{"id":"https://openalex.org/W7224340540","doi":"https://doi.org/10.64898/2026.10.27.762190","title":"De novo Protein Generating Model via Structure-Aware Graph Neural Networks","display_name":"De novo Protein Generating Model via Structure-Aware Graph Neural Networks","publication_year":2026,"publication_date":"2026-10-28","ids":{"openalex":"https://openalex.org/W7224340540","doi":"https://doi.org/10.64898/2026.10.27.762190"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.27.762190","doi":"https://doi.org/10.64898/2026.10.27.762190","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.27.762190","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/28/2026.10.27.762190.full.pdf","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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/28/2026.10.27.762190.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160040837","display_name":"Chance M Gammill","orcid":"https://orcid.org/0009-0002-6037-7371","observed_orcids":["https://orcid.org/0009-0002-6037-7371"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chance Gammill","raw_affiliation_strings":["Department of Biomedical Engineering, University of Texas at Dallas, United States of America"],"raw_orcid":"https://orcid.org/0009-0002-6037-7371","affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, University of Texas at Dallas, United States of America","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027973431","display_name":"Lakshman S. Tamil","orcid":"https://orcid.org/0000-0003-4523-9376","observed_orcids":["https://orcid.org/0000-0003-4523-9376"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lakshman Tamil","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at Dallas, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-4523-9376","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Dallas, United States of America","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5160040837"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9922000169754028,"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":0.9922000169754028,"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":0.003800000064074993,"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":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/de-novo-protein-design","display_name":"de novo protein design","score":0.9800000190734863},{"id":"https://openalex.org/keywords/protein-conformation-prediction","display_name":"protein conformation prediction","score":0.8220000267028809},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.8949999809265137},{"id":"https://openalex.org/keywords/esmfold","display_name":"ESMFold","score":0.7540000081062317},{"id":"https://openalex.org/keywords/structural-accuracy","display_name":"structural accuracy","score":0.5199999809265137}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6366999745368958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6280999779701233},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.5331000089645386},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.521399974822998},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C152769699","wikidata":"https://www.wikidata.org/wiki/Q410814","display_name":"Protein design","level":3,"score":0.5065000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49320000410079956},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.475600004196167},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.4609000086784363},{"id":"https://openalex.org/C200307862","wikidata":"https://www.wikidata.org/wiki/Q7797175","display_name":"Threading (protein sequence)","level":3,"score":0.4453999996185303},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.4359999895095825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.423799991607666},{"id":"https://openalex.org/C45475804","wikidata":"https://www.wikidata.org/wiki/Q6675846","display_name":"Loop modeling","level":4,"score":0.4025000035762787},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.37700000405311584},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.37619999051094055},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C132677234","wikidata":"https://www.wikidata.org/wiki/Q3273544","display_name":"Structural motif","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C69131567","wikidata":"https://www.wikidata.org/wiki/Q2068215","display_name":"Structural bioinformatics","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2988224531","wikidata":"https://www.wikidata.org/wiki/Q20830730","display_name":"Network structure","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.27.762190","doi":"https://doi.org/10.64898/2026.10.27.762190","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.27.762190","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/28/2026.10.27.762190.full.pdf","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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.27.762190","doi":"https://doi.org/10.64898/2026.10.27.762190","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.27.762190","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/28/2026.10.27.762190.full.pdf","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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224340540.pdf","grobid_xml":"https://content.openalex.org/works/W7224340540.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2899663614","https://openalex.org/W3037932933"],"related_works":["https://openalex.org/W7162398143","https://openalex.org/W4387310732","https://openalex.org/W4412454085","https://openalex.org/W3162262357","https://openalex.org/W4366520892","https://openalex.org/W4391530977","https://openalex.org/W7224107583","https://openalex.org/W7133221268","https://openalex.org/W7138343675","https://openalex.org/W3015047409"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"focus":[2],"of":[3,39,58,174],"this":[4,26],"paper":[5],"is":[6,15,101,131],"to":[7,134],"create":[8],"a":[9,30,51,78,87,106,175,182],"protein":[10,66,149,188],"conformation":[11,160],"prediction":[12,46,151],"model":[13,64,92,168,177,183],"that":[14,42,81,100,128,140,148],"optimized":[16],"for":[17,36,171,185],"structural":[18,52,84,94,137,159],"accuracy":[19,138],"rather":[20],"than":[21],"sequence":[22,76,108,116,123,129,150],"recovery.":[23,124],"To":[24],"achieve":[25,135],"goal,":[27],"we":[28],"created":[29],"graph":[31],"neural":[32],"network":[33],"(GNN)":[34],"[19]":[35],"the":[37,59,172],"design":[38],"computational":[40],"proteins":[41,141],"integrates":[43],"differentiable":[44],"structure":[45,169],"through":[47],"ESMFold":[48],"[13]":[49],"via":[50],"loss":[53,80],"function,":[54],"allowing":[55],"direct":[56,115],"optimization":[57],"3D":[60],"conformational":[61],"accuracy.":[62],"Our":[63,125],"takes":[65],"backbone":[67],"coordinates":[68],"as":[69],"input":[70],"and":[71,98,119,139,167],"predicts":[72],"an":[73],"amino":[74],"acid":[75],"using":[77],"composite":[79],"heavily":[82],"weights":[83],"similarity.":[85],"On":[86],"matched":[88],"evaluation":[89],"sample,":[90],"our":[91],"achieves":[93],"precision":[95],"(RMSD,":[96],"TM-score,":[97],"GDT-TS)":[99],"statistically":[102],"indistinguishable":[103],"from":[104],"ProteinMPNN,":[105],"leading":[107],"recovery-focused":[109],"method,":[110],"despite":[111],"training":[112,165,173],"with":[113],"no":[114],"recovery":[117,130],"supervision":[118],"substantially":[120],"lower":[121],"native":[122],"results":[126],"demonstrate":[127],"not":[132],"necessary":[133],"competitive":[136],"can":[142],"possess":[143],"multiple":[144],"non-unique":[145],"solutions,":[146],"suggesting":[147],"models":[152],"may":[153],"perform":[154],"comparably":[155],"well":[156],"under":[157],"purely":[158],"training.":[161],"This":[162],"distinction":[163],"in":[164],"data":[166],"allows":[170],"protein-generating":[176],"on":[178],"non-natural":[179],"proteins.":[180],"Creating":[181],"designed":[184],"de":[186],"novo":[187],"generation.":[189]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-30T00:00:00"}