{"id":"https://openalex.org/W7112436565","doi":null,"title":"Generative Diffusion Models Towards De Novo Protein Design","display_name":"Generative Diffusion Models Towards De Novo Protein Design","publication_year":2025,"publication_date":"2025-05-01","ids":{"openalex":"https://openalex.org/W7112436565"},"language":"en","primary_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/164143","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/1721.1/164143","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074628247","display_name":"Jason Yim","orcid":"https://orcid.org/0000-0003-0575-7400","observed_orcids":["https://orcid.org/0000-0003-0575-7400"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yim, Jason","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5074628247"],"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":0.9901999831199646,"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":0.9901999831199646,"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":0.00279999990016222,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0019000000320374966,"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/de-novo-protein-design","display_name":"de novo protein design","score":0.9940000176429749},{"id":"https://openalex.org/keywords/generative-diffusion-models","display_name":"generative diffusion models","score":0.9850000143051147},{"id":"https://openalex.org/keywords/protein-structure-generation","display_name":"protein structure generation","score":0.8730000257492065},{"id":"https://openalex.org/keywords/protein-sequence-generation","display_name":"protein sequence generation","score":0.9459999799728394},{"id":"https://openalex.org/keywords/riemannian-manifolds","display_name":"Riemannian manifolds","score":0.8960000276565552},{"id":"https://openalex.org/keywords/high-affinity-binders","display_name":"high-affinity binders","score":0.7929999828338623},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.453000009059906}],"concepts":[{"id":"https://openalex.org/C152769699","wikidata":"https://www.wikidata.org/wiki/Q410814","display_name":"Protein design","level":3,"score":0.7646999955177307},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.6219000220298767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5705999732017517},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5672000050544739},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.5388000011444092},{"id":"https://openalex.org/C147816474","wikidata":"https://www.wikidata.org/wiki/Q169525","display_name":"Protein engineering","level":3,"score":0.5199000239372253},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4366999864578247},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.42980000376701355},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3668999969959259},{"id":"https://openalex.org/C45475804","wikidata":"https://www.wikidata.org/wiki/Q6675846","display_name":"Loop modeling","level":4,"score":0.34700000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3467999994754791},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.34610000252723694},{"id":"https://openalex.org/C69131567","wikidata":"https://www.wikidata.org/wiki/Q2068215","display_name":"Structural bioinformatics","level":3,"score":0.3352000117301941},{"id":"https://openalex.org/C191908910","wikidata":"https://www.wikidata.org/wiki/Q862838","display_name":"Synthetic biology","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27149999141693115},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C169627665","wikidata":"https://www.wikidata.org/wiki/Q5767913","display_name":"Homology modeling","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.25429999828338623},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.2508000135421753},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dspace.mit.edu:1721.1/164143","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/1721.1/164143","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"}],"best_oa_location":null,"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/W4383957026","https://openalex.org/W4415065880","https://openalex.org/W4386629205","https://openalex.org/W4366520892","https://openalex.org/W4376108605","https://openalex.org/W4400600835","https://openalex.org/W7055885338","https://openalex.org/W7014909185","https://openalex.org/W7172236517","https://openalex.org/W4368374143"],"abstract_inverted_index":{"De":[0,216],"novo":[1,217],"protein":[2,15,55,60,76,109,153,161,171,214,218,231,271,276,292,325,369,377,387,430],"design":[3,61,162,172,219,277,378,388],"aims":[4,80,220,296],"to":[5,70,81,107,142,148,169,181,221,286,297,323,358,364,385,397],"generate":[6,87,108,149,200,222,303,324,365,416],"proteins":[7,202,223,418],"with":[8,28,176,203,224,244,392,419],"desired":[9,97,225,313],"functions":[10,226],"by":[11,113,174,227,329,390],"rationally":[12,228],"engineering":[13,229],"novel":[14,88,102,150,230,304,318,366],"structures":[16,89,110,154,232,305,326,370],"and":[17,90,111,124,133,151,155,178,194,212,233,306,327,340,349,367,371,394,410,428],"sequences.":[18,234],"The":[19,127,235,343],"structure":[20,189,236,405],"requires":[21,237],"modeling":[22,196,238,412],"continuous":[23,239],"3D":[24,240],"coordinates":[25,241],"of":[26,32,42,139,192,242,248,258,355,408],"atoms":[27,243],"rigid":[29,245],"biochemical":[30,246],"constraints":[31,247],"the":[33,37,54,72,137,145,188,249,253,270,288,353,361,404],"polymer":[34,250],"chain":[35,251],"while":[36,252],"sequence":[38,254],"is":[39,62,255,278],"a":[40,50,256,266],"series":[41,257],"discrete":[43,125,259,341],"amino":[44,260],"acids":[45,261],"that":[46,86,92,105,157,262,302,308,321,373],"should":[47,263],"fold":[48,264],"into":[49,265],"plausible":[51,267],"structure.":[52,268],"Understanding":[53,269],"function-structure-sequence":[56,272],"relationship":[57,73,273,289],"necessary":[58,274],"for":[59,275],"complex,":[63,279],"but":[64,280],"deep":[65,83,281,299],"learning":[66,84,282,300],"has":[67,283],"proven":[68,284],"promising":[69,285],"learn":[71,106,287,322],"from":[74,290],"large":[75,291],"datasets.":[77,293],"This":[78,294],"thesis":[79,295],"develop":[82,182,298,398],"models":[85,104,116,141,168,301,320,332,357,384],"sequences":[91,112,156,307,328,372],"can":[93,199,309,415],"be":[94,310],"guided":[95,311],"towards":[96,312],"functions.":[98,314],"We":[99,315],"first":[100,316],"describe":[101,317],"generative":[103,319],"developing":[114,330],"diffusion":[115,140,167,195,331,356,383,411],"over":[117,333],"general":[118,334],"state":[119,335],"spaces":[120,336],"including":[121,337],"Riemannian":[122,338],"manifolds":[123,339],"tokens.":[126,342],"resulting":[128,344],"methods":[129,345],"\u2013":[130,135,346,351],"FrameDiff,":[131,347],"FrameFlow,":[132,348],"MultiFlow":[134,350],"demonstrate":[136,352],"ability":[138,354],"extrapolate":[143,359],"beyond":[144,360],"training":[146,362],"data":[147,363],"diverse":[152,368],"pass":[158,374],"in":[159,204,375,420],"silico":[160,376],"filters.":[163,379],"Next,":[164,380],"we":[165,381],"apply":[166,382],"practical":[170,386],"challenges":[173,389],"collaborating":[175,391],"experimental":[177,393],"computational":[179,395],"biologists":[180,396],"RoseTTAFold":[183,193,399,409],"Diffusion":[184,400],"(RFdiffusion).":[185,401],"By":[186,402],"combining":[187,403],"prediction":[190,406],"capabilities":[191,407],"principles,":[197,413],"RFdiffusion":[198,414],"functional":[201,417],"vitro":[205,421],"validated":[206,422],"properties":[207,423],"such":[208,424],"as":[209,425],"high-affinity":[210,426],"binders":[211,427],"symmetric":[213,429],"assemblies.":[215,431]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-12-10T00:00:00"}