{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T03:11:14Z","timestamp":1773112274157,"version":"3.50.1"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2023,9,22]],"date-time":"2023-09-22T00:00:00Z","timestamp":1695340800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shanghai Artificial Intelligence Laboratory"},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2020B1515020048"],"award-info":[{"award-number":["2020B1515020048"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322608"],"award-info":[{"award-number":["62322608"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976250"],"award-info":[{"award-number":["61976250"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Proteins play crucial roles in biological processes, with their functions being closely tied to thermodynamic stability. However, measuring stability changes upon point mutations of amino acid residues using physical methods can be time-consuming. In recent years, several computational methods for protein thermodynamic stability prediction (PTSP) based on deep learning have emerged. Nevertheless, these approaches either overlook the natural topology of protein structures or neglect the inherent noisy samples resulting from theoretical calculation or experimental errors.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We propose a novel Global-Local Graph Neural Network powered by Unbiased Curriculum Learning for the PTSP task. Our method first builds a Siamese graph neural network to extract protein features before and after mutation. Since the graph\u2019s topological changes stem from local node mutations, we design a local feature transformation module to make the model focus on the mutated site. To address model bias caused by noisy samples, which represent unavoidable errors from physical experiments, we introduce an unbiased curriculum learning method. This approach effectively identifies and re-weights noisy samples during the training process. Extensive experiments demonstrate that our proposed method outperforms advanced protein stability prediction methods, and surpasses state-of-the-art learning methods for regression prediction tasks.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>All code and data\u00a0is available at https:\/\/github.com\/haifangong\/UCL-GLGNN.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad589","type":"journal-article","created":{"date-parts":[[2023,9,23]],"date-time":"2023-09-23T04:03:57Z","timestamp":1695441837000},"source":"Crossref","is-referenced-by-count":17,"title":["Unbiased curriculum learning enhanced global-local graph neural network for protein thermodynamic stability prediction"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2749-6830","authenticated-orcid":false,"given":"Haifan","family":"Gong","sequence":"first","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory , Shanghai 200000, China"},{"name":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou 510000, China"},{"name":"SRIBD, Chinese University of Hong Kong (Shenzhen) , Shenzhen 518000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6444-292X","authenticated-orcid":false,"given":"Yumeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University , Shanghai 200000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2211-5138","authenticated-orcid":false,"given":"Chenhe","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou 510000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2486-6071","authenticated-orcid":false,"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Qilu Hospital, Shandong University , Shandong 250000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1440-3340","authenticated-orcid":false,"given":"Guanqi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou 510000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bilin","family":"Liang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory , Shanghai 200000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9120-9843","authenticated-orcid":false,"given":"Haofeng","family":"Li","sequence":"additional","affiliation":[{"name":"SRIBD, Chinese University of Hong Kong (Shenzhen) , Shenzhen 518000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lanxuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory , Shanghai 200000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9233-4363","authenticated-orcid":false,"given":"Jie","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory , Shanghai 200000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou 510000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"2024030711345989500_btad589-B1","doi-asserted-by":"crossref","first-page":"3031","DOI":"10.1021\/acs.jctc.7b00125","article-title":"The rosetta all-atom