{"id":"https://openalex.org/W7204682361","doi":"https://doi.org/10.64898/2026.08.30.748136","title":"Retrieval of binding sites across the AlphaFold human proteome using protein language model representations","display_name":"Retrieval of binding sites across the AlphaFold human proteome using protein language model representations","publication_year":2026,"publication_date":"2026-09-03","ids":{"openalex":"https://openalex.org/W7204682361","doi":"https://doi.org/10.64898/2026.08.30.748136"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.30.748136","doi":"https://doi.org/10.64898/2026.08.30.748136","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.30.748136","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/03/2026.08.30.748136.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/03/2026.08.30.748136.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147019202","display_name":"Keshav Mohan","orcid":"https://orcid.org/0009-0005-1779-434X","observed_orcids":["https://orcid.org/0009-0005-1779-434X"]},"institutions":[{"id":"https://openalex.org/I4405284005","display_name":"Bhargava Systems Research Inc.","ror":"https://ror.org/02qebyr83","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4405284005"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keshav Mohan","raw_affiliation_strings":["Bhargava Systems Research Inc., Carmel, Indiana, USA"],"raw_orcid":"https://orcid.org/0009-0005-1779-434X","affiliations":[{"raw_affiliation_string":"Bhargava Systems Research Inc., Carmel, Indiana, USA","institution_ids":["https://openalex.org/I4405284005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012438040","display_name":"Yash Bhargava","orcid":"https://orcid.org/0009-0002-4615-1448","observed_orcids":["https://orcid.org/0009-0002-4615-1448"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4405284005","display_name":"Bhargava Systems Research Inc.","ror":"https://ror.org/02qebyr83","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4405284005"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yash Bhargava","raw_affiliation_strings":["Bhargava Systems Research Inc., Carmel, Indiana, USA","Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":"https://orcid.org/0009-0002-4615-1448","affiliations":[{"raw_affiliation_string":"Bhargava Systems Research Inc., Carmel, Indiana, USA","institution_ids":["https://openalex.org/I4405284005"]},{"raw_affiliation_string":"Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012438040"],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4405284005"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.8579000234603882,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.8579000234603882,"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"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.10700000077486038,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.011300000362098217,"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/protein-language-models","display_name":"protein language models","score":0.8489999771118164},{"id":"https://openalex.org/keywords/protein-cavities","display_name":"protein cavities","score":0.7590000033378601},{"id":"https://openalex.org/keywords/frozen-embeddings","display_name":"frozen embeddings","score":0.5759999752044678},{"id":"https://openalex.org/keywords/training-free-framework","display_name":"training-free framework","score":0.5740000009536743},{"id":"https://openalex.org/keywords/web-server","display_name":"web server","score":0.4749999940395355}],"concepts":[{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.7842000126838684},{"id":"https://openalex.org/C94795543","wikidata":"https://www.wikidata.org/wiki/Q3813754","display_name":"Human proteome project","level":4,"score":0.7797999978065491},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5695000290870667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5404999852180481},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4964999854564667},{"id":"https://openalex.org/C2911029443","wikidata":"https://www.wikidata.org/wiki/Q21296145","display_name":"Human proteins","level":3,"score":0.43560001254081726},{"id":"https://openalex.org/C107824862","wikidata":"https://www.wikidata.org/wiki/Q616005","display_name":"Binding site","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4259999990463257},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37450000643730164},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3264000117778778},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.289900004863739},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C51639874","wikidata":"https://www.wikidata.org/wiki/Q167149","display_name":"Plasma protein binding","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C94966510","wikidata":"https://www.wikidata.org/wiki/Q2252764","display_name":"DNA-binding protein","level":4,"score":0.2572999894618988},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.64898/2026.08.30.748136","doi":"https://doi.org/10.64898/2026.08.30.748136","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.30.748136","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/03/2026.08.30.748136.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"doi:10.5281/zenodo.22178549","doi":"https://doi.org/10.5281/zenodo.22178549","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22178549","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.64898/2026.08.30.748136","doi":"https://doi.org/10.64898/2026.08.30.748136","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.30.748136","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/03/2026.08.30.748136.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204682361.pdf","grobid_xml":"https://content.openalex.org/works/W7204682361.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W7162751133"],"related_works":["https://openalex.org/W4411735379","https://openalex.org/W7222472293","https://openalex.org/W4413105433","https://openalex.org/W6960436233","https://openalex.org/W4416535838","https://openalex.org/W7128721057","https://openalex.org/W4390971193","https://openalex.org/W7134922444","https://openalex.org/W4414738646","https://openalex.org/W7160277348"],"abstract_inverted_index":{"Abstract":[0],"Protein":[1],"language":[2],"models":[3],"(PLMs)":[4],"provide":[5],"powerful":[6],"representations":[7],"of":[8,72,82],"protein":[9],"sequence,":[10],"but":[11],"their":[12],"utility":[13],"for":[14,97],"proteome-scale":[15,98],"binding-site":[16],"retrieval":[17],"remains":[18],"unclear.":[19],"Here,":[20],"we":[21],"present":[22],"PocketScope,":[23],"a":[24,69,94,110],"training-free":[25],"framework":[26,96],"that":[27],"represents":[28],"cavity-lining":[29],"residues":[30],"using":[31],"frozen":[32],"ESM-C":[33],"600M":[34],"embeddings":[35],"and":[36,63,105],"retrieves":[37],"related":[38],"binding":[39],"sites":[40],"through":[41],"exhaustive":[42],"lateinteraction":[43],"MaxSim,":[44],"without":[45],"pooling":[46],"or":[47],"approximate":[48],"nearest-neighbor":[49],"search.":[50],"PocketScope":[51,79,92,101],"identified":[52],"153,805":[53],"cavities":[54],"across":[55,68,88],"37,682":[56],"proteins":[57],"in":[58],"the":[59,76,89],"AlphaFold":[60],"human":[61],"proteome":[62],"recovered":[64],"documented":[65],"drug":[66],"off-targets":[67],"curated":[70],"set":[71],"pharmacological":[73],"pairs.":[74],"On":[75],"ProSPECCTs":[77],"benchmark,":[78],"ranks":[80],"1st":[81],"23":[83],"methods":[84],"by":[85],"mean":[86],"rank":[87],"ten":[90],"collections.":[91],"provides":[93],"practical":[95],"off-target":[99],"prediction.":[100],"is":[102],"open":[103],"source":[104],"also":[106],"freely":[107],"available":[108],"as":[109],"web":[111],"server":[112],"at":[113],"https://www.bhargavaresearch.org/pocketscope":[114],".":[115]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-08-31T00:00:00"}