{"id":"https://openalex.org/W7221069738","doi":"https://doi.org/10.3390/ijms27198914","title":"Protein Language Models Identify Early Folding Residues as Critical Hotspots for Pathogenic Variants and Cancer Prognosis","display_name":"Protein Language Models Identify Early Folding Residues as Critical Hotspots for Pathogenic Variants and Cancer Prognosis","publication_year":2026,"publication_date":"2026-10-07","ids":{"openalex":"https://openalex.org/W7221069738","doi":"https://doi.org/10.3390/ijms27198914","pmid":"https://pubmed.ncbi.nlm.nih.gov/42884156","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13666245"},"language":"en","primary_location":{"id":"doi:10.3390/ijms27198914","doi":"https://doi.org/10.3390/ijms27198914","is_oa":true,"landing_page_url":"https://doi.org/10.3390/ijms27198914","pdf_url":null,"source":{"id":"https://openalex.org/S10623703","display_name":"International Journal of Molecular Sciences","issn_l":"1422-0067","issn":["1422-0067","1661-6596"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","medline","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Molecular Sciences","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/ijms27198914","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140135702","display_name":"Lisha Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4405253479","display_name":"National Supercomputing Center in Jinan","ror":"https://ror.org/00q2tt650","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405253479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lisha Guo","raw_affiliation_strings":["Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250100, China","Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan 250300, China","National Institute of Health Data Science of China, Shandong University, Jinan 250100, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250100, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan 250300, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748","https://openalex.org/I4405253479"]},{"raw_affiliation_string":"National Institute of Health Data Science of China, Shandong University, Jinan 250100, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088128294","display_name":"Fu Yuan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuchong Yuan","raw_affiliation_strings":["Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250100, China","National Institute of Health Data Science of China, Shandong University, Jinan 250100, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250100, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"National Institute of Health Data Science of China, Shandong University, Jinan 250100, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151859000","display_name":"Na Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Zhou","raw_affiliation_strings":["Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250100, China","National Institute of Health Data Science of China, Shandong University, Jinan 250100, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250100, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"National Institute of Health Data Science of China, Shandong University, Jinan 250100, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133300376","display_name":"Minghui Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghui Zhao","raw_affiliation_strings":["Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250100, China","National Institute of Health Data Science of China, Shandong University, Jinan 250100, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250100, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"National Institute of Health Data Science of China, Shandong University, Jinan 250100, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011011364","display_name":"Ruotong Liu","orcid":"https://orcid.org/0009-0008-1879-1433","observed_orcids":["https://orcid.org/0009-0008-1879-1433"]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruotong Liu","raw_affiliation_strings":["Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250100, China","National Institute of Health Data Science of China, Shandong University, Jinan 250100, China"],"raw_orcid":"https://orcid.org/0009-0008-1879-1433","affiliations":[{"raw_affiliation_string":"Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250100, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"National Institute of Health Data Science of China, Shandong University, Jinan 250100, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101947298","display_name":"Ming Jing","orcid":"https://orcid.org/0000-0001-5425-1188","observed_orcids":["https://orcid.org/0000-0001-5425-1188"]},"institutions":[{"id":"https://openalex.org/I4210151294","display_name":"Shandong Women\u2019s University","ror":"https://ror.org/03rp8h078","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151294"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Jing","raw_affiliation_strings":["School of Data and Computer Science, Shandong Women\u2019s University, Jinan 250300, China"],"raw_orcid":"https://orcid.org/0000-0001-5425-1188","affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Shandong Women\u2019s University, Jinan 250300, China","institution_ids":["https://openalex.org/I4210151294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021643162","display_name":"Klaas Antoni Feenstra","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"K. Anton Feenstra","raw_affiliation_strings":["IBIVU\u2013Center for Integrative Bioinformatics, Department of Computer Science, Vrije Universiteit Amsterdam, 1081HV Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBIVU\u2013Center for Integrative Bioinformatics, Department of Computer Science, Vrije Universiteit Amsterdam, 1081HV Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027816412","display_name":"Qingzhen Hou","orcid":"https://orcid.org/0000-0002-7655-0899","observed_orcids":["https://orcid.org/0000-0002-7655-0899"]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingzhen Hou","raw_affiliation_strings":["Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250100, China","National Institute of Health Data Science of China, Shandong University, Jinan 250100, China"],"raw_orcid":"https://orcid.org/0000-0002-7655-0899","affiliations":[{"raw_affiliation_string":"Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250100, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"National Institute of Health Data Science of China, Shandong University, Jinan 250100, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5021643162","https://openalex.org/A5027816412"],"corresponding_institution_ids":["https://openalex.org/I154099455","https://openalex.org/I865915315"],"apc_list":{"value":2900,"currency":"CHF","value_usd":3499},"apc_paid":{"value":2900,"currency":"CHF","value_usd":3499},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66714741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"19","first_page":"8914","last_page":"8914"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.8788999915122986,"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":0.8788999915122986,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.08290000259876251,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.01850000023841858,"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/protein-folding","display_name":"protein folding","score":0.7379999756813049},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.9039999842643738},{"id":"https://openalex.org/keywords/pathogenic-variants","display_name":"pathogenic variants","score":0.7760000228881836},{"id":"https://openalex.org/keywords/cancer-prognosis","display_name":"cancer prognosis","score":0.7329999804496765},{"id":"https://openalex.org/keywords/protein-stability","display_name":"protein stability","score":0.6499999761581421},{"id":"https://openalex.org/keywords/protein-misfolding","display_name":"protein misfolding","score":0.6859999895095825},{"id":"https://openalex.org/keywords/clinvar","display_name":"ClinVar","score":0.5580000281333923},{"id":"https://openalex.org/keywords/tp53","display_name":"TP53","score":0.6819999814033508},{"id":"https://openalex.org/keywords/overall-survival","display_name":"overall survival","score":0.5130000114440918},{"id":"https://openalex.org/keywords/sequence-based-prediction","display_name":"sequence-based prediction","score":0.5460000038146973},{"id":"https://openalex.org/keywords/pan-cancer","display_name":"pan-cancer","score":0.5519999861717224}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6995000243186951},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6402999758720398},{"id":"https://openalex.org/C204328495","wikidata":"https://www.wikidata.org/wiki/Q847556","display_name":"Protein folding","level":2,"score":0.5264999866485596},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C2776545253","wikidata":"https://www.wikidata.org/wiki/Q5464292","display_name":"Folding (DSP implementation)","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.4675999879837036},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.44339999556541443},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.41519999504089355},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4147000014781952},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.4041999876499176},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.37790000438690186},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.34940001368522644},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.34860000014305115},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C66153294","wikidata":"https://www.wikidata.org/wiki/Q899291","display_name":"CASP","level":4,"score":0.3107999861240387},{"id":"https://openalex.org/C2988375501","wikidata":"https://www.wikidata.org/wiki/Q847556","display_name":"Protein stability","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.3003000020980835},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C69131567","wikidata":"https://www.wikidata.org/wiki/Q2068215","display_name":"Structural bioinformatics","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.29019999504089355},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C2993683473","wikidata":"https://www.wikidata.org/wiki/Q30693176","display_name":"Amino acid substitution","level":4,"score":0.2685999870300293},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C2994376932","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Amino acid residue","level":4,"score":0.26249998807907104},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C2781452922","wikidata":"https://www.wikidata.org/wiki/Q2892805","display_name":"Proteostasis","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2554999887943268}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000473","qualifier_name":"pathology","is_major_topic":true},{"descriptor_ui":"D011379","descriptor_name":"Prognosis","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":true}],"locations_count":4,"locations":[{"id":"doi:10.3390/ijms27198914","doi":"https://doi.org/10.3390/ijms27198914","is_oa":true,"landing_page_url":"https://doi.org/10.3390/ijms27198914","pdf_url":null,"source":{"id":"https://openalex.org/S10623703","display_name":"International Journal of Molecular Sciences","issn_l":"1422-0067","issn":["1422-0067","1661-6596"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","medline","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Molecular Sciences","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13666245","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13666245/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13666245/pdf/ijms-27-08914.