{"id":"https://openalex.org/W7223846963","doi":"https://doi.org/10.64898/2026.10.24.761513","title":"Can Folding Models Tell Binders from Bluffers? Evidence from POISK: The Patent-Derived Antibody Dataset","display_name":"Can Folding Models Tell Binders from Bluffers? Evidence from POISK: The Patent-Derived Antibody Dataset","publication_year":2026,"publication_date":"2026-10-26","ids":{"openalex":"https://openalex.org/W7223846963","doi":"https://doi.org/10.64898/2026.10.24.761513"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.24.761513","doi":"https://doi.org/10.64898/2026.10.24.761513","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.24.761513","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/26/2026.10.24.761513.full.pdf","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":"acceptedVersion","is_accepted":true,"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://www.biorxiv.org/content/biorxiv/early/2026/10/26/2026.10.24.761513.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134872171","display_name":"Daria Tupikina","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daria Tupikina","raw_affiliation_strings":["Large Molecule Research, Roche Pharma Research and Early Development, Roche Innovation Center Munich, Penzberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Large Molecule Research, Roche Pharma Research and Early Development, Roche Innovation Center Munich, Penzberg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093211849","display_name":"Andrea Roncoli","orcid":"https://orcid.org/0009-0002-9168-0031","observed_orcids":["https://orcid.org/0009-0002-9168-0031"]},"institutions":[{"id":"https://openalex.org/I118019719","display_name":"F. Hoffmann-La Roche AG","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andrea Roncoli","raw_affiliation_strings":["Prescient Design \u2013 AI for Drug Discovery, Computational Science Center Of Excellence, Roche, Basel, Switzerland"],"raw_orcid":"https://orcid.org/0009-0002-9168-0031","affiliations":[{"raw_affiliation_string":"Prescient Design \u2013 AI for Drug Discovery, Computational Science Center Of Excellence, Roche, Basel, Switzerland","institution_ids":["https://openalex.org/I118019719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010987836","display_name":"Alexander Bujotzek","orcid":"https://orcid.org/0000-0001-5052-0221","observed_orcids":["https://orcid.org/0000-0001-5052-0221"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Bujotzek","raw_affiliation_strings":["Large Molecule Research, Roche Pharma Research and Early Development, Roche Innovation Center Munich, Penzberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Large Molecule Research, Roche Pharma Research and Early Development, Roche Innovation Center Munich, Penzberg, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005538694","display_name":"Brennan Abanades","orcid":"https://orcid.org/0000-0001-8712-533X","observed_orcids":["https://orcid.org/0000-0001-8712-533X"]},"institutions":[{"id":"https://openalex.org/I118019719","display_name":"F. Hoffmann-La Roche AG","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Brennan Abanades","raw_affiliation_strings":["Prescient Design \u2013 AI for Drug Discovery, Computational Science Center Of Excellence, Roche, Basel, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-8712-533X","affiliations":[{"raw_affiliation_string":"Prescient Design \u2013 AI for Drug Discovery, Computational Science Center Of Excellence, Roche, Basel, Switzerland","institution_ids":["https://openalex.org/I118019719"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5005538694"],"corresponding_institution_ids":["https://openalex.org/I118019719"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.48559999465942383,"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":0.48559999465942383,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.2847000062465668,"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":0.09690000116825104,"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/antibody-screening","display_name":"antibody screening","score":0.4790000021457672},{"id":"https://openalex.org/keywords/epitope-localization","display_name":"epitope localization","score":0.9089999794960022},{"id":"https://openalex.org/keywords/alphafold-multimer","display_name":"AlphaFold-Multimer","score":0.9190000295639038},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.46399998664855957}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7791000008583069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6233000159263611},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6151999831199646},{"id":"https://openalex.org/C195616568","wikidata":"https://www.wikidata.org/wiki/Q128711","display_name":"Epitope","level":3,"score":0.5742999911308289},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.51910001039505},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48019999265670776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45969998836517334},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41679999232292175},{"id":"https://openalex.org/C2776545253","wikidata":"https://www.wikidata.org/wiki/Q5464292","display_name":"Folding (DSP