{"id":"https://openalex.org/W7225267260","doi":"https://doi.org/10.48550/arxiv.2611.05055","title":"Ablating Design Choices for Protein Ensemble Generators Across Structural Regimes","display_name":"Ablating Design Choices for Protein Ensemble Generators Across Structural Regimes","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225267260","doi":"https://doi.org/10.48550/arxiv.2611.05055"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.05055","doi":"https://doi.org/10.48550/arxiv.2611.05055","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.05055","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"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.05055","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067267663","display_name":"Eoin Quinn","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quinn, Eoin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001239661","display_name":"Oliver Bent","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bent, Oliver","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":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/T10044","display_name":"Protein Structure and Dynamics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11162","display_name":"Enzyme Structure and Function","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1315","display_name":"Structural 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/T10211","display_name":"Computational Drug Discovery Methods","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/protein-conformational-ensembles","display_name":"protein conformational ensembles","score":0.8550000190734863},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.7749999761581421},{"id":"https://openalex.org/keywords/intrinsically-disordered-proteins","display_name":"intrinsically disordered proteins","score":0.902999997138977},{"id":"https://openalex.org/keywords/multidomain-proteins","display_name":"multidomain proteins","score":0.8629999756813049},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.6650000214576721},{"id":"https://openalex.org/keywords/small-angle-x-ray-scattering","display_name":"small-angle X-ray scattering","score":0.5149999856948853},{"id":"https://openalex.org/keywords/nmr-chemical-shifts","display_name":"NMR chemical shifts","score":0.9459999799728394},{"id":"https://openalex.org/keywords/mixture-of-experts","display_name":"mixture of experts","score":0.6809999942779541},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.8640000224113464},{"id":"https://openalex.org/keywords/fragment-assembly","display_name":"fragment assembly","score":0.6209999918937683},{"id":"https://openalex.org/keywords/training-data","display_name":"training data","score":0.4569999873638153},{"id":"https://openalex.org/keywords/ablation-study","display_name":"ablation study","score":0.5989999771118164}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5641999840736389},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5493999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5224000215530396},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.45159998536109924},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.4099999964237213},{"id":"https://openalex.org/C152769699","wikidata":"https://www.wikidata.org/wiki/Q410814","display_name":"Protein design","level":3,"score":0.3903999924659729},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.38530001044273376},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.37560001015663147},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3718999922275543},{"id":"https://openalex.org/C2778815515","wikidata":"https://www.wikidata.org/wiki/Q3408242","display_name":"Intrinsically disordered proteins","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C8010536","wikidata":"https://www.wikidata.org/wiki/Q160398","display_name":"Crystallography","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C2775981520","wikidata":"https://www.wikidata.org/wiki/Q17156992","display_name":"Protein dynamics","level":3,"score":0.34049999713897705},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C2777936996","wikidata":"https://www.wikidata.org/wiki/Q17148461","display_name":"Conformational ensembles","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3093000054359436},{"id":"https://openalex.org/C2988375501","wikidata":"https://www.wikidata.org/wiki/Q847556","display_name":"Protein stability","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.29580000042915344},{"id":"https://openalex.org/C131888329","wikidata":"https://www.wikidata.org/wiki/Q3027679","display_name":"Small-angle X-ray scattering","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C2989255885","wikidata":"https://www.wikidata.org/wiki/Q500256","display_name":"Molecular conformation","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C191486275","wikidata":"https://www.wikidata.org/wiki/Q210028","display_name":"Scattering","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.25949999690055847},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2611.05055","doi":"https://doi.org/10.48550/arxiv.2611.05055","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.05055","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":"doi:10.48550/arxiv.2611.05055","doi":"https://doi.org/10.48550/arxiv.2611.05055","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.05055","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415329770","https://openalex.org/W4389341076","https://openalex.org/W4319915684","https://openalex.org/W4391673325","https://openalex.org/W7219836094","https://openalex.org/W7214307653","https://openalex.org/W7204942480","https://openalex.org/W1988878165","https://openalex.org/W7155052477","https://openalex.org/W4398257517"],"abstract_inverted_index":{"Generative":[0],"models":[1],"of":[2,8,45,114,134,139],"protein":[3,89],"conformational":[4],"ensembles":[5,119],"inherit":[6],"much":[7],"their":[9],"design":[10,30],"from":[11],"structure":[12],"prediction":[13],"for":[14],"folded":[15],"proteins.":[16,72],"Ordered":[17],"and":[18,26,51,54,61,70,79,102],"disordered":[19,100,115],"proteins,":[20],"however,":[21],"occupy":[22],"distinct":[23],"structural":[24],"regimes,":[25],"we":[27,42],"investigate":[28],"how":[29],"choices":[31,44],"hold":[32],"up":[33],"across":[34],"them.":[35],"Using":[36],"a":[37,75,80,87,126,143],"minimal":[38],"C$\u03b1$":[39],"flow-matching":[40],"model,":[41],"ablate":[43],"architecture,":[46,155],"sequence":[47],"conditioning,":[48],"rigid-body":[49],"alignment":[50,103],"training":[52,150],"source,":[53],"evaluate":[55],"each":[56],"variant":[57],"against":[58],"experimental":[59],"SAXS":[60],"NMR":[62],"chemical-shift":[63],"data":[64],"partitioned":[65],"into":[66],"ordered,":[67],"disordered,":[68],"multi-domain":[69],"transitional":[71],"Mixture-of-experts":[73],"routing,":[74],"static":[76],"pair":[77],"representation":[78],"disorder":[81],"probe":[82],"have":[83],"no":[84],"detectable":[85],"effect,":[86],"smaller":[88,144],"language":[90],"model":[91],"performs":[92],"worse":[93],"on":[94,99],"ordered":[95],"proteins":[96,116],"but":[97],"not":[98],"ones,":[101],"in":[104],"the":[105,135,140,149,154,157],"loss":[106],"degrades":[107],"agreement":[108,121],"with":[109,117,122],"SAXS.":[110],"Replacing":[111],"coarse-grained":[112],"simulations":[113],"fragment-assembled":[118],"improves":[120],"chemical":[123],"shifts":[124],"at":[125,142],"cost":[127],"to":[128,148],"SAXS,":[129],"while":[130],"an":[131],"equal":[132],"mixture":[133],"two":[136],"keeps":[137],"most":[138],"gain":[141],"cost.":[145],"This":[146],"points":[147],"data,":[151],"rather":[152],"than":[153],"as":[156],"main":[158],"constraint.":[159]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}