{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T23:05:15Z","timestamp":1784761515814,"version":"3.55.0"},"reference-count":53,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"vor","delay-in-days":8,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"University of South Florida, FL, USA"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Protein folding stability is a key determinant for understanding protein dynamics, including molecular function, pathogenicity, and protein engineering. Yet, accurate prediction of protein stability remains challenging due to high variability in available data, particularly when only sequence information is available and structural knowledge is limited or unavailable. In this work, we introduce LoMuS, a multi-representation-based deep learning model that predicts dataset-provided protein stability scores directly from the primary sequence. In the core of the model architecture, a fusion network integrates explicit physicochemical descriptors with low-rank adapted protein language model derived embeddings from the sequence that consistently gains across standard experimental stability benchmarks.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We rigorously evaluate LoMuS across multiple settings, such as absolute folding stability scoring, mutation landscape stability scoring, held-out protein domains, out-of-distribution label regimes, and per-protein evaluation. LoMuS consistently outperforms sequence-only baselines, achieving an absolute performance gain of at least 10% in Spearman\u2019s rank correlation across several benchmarks. Per-protein evaluations further demonstrate robust performance gains. Ablation analyses confirm that complementary signals from physicochemical descriptors and sequence embeddings are critical to the effectiveness of the proposed multi-representation approach. We believe LoMuS advances protein engineering research by improving the prediction and ranking of protein stability scores.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability<\/jats:title>\n                    <jats:p>All codes including data preparation scripts, training and validation recipes, and experimental configurations for LoMuS are available at: https:\/\/github.com\/kabir-ai2bio-lab\/LoMuS.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag509","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T11:52:44Z","timestamp":1783511564000},"source":"Crossref","is-referenced-by-count":0,"title":["LoMuS: low-rank adaptation with sequence multi-representation improves protein stability prediction"],"prefix":"10.1093","volume":"42","author":[{"given":"Samuel","family":"Infante","sequence":"first","affiliation":[{"name":"Bellini College of AI, Cybersecurity and Computing, University of South Florida , Tampa, Florida 33620,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akash","family":"Singh","sequence":"additional","affiliation":[{"name":"Bellini College of AI, Cybersecurity and Computing, University of South Florida , Tampa, Florida 33620,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8060-2084","authenticated-orcid":false,"given":"Anowarul","family":"Kabir","sequence":"additional","affiliation":[{"name":"Bellini College of AI, Cybersecurity and Computing, University of South Florida , Tampa, Florida 33620,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"key":"2026072218420991500_btag509-B1","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1038\/s41592-019-0598-1","article-title":"Unified rational protein engineering with sequence-based deep representation learning","volume":"16","author":"Alley","year":"2019","journal-title":"Nat Methods"},{"key":"2026072218420991500_btag509-B2","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.82593","article-title":"Rapid protein stability prediction using deep learning representations","volume":"12","author":"Blaabjerg","year":"2023","journal-title":"eLife"},{"key":"2026072218420991500_btag509-B3","doi-asserted-by":"crossref","first-page":"a041467","DOI":"10.1101\/cshperspect.a041467","article-title":"Variant effect prediction in the age of machine learning","volume":"16","author":"Bromberg","year":"2024","journal-title":"Cold Spring Harb Perspect Biol"},{"key":"2026072218420991500_btag509-B4","doi-asserted-by":"crossref","first-page":"1508","DOI":"10.1021\/acs.jcim.8b00697","article-title":"Deepddg: predicting the stability change of protein point mutations using neural