{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T22:04:05Z","timestamp":1789596245106,"version":"build-2803163510"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":225,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000183","name":"United States Army Research Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"ARO","doi-asserted-by":"publisher","award":["80093-CH-MUR"],"award-info":[{"award-number":["80093-CH-MUR"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Defense Advanced Projects Research Agency","award":["DOD HR001121S0039"],"award-info":[{"award-number":["DOD HR001121S0039"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Protein solubility is a critical property that significantly impacts therapeutic efficacy and protein reengineering applications. Recent advances in machine learning and deep learning techniques provide unprecedented opportunities to develop predictive models for solubility, enabling more efficient protein design and optimization. This work is motivated by the potential of leveraging deep learning to address the solubility prediction challenge and to accelerate protein engineering workflows.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Leveraging and combining multiple protein language model representations, our MiLaSol model attains 81% accuracy, outperforming prior methods, with the highest Matthews Correlation Coefficient (MCC) score of 0.63 demonstrating balanced performance across both soluble and insoluble proteins. Through simulated annealing optimization coupled with the Raygun model, we also present a computational method to reengineer insoluble protein variants into soluble forms, with predictions confirmed by multiple independent solubility prediction methods. Our results demonstrate the effectiveness of combining machine learning-based solubility prediction with generative optimization for protein engineering.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>MiLaSol is available at https:\/\/github.com\/weiweiloutufts\/milasol<\/jats:p>\n                    <jats:p>An archived version of the code at the time of submission can be found at https:\/\/doi.org\/10.5281\/zenodo.21495202<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioadv\/vbag233","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T11:47:52Z","timestamp":1786535272000},"source":"Crossref","is-referenced-by-count":0,"title":["MiLaSol: modeling protein solubility by mixing up multiple protein language models"],"prefix":"10.1093","volume":"6","author":[{"given":"Weiwei","family":"Lou","sequence":"first","affiliation":[{"name":"Department of Computer Science, Tufts University , Medford, MA 02155,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mert","family":"Erden","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tufts University , Medford, MA 02155,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6698-6413","authenticated-orcid":false,"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tufts University , Medford, MA 02155,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"key":"2026091617364309900_vbag233-B2","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.jmb.2011.12.005","article-title":"Sequence-based prediction of protein solubility","volume":"421","author":"Agostini","year":"2012","journal-title":"J Mol Biol"},{"key":"2026091617364309900_vbag233-B3","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1016\/j.tibtech.2011.04.003","article-title":"Deep mutational scanning: assessing protein function on a massive scale","volume":"29","author":"Araya","year":"2011","journal-title":"Trends Biotechnol"},{"key":"2026091617364309900_vbag233-B4","doi-asserted-by":"crossref","first-page":"D365","DOI":"10.1093\/nar\/gkn790","article-title":"The protein structure initiative structural genomics knowledgebase","volume":"37","author":"Berman","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2026091617364309900_vbag233-B5","doi-asserted-by":"crossref","first-page":"4691","DOI":"10.1093\/bioinformatics\/btaa578","article-title":"Solubility-weighted index: fast and accurate prediction of protein solubility","volume":"36","author":"Bhandari","year":"2020","journal-title":"Bioinformatics"},{"key":"2026091617364309900_vbag233-B6","doi-asserted-by":"crossref","first-page":"2102","DOI":"10.1093\/bioinformatics\/btac020","article-title":"Proteinbert: a universal deep-learning model of protein sequence and function","volume":"38","author":"Brandes","year":"2022","journal-title":"Bioinformatics"},{"key":"2026091617364309900_vbag233-B7","doi-asserted-by":"crossref","first-page":"3035","DOI":"10.1093\/bioinformatics\/bty222","article-title":"Pysster: classification of biological sequences by learning sequence and structure motifs with convolutional neural networks","volume":"34","author":"Budach","year":"2018","journal-title":"Bioinformatics"},{"key":"2026091617364309900_vbag233-B8","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1093\/bib\/bbt057","article-title":"Bioinformatics approaches for improved recombinant protein production in Escherichia coli: protein solubility prediction","volume":"15","author":"Chang","year":"2014","journal-title":"Brief Bioinform"},{"key":"2026091617364309900_vbag233-B9","first-page":"1","author":"Devkota","year":"2026"},{"key":"2026091617364309900_vbag233-B10","doi-asserted-by":"crossref","first-page":"107584","DOI":"10.1016\/j.compbiolchem.2021.107584","article-title":"Deep_CNN_LSTM_GO: protein function prediction from amino-acid sequences","volume":"95","author":"Elhaj-Abdou","year":"2021","journal-title":"Comput Biol Chem"},{"key":"2026091617364309900_vbag233-B11","author":"Elnaggar","year":"2023"},{"key":"2026091617364309900_vbag233-B12","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"Prottrans: towards cracking the language of life\u2019s code through self-supervised learning","volume":"44","author":"Elnaggar","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026091617364309900_vbag233-B14","doi-asserted-by":"crossref","first-page":"2030","DOI":"10.1110\/ps.072855507","article-title":"Modeling mutations in protein structures","volume":"16","author":"Feyfant","year":"2007","journal-title":"Protein Sci"},{"key":"2026091617364309900_vbag233-B15","doi-asserted-by":"crossref","first-page":"3150","DOI":"10.1093\/bioinformatics\/bts565","article-title":"CD-HIT: accelerated for clustering the next-generation sequencing data","volume":"28","author":"Fu","year":"2012","journal-title":"Bioinformatics"},{"key":"2026091617364309900_vbag233-B16","doi-asserted-by":"crossref","first-page":"1323","DOI":"10.1093\/bioinformatics\/btw006","article-title":"MMseqs software suite for fast and deep clustering and searching of large protein sequence sets","volume":"32","author":"Hauser","year":"2016","journal-title":"Bioinformatics"},{"key":"2026091617364309900_vbag233-B17","doi-asserted-by":"crossref","first-page":"e70208","DOI":"10.1002\/pro.70208","article-title":"DSSP 4: FAIR annotation of protein secondary structure","volume":"34","author":"Hekkelman","year":"2025","journal-title":"Protein Sci"},{"key":"2026091617364309900_vbag233-B18","doi-asserted-by":"crossref","first-page":"S3","DOI":"10.1186\/1471-2105-13-S17-S3","article-title":"Prediction and analysis of protein solubility using a novel scoring card method with dipeptide composition","volume":"13 Suppl 17","author":"Huang","year":"2012","journal-title":"BMC Bioinformatics"},{"key":"2026091617364309900_vbag233-B19","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":"2026091617364309900_vbag233-B20","doi-asserted-by":"crossref","first-page":"2814","DOI":"10.1093\/bioinformatics\/bti442","article-title":"LS-SNP: large-scale annotation of coding non-synonymous SNPs based on multiple information sources","volume":"21","author":"Karchin","year":"2005","journal-title":"Bioinformatics"},{"key":"2026091617364309900_vbag233-B21","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026091617364309900_vbag233-B22","doi-asserted-by":"crossref","first-page":"2605","DOI":"10.1093\/bioinformatics\/bty166","article-title":"DeepSol: a deep learning framework for sequence-based protein solubility prediction","volume":"34","author":"Khurana","year":"2018","journal-title":"Bioinformatics"},{"key":"2026091617364309900_vbag233-B1","author":"Kingma","year":"2014"},{"key":"2026091617364309900_vbag233-B23","author":"Li","year":"2021"},{"key":"2026091617364309900_vbag233-B24","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","article-title":"Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences","volume":"22","author":"Li","year":"2006","journal-title":"Bioinformatics"},{"key":"2026091617364309900_vbag233-B25","author":"Lin","year":"2022"},{"key":"2026091617364309900_vbag233-B26","doi-asserted-by":"crossref","first-page":"2200","DOI":"10.1093\/bioinformatics\/btp386","article-title":"SOLpro: