{"id":"https://openalex.org/W7162398143","doi":"https://doi.org/10.1186/s12859-026-06482-4","title":"ProtSeqGen: a novel deep learning model for protein sequence design","display_name":"ProtSeqGen: a novel deep learning model for protein sequence design","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162398143","doi":"https://doi.org/10.1186/s12859-026-06482-4","pmid":"https://pubmed.ncbi.nlm.nih.gov/42192491"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-026-06482-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06482-4","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12859-026-06482-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137051931","display_name":"Qiang Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Gao","raw_affiliation_strings":["Center for Data Science and Intelligent Computing, Nanjing Agricultural University, No. 666 Binjiang Avenue, Nanjing, 211800, Jiangsu, China","College of Artificial Intelligence, Nanjing Agricultural University, No. 666 Binjiang Avenue, Nanjing, 211800, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science and Intelligent Computing, Nanjing Agricultural University, No. 666 Binjiang Avenue, Nanjing, 211800, Jiangsu, China","institution_ids":["https://openalex.org/I119454577"]},{"raw_affiliation_string":"College of Artificial Intelligence, Nanjing Agricultural University, No. 666 Binjiang Avenue, Nanjing, 211800, Jiangsu, China","institution_ids":["https://openalex.org/I119454577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121204453","display_name":"Zhijin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210129412","display_name":"Anhui Provincial Hospital","ror":"https://ror.org/03n5gdd09","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210129412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijin Li","raw_affiliation_strings":["Department of Neurosurgery, Division of Life Science and Medicine, The First Affiliated Hospital of USTC (Anhui Provincial Hospital), University of Science and Technology of China, Hefei, 230036, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neurosurgery, Division of Life Science and Medicine, The First Affiliated Hospital of USTC (Anhui Provincial Hospital), University of Science and Technology of China, Hefei, 230036, Anhui, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210129412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137035902","display_name":"Yang Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Deng","raw_affiliation_strings":["School of Life Science and Technology, Harbin Institute of Technology, Harbin, 150001, Heilongjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Life Science and Technology, Harbin Institute of Technology, Harbin, 150001, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137076919","display_name":"Zhiwei Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiwei Ji","raw_affiliation_strings":["Center for Data Science and Intelligent Computing, Nanjing Agricultural University, No. 666 Binjiang Avenue, Nanjing, 211800, Jiangsu, China. Zhiwei.Ji@njau.edu.cn","College of Artificial Intelligence, Nanjing Agricultural University, No. 666 Binjiang Avenue, Nanjing, 211800, Jiangsu, China. Zhiwei.Ji@njau.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science and Intelligent Computing, Nanjing Agricultural University, No. 666 Binjiang Avenue, Nanjing, 211800, Jiangsu, China. Zhiwei.Ji@njau.edu.cn","institution_ids":["https://openalex.org/I119454577"]},{"raw_affiliation_string":"College of Artificial Intelligence, Nanjing Agricultural University, No. 666 Binjiang Avenue, Nanjing, 211800, Jiangsu, China. Zhiwei.Ji@njau.edu.cn","institution_ids":["https://openalex.org/I119454577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5137076919"],"corresponding_institution_ids":["https://openalex.org/I119454577"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45486912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","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":0.7994999885559082,"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":0.7994999885559082,"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":0.13019999861717224,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.013199999928474426,"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/deep-learning","display_name":"Deep learning","score":0.6990000009536743},{"id":"https://openalex.org/keywords/protein-design","display_name":"Protein design","score":0.647599995136261},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6044999957084656},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5479999780654907},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.5400000214576721},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.516700029373169},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5134999752044678},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.4537999927997589},{"id":"https://openalex.org/keywords/folding","display_name":"Folding (DSP implementation)","score":0.4498000144958496}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6990000009536743},{"id":"https://openalex.org/C152769699","wikidata":"https://www.wikidata.org/wiki/Q410814","display_name":"Protein design","level":3,"score":0.647599995136261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6295999884605408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6151999831199646},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6044999957084656},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5400000214576721},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.526199996471405},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.516700029373169},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.4537999927997589},{"id":"https://openalex.org/C2776545253","wikidata":"https://www.wikidata.org/wiki/Q5464292","display_name":"Folding (DSP implementation)","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C204328495","wikidata":"https://www.wikidata.org/wiki/Q847556","display_name":"Protein