networks","volume":"59","author":"Cao","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2026072218420991500_btag509-B5","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.82819","article-title":"Transformer-based deep learning for predicting protein properties in the life sciences","volume":"12","author":"Chandra","year":"2023","journal-title":"eLife"},{"key":"2026072218420991500_btag509-B6","doi-asserted-by":"crossref","first-page":"e1008543","DOI":"10.1371\/journal.pcbi.1008543","article-title":"PremPS: predicting the impact of missense mutations on protein stability","volume":"16","author":"Chen","year":"2020","journal-title":"PLoS Comput Biol"},{"key":"2026072218420991500_btag509-B7","doi-asserted-by":"crossref","first-page":"eadg7492","DOI":"10.1126\/science.adg7492","article-title":"Accurate proteome-wide missense variant effect prediction with AlphaMissense","volume":"381","author":"Cheng","year":"2023","journal-title":"Science"},{"key":"2026072218420991500_btag509-B8","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1002\/prot.20810","article-title":"Prediction of protein stability changes for single-site mutations using support vector machines","volume":"62","author":"Cheng","year":"2006","journal-title":"Proteins"},{"key":"2026072218420991500_btag509-B9","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1038\/s41422-024-00989-2","article-title":"Zero-shot prediction of mutation effects with multimodal deep representation learning guides protein engineering","volume":"34","author":"Cheng","year":"2024","journal-title":"Cell Res"},{"key":"2026072218420991500_btag509-B10","doi-asserted-by":"crossref","first-page":"e1012248","DOI":"10.1371\/journal.pcbi.1012248","article-title":"Protein stability prediction by fine-tuning a protein language model on a mega-scale dataset","volume":"20","author":"Chu","year":"2024","journal-title":"PLoS Comput Biol"},{"key":"2026072218420991500_btag509-B11","first-page":"61","volume-title":"Molecular Chaperones in Human Disorders, Volume 114 of Advances in Protein Chemistry and Structural Biology","author":"Clausen","year":"2019"},{"key":"2026072218420991500_btag509-B12","doi-asserted-by":"crossref","first-page":"1422","DOI":"10.1093\/bioinformatics\/btp163","article-title":"Biopython: freely available python tools for computational molecular biology and bioinformatics","volume":"25","author":"Cock","year":"2009","journal-title":"Bioinformatics"},{"key":"2026072218420991500_btag509-B13","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: toward understanding the language of life through self-supervised learning","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026072218420991500_btag509-B14","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1038\/s42256-023-00721-6","article-title":"A method for multiple-sequence-alignment-free protein structure prediction using a protein language model","volume":"5","author":"Fang","year":"2023","journal-title":"Nat Mach Intell"},{"key":"2026072218420991500_btag509-B15","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1385\/1-59259-890-0:571","volume-title":"The Proteomics Protocols Handbook","author":"Gasteiger","year":"2005"},{"key":"2026072218420991500_btag509-B16","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1016\/S0022-2836(02)00442-4","article-title":"Predicting changes in the stability of proteins and protein complexes: a study of more than 1000 mutations","volume":"320","author":"Guerois","year":"2002","journal-title":"J Mol Biol"},{"key":"2026072218420991500_btag509-B17","doi-asserted-by":"crossref","first-page":"113863","DOI":"10.1016\/j.ab.2020.113863","article-title":"Global analysis of protein stability by temperature and chemical denaturation","volume":"605","author":"Hamborg","year":"2020","journal-title":"Anal Biochem"},{"key":"2026072218420991500_btag509-B18","author":"Hu","year":"2021"},{"key":"2026072218420991500_btag509-B19","volume-title":"Sci Adv","author":"Jiang","year":"2023"},{"key":"2026072218420991500_btag509-B20","doi-asserted-by":"crossref","first-page":"vbae119","DOI":"10.1093\/bioadv\/vbae119","article-title":"In the twilight zone of protein sequence homology: do protein language models learn protein structure?","volume":"4","author":"Kabir","year":"2024","journal-title":"Bioinform Adv"},{"key":"2026072218420991500_btag509-B21","doi-asserted-by":"crossref","first-page":"1709","DOI":"10.3390\/biom12111709","article-title":"Goproformer: a multi-modal