{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T14:18:21Z","timestamp":1789395501261,"version":"build-2803163510"},"reference-count":33,"publisher":"American Chemical Society (ACS)","issue":"17","license":[{"start":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T00:00:00Z","timestamp":1787961600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T00:00:00Z","timestamp":1787961600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T00:00:00Z","timestamp":1787961600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2025YFC2311700"],"award-info":[{"award-number":["2025YFC2311700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Predicting the impact of single-point mutations on protein thermodynamic stability is crucial for protein engineering of therapeutic and industrial applications. By effectively capturing the three-dimensional structural information of proteins and the spatial physical environment of each residue, the inverse folding models (IFMs) upon fine-tuning, such as ThermoMPNN, achieved state-of-the-art performance in predicting thermostability changes in proteins caused by mutations. However, IFMs are limited in their capacity to capture protein deep evolutionary information, whereas protein language models (pLMs) excel. Here, we present SA-MPNN, a lightweight, end-to-end hybrid framework that dynamically integrates the protein sequence representations from a protein language model (ESM2) into the ThermoMPNN architecture to improve protein stability prediction by combining evolutionary representations with geometric structural embeddings. By evaluating various feature fusion strategies, we selected a self-attention-based integration mechanism to effectively combine the two modalities. Trained on the large-scale Megascale data set, SA-MPNN achieved modest but consistent gains over ThermoMPNN on various benchmark data sets, with particularly noticeable improvements in several correlation analysis and screening-oriented evaluations. Finally, wet-lab validation was performed on the top-ranking variants of Acetivibrio thermocellus\u03b2-glucosidase (AtBgl1A) as a case study. The experimental results demonstrated that multiple designed mutants exhibited improved thermostability, and the optimal variant, GC20, achieved a melting temperature (Tm) of 76.98 \u00b0C, representing a 5.97 \u00b0C increase over the wild-type, thereby supporting the practical applicability of SA-MPNN in protein engineering.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01644","type":"journal-article","created":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T12:31:18Z","timestamp":1788352278000},"page":"10770-10781","source":"Crossref","is-referenced-by-count":0,"title":["SA-MPNN: A Sequence-Aware\nThermoMPNN for Accurate\nPrediction of Mutational Effects on Protein Thermodynamic Stability"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5826-1352","authenticated-orcid":true,"given":"Xin Yue","family":"Zhang","sequence":"first","affiliation":[{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]},{"name":"National Engineering Center for New Vaccine Research , ,","place":["Beijing, China, 101111"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Zheng","sequence":"additional","affiliation":[{"name":"National Engineering Center for New Vaccine Research , ,","place":["Beijing, China, 101111"]},{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ze Yuan","family":"Dong","sequence":"additional","affiliation":[{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]},{"name":"National Engineering Center for New Vaccine Research , ,","place":["Beijing, China, 101111"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8239-2035","authenticated-orcid":true,"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]},{"name":"National Engineering Center for New Vaccine Research , ,","place":["Beijing, China, 101111"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Center for New Vaccine Research , ,","place":["Beijing, China, 101111"]},{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min Cong","family":"Wu","sequence":"additional","affiliation":[{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]},{"name":"National Engineering Center for New Vaccine Research , ,","place":["Beijing, China, 101111"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao Ming","family":"Liu","sequence":"additional","affiliation":[{"name":"National Engineering Center for New Vaccine Research , ,","place":["Beijing, China, 101111"]},{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guo Hui","family":"Li","sequence":"additional","affiliation":[{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]},{"name":"China National Biotec Group Company Limited , , ,","place":["Beijing, China, 100024"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0363-7018","authenticated-orcid":true,"given":"Jiao","family":"Li","sequence":"additional","affiliation":[{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]},{"name":"National Engineering Center for New Vaccine Research , ,","place":["Beijing, China, 101111"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei Bu","family":"Wang","sequence":"additional","affiliation":[{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]},{"name":"China National Biotec Group Company Limited , , ,","place":["Beijing, China, 100024"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Liang","sequence":"additional","affiliation":[{"name":"National Engineering Center for New Vaccine Research , ,","place":["Beijing, China, 101111"]},{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi