{"id":"https://openalex.org/W7225794368","doi":"https://doi.org/10.64898/2026.11.10.765562","title":"Pocket similarity guided selection of protein targets for systematic protein ligand dataset generation","display_name":"Pocket similarity guided selection of protein targets for systematic protein ligand dataset generation","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225794368","doi":"https://doi.org/10.64898/2026.11.10.765562"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.10.765562","doi":"https://doi.org/10.64898/2026.11.10.765562","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.10.765562","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-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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.64898/2026.11.10.765562","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161473441","display_name":"montserrat Garcia-Cerqueda","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210122345","display_name":"Institute for Research in Biomedicine","ror":"https://ror.org/01z1gye03","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210122345","https://openalex.org/I4210132884","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"montserrat Garcia-Cerqueda","raw_affiliation_strings":["IRB Barcelona;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRB Barcelona;","institution_ids":["https://openalex.org/I4210122345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076484281","display_name":"Matthieu Schapira","orcid":"https://orcid.org/0000-0002-1047-3309","observed_orcids":["https://orcid.org/0000-0002-1047-3309"]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Matthieu Schapira","raw_affiliation_strings":["University of Toronto;"],"raw_orcid":"https://orcid.org/0000-0002-1047-3309","affiliations":[{"raw_affiliation_string":"University of Toronto;","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062183469","display_name":"Albert A. Antol\u00edn","orcid":"https://orcid.org/0000-0002-1634-9034","observed_orcids":["https://orcid.org/0000-0002-1634-9034"]},"institutions":[{"id":"https://openalex.org/I4387155398","display_name":"Vall d'Hebron Institute of Oncology","ror":"https://ror.org/054xx3904","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387155398"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Albert A Antolin","raw_affiliation_strings":["VHIO;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VHIO;","institution_ids":["https://openalex.org/I4387155398"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014770642","display_name":"A.M. Edwards","orcid":"https://orcid.org/0000-0002-4782-6016","observed_orcids":["https://orcid.org/0000-0002-4782-6016","https://orcid.org/0000-0002-9739-9593"]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Aled Edwards","raw_affiliation_strings":["University of Toronto;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto;","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015088787","display_name":"Patrick Aloy","orcid":"https://orcid.org/0000-0002-3557-0236","observed_orcids":["https://orcid.org/0000-0002-3557-0236"]},"institutions":[{"id":"https://openalex.org/I4210122345","display_name":"Institute for Research in Biomedicine","ror":"https://ror.org/01z1gye03","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210122345","https://openalex.org/I4210132884","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Patrick Aloy","raw_affiliation_strings":["Institute for Research in Biomedicine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Research in Biomedicine","institution_ids":["https://openalex.org/I4210122345"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015088787"],"corresponding_institution_ids":["https://openalex.org/I4210122345"],"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9984999895095825,"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":0.9984999895095825,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.0003000000142492354,"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":0.00019999999494757503,"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":[],"concepts":[{"id":"https://openalex.org/C10679952","wikidata":"https://www.wikidata.org/wiki/Q5308937","display_name":"Druggability","level":3,"score":0.8912000060081482},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6769999861717224},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49559998512268066},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4674000144004822},{"id":"https://openalex.org/C2911029443","wikidata":"https://www.wikidata.org/wiki/Q21296145","display_name":"Human proteins","level":3,"score":0.4571000039577484},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C51639874","wikidata":"https://www.wikidata.org/wiki/Q167149","display_name":"Plasma protein binding","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C107824862","wikidata":"https://www.wikidata.org/wiki/Q616005","display_name":"Binding site","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C105168689","wikidata":"https://www.wikidata.org/wiki/Q901969","display_name":"Globular protein","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.37790000438690186},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.37130001187324524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3619999885559082},{"id":"https://openalex.org/C109095088","wikidata":"https://www.wikidata.org/wiki/Q899107","display_name":"Protein