folding","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4000000059604645},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C147816474","wikidata":"https://www.wikidata.org/wiki/Q169525","display_name":"Protein engineering","level":3,"score":0.36559998989105225},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.3546999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.3098999857902527},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C132917006","wikidata":"https://www.wikidata.org/wiki/Q5250436","display_name":"Deep sequencing","level":4,"score":0.29589998722076416},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.28839999437332153},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2782000005245209},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C30711495","wikidata":"https://www.wikidata.org/wiki/Q289411","display_name":"Sequence space","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25380000472068787}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D015202","descriptor_name":"Protein Engineering","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D015202","descriptor_name":"Protein Engineering","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D015202","descriptor_name":"Protein Engineering","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-026-06482-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06482-4","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:42192491","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42192491","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13390367","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13390367/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13390367/pdf/12859_2026_Article_6482.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:4c62fa467b8346eab273975de65f8372","is_oa":false,"landing_page_url":"https://doaj.org/article/4c62fa467b8346eab273975de65f8372","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-026-06482-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06482-4","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2052171678","display_name":null,"funder_award_id":"106/804001","funder_id":"https://openalex.org/F4320325211","funder_display_name":"Nanjing Agricultural University"}],"funders":[{"id":"https://openalex.org/F4320313675","display_name":"University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39"},{"id":"https://openalex.org/F4320325211","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1954297438","https://openalex.org/W1969644422","https://openalex.org/W1996755112","https://openalex.org/W2038139711","https://openalex.org/W2164718466","https://openalex.org/W2280207768","https://openalex.org/W2557252183","https://openalex.org/W2743257006","https://openalex.org/W2785273668","https://openalex.org/W2790952361","https://openalex.org/W2899664253","https://openalex.org/W2991877021","https://openalex.org/W2996986155","https://openalex.org/W2997234557","https://openalex.org/W3010339412","https://openalex.org/W3101977221","https://openalex.org/W3134186384","https://openalex.org/W3164018573","https://openalex.org/W3164046276","https://openalex.org/W3177828909","https://openalex.org/W4214937996","https://openalex.org/W4296032638","https://openalex.org/W4304606876","https://openalex.org/W4309210771","https://openalex.org/W4372348062","https://openalex.org/W4378782355","https://openalex.org/W4385073318","https://openalex.org/W4391383720","https://openalex.org/W4391431979","https://openalex.org/W4393392279","https://openalex.org/W4393552888","https://openalex.org/W4402650071","https://openalex.org/W4409483513","https://openalex.org/W4410314102","https://openalex.org/W4411382243","https://openalex.org/W4414149931","https://openalex.org/W4414169548","https://openalex.org/W4414657190","https://openalex.org/W4415795479","https://openalex.org/W7117113816"],"related_works":[],"abstract_inverted_index":{"The":[0],"protein":[1,30,71,146,153],"inverse":[2,147],"folding":[3,148],"problem,":[4,149],"which":[5],"is":[6],"the":[7,145],"task":[8],"of":[9],"designing":[10],"an":[11],"amino":[12,89],"acid":[13],"sequence":[14,111],"that":[15,60],"will":[16],"fold":[17],"into":[18],"a":[19,24,56,65,82,92,139],"specified":[20],"backbone":[21],"structure,":[22],"represents":[23],"fundamental":[25],"challenge":[26],"in":[27],"de":[28,151],"novo":[29,152],"design.":[31],"Existing":[32],"computational":[33],"methods,":[34],"including":[35],"deep":[36,57],"learning-based":[37],"approaches,":[38],"often":[39],"fail":[40],"to":[41,114,144],"simultaneously":[42],"optimize":[43],"accuracy,":[44],"stability,":[45],"efficiency,":[46],"and":[47,86,101,105,141],"generalizability":[48],"across":[49],"diverse":[50,128],"folds.":[51],"Here,":[52],"we":[53],"present":[54],"ProtSeqGen,":[55],"learning":[58],"model":[59],"overcomes":[61],"these":[62],"limitations":[63],"through":[64],"multi-stage":[66],"graph-based":[67],"framework.":[68],"ProtSeqGen":[69,108,137],"encodes":[70],"structures":[72],"as":[73,138],"local":[74],"geometric":[75],"graphs,":[76],"explicitly":[77],"models":[78],"residue-level":[79],"interactions":[80],"using":[81],"message-passing":[83],"neural":[84],"network,":[85],"predicts":[87],"optimal":[88],"acids":[90],"with":[91,155],"multi-layer":[93],"perceptron.":[94],"When":[95],"trained":[96],"on":[97,103],"CATH":[98],"4.2":[99],"dataset":[100],"evaluated":[102],"standard":[104],"challenging":[106],"benchmarks,":[107],"achieved":[109],"superior":[110],"recovery":[112],"compared":[113],"numerous":[115],"state-of-the-art":[116],"(SOTA)":[117],"methods.":[118],"It":[119],"also":[120],"generated":[121],"accurate,":[122],"designable":[123],"sequences":[124],"for":[125],"nine":[126],"topologically":[127],"proteins,":[129],"demonstrating":[130],"remarkable":[131],"generalization":[132],"capability.":[133],"These":[134],"results":[135],"establish":[136],"robust":[140],"scalable":[142],"solution":[143],"propelling":[150],"design":[154],"high":[156],"structural":[157],"precision.":[158]},"counts_by_year":[],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2026-05-27T00:00:00"}