{"id":"https://openalex.org/W7155216055","doi":"https://doi.org/10.1186/s12859-026-06457-5","title":"Protein and ligand novelty in drug\u2013target interaction prediction: a dual-encoder fusion strategy for more interpretable and generalizable modeling","display_name":"Protein and ligand novelty in drug\u2013target interaction prediction: a dual-encoder fusion strategy for more interpretable and generalizable modeling","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155216055","doi":"https://doi.org/10.1186/s12859-026-06457-5","pmid":"https://pubmed.ncbi.nlm.nih.gov/42021142"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-026-06457-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06457-5","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC 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/10.1186/s12859-026-06457-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082707477","display_name":"Lina Abou-Abbas","orcid":"https://orcid.org/0000-0001-7899-5704"},"institutions":[{"id":"https://openalex.org/I56306041","display_name":"Lebanese American University","ror":"https://ror.org/00hqkan37","country_code":"LB","type":"education","lineage":["https://openalex.org/I56306041"]}],"countries":["LB"],"is_corresponding":true,"raw_author_name":"Lina Abou-Abbas","raw_affiliation_strings":["Electrical and Computer Engineering Department, Lebanese American University, Byblos, Lebanon. lina.abouabbas@lau.edu.lb"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Lebanese American University, Byblos, Lebanon. lina.abouabbas@lau.edu.lb","institution_ids":["https://openalex.org/I56306041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077379625","display_name":"Khadidja Henni","orcid":"https://orcid.org/0000-0002-3019-3187"},"institutions":[{"id":"https://openalex.org/I200745827","display_name":"Universit\u00e9 T\u00c9LUQ","ror":"https://ror.org/007y6q934","country_code":"CA","type":"education","lineage":["https://openalex.org/I200745827","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Khadidja Henni","raw_affiliation_strings":["Science and Technology Department, Institute of Applied Artificial Intelligence, T\u00c9LUQ University, Montreal, Canada. khadidja.henni@teluq.ca"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology Department, Institute of Applied Artificial Intelligence, T\u00c9LUQ University, Montreal, Canada. khadidja.henni@teluq.ca","institution_ids":["https://openalex.org/I200745827"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077379625","https://openalex.org/A5082707477"],"corresponding_institution_ids":["https://openalex.org/I200745827","https://openalex.org/I56306041"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41600606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","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":0.9082000255584717,"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":0.9082000255584717,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.042100001126527786,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.01209999993443489,"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/novelty","display_name":"Novelty","score":0.7383000254631042},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5878999829292297},{"id":"https://openalex.org/keywords/fusion-protein","display_name":"Fusion protein","score":0.44909998774528503},{"id":"https://openalex.org/keywords/ligand","display_name":"Ligand (biochemistry)","score":0.4302999973297119},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.41110000014305115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3472000062465668}],"concepts":[{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.7383000254631042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6251999735832214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6037999987602234},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5878999829292297},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5045999884605408},{"id":"https://openalex.org/C123894998","wikidata":"https://www.wikidata.org/wiki/Q425158","display_name":"Fusion protein","level":4,"score":0.44909998774528503},{"id":"https://openalex.org/C116569031","wikidata":"https://www.wikidata.org/wiki/Q899107","display_name":"Ligand (biochemistry)","level":3,"score":0.4302999973297119},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.41110000014305115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27570000290870667},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.2680000066757202}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"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":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-026-06457-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06457-5","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:42021142","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42021142","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":"BMC