{"id":"https://openalex.org/W7170883142","doi":"https://doi.org/10.48550/arxiv.2607.21561","title":"EnsembleEGNN: Set-Based Graph Learning for Thermodynamic Ensembles of Cyclic Peptides","display_name":"EnsembleEGNN: Set-Based Graph Learning for Thermodynamic Ensembles of Cyclic Peptides","publication_year":2026,"publication_date":"2026-07-23","ids":{"openalex":"https://openalex.org/W7170883142","doi":"https://doi.org/10.48550/arxiv.2607.21561"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2607.21561","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.21561","pdf_url":"https://arxiv.org/pdf/2607.21561","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.21561","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020473978","display_name":"Aaron L. Feller","orcid":"https://orcid.org/0000-0002-4476-1026","observed_orcids":["https://orcid.org/0000-0002-4476-1026"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feller, Aaron L.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076771264","display_name":"Kristine Deibler","orcid":"https://orcid.org/0000-0002-2376-8456","observed_orcids":["https://orcid.org/0000-0002-2376-8456"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deibler, Kris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042328989","display_name":"Maxim Secor","orcid":"https://orcid.org/0000-0003-2569-2384","observed_orcids":["https://orcid.org/0000-0003-2569-2384"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Secor, Maxim","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":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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9922000169754028,"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":0.9922000169754028,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.00139999995008111,"subfield":{"id":"https://openalex.org/subfields/1605","display_name":"Organic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cyclic-peptides","display_name":"cyclic peptides","score":0.7239999771118164},{"id":"https://openalex.org/keywords/thermodynamic-ensembles","display_name":"thermodynamic ensembles","score":0.8679999709129333},{"id":"https://openalex.org/keywords/equivariant-graph-neural-networks","display_name":"equivariant graph neural networks","score":0.8270000219345093},{"id":"https://openalex.org/keywords/membrane-permeability-prediction","display_name":"membrane permeability prediction","score":0.9660000205039978},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.7450000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6514999866485596},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6287000179290771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827999711036682},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36419999599456787},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.35569998621940613},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3513000011444092},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3142000138759613},{"id":"https://openalex.org/C47458327","wikidata":"https://www.wikidata.org/wiki/Q910404","display_name":"Random graph","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C51865526","wikidata":"https://www.wikidata.org/wiki/Q5379962","display_name":"Ensemble average","level":2,"score":0.2712000012397766}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2607.21561","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.21561","pdf_url":"https://arxiv.org/pdf/2607.21561","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2607.21561","doi":"https://doi.org/10.48550/arxiv.2607.21561","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.21561","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2607.21561","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.21561","pdf_url":"https://arxiv.org/pdf/2607.21561","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322436","display_name":"Novo Nordisk","ror":"https://ror.org/0435rc536"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7170883142.pdf","grobid_xml":"https://content.openalex.org/works/W7170883142.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W7134897954"],"related_works":["https://openalex.org/W7223156667","https://openalex.org/W4378469484","https://openalex.org/W4390092742","https://openalex.org/W7160899084","https://openalex.org/W7163985762","https://openalex.org/W4410373760","https://openalex.org/W7211903526","https://openalex.org/W7221019820","https://openalex.org/W7169874602","https://openalex.org/W4387348565"],"abstract_inverted_index":{"Molecular":[0],"graph":[1,39],"encoding":[2,142],"often":[3],"relies":[4],"on":[5,58],"a":[6,25,45,97,115],"single,":[7],"static":[8],"structure,":[9],"ignoring":[10],"the":[11,54,59,67,73,84,121,125],"thermodynamic":[12],"ensemble":[13],"of":[14,76,91],"molecules":[15],"that":[16,28,141],"are":[17],"present":[18],"in":[19],"solution.":[20],"Here,":[21],"we":[22],"introduce":[23],"EnsembleEGNN,":[24],"foundation":[26],"model":[27,68,123],"encodes":[29],"structural":[30,134],"ensembles":[31,144],"by":[32,153],"processing":[33],"individual":[34],"conformers":[35],"through":[36],"shared":[37],"equivariant":[38],"neural":[40],"network":[41],"layers,":[42],"pooled":[43],"with":[44,120],"set":[46],"attention":[47],"block,":[48],"to":[49,71],"make":[50],"property":[51],"predictions":[52,149],"from":[53,83],"whole":[55],"ensemble.":[56],"Pretrained":[57],"CREMP":[60],"cyclic":[61],"peptide":[62],"dataset":[63],"using":[64],"multi-task":[65],"self-supervision,":[66],"is":[69],"trained":[70],"encode":[72],"conformational":[74,143],"variability":[75],"each":[77],"molecule.":[78],"When":[79],"predicting":[80],"membrane":[81],"permeability":[82],"CycPeptMPDB":[85],"benchmark,":[86],"EnsembleEGNN":[87,119],"achieves":[88,124],"an":[89],"$R^2$":[90],"$0.477$":[92],"under":[93,106],"random":[94,131],"cross-validation,":[95],"outperforming":[96],"sequence-only":[98],"BERT":[99,122],"baseline":[100],"($R^2=0.439$).":[101],"This":[102],"representation":[103],"advantage":[104],"persists":[105],"rigorous":[107],"out-of-distribution":[108],"Butina":[109],"splits":[110],"($R^2=0.401$":[111],"versus":[112],"$0.354$).":[113],"Finally,":[114],"hybrid":[116],"architecture":[117],"co-training":[118],"highest":[126],"overall":[127],"accuracy":[128],"across":[129],"both":[130],"($R^2=0.538$)":[132],"and":[133],"holdout":[135],"evaluations":[136],"($R^2=0.444$).":[137],"These":[138],"results":[139],"demonstrate":[140],"into":[145],"latent":[146],"representations":[147],"improves":[148],"for":[150],"properties":[151],"governed":[152],"thermodynamics.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-07-25T00:00:00"}