{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T12:52:27Z","timestamp":1791895947914,"version":"4.3.4"},"reference-count":52,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Protein Science"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Accurately predicting mutation\u2010induced protein stability changes remains a central challenge in structural bioinformatics. Existing methods exhibit a strong bias toward destabilizing mutations, leading to limited performance for stabilizing mutations and constraining their utility in protein engineering. Here, we address this limitation through two complementary strategies: balanced dataset construction and integrative modeling. To mitigate the severe class imbalance in current stability datasets, we constructed undersampling\u2010based balanced datasets and further evaluated reverse\u2010mutation augmentation as a comparative strategy. Building on the rapid development of high\u2010performing predictors, we hypothesized that integrating their outputs could exploit complementary strengths and improve predictive accuracy. Accordingly, we developed three modeling frameworks, including models based on handcrafted features, models using embedding representations extracted from ProteinMPNN, and ensemble models integrating a diverse set of state\u2010of\u2010the\u2010art predictors. Across multiple independent test sets, ensemble models consistently outperformed individual approaches, with particularly pronounced gains in identifying stabilizing mutations. These findings demonstrate that combining undersampling\u2010based balanced data construction with systematic predictor integration provides an effective and practical strategy for achieving more balanced and accurate protein stability prediction, and offers a useful framework for identifying stabilizing mutations in protein engineering and related applications. StaMutAble is freely available at:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/minghuilab\/StaMutAble\">https:\/\/github.com\/minghuilab\/StaMutAble<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1002\/pro.70728","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T12:48:59Z","timestamp":1785934139000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An ensemble learning framework for protein stability prediction with enhanced recognition of stabilizing mutations"],"prefix":"10.1002","volume":"35","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[{"name":"Jiangsu Key Laboratory of Drug Discovery and Translational Research for Brain Diseases, School of Basic Medical Sciences Soochow University  Suzhou Jiangsu China"},{"name":"Biomedical Basic Research Center (BBRC) of Jiangsu Soochow University  Suzhou Jiangsu China"},{"name":"MOE Key Laboratory of Geriatric Diseases and Immunology, School of Basic Medical Sciences Suzhou Medical College of Soochow University  Suzhou Jiangsu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Jiangsu Key Laboratory of Drug Discovery and Translational Research for Brain Diseases, School of Basic Medical Sciences Soochow University  Suzhou Jiangsu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghui","family":"Li","sequence":"additional","affiliation":[{"name":"Jiangsu Key Laboratory of Drug Discovery and Translational Research for Brain Diseases, School of Basic Medical Sciences Soochow University  Suzhou Jiangsu China"},{"name":"Biomedical Basic Research Center (BBRC) of Jiangsu Soochow University  Suzhou Jiangsu China"},{"name":"MOE Key Laboratory of Geriatric Diseases and Immunology, School of Basic Medical Sciences Suzhou Medical College of Soochow University  Suzhou Jiangsu China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.7b00125"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.26810"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.3389\/fmolb.2022.1075570"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6463\/abedfb"},{"key":"e_1_2_8_7_1","volume-title":"Advances in Neural Information Processing Systems 24","author":"Bergstra J","year":"2011"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.82593"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.1c00201"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/humu.21555"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008543"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-51776-x"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.add2187"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp445"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-12-151"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btm481"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2314853121"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.molcel.2009.11.022"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1006\/jmbi.1997.1237"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-2836(02)00442-4"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.3c00036"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_2_8_24_1","volume-title":"Advances in neural information processing systems 4","author":"Krogh A","year":"1991"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-015-0548-6"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008291"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijms22020606"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-14-3812"},{"key":"e_1_2_8_29_1","unstructured":"LoshchilovI HutterF.Sgdr: stochastic gradient descent with warm restarts. Preprint. arXiv: 1608.03983.2016."},{"key":"e_1_2_8_30_1","unstructured":"LoshchilovI HutterF.Decoupled weight decay regularization. arXiv Preprint. arXiv: 1711.05101.2017."},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaa074"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-019-2923-1"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty979"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa1035"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab555"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.24968"},{"key":"e_1_2_8_37_1","first-page":"55","volume-title":"Neural networks: tricks of the trade","author":"Prechelt L","year":"2002"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2021.11.001"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiolchem.2004.12.002"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.92.2.452"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa981"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-021-02826-3"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06328-6"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00439-024-02724-8"},{"key":"e_1_2_8_45_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty340"},{"key":"e_1_2_8_46_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.23065"},{"key":"e_1_2_8_47_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa925"},{"key":"e_1_2_8_48_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-024-00716-2"},{"key":"e_1_2_8_49_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1914677117"},{"key":"e_1_2_8_50_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2524289123"},{"key":"e_1_2_8_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2020.100939"},{"key":"e_1_2_8_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2023.12.018"},{"key":"e_1_2_8_53_1","doi-asserted-by":"publisher","DOI":"10.1002\/pro.4861"}],"container-title":["Protein Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/pro.70728","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/pro.70728","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/pro.70728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T12:24:46Z","timestamp":1791894286000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/pro.70728"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":52,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1002\/pro.70728"],"URL":"https:\/\/doi.org\/10.1002\/pro.70728","archive":["Portico"],"relation":{},"ISSN":["0961-8368","1469-896X"],"issn-type":[{"value":"0961-8368","type":"print"},{"value":"1469-896X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"assertion":[{"value":"2026-04-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70728"}}