity":[46],"to":[47,62,93,156,168],"incorporate":[48],"the":[49,100,131],"constraint.":[50],"RESULTS:":[51],"To":[52],"address":[53],"this,":[54],"we":[55,112],"present":[56],"NumMolFormer,":[57],"Transformer-based":[59],"framework":[60],"designed":[61],"explicitly":[63],"model":[64,132],"group":[66,91,123,154],"numbers.":[67],"NumMolFormer":[68,150],"adopts":[69],"dual-sequence":[71],"input":[72],"strategy,":[73],"integrated":[74],"numerical":[77,108],"embedding":[78],"module":[79],"and":[80,89,128,139,165,177],"dual-stream":[82],"differential":[83],"attention":[84],"mechanism,":[85],"allowing":[86],"molecular":[87,126],"structures":[88],"numbers":[92],"be":[94],"encoded":[95],"separately.":[96],"This":[97],"formulation":[98],"alleviates":[99],"inherent":[101],"limitations":[102],"standard":[104],"Transformer":[105],"handling":[107],"information.":[109],"In":[110],"addition,":[111],"construct":[113],"large-scale":[115],"dataset":[116],"18":[118],"million":[119],"molecules":[120,158],"annotations":[124],"for":[125],"pre-training,":[127],"further":[129],"fine-tune":[130],"using":[133],"combination":[135],"self-supervised":[137],"learning":[138,141],"reinforcement":[140],"under":[142],"protein":[143],"pocket":[144],"constraints.":[145],"results":[147],"demonstrate":[148],"effectively":[151],"leverages":[152],"information":[155],"generate":[157],"improved":[160],"affinity,":[162],"synthetic":[163],"accessibility,":[164],"drug-likeness":[166],"compared":[167],"baseline":[169],"methods.":[170],"AVAILABILITY":[171],"AND":[172],"IMPLEMENTATION:":[173],"source":[175],"code":[176],"datasets":[178],"available":[180],"at":[181],"http://www.github.com/zengzhicun/nummolformer.":[182]},"counts_by_year":[],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2026-04-10T00:00:00"}