{"id":"https://openalex.org/W7163204050","doi":"https://doi.org/10.64898/2026.05.29.728739","title":"Learning Protein-Protein Interaction Interfaces from Multimodal Representations","display_name":"Learning Protein-Protein Interaction Interfaces from Multimodal Representations","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163204050","doi":"https://doi.org/10.64898/2026.05.29.728739"},"language":"en","primary_location":{"id":"doi:10.64898/2026.05.29.728739","doi":"https://doi.org/10.64898/2026.05.29.728739","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.05.29.728739","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.64898/2026.05.29.728739","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098814645","display_name":"Yuri Gardinazzi","orcid":"https://orcid.org/0009-0003-8602-3552","observed_orcids":["https://orcid.org/0009-0003-8602-3552"]},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]},{"id":"https://openalex.org/I2801626668","display_name":"AREA Science Park","ror":"https://ror.org/01dt7qh15","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2801626668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Yuri Gardinazzi","raw_affiliation_strings":["Department of Mathematics, Informatics and Geosciences, University of Trieste, Trieste, Italy","Research and Technology Institute, Area Science Park, Trieste, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Informatics and Geosciences, University of Trieste, Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]},{"raw_affiliation_string":"Research and Technology Institute, Area Science Park, Trieste, Italy","institution_ids":["https://openalex.org/I2801626668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078890613","display_name":"Edith Natalia Villegas Garcia","orcid":"https://orcid.org/0000-0002-7338-2068","observed_orcids":["https://orcid.org/0000-0002-7338-2068"]},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]},{"id":"https://openalex.org/I2801626668","display_name":"AREA Science Park","ror":"https://ror.org/01dt7qh15","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2801626668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Edith Natalia Villegas Garcia","raw_affiliation_strings":["Department of Mathematics, Informatics and Geosciences, University of Trieste, Trieste, Italy","Research and Technology Institute, Area Science Park, Trieste, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Informatics and Geosciences, University of Trieste, Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]},{"raw_affiliation_string":"Research and Technology Institute, Area Science Park, Trieste, Italy","institution_ids":["https://openalex.org/I2801626668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137377858","display_name":"Sergio Senci","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2801626668","display_name":"AREA Science Park","ror":"https://ror.org/01dt7qh15","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2801626668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sergio Senci","raw_affiliation_strings":["Research and Technology Institute, Area Science Park, Trieste, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Technology Institute, Area Science Park, Trieste, Italy","institution_ids":["https://openalex.org/I2801626668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137379960","display_name":"Davide Di Vora","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]},{"id":"https://openalex.org/I2801626668","display_name":"AREA Science Park","ror":"https://ror.org/01dt7qh15","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2801626668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Di Vora","raw_affiliation_strings":["Department of Mathematics, Informatics and Geosciences, University of Trieste, Trieste, Italy","Research and Technology Institute, Area Science Park, Trieste, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Informatics and Geosciences, University of Trieste, Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]},{"raw_affiliation_string":"Research and Technology Institute, Area Science Park, Trieste, Italy","institution_ids":["https://openalex.org/I2801626668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099870998","display_name":"Antonio Feltrin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2801626668","display_name":"AREA Science Park","ror":"https://ror.org/01dt7qh15","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2801626668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Antonio Feltrin","raw_affiliation_strings":["Research and Technology Institute, Area Science Park, Trieste, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Technology Institute, Area Science Park, Trieste, Italy","institution_ids":["https://openalex.org/I2801626668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008581467","display_name":"Francesca Cuturello","orcid":"https://orcid.org/0000-0001-7242-7298","observed_orcids":["https://orcid.org/0000-0001-7242-7298"]},"institutions":[{"id":"https://openalex.org/I2801626668","display_name":"AREA Science Park","ror":"https://ror.org/01dt7qh15","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2801626668"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Francesca Cuturello","raw_affiliation_strings":["Research and Technology Institute, Area Science Park, Trieste, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Technology Institute, Area Science Park, Trieste, Italy","institution_ids":["https://openalex.org/I2801626668"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008581467"],"corresponding_institution_ids":["https://openalex.org/I2801626668"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.6366999745368958,"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":0.6366999745368958,"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":0.33980000019073486,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.008100000210106373,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/protein-protein-interfaces","display_name":"protein-protein interfaces","score":0.8629999756813049},{"id":"https://openalex.org/keywords/evolutionary-context","display_name":"evolutionary context","score":0.6650000214576721},{"id":"https://openalex.org/keywords/solid-geometry","display_name":"solid