{"id":"https://openalex.org/W7203786385","doi":"https://doi.org/10.1021/acs.jcim.6c01188","title":"MMU-DPI: Enhancing Generalization in Drug\u2013Protein Interaction Prediction through Multimodal Learning and a Label Mix Strategy","display_name":"MMU-DPI: Enhancing Generalization in Drug\u2013Protein Interaction Prediction through Multimodal Learning and a Label Mix Strategy","publication_year":2026,"publication_date":"2026-08-19","ids":{"openalex":"https://openalex.org/W7203786385","doi":"https://doi.org/10.1021/acs.jcim.6c01188","pmid":"https://pubmed.ncbi.nlm.nih.gov/42734516"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.6c01188","doi":"https://doi.org/10.1021/acs.jcim.6c01188","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.6c01188","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W7203786385"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref","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/A5029170796","display_name":"Jiahao Wei","orcid":"https://orcid.org/0000-0002-5127-5739","observed_orcids":["https://orcid.org/0000-0002-5127-5739","https://orcid.org/0009-0007-8693-6086"]},"institutions":[{"id":"https://openalex.org/I154893126","display_name":"Guizhou Normal University","ror":"https://ror.org/02x1pa065","country_code":"CN","type":"education","lineage":["https://openalex.org/I154893126"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Wei","raw_affiliation_strings":["Guizhou Normal University , , ,"],"raw_orcid":"https://orcid.org/0009-0007-8693-6086","affiliations":[{"raw_affiliation_string":"Guizhou Normal University , , ,","institution_ids":["https://openalex.org/I154893126"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102725953","display_name":"Tie Shen","orcid":"https://orcid.org/0000-0001-7313-3494","observed_orcids":["https://orcid.org/0000-0001-7313-3494"]},"institutions":[{"id":"https://openalex.org/I154893126","display_name":"Guizhou Normal University","ror":"https://ror.org/02x1pa065","country_code":"CN","type":"education","lineage":["https://openalex.org/I154893126"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tie Shen","raw_affiliation_strings":["Guizhou Normal University , , ,"],"raw_orcid":"https://orcid.org/0000-0001-7313-3494","affiliations":[{"raw_affiliation_string":"Guizhou Normal University , , ,","institution_ids":["https://openalex.org/I154893126"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102725953"],"corresponding_institution_ids":["https://openalex.org/I154893126"],"apc_list":{"value":4500,"currency":"USD","value_usd":4500},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"66","issue":"17","first_page":"10548","last_page":"10563"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.002899999963119626,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.000699999975040555,"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/drug-protein-interaction-prediction","display_name":"drug-protein interaction prediction","score":0.9959999918937683},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"multimodal learning","score":0.9399999976158142},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.550000011920929},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"drug discovery","score":0.6079999804496765},{"id":"https://openalex.org/keywords/message-passing-neural-networks","display_name":"message passing neural networks","score":0.8199999928474426},{"id":"https://openalex.org/keywords/graph-attention-networks","display_name":"graph attention networks","score":0.9150000214576721},{"id":"https://openalex.org/keywords/amino-acid-sequence-features","display_name":"amino acid sequence features","score":0.8169999718666077},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.5720000267028809}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455999851226807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6464999914169312},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6424000263214111},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.4860000014305115},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4611999988555908},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C55105296","wikidata":"https://www.wikidata.org/wiki/Q841382","display_name":"Interaction network","level":3,"score":0.3208000063896179},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2989108626","wikidata":"https://www.wikidata.org/wiki/Q904407","display_name":"Drug target","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.25029999017715454}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098422","descriptor_name":"Graph Neural Networks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004364","descriptor_name":"Pharmaceutical Preparations","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004364","descriptor_name":"Pharmaceutical Preparations","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.6c01188","doi":"https://doi.org/10.1021/acs.jcim.6c01188","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.6c01188","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:42734516","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42734516","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,"listed_in":[],"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":"Journal