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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Int J Mol Sci","raw_type":"Text"},{"id":"pmid:42884156","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42884156","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,"listed_in":[],"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":"International journal of molecular sciences","raw_type":"Journal Article"},{"id":"pmh:oai:research.vu.nl:openaire/d7f1c91f-e05a-4a02-b998-73434fbc811a","doi":null,"is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/d7f1c91f-e05a-4a02-b998-73434fbc811a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Guo, L, Yuan, F, Zhou, N, Zhao, M, Liu, R, Jing, M, Feenstra, K A & Hou, Q 2026, 'Protein Language Models Identify Early Folding Residues as Critical Hotspots for Pathogenic Variants and Cancer Prognosis', International Journal of Molecular Sciences, vol. 27, no. 19, 8914, pp. 1-22. https://doi.org/10.3390/ijms27198914","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.3390/ijms27198914","doi":"https://doi.org/10.3390/ijms27198914","is_oa":true,"landing_page_url":"https://doi.org/10.3390/ijms27198914","pdf_url":null,"source":{"id":"https://openalex.org/S10623703","display_name":"International Journal of Molecular Sciences","issn_l":"1422-0067","issn":["1422-0067","1661-6596"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","medline","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Molecular Sciences","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.8371999859809875,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G441919694","display_name":null,"funder_award_id":"82473733","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5905733410","display_name":null,"funder_award_id":"ZR2024ZD18","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221069738.pdf","grobid_xml":"https://content.openalex.org/works/W7221069738.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1973897761","https://openalex.org/W1988624456","https://openalex.org/W1993543753","https://openalex.org/W2059145105","https://openalex.org/W2059706314","https://openalex.org/W2082704080","https://openalex.org/W2107165577","https://openalex.org/W2119097398","https://openalex.org/W2143238378","https://openalex.org/W2150444353","https://openalex.org/W2156125289","https://openalex.org/W2174708591","https://openalex.org/W2376573086","https://openalex.org/W2417483443","https://openalex.org/W2614053601","https://openalex.org/W2750565002","https://openalex.org/W2752403657","https://openalex.org/W2913078802","https://openalex.org/W2955168413","https://openalex.org/W3029661147","https://openalex.org/W3094550675","https://openalex.org/W3146944767","https://openalex.org/W3165745490","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3197273087","https://openalex.org/W3198067740","https://openalex.org/W3209580699","https://openalex.org/W4220873173","https://openalex.org/W4223623159","https://openalex.org/W4327550249","https://openalex.org/W4386861232","https://openalex.org/W4386886999","https://openalex.org/W4390610516","https://openalex.org/W4404641556"],"related_works":["https://openalex.org/W2750565002","https://openalex.org/W4225891318","https://openalex.org/W2898987406","https://openalex.org/W3198067740","https://openalex.org/W4416192709","https://openalex.org/W4300817677","https://openalex.org/W7130857691","https://openalex.org/W4309585072","https://openalex.org/W7212033980","https://openalex.org/W649455540"],"abstract_inverted_index":{"Identifying":[0],"the":[1,15,21,68,127,138,178,198],"specific":[2],"residues":[3,29],"that":[4,105],"initiate":[5],"protein":[6,12,49,174],"folding":[7,28,180],"is":[8],"critical":[9,187],"for":[10,197],"understanding":[11],"stability":[13],"and":[14,37,75,129,151,192],"mechanisms":[16],"of":[17,25,120,159,189,201],"misfolding-related":[18],"diseases.":[19],"However,":[20],"systematic,":[22],"proteome-wide":[23],"identification":[24,200],"these":[26,171],"early":[27,179],"(EFRs)":[30],"has":[31],"been":[32],"hampered":[33],"by":[34,176],"both":[35],"experimental":[36],"computational":[38],"limitations.":[39],"Here,":[40],"we":[41,103],"present":[42],"LMEFold,":[43],"a":[44,168,194],"deep":[45],"learning":[46],"framework":[47,196],"using":[48,205],"language":[50],"models":[51],"(PLMs)":[52],"to":[53,93,118],"accurately":[54],"predict":[55],"EFRs":[56,115,185],"from":[57,123],"amino":[58],"acid":[59],"sequence":[60,206],"alone.":[61],"LMEFold":[62,92],"outperforms":[63],"existing":[64],"sequence-based":[65],"predictors":[66],"on":[67],"Start2Fold":[69],"benchmark":[70],"(ROC":[71],"AUC":[72],"=":[73],"0.831),":[74],"its":[76],"predicted":[77],"scores":[78],"show":[79],"consistent":[80],"associations":[81],"with":[82,147],"independent":[83],"HDX-NMR":[84],"protection-factor":[85],"measurements,":[86],"providing":[87],"complementary":[88],"biophysical":[89],"evidence.":[90],"Applying":[91],"annotate":[94],"over":[95],"6.6":[96],"million":[97],"variants":[98,122,172],"across":[99],"diverse":[100],"genomic":[101],"datasets,":[102],"find":[104],"pathogenic":[106,190],"mutations":[107,144],"curated":[108],"in":[109,137],"ClinVar":[110],"are":[111,145],"significantly":[112,152],"enriched":[113],"within":[114],"(~17%)":[116],"compared":[117],"millions":[119],"population":[121],"large-scale":[124],"cohorts":[125],"including":[126],"UKB":[128],"gnomAD":[130],"databases":[131],"(~10%,":[132],"P":[133],"<":[134],"0.001).":[135],"Critically,":[136],"MSK-MET":[139],"pan-cancer":[140],"clinical":[141],"cohort,":[142],"EFR":[143],"associated":[146],"severe":[148],"functional":[149],"disruption":[150],"reduced":[153],"overall":[154],"patient":[155],"survival.":[156],"Structural":[157],"analysis":[158],"hotspot":[160],"cancer":[161],"mutations,":[162],"such":[163],"as":[164,186],"TP53":[165],"p.Y163C,":[166],"suggests":[167],"mechanism":[169],"whereby":[170],"destabilize":[173],"structure":[175],"disrupting":[177],"core.":[181],"Our":[182],"work":[183],"establishes":[184],"sites":[188],"vulnerability":[191],"provides":[193],"powerful":[195],"rapid":[199],"folding-centric":[202],"prognostic":[203],"markers":[204],"only.":[207]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-10T00:00:00"}