{"id":"https://openalex.org/W7127329658","doi":"https://doi.org/10.64898/2026.10.02.756215","title":"SIMORGH: Ensemble-Aware Geometric Deep Learning for Apo-State and Cryptic Ligand Binding Site Prediction","display_name":"SIMORGH: Ensemble-Aware Geometric Deep Learning for Apo-State and Cryptic Ligand Binding Site Prediction","publication_year":2026,"publication_date":"2026-10-08","ids":{"openalex":"https://openalex.org/W7127329658","doi":"https://doi.org/10.64898/2026.10.02.756215"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.02.756215","doi":"https://doi.org/10.64898/2026.10.02.756215","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.02.756215","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-nd","license_id":"https://openalex.org/licenses/cc-by-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://doi.org/10.64898/2026.10.02.756215","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116573543","display_name":"Omid Mokhtari","orcid":"https://orcid.org/0009-0000-8751-8117","observed_orcids":["https://orcid.org/0009-0000-8751-8117"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Omid Mokhtari","raw_affiliation_strings":["Universit\u00e9 de Lorraine, Inria, F-54000 Nancy, France"],"raw_orcid":"https://orcid.org/0009-0000-8751-8117","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, Inria, F-54000 Nancy, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026809981","display_name":"Amirhossein Naghsh Nilchi","orcid":"https://orcid.org/0000-0003-1329-3044","observed_orcids":["https://orcid.org/0000-0003-1329-3044"]},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Amirhossein Naghsh Nilchi","raw_affiliation_strings":["Chair for Bioinformatics, Department of Computer Science, University of Freiburg, Georges-Koehler-Allee 079, 79110 Freiburg, Germany","Institute of Experimental and Clinical Pharmacology and Toxicology, Faculty of Medicine, University of Freiburg, Freiburg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1329-3044","affiliations":[{"raw_affiliation_string":"Chair for Bioinformatics, Department of Computer Science, University of Freiburg, Georges-Koehler-Allee 079, 79110 Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"Institute of Experimental and Clinical Pharmacology and Toxicology, Faculty of Medicine, University of Freiburg, Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006559585","display_name":"Bj\u00f6rn Andreas Gr\u00fcning","orcid":"https://orcid.org/0000-0002-3079-6586","observed_orcids":["https://orcid.org/0000-0002-3079-6586","https://orcid.org/0000-0001-7364-821X"]},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Gr\u00fcning","raw_affiliation_strings":["Chair for Bioinformatics, Department of Computer Science, University of Freiburg, Georges-Koehler-Allee 079, 79110 Freiburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3079-6586","affiliations":[{"raw_affiliation_string":"Chair for Bioinformatics, Department of Computer Science, University of Freiburg, Georges-Koehler-Allee 079, 79110 Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040990618","display_name":"Yasaman Karami","orcid":"https://orcid.org/0000-0001-8413-2665","observed_orcids":["https://orcid.org/0000-0001-8413-2665"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Yasaman Karami","raw_affiliation_strings":["Universit\u00e9 de Lorraine, Inria, F-54000 Nancy, France"],"raw_orcid":"https://orcid.org/0000-0001-8413-2665","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, Inria, F-54000 Nancy, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I90183372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082401528","display_name":"Hamed Khakzad","orcid":"https://orcid.org/0000-0002-8556-0650","observed_orcids":["https://orcid.org/0000-0002-8556-0650"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Hamed Khakzad","raw_affiliation_strings":["Universit\u00e9 de Lorraine, Inria, F-54000 Nancy, France"],"raw_orcid":"https://orcid.org/0000-0002-8556-0650","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, Inria, F-54000 