of chemical information and modeling","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.5683000087738037}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1500036797","https://openalex.org/W1968319881","https://openalex.org/W1971387816","https://openalex.org/W1976526581","https://openalex.org/W2018408116","https://openalex.org/W2035585923","https://openalex.org/W2070789802","https://openalex.org/W2086286404","https://openalex.org/W2109991441","https://openalex.org/W2138512826","https://openalex.org/W2162011385","https://openalex.org/W2204695023","https://openalex.org/W2336040088","https://openalex.org/W2346950316","https://openalex.org/W2583907533","https://openalex.org/W2753953057","https://openalex.org/W2767891136","https://openalex.org/W2785947426","https://openalex.org/W2899292521","https://openalex.org/W2997680655","https://openalex.org/W3000043291","https://openalex.org/W3000503908","https://openalex.org/W3018980093","https://openalex.org/W3096561213","https://openalex.org/W3136918052","https://openalex.org/W3177318507","https://openalex.org/W4205510792","https://openalex.org/W4214873089","https://openalex.org/W4283576974","https://openalex.org/W4283810898","https://openalex.org/W4318391592","https://openalex.org/W4323653718","https://openalex.org/W4385252548","https://openalex.org/W4388080288","https://openalex.org/W4388615774","https://openalex.org/W4392693790","https://openalex.org/W4393158946","https://openalex.org/W4401532898","https://openalex.org/W4402543465","https://openalex.org/W4403210286","https://openalex.org/W4404572688","https://openalex.org/W4406885099","https://openalex.org/W4409364444","https://openalex.org/W4413041804","https://openalex.org/W4415377956","https://openalex.org/W4416459788"],"related_works":["https://openalex.org/W4367297900","https://openalex.org/W4214530112","https://openalex.org/W7128439326","https://openalex.org/W4206617747","https://openalex.org/W4404572688","https://openalex.org/W4394997844","https://openalex.org/W7131876938","https://openalex.org/W7208208488","https://openalex.org/W7165547030"],"abstract_inverted_index":{"Accurate":[0],"prediction":[1,181,200],"of":[2,17,25,49,208],"drug-protein":[3,184],"interactions":[4,20],"(DPIs)":[5],"is":[6,52],"crucial":[7],"for":[8,30,182,226],"accelerating":[9],"the":[10,15,23,43,67,72,179,206],"drug":[11,122,227],"discovery":[12],"process.":[13],"However,":[14],"scarcity":[16],"experimentally":[18],"validated":[19],"can":[21,219],"limit":[22],"learning":[24],"transferable":[26],"interaction":[27,150],"patterns,":[28],"particularly":[29],"previously":[31],"unseen":[32],"drugs":[33,165],"and":[34,82,88,97,137,152,166],"proteins.":[35,167],"To":[36,94],"address":[37],"this":[38,50],"fundamental":[39],"challenge,":[40],"we":[41],"propose":[42],"MMU-DPI":[44,101,195,209,218],"framework.":[45],"A":[46,168],"key":[47,135],"component":[48],"framework":[51],"a":[53,103,111,128,148,154,222],"Label":[54],"Mix":[55],"strategy":[56,77],"tailored":[57],"to":[58,117,133,159,177,210],"multimodal":[59,99,104],"DPI":[60,199],"prediction,":[61],"which":[62],"performs":[63],"interpolation":[64],"only":[65],"in":[66],"label":[68],"space":[69],"while":[70],"keeping":[71],"input":[73],"modalities":[74],"unchanged.":[75],"This":[76],"provides":[78],"stochastic":[79],"soft-target":[80],"regularization":[81],"improves":[83],"generalization":[84],"performance":[85],"under":[86],"reduced-data":[87],"independent":[89],"external":[90],"Cold-both":[91],"evaluation":[92],"settings.":[93],"effectively":[95],"process":[96],"utilize":[98],"data,":[100],"adopts":[102],"dual-branch":[105],"architecture.":[106],"The":[107,144],"first":[108],"branch":[109,146,175],"uses":[110,127,153],"Message":[112],"Passing":[113],"Neural":[114,130],"Network":[115,131,157],"(MPNN)":[116],"extract":[118],"structured":[119],"representations":[120],"from":[121,140],"molecular":[123],"graphs.":[124],"It":[125],"also":[126],"Convolutional":[129],"(CNN)":[132],"capture":[134],"biological":[136],"functional":[138],"features":[139],"amino":[141],"acid":[142],"sequences.":[143],"second":[145],"constructs":[147],"heterogeneous":[149],"graph":[151],"Graph":[155],"Attention":[156],"(GAT)":[158],"learn":[160],"deep":[161],"contextual":[162],"relationships":[163],"between":[164],"learnable":[169],"global":[170],"fusion":[171],"weight":[172],"combines":[173],"complementary":[174],"logits":[176],"generate":[178],"final":[180],"each":[183],"pair.":[185],"Experimental":[186],"results":[187,215],"on":[188],"multiple":[189],"benchmark":[190],"data":[191],"sets":[192],"demonstrate":[193],"that":[194,217],"outperforms":[196],"several":[197],"state-of-the-art":[198],"methods.":[201],"Case":[202],"studies":[203],"further":[204],"support":[205],"ability":[207],"identify":[211],"potential":[212],"DPIs.":[213],"These":[214],"indicate":[216],"serve":[220],"as":[221],"useful":[223],"computational":[224],"tool":[225],"discovery.":[228]},"counts_by_year":[],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2026-08-20T00:00:00"}