geometry","score":0.7110000252723694},{"id":"https://openalex.org/keywords/protein-docking","display_name":"protein docking","score":0.38100001215934753},{"id":"https://openalex.org/keywords/haddock","display_name":"haddock","score":0.9679999947547913},{"id":"https://openalex.org/keywords/protein-engineering","display_name":"protein engineering","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.725600004196167},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5361999869346619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4740999937057495},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.420199990272522},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C41685203","wikidata":"https://www.wikidata.org/wiki/Q1974042","display_name":"Docking (animal)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3540000021457672},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.05.29.728739","doi":"https://doi.org/10.64898/2026.05.29.728739","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.05.29.728739","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.05.29.728739","doi":"https://doi.org/10.64898/2026.05.29.728739","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.05.29.728739","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1030883578","https://openalex.org/W1483099488","https://openalex.org/W1926568554","https://openalex.org/W1969327849","https://openalex.org/W1985222378","https://openalex.org/W1997803213","https://openalex.org/W2000093524","https://openalex.org/W2009672036","https://openalex.org/W2018661561","https://openalex.org/W2031772330","https://openalex.org/W2041673942","https://openalex.org/W2051710717","https://openalex.org/W2058017150","https://openalex.org/W2075770210","https://openalex.org/W2091565674","https://openalex.org/W2092285329","https://openalex.org/W2114162221","https://openalex.org/W2136206140","https://openalex.org/W2141627824","https://openalex.org/W2153983456","https://openalex.org/W2155194485","https://openalex.org/W2192578595","https://openalex.org/W2264362083","https://openalex.org/W2280888683","https://openalex.org/W2722005050","https://openalex.org/W2754800853","https://openalex.org/W2946430181","https://openalex.org/W2950954328","https://openalex.org/W2955690154","https://openalex.org/W2992752586","https://openalex.org/W2995514860","https://openalex.org/W3080498684","https://openalex.org/W3118865711","https://openalex.org/W3123226037","https://openalex.org/W3135883064","https://openalex.org/W3146944767","https://openalex.org/W3163258067","https://openalex.org/W3166142427","https://openalex.org/W4210318145","https://openalex.org/W4223644783","https://openalex.org/W4239311106","https://openalex.org/W4296293027","https://openalex.org/W4309862248","https://openalex.org/W4366279959","https://openalex.org/W4367049161","https://openalex.org/W4375858802","https://openalex.org/W4382982095","https://openalex.org/W4387865532","https://openalex.org/W4390793818","https://openalex.org/W4406440058","https://openalex.org/W4407153268","https://openalex.org/W4411370561"],"related_works":["https://openalex.org/W7220958235","https://openalex.org/W2103485392","https://openalex.org/W2940821463","https://openalex.org/W7171843175","https://openalex.org/W4415914883","https://openalex.org/W7207655001","https://openalex.org/W7212143755","https://openalex.org/W7166522743","https://openalex.org/W4406682344","https://openalex.org/W2984274952"],"abstract_inverted_index":{"Abstract":[0],"Background":[1],"Protein-protein":[2],"interactions":[3],"govern":[4],"essential":[5],"cellular":[6],"processes,":[7],"making":[8],"the":[9,67,74,84,117,123,143],"identification":[10,168],"of":[11,145,157],"interface":[12,39,79],"residues":[13],"critical":[14],"for":[15,37,77,185],"protein":[16,69],"engineering":[17],"and":[18,95,104,181],"molecular":[19],"design.":[20],"Although":[21],"complex":[22,172],"deep":[23],"learning":[24],"algorithms":[25],"like":[26],"AlphaFold3":[27],"generate":[28],"full":[29],"atom":[30],"resolution":[31],"assemblies,":[32],"they":[33],"are":[34],"not":[35],"optimized":[36],"residue-level":[38,78],"identification.":[40],"Existing":[41],"methods":[42,91],"face":[43],"inherent":[44],"limitations:":[45],"sequence-based":[46],"models":[47],"lack":[48],"explicit":[49],"3D":[50,65],"context,":[51],"while":[52,149],"structure-based":[53,105],"approaches":[54],"can":[55],"overlook":[56],"evolutionary":[57,62],"signals.":[58],"Results":[59],"By":[60],"combining":[61],"context":[63],"with":[64,126,160],"geometry,":[66],"multimodal":[68],"language":[70],"model":[71],"ESM3":[72,119],"offers":[73],"ideal":[75],"foundation":[76],"classification.":[80],"This":[81],"results":[82],"in":[83],"ESM3-PPISites":[85,164],"model,":[86],"which":[87],"outperforms":[88],"existing":[89],"state-of-the-art":[90],"across":[92],"diverse":[93],"training":[94],"benchmark":[96],"sets.":[97],"Generalization":[98],"is":[99],"assessed":[100],"through":[101],"stringent":[102],"sequence-":[103],"redundancy":[106],"filtering":[107],"to":[108],"ensure":[109],"evaluation":[110],"on":[111,171],"previously":[112],"unseen":[113],"proteins.":[114],"Notably,":[115],"finetuning":[116],"open-weight":[118],"architecture":[120],"meaningfully":[121],"narrows":[122],"performance":[124],"gap":[125],"its":[127],"proprietary":[128],"full-scale":[129],"counterpart.":[130],"Furthermore,":[131],"integrating":[132],"predicted":[133],"interaction":[134,188],"sites":[135],"as":[136],"spatial":[137],"restraints":[138],"into":[139],"HADDOCK":[140],"significantly":[141],"improves":[142],"recovery":[144],"near-native":[146],"binding":[147],"poses":[148],"reducing":[150],"computational":[151],"search":[152],"time":[153],"by":[154],"an":[155],"order":[156],"magnitude":[158],"compared":[159],"blind":[161],"docking.":[162],"Conclusions":[163],"enables":[165],"accurate":[166],"interfaces":[167],"without":[169],"relying":[170],"structural":[173],"inputs":[174],"at":[175],"inference":[176],"time,":[177],"establishing":[178],"a":[179],"reliable":[180],"computationally":[182],"efficient":[183],"strategy":[184],"mapping":[186],"protein-protein":[187],"sites.":[189]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-06-03T00:00:00"}