Nancy, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I90183372"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040990618","https://openalex.org/A5082401528"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I90183372"],"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":0.7339000105857849,"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":0.7339000105857849,"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":0.24629999697208405,"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":0.007199999876320362,"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/cryptic-binding-sites","display_name":"cryptic binding sites","score":0.671999990940094},{"id":"https://openalex.org/keywords/protein-ligand-binding-site-prediction","display_name":"protein-ligand binding site prediction","score":0.8930000066757202},{"id":"https://openalex.org/keywords/conformational-ensembles","display_name":"conformational ensembles","score":0.8349999785423279},{"id":"https://openalex.org/keywords/se-3-equivariance","display_name":"SE(3) equivariance","score":0.9190000295639038},{"id":"https://openalex.org/keywords/geometric-deep-learning","display_name":"geometric deep learning","score":0.9919999837875366},{"id":"https://openalex.org/keywords/ensemble-aggregation","display_name":"ensemble aggregation","score":0.6209999918937683},{"id":"https://openalex.org/keywords/molecular-dynamics-trajectories","display_name":"molecular dynamics trajectories","score":0.7329999804496765},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"drug discovery","score":0.36800000071525574}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6183000206947327},{"id":"https://openalex.org/C65556437","wikidata":"https://www.wikidata.org/wiki/Q766195","display_name":"Protein Data Bank (RCSB PDB)","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49160000681877136},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3725000023841858},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3521000146865845},{"id":"https://openalex.org/C2777936996","wikidata":"https://www.wikidata.org/wiki/Q17148461","display_name":"Conformational ensembles","level":3,"score":0.33629998564720154},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.33489999175071716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3149999976158142},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C116569031","wikidata":"https://www.wikidata.org/wiki/Q899107","display_name":"Ligand (biochemistry)","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C2989255885","wikidata":"https://www.wikidata.org/wiki/Q500256","display_name":"Molecular conformation","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.26010000705718994}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.64898/2026.10.02.756215","doi":"https://doi.org/10.64898/2026.10.02.756215","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.02.756215","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-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"doi:10.5281/zenodo.18414049","doi":"https://doi.org/10.5281/zenodo.18414049","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18414049","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.18414050","doi":"https://doi.org/10.5281/zenodo.18414050","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18414050","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.21930282","doi":"https://doi.org/10.5281/zenodo.21930282","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21930282","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.64898/2026.10.02.756215","doi":"https://doi.org/10.64898/2026.10.02.756215","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.02.756215","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-nd","license_id":"https://openalex.org/licenses/cc-by-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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W151377110","https://openalex.org/W2025768791","https://openalex.org/W2035266068","https://openalex.org/W2057477511","https://openalex.org/W2065283382","https://openalex.org/W2097464861","https://openalex.org/W2114850508","https://openalex.org/W2115339329","https://openalex.org/W2128572087","https://openalex.org/W2171268876","https://openalex.org/W2612445135","https://openalex.org/W2617750324","https://openalex.org/W2887981960","https://openalex.org/W2950954328","https://openalex.org/W3005669732","https://openalex.org/W3035076119","https://openalex.org/W3045610411","https://openalex.org/W3081836708","https://openalex.org/W4283641078","