bioinformatics","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:da87ef877e80459abd6a963c82f64c73","is_oa":true,"landing_page_url":"https://doaj.org/article/da87ef877e80459abd6a963c82f64c73","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13238130","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13238130/","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-026-06457-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06457-5","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.5988044142723083}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2035585923","https://openalex.org/W2086286404","https://openalex.org/W2096864392","https://openalex.org/W2204695023","https://openalex.org/W2558999090","https://openalex.org/W2767891136","https://openalex.org/W2785947426","https://openalex.org/W2889321024","https://openalex.org/W2955986556","https://openalex.org/W3018980093","https://openalex.org/W3084084616","https://openalex.org/W3094492244","https://openalex.org/W3096561213","https://openalex.org/W3198879735","https://openalex.org/W4205167309","https://openalex.org/W4206334877","https://openalex.org/W4220703734","https://openalex.org/W4224981527","https://openalex.org/W4280572290","https://openalex.org/W4296890754","https://openalex.org/W4323338513","https://openalex.org/W4378190790","https://openalex.org/W4382502211","https://openalex.org/W4384277067","https://openalex.org/W4386898749","https://openalex.org/W4388838206","https://openalex.org/W4391827434","https://openalex.org/W4392454059","https://openalex.org/W4393431775","https://openalex.org/W4394582099","https://openalex.org/W4394754058","https://openalex.org/W4399662868","https://openalex.org/W4400112692","https://openalex.org/W4402131052","https://openalex.org/W4403118713","https://openalex.org/W4406521396","https://openalex.org/W4407956434","https://openalex.org/W4411925407","https://openalex.org/W4411961335","https://openalex.org/W4412100295","https://openalex.org/W4412404956","https://openalex.org/W4413100503","https://openalex.org/W4414222967","https://openalex.org/W7118177424","https://openalex.org/W7118265010"],"related_works":[],"abstract_inverted_index":{"Predicting":[0],"drug-target":[1],"interactions":[2],"(DTIs)":[3],"is":[4,21,125],"a":[5,60,82,88,107,241],"fundamental":[6],"task":[7],"in":[8,53,201],"computational":[9],"drug":[10,28],"discovery,":[11],"where":[12],"reliable":[13,245],"generalization":[14,173],"to":[15,44,128,134],"novel":[16],"compounds":[17],"and":[18,27,48,66,87,116,156,182,210,219,235,246],"protein":[19,49,75,114,167],"targets":[20],"essential":[22],"for":[23,64],"practical":[24,242],"virtual":[25],"screening":[26],"repurposing.":[29],"However,":[30],"most":[31,193],"deep":[32],"learning":[33],"models":[34],"are":[35,96],"evaluated":[36],"using":[37],"random":[38],"or":[39],"single-split":[40],"settings":[41,158],"that":[42,110,144,237],"fail":[43],"reflect":[45],"the":[46,139,171,176,188,192,202,208,230],"ligand":[47,80,112,145],"novelty":[50,146,168],"conditions":[51],"encountered":[52],"real-world":[54],"discovery":[55],"pipelines.":[56],"This":[57],"work":[58],"proposes":[59],"dual-encoder":[61],"fusion":[62,189,239],"framework":[63],"robust":[65],"interpretable":[67,247],"DTI":[68,248],"prediction.":[69,249],"The":[70],"model":[71,190],"combines":[72],"pretrained":[73],"ESM":[74],"embeddings":[76],"with":[77,151],"two":[78],"complementary":[79],"representations:":[81],"ChemBERTa-based":[83],"molecular":[84,131],"language":[85],"encoder":[86],"graph-based":[89],"structural":[90],"encoder.":[91],"Predictions":[92],"from":[93],"both":[94],"branches":[95],"integrated":[97],"through":[98],"decision-level":[99,238],"fusion.":[100],"To":[101],"rigorously":[102],"evaluate":[103],"generalization,":[104],"we":[105],"adopt":[106],"novelty-aware":[108,233],"protocol":[109],"isolates":[111],"novelty,":[113,115],"their":[117],"joint":[118],"occurrence.":[119],"A":[120],"ligand-centered,":[121],"gradientbased":[122],"interpretability":[123],"analysis":[124],"also":[126],"employed":[127],"examine":[129],"how":[130],"substructures":[132],"contribute":[133],"binding":[135],"predictions.":[136],"Experiments":[137],"on":[138,207],"largescale":[140],"BindingDB":[141],"dataset":[142],"show":[143,236],"induces":[147],"minimal":[148],"performance":[149,178],"degradation,":[150],"strong":[152],"results":[153,228],"under":[154,180],"warm":[155,203],"cold-drug":[157],"(F1":[159],"=":[160,163],"0.84-0.87;":[161],"AUC":[162,198,216],"0.87-0.89).":[164],"In":[165],"contrast,":[166],"emerges":[169],"as":[170],"dominant":[172],"bottleneck,":[174],"producing":[175],"largest":[177],"drops":[179],"cold-protein":[181],"double-cold":[183],"conditions.":[184],"Across":[185],"all":[186],"scenarios,":[187],"exhibits":[191],"stable":[194],"behavior,":[195],"achieving":[196],"an":[197],"of":[199,232],"0.90":[200],"setting.":[204],"External":[205],"validation":[206],"Davis":[209],"KIBA":[211],"datasets":[212],"further":[213],"demonstrates":[214],"consistent":[215],"values":[217],"(0.60-0.64)":[218],"high":[220],"recall":[221],"despite":[222],"substantial":[223],"biochemical":[224],"domain":[225],"shift.":[226],"These":[227],"highlight":[229],"importance":[231],"evaluation":[234],"provides":[240],"pathway":[243],"toward":[244]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-04-23T00:00:00"}