energy function for macromolecular modeling and design","volume":"13","author":"Alford","year":"2017","journal-title":"J Chem Theory Comput"},{"key":"2024030711345989500_btad589-B2","doi-asserted-by":"crossref","first-page":"245403","DOI":"10.1088\/1361-6463\/abedfb","article-title":"An antisymmetric neural network to predict free energy changes in protein variants","volume":"54","author":"Benevenuta","year":"2021","journal-title":"J Phys D Appl Phys"},{"key":"2024030711345989500_btad589-B3","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1145\/1553374.1553380","article-title":"Curriculum learning","volume":"382","author":"Bengio","year":"2009","journal-title":"ICML"},{"key":"2024030711345989500_btad589-B4","first-page":"4308","author":"Castells"},{"key":"2024030711345989500_btad589-B5","doi-asserted-by":"crossref","first-page":"e0253411","DOI":"10.1371\/journal.pone.0253411","article-title":"PDBrenum: a webserver and program providing protein data bank files renumbered according to their uniprot sequences","volume":"16","author":"Faezov","year":"2021","journal-title":"PLoS One"},{"key":"2024030711345989500_btad589-B6","doi-asserted-by":"crossref","first-page":"2816","DOI":"10.1093\/bioinformatics\/btv291","article-title":"INPS: predicting the impact of non-synonymous variations on protein stability from sequence","volume":"31","author":"Fariselli","year":"2015","journal-title":"Bioinformatics"},{"key":"2024030711345989500_btad589-B7"},{"key":"2024030711345989500_btad589-B8","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1146\/annurev.bb.17.060188.002315","article-title":"Conformational substates in proteins","volume":"17","author":"Frauenfelder","year":"1988","journal-title":"Annu Rev Biophys Biophys Chem"},{"key":"2024030711345989500_btad589-B9","first-page":"248","author":"Gong","year":"2022"},{"key":"2024030711345989500_btad589-B10","article-title":"Inductive representation learning on large graphs","volume":"1024\u201334","author":"Hamilton","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024030711345989500_btad589-B11","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1146\/annurev-biochem-061516-044518","article-title":"Protein misfolding diseases","volume":"86","author":"Hartl","year":"2017","journal-title":"Annu Rev Biochem"},{"key":"2024030711345989500_btad589-B12","doi-asserted-by":"crossref","first-page":"btad011","DOI":"10.1093\/bioinformatics\/btad011","article-title":"Predicting protein stability changes upon mutation using a simple orientational potential","volume":"39","author":"Hern\u00e1ndez","year":"2023","journal-title":"Bioinformatics"},{"key":"2024030711345989500_btad589-B13","author":"Huang","year":"2022"},{"key":"2024030711345989500_btad589-B14","author":"Ingraham","year":"2019."},{"key":"2024030711345989500_btad589-B15","author":"Jing","year":"2021"},{"key":"2024030711345989500_btad589-B16","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with alphafold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2024030711345989500_btad589-B17","author":"Kipf","year":"2017"},{"key":"2024030711345989500_btad589-B18","doi-asserted-by":"crossref","first-page":"e1008291","DOI":"10.1371\/journal.pcbi.1008291","article-title":"Predicting changes in protein thermodynamic stability upon point mutation with deep 3D convolutional neural networks","volume":"16","author":"Li","year":"2020","journal-title":"PLoS Comput Biol"},{"key":"2024030711345989500_btad589-B19","doi-asserted-by":"crossref","first-page":"3273","DOI":"10.1038\/s41467-022-30936-x","article-title":"The 3D mutational constraint on amino acid sites in the human proteome","volume":"13","author":"Li","year":"2022","journal-title":"Nat Commun"},{"key":"2024030711345989500_btad589-B20","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1186\/s12859-022-04950-1","article-title":"Risk stratification and pathway analysis based on graph neural network and interpretable algorithm","volume":"23","author":"Liang","year":"2022","journal-title":"BMC Bioinformatics"},{"key":"2024030711345989500_btad589-B22","author":"Lv","year":"2021"},{"key":"2024030711345989500_btad589-B23","doi-asserted-by":"crossref","first-page":"bbaa074","DOI":"10.1093\/bib\/bbaa074","article-title":"Predicting the stability of mutant proteins by computational approaches: an overview","volume":"22","author":"Marabotti","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024030711345989500_btad589-B24","doi-asserted-by":"crossref","first-page":"D170","DOI":"10.1093\/nar\/gkw1081","article-title":"Uniclust databases of clustered and deeply annotated protein sequences and alignments","volume":"45","author":"Mirdita","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2024030711345989500_btad589-B25","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1186\/s12859-019-2923-1","article-title":"DDGun: an untrained method for the prediction of protein stability changes upon single and multiple point variations","volume":"20","author":"Montanucci","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2024030711345989500_btad589-B26","doi-asserted-by":"crossref","first-page":"bbab555","DOI":"10.1093\/bib\/bbab555","article-title":"Predicting protein stability changes upon single-point mutation: a thorough comparison of the available tools on a new dataset","volume":"23","author":"Pancotti","year":"2022","journal-title":"Brief Bioinform"},{"key":"2024030711345989500_btad589-B27","doi-asserted-by":"crossref","first-page":"W229","DOI":"10.1093\/nar\/gkx439","article-title":"SDM: a server for predicting effects of mutations on protein stability","volume":"45","author":"Pandurangan","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2024030711345989500_btad589-B28","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1016\/j.sbi.2004.06.002","article-title":"Advances in computational protein design","volume":"14","author":"Park","year":"2004","journal-title":"Curr Opin Struct Biol"},{"key":"2024030711345989500_btad589-B29","author":"Platanios","year":"2019"},{"key":"2024030711345989500_btad589-B30","doi-asserted-by":"crossref","first-page":"3659","DOI":"10.1093\/bioinformatics\/bty348","article-title":"Quantification of biases in predictions of protein stability changes upon mutations","volume":"34","author":"Pucci","year":"2018","journal-title":"Bioinformatics"},{"key":"2024030711345989500_btad589-B31","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1038\/nmeth.1818","article-title":"HHblits: lightning-fast iterative protein sequence searching by HMM\u2013HMM alignment","volume":"9","author":"Remmert","year":"2011","journal-title":"Nat Methods"},{"key":"2024030711345989500_btad589-B32","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1002\/pro.3942","article-title":"Dynamut2: assessing changes in stability and flexibility upon single and multiple point missense mutations","volume":"30","author":"Rodrigues","year":"2021","journal-title":"Protein Sci"},{"key":"2024030711345989500_btad589-B33","first-page":"9323","author":"Satorras","year":"2021"},{"key":"2024030711345989500_btad589-B34","doi-asserted-by":"crossref","first-page":"3919","DOI":"10.1016\/j.jmb.2013.07.014","article-title":"Molecular mechanisms of disease-causing missense mutations","volume":"425","author":"Stefl","year":"2013","journal-title":"J Mol Biol"},{"key":"2024030711345989500_btad589-B35","doi-asserted-by":"crossref","first-page":"D319","DOI":"10.1093\/nar\/gkaa981","article-title":"FireProtDB: database of manually curated protein stability data","volume":"49","author":"Stourac","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2024030711345989500_btad589-B36","first-page":"378","author":"Torgo"},{"key":"2024030711345989500_btad589-B37","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"2024030711345989500_btad589-B38","first-page":"1238","author":"Wang","year":"2021"},{"key":"2024030711345989500_btad589-B39","doi-asserted-by":"crossref","first-page":"2178","DOI":"10.1093\/bioinformatics\/btac088","article-title":"Multi-level attention graph neural network based on co-expression gene modules for disease diagnosis and prognosis","volume":"38","author":"Xing","year":"2022","journal-title":"Bioinformatics"},{"key":"2024030711345989500_btad589-B40","author":"Xu","year":"2019"},{"key":"2024030711345989500_btad589-B41","author":"Yan","year":"2023."},{"key":"2024030711345989500_btad589-B42","first-page":"9952","author":"Yang","year":"2020"},{"key":"2024030711345989500_btad589-B43","doi-asserted-by":"crossref","first-page":"2765","DOI":"10.1109\/TPAMI.2020.2973983","article-title":"Relationship-embedded representation learning for grounding referring expressions","volume":"43","author":"Yang","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2024030711345989500_btad589-B44","first-page":"11842","author":"Yang"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad589\/51728113\/btad589.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/10\/btad589\/56890513\/btad589.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/10\/btad589\/56890513\/btad589.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T11:35:58Z","timestamp":1709811358000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad589\/7280695"}},"subtitle":[],"editor":[{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,9,22]]},"references-count":43,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad589","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,10,1]]},"published":{"date-parts":[[2023,9,22]]},"article-number":"btad589"}}