{"id":"https://openalex.org/W7163517812","doi":"https://doi.org/10.48550/arxiv.2606.04154","title":"EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning","display_name":"EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163517812","doi":"https://doi.org/10.48550/arxiv.2606.04154"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.04154","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04154","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.04154","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137889595","display_name":"Mansoor Ahmed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed, Mansoor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137899682","display_name":"Huirong Chai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chai, Huirong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137877336","display_name":"Haoxin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haoxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129718719","display_name":"Hemanth Venkateswara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Venkateswara, Hemanth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136723981","display_name":"Murray Patterson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patterson, Murray","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.7773000001907349,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.7773000001907349,"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/T11016","display_name":"Monoclonal and Polyclonal Antibodies Research","score":0.17260000109672546,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10580","display_name":"Immunotherapy and Immune Responses","score":0.03229999914765358,"subfield":{"id":"https://openalex.org/subfields/2403","display_name":"Immunology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/epitope","display_name":"Epitope","score":0.6949999928474426},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5800999999046326},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5658000111579895},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5501999855041504},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5315999984741211},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42829999327659607},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.41920000314712524},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.415800005197525},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3961000144481659}],"concepts":[{"id":"https://openalex.org/C195616568","wikidata":"https://www.wikidata.org/wiki/Q128711","display_name":"Epitope","level":3,"score":0.6949999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6337000131607056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6291000247001648},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5800999999046326},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5658000111579895},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5501999855041504},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3946000039577484},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38839998841285706},{"id":"https://openalex.org/C152769699","wikidata":"https://www.wikidata.org/wiki/Q410814","display_name":"Protein design","level":3,"score":0.38179999589920044},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C3018252375","wikidata":"https://www.wikidata.org/wiki/Q1059","display_name":"Immune recognition","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.04154","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04154","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.04154","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04154","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Antibodies":[0],"neutralize":[1],"foreign":[2],"antigens":[3],"by":[4,150],"binding":[5,54,196],"to":[6,47,122],"specific":[7],"surface":[8],"regions":[9],"called":[10],"epitopes.":[11],"Computational":[12],"epitope":[13,140,213],"prediction":[14,141],"is":[15,87,111,222],"critical":[16],"for":[17,138,202],"understanding":[18],"immune":[19],"recognition":[20],"and":[21,38,60,161,198],"guiding":[22],"antibody":[23],"engineering.":[24],"However,":[25],"existing":[26],"methods":[27],"face":[28],"three":[29],"fundamental":[30],"challenges:":[31],"antibody-aware":[32],"models":[33],"encode":[34],"each":[35],"chain":[36],"independently":[37],"combine":[39],"them":[40],"only":[41,104],"at":[42,105,194],"a":[43,74],"late":[44],"stage,":[45],"failing":[46],"capture":[48],"co-dependent":[49],"structural":[50],"features":[51,206],"that":[52,78,128,212],"define":[53],"interfaces,":[55],"whereas":[56],"severe":[57],"class":[58],"imbalance":[59],"scarcity":[61],"of":[62,173,190],"known":[63,167],"antibody-antigen":[64],"complexes":[65],"render":[66],"standard":[67,157],"training":[68],"objectives":[69,130],"ineffective.":[70],"We":[71,125],"propose":[72],"EpiFormer,":[73],"general":[75],"encoder-decoder":[76],"framework":[77],"addresses":[79],"these":[80],"challenges":[81],"jointly.":[82],"Our":[83],"key":[84],"design":[85],"principle":[86,110],"interleaved":[88],"cross-attention":[89,179],"within":[90],"GNN":[91,117],"encoding":[92],"layers,":[93],"enabling":[94],"bidirectional":[95],"antigen-antibody":[96],"information":[97,183],"flow":[98],"throughout":[99],"representation":[100],"learning":[101],"rather":[102],"than":[103],"the":[106,139,146,177,187,191,195,199,209],"output.":[107],"This":[108],"early-fusion":[109,136],"backbone-agnostic,":[112],"providing":[113],"consistent":[114,185],"gains":[115],"across":[116],"architectures":[118,137],"from":[119],"simple":[120],"GCNs":[121],"equivariant":[123],"models.":[124],"further":[126],"show":[127],"sparsity-aware":[129],"are":[131,215],"effective":[132],"when":[133],"paired":[134],"with":[135,186,208],"task.":[142],"EpiFormer":[143,165],"improves":[144],"over":[145,151,204],"previous":[147],"best":[148],"method":[149],"40%":[152],"in":[153],"F1":[154],"score":[155],"on":[156],"benchmarks,":[158],"demonstrating":[159],"generalizability":[160],"cross-dataset":[162],"transferability.":[163],"Notably,":[164],"discovers":[166],"biological":[168],"principles":[169],"as":[170],"emergent":[171],"behaviors":[172],"end-to-end":[174],"training,":[175],"where":[176],"learned":[178],"gates":[180],"favor":[181],"antigen-to-antibody":[182],"flow,":[184],"asymmetric":[188],"roles":[189],"two":[192],"chains":[193],"interface,":[197],"model's":[200],"preference":[201],"geometric":[203],"evolutionary":[205],"aligns":[207],"established":[210],"finding":[211],"residues":[214],"not":[216],"evolutionarily":[217],"conserved.":[218],"The":[219],"source":[220],"code":[221],"available":[223],"at:":[224],"https://github.com/mansoor181/epiformer.git":[225]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-05T00:00:00"}