https://openalex.org/W4313880130","https://openalex.org/W4319294199","https://openalex.org/W4322732093","https://openalex.org/W4365145257","https://openalex.org/W4366279959","https://openalex.org/W4386446579","https://openalex.org/W4388870515","https://openalex.org/W4390578919","https://openalex.org/W4390740875","https://openalex.org/W4396789292","https://openalex.org/W4399437600","https://openalex.org/W4403460892","https://openalex.org/W4403541200","https://openalex.org/W4405531686","https://openalex.org/W4407897317","https://openalex.org/W4409838398","https://openalex.org/W4410015912","https://openalex.org/W4411963055","https://openalex.org/W4412102685","https://openalex.org/W4413311999","https://openalex.org/W4413344468","https://openalex.org/W4415513371","https://openalex.org/W4416177558","https://openalex.org/W4417427748","https://openalex.org/W7116684894","https://openalex.org/W7160647050","https://openalex.org/W7196932879"],"related_works":["https://openalex.org/W2086279137","https://openalex.org/W7202383329","https://openalex.org/W4389470796","https://openalex.org/W7171799058","https://openalex.org/W7203755971","https://openalex.org/W7148195270","https://openalex.org/W7213540163","https://openalex.org/W7135864791","https://openalex.org/W7140088423","https://openalex.org/W7204893041"],"abstract_inverted_index":{"Abstract":[0],"Most":[1],"computational":[2],"methods":[3,172],"identify":[4],"protein\u2013ligand":[5],"binding":[6,15,35,91,129,181],"sites":[7,36,92],"from":[8,27,40,70,115],"ligand-bound":[9],"(holo)":[10],"protein":[11,97,136],"structures,":[12,192],"where":[13],"the":[14,28,54,148,174,211],"pocket":[16],"is":[17,75,208],"already":[18],"preorganized.":[19],"Although":[20],"convenient":[21],"for":[22],"benchmarking,":[23],"this":[24],"setting":[25],"differs":[26],"practical":[29],"drug":[30],"discovery":[31],"scenario,":[32],"in":[33],"which":[34],"must":[37],"be":[38],"inferred":[39],"ligand-free":[41,176],"(apo)":[42],"proteins.":[43],"In":[44],"fact,":[45],"binding-competent":[46],"conformations":[47,117],"may":[48],"represent":[49],"only":[50],"a":[51,71,102,107,119],"subset":[52],"of":[53,106],"accessible":[55,205],"structural":[56],"ensemble,":[57],"while":[58,131,178],"transient":[59],"and":[60,118,137,161,170,190,193,204],"cryptic":[61,180],"pockets":[62],"can":[63],"emerge":[64],"through":[65,210],"conformational":[66,98],"fluctuations.":[67],"Consequently,":[68],"prediction":[69,185],"single":[72],"static":[73,169],"structure":[74],"often":[76],"insufficient.":[77],"Here":[78],"we":[79],"present":[80],"SIMORGH,":[81],"an":[82],"ensemble-aware":[83],"SE(3)-equivariant":[84],"geometric":[85,113],"learning":[86],"framework":[87],"that":[88,111,124],"predicts":[89],"ligand":[90],"by":[93],"integrating":[94],"information":[95],"across":[96,143],"ensembles.":[99],"SIMORGH":[100,142,165],"employs":[101],"two-stage":[103],"architecture":[104],"consisting":[105],"structure-level":[108],"equivariant":[109],"encoder":[110],"learns":[112],"representations":[114],"individual":[116],"lightweight":[120],"ensemble-level":[121],"aggregation":[122],"module":[123],"combines":[125],"them":[126],"into":[127],"residue-level":[128],"predictions":[130],"scaling":[132,194],"near-linearly":[133],"with":[134],"both":[135],"ensemble":[138],"size.":[139],"We":[140],"evaluate":[141],"multiple":[144],"complementary":[145],"settings,":[146],"including":[147],"PLINDER":[149],"apo":[150,189],"benchmark,":[151],"molecular":[152],"dynamics":[153],"trajectories":[154],"spanning":[155],"more":[156],"than":[157],"200":[158],"cryptic-pocket":[159],"proteins,":[160],"established":[162],"community":[163],"benchmarks.":[164],"consistently":[166],"outperforms":[167],"existing":[168],"dynamics-aware":[171],"under":[173],"challenging":[175],"setting,":[177],"identifying":[179],"pockets,":[182],"maintaining":[183],"strong":[184],"consistency":[186],"between":[187],"paired":[188],"holo":[191],"efficiently":[195],"to":[196],"large":[197],"multi-chain":[198],"complexes.":[199],"To":[200],"facilitate":[201],"reproducible,":[202],"transparent,":[203],"use,":[206],"Simorgh":[207],"available":[209],"Galaxy":[212],"Europe":[213],"server":[214],"(":[215],"https://usegalaxy.eu":[216],").":[217]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-02-04T00:00:00"}