implementation)","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C9086966","wikidata":"https://www.wikidata.org/wiki/Q489135","display_name":"Paratope","level":4,"score":0.3215000033378601},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2781241564","wikidata":"https://www.wikidata.org/wiki/Q1347450","display_name":"Epitope mapping","level":4,"score":0.2766999900341034},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.24.761513","doi":"https://doi.org/10.64898/2026.10.24.761513","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.24.761513","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/26/2026.10.24.761513.full.pdf","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.24.761513","doi":"https://doi.org/10.64898/2026.10.24.761513","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.24.761513","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/26/2026.10.24.761513.full.pdf","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223846963.pdf","grobid_xml":"https://content.openalex.org/works/W7223846963.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4390041933","https://openalex.org/W7134095342","https://openalex.org/W7147673913"],"related_works":["https://openalex.org/W7139969690","https://openalex.org/W4407498410","https://openalex.org/W4408763951","https://openalex.org/W4396787690","https://openalex.org/W4241555716","https://openalex.org/W4366998330","https://openalex.org/W7133490307","https://openalex.org/W7134095342","https://openalex.org/W7161276184","https://openalex.org/W7170761664"],"abstract_inverted_index":{"Abstract":[0],"Structure":[1],"prediction":[2,119],"models":[3,120,191,206,252],"are":[4],"increasingly":[5],"deployed":[6],"as":[7,271],"zero-shot":[8],"digital":[9],"screens":[10],"in":[11,169,231],"antibody":[12,259],"design,":[13],"operating":[14],"under":[15],"the":[16,42,65,151,160,224],"assumption":[17],"that":[18,237,249],"high":[19],"folding":[20,251],"confidence":[21],"implies":[22],"true":[23,161],"binding.":[24],"However,":[25],"rigorous":[26],"validation":[27],"of":[28,44,56,90,155,166,171,218,234],"this":[29,82,112,173],"premise":[30],"has":[31],"been":[32],"limited":[33,256],"by":[34,265],"small":[35],"test":[36],"sets,":[37],"narrow":[38],"target":[39],"diversity,":[40],"and":[41,127,148,157,261,278],"risk":[43],"data":[45],"leakage":[46],"from":[47,64,74,106,135,163,184,195],"training-adjacent":[48],"structures.":[49],"Here":[50],"we":[51,84,114],"introduce":[52],"POISK:":[53],"Patent-extracted":[54],"Organization":[55],"Immunoglobulin":[57],"Sequence":[58],"Knowledge,":[59],"a":[60,86,97,164,175,209,272],"large-scale":[61],"dataset":[62],"derived":[63],"US":[66],"patent":[67],"literature,":[68],"comprising":[69],"89,074":[70],"antibody-antigen":[71],"records":[72],"extracted":[73],"10,110":[75],"patents":[76],"using":[77],"an":[78],"LLM-based":[79],"pipeline.":[80],"From":[81],"resource,":[83],"curate":[85],"balanced":[87],"benchmark":[88,115],"set":[89],"22,494":[91],"complexes:":[92],"11,247":[93],"patent-validated":[94],"binders":[95,134,194],"without":[96],"known":[98],"resolved":[99],"structure":[100,118],"paired":[101],"with":[102,197],"putative":[103],"non-binders":[104],"constructed":[105],"sequence-similar":[107],"human":[108],"repertoire":[109],"antibodies.":[110],"Using":[111],"dataset,":[113],"six":[116],"leading":[117],"(AlphaFold-Multimer,":[121],"Boltz-2,":[122],"IntelliFold":[123],"v2,":[124],"OpenFold3,":[125],"Protenix-v1,":[126],"Protenix-v2)":[128],"on":[129,150,208],"their":[130],"ability":[131],"to":[132],"discriminate":[133],"decoys.":[136],"The":[137],"best-performing":[138],"model,":[139],"Protenix-v2,":[140],"achieves":[141],"72%":[142],"pairwise":[143,198],"accuracy":[144,199],"over":[145,178],"all":[146],"pairs":[147],"87%":[149],"most":[152],"confident":[153],"half":[154],"predictions,":[156],"correctly":[158],"identifies":[159],"binder":[162],"pool":[165],"50":[167],"candidates":[168],"29%":[170],"trials;":[172],"represents":[174],"substantial":[176],"enrichment":[177],"random":[179],"selection,":[180],"yet":[181],"remains":[182,222],"far":[183],"reliable":[185],"single-candidate":[186],"identification.":[187],"Structural":[188],"consensus":[189],"across":[190],"also":[192],"discriminates":[193],"decoys,":[196],"reaching":[200],"73.1%":[201],"when":[202],"three":[203],"or":[204],"more":[205],"converge":[207],"pose":[210],"(":[211],"DockQ":[212],"\u2265":[213],"0.23,":[214],"covering":[215],"around":[216],"54.2%":[217],"pairs).":[219],"Epitope":[220],"localization":[221],"unreliable:":[223],"best":[225],"model":[226,279],"contacts":[227],"annotated":[228],"epitope":[229,244],"residues":[230],"only":[232],"62.8%":[233],"cases,":[235],"indicating":[236],"binding":[238],"discrimination":[239],"does":[240],"not":[241],"establish":[242],"accurate":[243],"localization.":[245],"Our":[246],"results":[247],"suggest":[248],"current":[250],"provide":[253],"useful":[254],"but":[255],"signal":[257],"for":[258,275],"screening":[260],"should":[262],"be":[263],"complemented":[264],"orthogonal":[266],"methods.":[267],"We":[268],"release":[269],"POISK":[270],"community":[273],"resource":[274],"future":[276],"benchmarking":[277],"training.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-10-28T00:00:00"}