transformer method for gene ontology protein function prediction","volume":"12","author":"Kabir","year":"2022","journal-title":"Biomolecules"},{"key":"2026072218420991500_btag509-B22","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1093\/nar\/28.1.374","article-title":"AAindex: amino acid index database","volume":"28","author":"Kawashima","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2026072218420991500_btag509-B23","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1093\/nar\/27.1.368","article-title":"AAindex: amino acid index database","volume":"27","author":"Kawashima","year":"1999","journal-title":"Nucleic Acids Res"},{"key":"2026072218420991500_btag509-B24","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1002\/prot.22921","article-title":"Role of conformational sampling in computing mutation-induced changes in protein structure and stability","volume":"79","author":"Kellogg","year":"2011","journal-title":"Proteins"},{"key":"2026072218420991500_btag509-B25","doi-asserted-by":"crossref","first-page":"8379","DOI":"10.3390\/ijms25158379","article-title":"PON-Tm: a sequence-based method for prediction of missense mutation effects on protein thermal stability changes","volume":"25","author":"Kuang","year":"2024","journal-title":"Int J Mol Sci"},{"key":"2026072218420991500_btag509-B26","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1186\/s12859-015-0548-6","article-title":"MAESTRO\u2014multi agent stability prediction upon point mutations","volume":"16","author":"Laimer","year":"2015","journal-title":"BMC Bioinformatics"},{"key":"2026072218420991500_btag509-B27","first-page":"35700","volume-title":"Advances in Neural Information Processing Systems","author":"Li","year":"2024"},{"key":"2026072218420991500_btag509-B28","volume-title":"Forty-second International Conference on Machine Learning","author":"Li","year":"2025"},{"key":"2026072218420991500_btag509-B29","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2026072218420991500_btag509-B30","author":"Liu","year":"2023"},{"key":"2026072218420991500_btag509-B31","doi-asserted-by":"crossref","first-page":"6861","DOI":"10.3390\/molecules27206861","article-title":"Conformational stability and denaturation processes of proteins investigated by electrophoresis under extreme conditions","volume":"27","author":"Masson","year":"2022","journal-title":"Molecules"},{"key":"2026072218420991500_btag509-B32","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1093\/protein\/2.2.93","article-title":"Cluster analysis of amino acid indices for prediction of protein structure and function","volume":"2","author":"Nakai","year":"1988","journal-title":"Protein Eng"},{"key":"2026072218420991500_btag509-B33","volume-title":"ProteinGym: large-scale benchmarks for protein design and fitness prediction","author":"Notin","year":"2023"},{"key":"2026072218420991500_btag509-B34","doi-asserted-by":"crossref","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":"2026072218420991500_btag509-B35","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1093\/bioinformatics\/btt691","article-title":"mCSM: predicting the effects of mutations in proteins using graph-based signatures","volume":"30","author":"Pires","year":"2014","journal-title":"Bioinformatics"},{"key":"2026072218420991500_btag509-B36","first-page":"9689","volume-title":"Advances in Neural Information Processing Systems","author":"Rao","year":"2019"},{"key":"2026072218420991500_btag509-B37","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1126\/science.aan0693","article-title":"Global analysis of protein folding using massively parallel design, synthesis, and testing","volume":"357","author":"Rocklin","year":"2017","journal-title":"Science"},{"key":"2026072218420991500_btag509-B38","doi-asserted-by":"crossref","first-page":"1968","DOI":"10.1016\/j.csbj.2020.07.011","article-title":"Limitations and challenges in protein stability prediction upon genome variations: towards future applications in precision medicine","volume":"18","author":"Sanavia","year":"2020","journal-title":"Comput Struct Biotechnol J"},{"key":"2026072218420991500_btag509-B39","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btaf019","article-title":"DDGemb: predicting protein stability change upon single- and multi-point variations with embeddings and deep learning","volume":"41","author":"Savojardo","year":"2024","journal-title":"Bioinformatics"},{"key":"2026072218420991500_btag509-B40","doi-asserted-by":"crossref","first-page":"7407","DOI":"10.1038\/s41467-024-51844-2","article-title":"Fine-tuning