Ming","family":"Li","sequence":"additional","affiliation":[{"name":"National Engineering Center for New Vaccine Research , ,","place":["Beijing, China, 101111"]},{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji Guo","family":"Su","sequence":"additional","affiliation":[{"name":"National Vaccine and Serum Institute (NVSI) , , ,","place":["Beijing, China, 101111"]},{"name":"National Engineering Center for New Vaccine Research , ,","place":["Beijing, China, 101111"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,29]]},"reference":[{"key":"2026091409072301800_cit1","doi-asserted-by":"publisher","first-page":"113","DOI":"10.12688\/f1000research.9970.1","article-title":"Recent advances in (therapeutic protein)\ndrug development","volume":"6","author":"Lagasse\u0301","year":"2017","journal-title":"F1000research"},{"issue":"6158","key":"2026091409072301800_cit2","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1126\/science.1243283","article-title":"Structure-based\ndesign of a fusion glycoprotein vaccine\nfor respiratory syncytial virus","volume":"342","author":"Mclellan","year":"2013","journal-title":"Science"},{"issue":"35","key":"2026091409072301800_cit3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1707304114","article-title":"Immunogenicity\nand structures of a rationally designed\nprefusion MERS-CoV spike antigen","volume":"114","author":"Pallesen","year":"2017","journal-title":"Proc. Natl.\nAcad. Sci. U. S. A."},{"issue":"6716","key":"2026091409072301800_cit4","doi-asserted-by":"publisher","first-page":"1484","DOI":"10.1126\/science.adp2362","article-title":"Mutating a flexible region of the RSV F protein\ncan stabilize the prefusion conformation","volume":"385","author":"Liang","year":"2024","journal-title":"Science"},{"issue":"2","key":"2026091409072301800_cit5","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/S0378-5173(99)00152-0","article-title":"Instability,\nstabilization, and formulation of liquid protein pharmaceuticals","volume":"185","author":"Wang","year":"1999","journal-title":"Int. J. Pharm."},{"issue":"1","key":"2026091409072301800_cit6","doi-asserted-by":"publisher","first-page":"11501","DOI":"10.1063\/1.4997367","article-title":"Engineering\nof thermostable enzymes for industrial applications","volume":"2","author":"Rigoldi","year":"2018","journal-title":"APL Bioeng."},{"issue":"1\u20132","key":"2026091409072301800_cit7","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.abb.2012.09.008","article-title":"Differential\nscanning calorimetry as a tool for protein folding and stability","volume":"531","author":"Johnson","year":"2013","journal-title":"Arch. Biochem. Biophys."},{"issue":"9","key":"2026091409072301800_cit8","doi-asserted-by":"publisher","first-page":"2212","DOI":"10.1038\/nprot.2007.321","article-title":"The use of\ndifferential scanning\nfluorimetry to detect ligand interactions that promote protein stability","volume":"2","author":"Niesen","year":"2007","journal-title":"Nat. Protoc."},{"issue":"8","key":"2026091409072301800_cit9","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1038\/nmeth.3027","article-title":"Deep mutational scanning:\na new style of protein science","volume":"11","author":"Fowler","year":"2014","journal-title":"Nat. Methods"},{"issue":"10","key":"2026091409072301800_cit10","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1038\/s41592-018-0138-4","article-title":"Deep generative models of genetic\nvariation capture the effects of mutations","volume":"15","author":"Riesselman","year":"2018","journal-title":"Nat. Methods"},{"issue":"2","key":"2026091409072301800_cit11","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1016\/S0022-2836(02)00442-4","article-title":"Predicting changes\nin the stability\nof proteins and protein complexes: a study of more than 1000 mutations","volume":"320","author":"Guerois","year":"2002","journal-title":"J. Mol. Biol."},{"issue":"3","key":"2026091409072301800_cit12","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1002\/prot.22921","article-title":"Role of conformational sampling in\ncomputing mutation-induced changes in protein structure and stability","volume":"79","author":"Kellogg","year":"2011","journal-title":"Proteins"},{"issue":"6637","key":"2026091409072301800_cit13","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with\na language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"issue":"6615","key":"2026091409072301800_cit14","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1126\/science.add2187","article-title":"Robust deep learning\u2013based\nprotein sequence\ndesign using ProteinMPNN","volume":"378","author":"Dauparas","year":"2022","journal-title":"Science"},{"issue":"9","key":"2026091409072301800_cit15","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1038\/s42256-024-00887-7","article-title":"Zero-shot\ntransfer of protein sequence likelihood models\nto thermostability prediction","volume":"6","author":"Reeves","year":"2024","journal-title":"Nat. Mach. Intell."},{"issue":"7","key":"2026091409072301800_cit16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1012248","article-title":"Protein stability prediction by fine-tuning\na protein language model on a mega-scale dataset","volume":"20","author":"Chu","year":"2024","journal-title":"PLoS Comput. Biol."