ligand","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C116569031","wikidata":"https://www.wikidata.org/wiki/Q899107","display_name":"Ligand (biochemistry)","level":3,"score":0.3402000069618225},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.3179999887943268},{"id":"https://openalex.org/C139489369","wikidata":"https://www.wikidata.org/wiki/Q770846","display_name":"Structural similarity","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C111364199","wikidata":"https://www.wikidata.org/wiki/Q2915896","display_name":"Protein methods","level":4,"score":0.3077999949455261},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.296099990606308},{"id":"https://openalex.org/C94966510","wikidata":"https://www.wikidata.org/wiki/Q2252764","display_name":"DNA-binding protein","level":4,"score":0.28600001335144043},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C204328495","wikidata":"https://www.wikidata.org/wiki/Q847556","display_name":"Protein folding","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C3019232848","wikidata":"https://www.wikidata.org/wiki/Q29548","display_name":"Surface protein","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C3018795828","wikidata":"https://www.wikidata.org/wiki/Q899107","display_name":"Binding affinities","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C119145174","wikidata":"https://www.wikidata.org/wiki/Q7251429","display_name":"Protein Data Bank","level":3,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.10.765562","doi":"https://doi.org/10.64898/2026.11.10.765562","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.10.765562","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-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"}],"best_oa_location":{"id":"doi:10.64898/2026.11.10.765562","doi":"https://doi.org/10.64898/2026.11.10.765562","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.10.765562","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-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":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,25],"scarcity":[1],"of":[2,14,54,91,102,140,160,232,250],"large,":[3],"diverse,":[4],"and":[5,128,167,196,205,254,275],"unbiased":[6],"protein":[7,126,279],"ligand":[8,164,280],"binding":[9,37,67,103,143],"datasets":[10],"limits":[11],"the":[12,52,55,81,92,107,131,156,161,197,233,248],"performance":[13],"machine":[15],"learning":[16],"approaches":[17],"in":[18,219,227,247,284],"drug":[19],"discovery,":[20],"particularly":[21],"for":[22,39,84,272],"understudied":[23],"proteins.":[24,118],"Target":[26,273],"2035":[27,274],"initiative":[28],"aims":[29],"to":[30,105,180,201,244,268],"address":[31],"this":[32],"gap":[33],"by":[34,177],"generating":[35],"open-access":[36],"data":[38,281],"more":[40],"than":[41,75,256],"2,000":[42],"human":[43,93,108,234],"proteins,":[44,229],"a":[45,242,265],"goal":[46],"whose":[47],"value":[48],"depends":[49],"on":[50],"maximizing":[51],"diversity":[53],"selected":[56,155,206],"targets.":[57],"Because":[58],"proteins":[59,195,199,235,255],"with":[60,151,216,236],"different":[61,211],"folds":[62],"can":[63],"share":[64],"chemically":[65,141],"analogous":[66],"sites,":[68,104],"we":[69,96,154,185],"reasoned":[70],"that":[71,88],"pocket":[72,261],"similarity,":[73,79],"rather":[74],"sequence":[76],"or":[77],"fold":[78],"is":[80],"appropriate":[82],"criterion":[83],"selecting":[85],"representative":[86,172],"targets":[87,271],"maximize":[89],"coverage":[90],"pocketome.":[94],"Here,":[95],"use":[97],"PocketVec,":[98],"an":[99],"alignment-free":[100],"descriptor":[101],"map":[106],"globular":[109],"pocketome,":[110],"identifying":[111],"51,535":[112],"predicted":[113],"druggable":[114,238],"pockets":[115,136,150,173,208,226],"across":[116,130],"15,559":[117],"A":[119],"two":[120,169,187],"level":[121],"hierarchical":[122],"clustering,":[123],"first":[124],"within":[125],"families":[127],"then":[129],"whole":[132],"proteome,":[133],"grouped":[134],"these":[135],"into":[137],"1,865":[138],"clusters":[139,148,166,212,218],"similar":[142],"sites.":[144,183],"After":[145],"discarding":[146],"533":[147],"containing":[149],"known":[152,181],"ligands,":[153],"100":[157,210],"most":[158],"populated":[159],"remaining":[162],"1,332":[163],"free":[165],"chose":[168],"high":[170],"quality":[171],"per":[174],"cluster,":[175],"ranked":[176],"their":[178],"resemblance":[179],"ligand-binding":[182],"Finally,":[184],"implemented":[186],"complementary":[188],"prioritization":[189],"strategies,":[190],"one":[191],"favoring":[192],"structurally":[193],"unexplored":[194],"other":[198,276],"amenable":[200],"experimental":[202],"follow":[203],"up,":[204],"200":[207],"from":[209,213],"each":[214],"strategy,":[215],"89":[217],"common.":[220],"Both":[221],"selections":[222],"cover":[223],"over":[224],"10,000":[225],"~5,600":[228],"approximately":[230],"36%":[231],"annotated":[237],"pockets,":[239,252],"which":[240],"represents":[241],"2.8-":[243],"4.4-fold":[245],"increase":[246],"number":[249],"covered":[251],"domains,":[253],"random":[257],"selection":[258],"baselines.":[259],"This":[260],"based":[262],"framework":[263],"offers":[264],"principled":[266],"strategy":[267],"select":[269],"diverse":[270],"large":[277],"scale":[278],"generation":[282],"efforts":[283],"chemical":[285],"biology.":[286]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}