protein language models boosts predictions across diverse tasks","volume":"15","author":"Schmirler","year":"2024","journal-title":"Nat Commun"},{"key":"2026072218420991500_btag509-B41","doi-asserted-by":"crossref","first-page":"3352","DOI":"10.1021\/acs.jpcb.3c00882","article-title":"Protein stability-analysis of heat and cold denaturation without and with unfolding models","volume":"127","author":"Seelig","year":"2023","journal-title":"J Phys Chem B"},{"key":"2026072218420991500_btag509-B42","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Shen","year":"2024"},{"key":"2026072218420991500_btag509-B43","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbaf294","article-title":"Out of distribution learning in bioinformatics: advancements and challenges","volume":"26","author":"Shi","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026072218420991500_btag509-B44","doi-asserted-by":"crossref","first-page":"166810","DOI":"10.1016\/j.jmb.2021.166810","article-title":"Elaspic2 (EL2): combining contextualized language models and graph neural networks to predict effects of mutations","volume":"433","author":"Strokach","year":"2021","journal-title":"J Mol Biol"},{"key":"2026072218420991500_btag509-B45","doi-asserted-by":"crossref","first-page":"838","DOI":"10.1016\/j.str.2024.02.016","article-title":"PMSPcnn: predicting protein stability changes upon single point mutations with convolutional neural network","volume":"32","author":"Sun","year":"2024","journal-title":"Structure"},{"key":"2026072218420991500_btag509-B46","first-page":"3319","volume-title":"ICML\u201917: Proceedings of the 34th International Conference on Machine Learning","author":"Sundararajan","year":"2017"},{"key":"2026072218420991500_btag509-B47","doi-asserted-by":"crossref","first-page":"926","DOI":"10.1093\/bioinformatics\/btu739","article-title":"Uniref clusters: a comprehensive and scalable alternative for improving sequence similarity searches","volume":"31","author":"Suzek","year":"2015","journal-title":"Bioinformatics"},{"key":"2026072218420991500_btag509-B48","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1093\/protein\/9.1.27","article-title":"Analysis of amino acid indices and mutation matrices for sequence comparison and structure prediction of proteins","volume":"9","author":"Tomii","year":"1996","journal-title":"Protein Eng"},{"key":"2026072218420991500_btag509-B49","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1038\/s41586-023-06328-6","article-title":"Mega-scale experimental analysis of protein folding stability in biology and design","volume":"620","author":"Tsuboyama","year":"2023","journal-title":"Nature"},{"key":"2026072218420991500_btag509-B50","doi-asserted-by":"crossref","first-page":"107952","DOI":"10.1016\/j.compbiolchem.2023.107952","article-title":"ProS-GNN: predicting effects of mutations on protein stability using graph neural networks","volume":"107","author":"Wang","year":"2023","journal-title":"Comput Biol Chem"},{"key":"2026072218420991500_btag509-B51","doi-asserted-by":"crossref","first-page":"10798","DOI":"10.3390\/ijms231810798","article-title":"ProTstab2 for prediction of protein thermal stabilities","volume":"23","author":"Yang","year":"2022","journal-title":"Int J Mol Sci"},{"key":"2026072218420991500_btag509-B52","volume-title":"Efficiently predicting protein stability changes upon single-point mutation with large language models.","author":"Zhang","year":"2023"},{"key":"2026072218420991500_btag509-B53","doi-asserted-by":"crossref","first-page":"W122","DOI":"10.1093\/nar\/gkad472","article-title":"Ddmut: predicting effects of mutations on protein stability using deep learning","volume":"51","author":"Zhou","year":"2023","journal-title":"Nucleic Acids Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag509\/68738647\/btag509.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/7\/btag509\/68738647\/btag509.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/7\/btag509\/68738647\/btag509.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T22:42:24Z","timestamp":1784760144000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag509\/8729051"}},"subtitle":[],"editor":[{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":53,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag509","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,7]]},"article-number":"btag509"}}