},{"issue":"6","key":"2026091409072301800_cit17","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2314853121","article-title":"Transfer learning\nto leverage larger datasets for improved prediction of protein stability\nchanges","volume":"121","author":"Dieckhaus","year":"2024","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"issue":"25","key":"2026091409072301800_cit18","doi-asserted-by":"publisher","first-page":"27153","DOI":"10.1021\/acsomega.5c02381","article-title":"Structure-Based\nEngineering to Improve Thermostability of Acetivibrio thermocellus\nAtBgl1A \u03b2-Glucosidase","volume":"10","author":"Pitchayatanakorn","year":"2025","journal-title":"ACS Omega"},{"issue":"7973","key":"2026091409072301800_cit19","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1038\/s41586-023-06328-6","article-title":"Mega-scale\nexperimental analysis of protein folding stability in biology and\ndesign","volume":"620","author":"Tsuboyama","year":"2023","journal-title":"Nature"},{"issue":"D1","key":"2026091409072301800_cit20","doi-asserted-by":"publisher","first-page":"D319","DOI":"10.1093\/nar\/gkaa981","article-title":"FireProtDB: database\nof manually curated protein stability data","volume":"49","author":"Stourac","year":"2021","journal-title":"Nucleic Acids Res."},{"issue":"2","key":"2026091409072301800_cit21","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab555","article-title":"Predicting\nprotein stability changes upon single-point mutation: a thorough comparison\nof the available tools on a new dataset","volume":"23","author":"Pancotti","year":"2022","journal-title":"Briefings\nBioinf."},{"issue":"21","key":"2026091409072301800_cit22","doi-asserted-by":"publisher","first-page":"3659","DOI":"10.1093\/bioinformatics\/bty348","article-title":"Quantification of biases\nin predictions of protein stability changes upon mutations","volume":"34","author":"Pucci","year":"2018","journal-title":"Bioinformatics"},{"issue":"19","key":"2026091409072301800_cit23","doi-asserted-by":"publisher","first-page":"2537","DOI":"10.1093\/bioinformatics\/btp445","article-title":"Fast and accurate predictions\nof protein stability\nchanges upon mutations using statistical potentials and neural networks:\nPoPMuSiC-2.0","volume":"25","author":"Dehouck","year":"2009","journal-title":"Bioinformatics"},{"issue":"90001","key":"2026091409072301800_cit24","doi-asserted-by":"publisher","first-page":"120D","DOI":"10.1093\/nar\/gkh082","article-title":"ProTherm,\nversion 4.0: thermodynamic database for proteins and mutants","volume":"32","author":"Bava","year":"2004","journal-title":"Nucleic Acids Res."},{"issue":"5","key":"2026091409072301800_cit25","doi-asserted-by":"publisher","DOI":"10.1002\/pro.70112","article-title":"Deep mutational\nscanning reveals a de novo disulfide bond and combinatorial mutations\nfor engineering thermostable myoglobin","volume":"34","author":"Ku\u0308ng","year":"2025","journal-title":"Protein\nSci."},{"key":"2026091409072301800_cit26","doi-asserted-by":"publisher","DOI":"10.1101\/2025.11.12.688125","article-title":"E1:\nRetrieval-Augmented\nProtein Encoder Models","author":"Jain","year":"2025","journal-title":"bioRxiv"},{"key":"2026091409072301800_cit27","first-page":"8844","article-title":"MSA Transformer","volume-title":"International\nConference on Machine Learning","author":"Rao","year":"2021"},{"issue":"11","key":"2026091409072301800_cit28","doi-asserted-by":"publisher","first-page":"1859","DOI":"10.1002\/bip.360261104","article-title":"Protein stability curves","volume":"26","author":"Becktel","year":"1987","journal-title":"Biopolymers"},{"issue":"11","key":"2026091409072301800_cit29","doi-asserted-by":"publisher","first-page":"btad671","DOI":"10.1093\/bioinformatics\/btad671","article-title":"PROSTATA: a framework for protein stability assessment\nusing transformers","volume":"39","author":"Umerenkov","year":"2023","journal-title":"Bioinformatics"},{"key":"2026091409072301800_cit30","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.82593","article-title":"Rapid protein\nstability prediction using deep learning representations","volume":"12","author":"Blaabjerg","year":"2023","journal-title":"Elife"},{"issue":"3","key":"2026091409072301800_cit31","doi-asserted-by":"publisher","first-page":"2379","DOI":"10.1016\/j.rser.2017.08.074","article-title":"Applications of\nfungal cellulases in biofuel production: advances and limitations","volume":"82","author":"Srivastava","year":"2018","journal-title":"Renewable Sustainable Energy Rev."},{"issue":"1","key":"2026091409072301800_cit32","doi-asserted-by":"publisher","first-page":"18102","DOI":"10.1103\/PhysRevLett.91.018102","article-title":"Adherence of packing\ndefects in soluble proteins","volume":"91","author":"Ferna\u0301ndez","year":"2003","journal-title":"Phys. Rev. Lett."},{"issue":"11","key":"2026091409072301800_cit33","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1038\/s43588-024-00716-2","article-title":"Improving\nthe prediction of protein stability changes\nupon mutations by geometric learning and a pre-training strategy","volume":"4","author":"Xu","year":"2024","journal-title":"Nat. Comput. Sci."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01644","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/10770\/67741538\/acs.jcim.6c01644.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/10770\/67741538\/acs.jcim.6c01644.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T13:30:14Z","timestamp":1789392614000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/17\/10770\/5361513\/SA-MPNN-A-Sequence-Aware-ThermoMPNN-for-Accurate"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,29]]},"references-count":33,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,8,29]]},"published-print":{"date-parts":[[2026,9,14]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01644","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,29]]}}}