{"id":"https://openalex.org/W7126027313","doi":"https://doi.org/10.1109/bibm66473.2025.11356840","title":"Beyond Exact Matches: Near-Hit Scoring for Protein Binding Site Prediction with Protein Language Models","display_name":"Beyond Exact Matches: Near-Hit Scoring for Protein Binding Site Prediction with Protein Language Models","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126027313","doi":"https://doi.org/10.1109/bibm66473.2025.11356840"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":null,"display_name":"Yana Podlesna","orcid":null},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Yana Podlesna","raw_affiliation_strings":["Department of Software Engineering Faculty of Mathematics and Physics Charles University Prague, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Engineering Faculty of Mathematics and Physics Charles University Prague, Czech Republic","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009850391","display_name":"V\u00edt \u0160krh\u00e1k","orcid":"https://orcid.org/0009-0007-0712-0661"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"V\u00edt \u0160krh\u00e1k","raw_affiliation_strings":["Charles University,Faculty of Mathematics and Physics,Department of Software Engineering,Prague,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University,Faculty of Mathematics and Physics,Department of Software Engineering,Prague,Czech Republic","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124150868","display_name":"David Hoksza","orcid":null},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"David Hoksza","raw_affiliation_strings":["Charles University,Faculty of Mathematics and Physics,Department of Software Engineering,Prague,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University,Faculty of Mathematics and Physics,Department of Software Engineering,Prague,Czech Republic","institution_ids":["https://openalex.org/I21250087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59766451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5486","last_page":"5492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.36500000953674316,"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"}},"topics":[{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.36500000953674316,"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":0.17430000007152557,"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":0.14339999854564667,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6230000257492065},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6039000153541565},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.48809999227523804},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4683000147342682},{"id":"https://openalex.org/keywords/protein\u2013protein-interaction","display_name":"Protein\u2013protein interaction","score":0.4009999930858612},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3449999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6295999884605408},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6230000257492065},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6039000153541565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5706999897956848},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37059998512268066},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C3019813237","wikidata":"https://www.wikidata.org/wiki/Q65089264","display_name":"Model validation","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7369677097","display_name":null,"funder_award_id":"23-07349S","funder_id":"https://openalex.org/F4320321006","funder_display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky"}],"funders":[{"id":"https://openalex.org/F4320321006","display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky","ror":"https://ror.org/01pv73b02"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1979914800","https://openalex.org/W1980969309","https://openalex.org/W2066143642","https://openalex.org/W2119470100","https://openalex.org/W2164088236","https://openalex.org/W2887981960","https://openalex.org/W2943495267","https://openalex.org/W2950200056","https://openalex.org/W2950954328","https://openalex.org/W2980789587","https://openalex.org/W3010338076","https://openalex.org/W3092737886","https://openalex.org/W3116801402","https://openalex.org/W3165603781","https://openalex.org/W3168436232","https://openalex.org/W3177828909","https://openalex.org/W3197082762","https://openalex.org/W4210842338","https://openalex.org/W4327550249","https://openalex.org/W4375858802","https://openalex.org/W4389076414","https://openalex.org/W4390971193","https://openalex.org/W4392792941","https://openalex.org/W4401966068","https://openalex.org/W4404226808","https://openalex.org/W4404447386","https://openalex.org/W4405531686","https://openalex.org/W4406440058","https://openalex.org/W4410444270"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"understanding":[1],"of":[2,58,138],"protein":[3,29],"behavior":[4],"and":[5,45,105,134],"its":[6],"role":[7],"in":[8,28],"particular":[9],"biological":[10],"processes":[11],"is":[12],"a":[13,74,95,132],"task":[14],"crucial":[15],"for":[16,110],"many":[17],"real-world":[18],"applications,":[19],"such":[20],"as":[21],"bioengineering":[22],"or":[23],"drug":[24],"design.":[25],"Recent":[26],"advances":[27],"informatics,":[30],"particularly":[31],"Protein":[32],"Language":[33],"Models":[34],"(PLMs),":[35],"have":[36],"transformed":[37],"the":[38,56,101,124],"field":[39],"by":[40,108],"capturing":[41],"rich":[42],"evolutionary,":[43],"physicochemical,":[44],"structural":[46],"features":[47],"into":[48],"high-dimensional":[49],"embeddings.":[50,87],"In":[51],"this":[52,117],"work,":[53],"we":[54,66,91],"investigate":[55],"application":[57],"PLMs":[59],"to":[60,85,113,119],"residue-level":[61],"ligand-binding":[62],"site":[63,140],"prediction.":[64],"Specifically,":[65],"show":[67],"that":[68,99,128],"standard":[69],"evaluation":[70,97],"metrics,":[71],"which":[72],"apply":[73],"hard":[75],"spatial":[76],"cutoff,":[77],"systematically":[78],"penalize":[79],"biologically":[80],"plausible":[81],"\u201cnear-miss\u201d":[82],"predictions":[83,107],"inherent":[84],"PLM":[86],"To":[88],"address":[89],"this,":[90],"introduce":[92],"near-hit":[93,129],"scoring,":[94],"distance-weighted":[96],"metric":[98],"softens":[100],"boundary":[102],"between":[103],"correct":[104],"incorrect":[106],"accounting":[109],"sequential":[111],"proximity":[112],"annotated":[114],"sites.":[115],"Applying":[116],"framework":[118],"state-of-the-art":[120],"PLM-based":[121],"predictors":[122],"on":[123],"LIGYSIS":[125],"benchmark":[126],"demonstrates":[127],"scoring":[130],"provides":[131],"fairer":[133],"more":[135],"informative":[136],"assessment":[137],"binding":[139],"prediction":[141],"performance.":[142]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-30T00:00:00"}