accurate sequence-based prediction of protein solubility","volume":"25","author":"Magnan","year":"2009","journal-title":"Bioinformatics"},{"key":"2026091617364309900_vbag233-B27","author":"Passaro","year":"2025"},{"key":"2026091617364309900_vbag233-B28","doi-asserted-by":"crossref","first-page":"14085","DOI":"10.1021\/acs.chemrev.1c00757","article-title":"Protein design: from the aspect of water solubility and stability","volume":"122","author":"Qing","year":"2022","journal-title":"Chem Rev"},{"key":"2026091617364309900_vbag233-B29","doi-asserted-by":"crossref","first-page":"1092","DOI":"10.1093\/bioinformatics\/btx662","article-title":"PaRSnIP: sequence-based protein solubility prediction using gradient boosting machine","volume":"34","author":"Rawi","year":"2018","journal-title":"Bioinformatics"},{"key":"2026091617364309900_vbag233-B30","doi-asserted-by":"crossref","first-page":"2192","DOI":"10.1111\/j.1742-4658.2012.08603.x","article-title":"PROSO II\u2013a new method for protein solubility prediction","volume":"279","author":"Smialowski","year":"2012","journal-title":"FEBS J"},{"key":"2026091617364309900_vbag233-B31","doi-asserted-by":"crossref","first-page":"2536","DOI":"10.1093\/bioinformatics\/btl623","article-title":"Protein solubility: sequence based prediction and experimental verification","volume":"23","author":"Smialowski","year":"2007","journal-title":"Bioinformatics"},{"key":"2026091617364309900_vbag233-B32","first-page":"4080","article-title":"Prototypical networks for few-shot learning","volume":"30","author":"Snell","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026091617364309900_vbag233-B33","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1016\/j.jmb.2014.09.026","article-title":"The camsol method of rational design of protein mutants with enhanced solubility","volume":"427","author":"Sormanni","year":"2015","journal-title":"J Mol Biol"},{"key":"2026091617364309900_vbag233-B34","doi-asserted-by":"crossref","first-page":"6338","DOI":"10.1021\/acs.jcim.4c00689","article-title":"Simple, efficient, and scalable structure-aware adapter boosts protein language models","volume":"64","author":"Tan","year":"2024","journal-title":"J Chem Inf Model"},{"key":"2026091617364309900_vbag233-B35","author":"Tan","year":"2024"},{"key":"2026091617364309900_vbag233-B36","first-page":"243","author":"van Kempen"},{"key":"2026091617364309900_vbag233-B37","doi-asserted-by":"crossref","first-page":"6339","DOI":"10.1016\/j.csbj.2022.11.009","article-title":"SoluProtMutDB: a manually curated database of protein solubility changes upon mutations","volume":"20","author":"Veleck\u00fd","year":"2022","journal-title":"Comput Struct Biotechnol J"},{"key":"2026091617364309900_vbag233-B38","author":"Verma","year":"2019"},{"key":"2026091617364309900_vbag233-B39","author":"Vincent","year":"2008"},{"key":"2026091617364309900_vbag233-B40","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1002\/cpbi.3","article-title":"Comparative protein structure modeling using MODELLER","volume":"54","author":"Webb","year":"2016","journal-title":"Curr Protoc Bioinformatics"},{"key":"2026091617364309900_vbag233-B41","first-page":"443","article-title":"Predicting the solubility of recombinant proteins in Escherichia coli","volume":"9","author":"Wilkinson","year":"1991","journal-title":"Biotechnology (N Y)"},{"key":"2026091617364309900_vbag233-B42","doi-asserted-by":"crossref","first-page":"4314","DOI":"10.1093\/bioinformatics\/btab463","article-title":"EPSOL: sequence-based protein solubility prediction using multidimensional embedding","volume":"37","author":"Wu","year":"2021","journal-title":"Bioinformatics"},{"key":"2026091617364309900_vbag233-B43","author":"Zhang","year":"2017"},{"key":"2026091617364309900_vbag233-B44","first-page":"9597","article-title":"Lookahead optimizer: k steps forward, 1 step back","author":"Zhang","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026091617364309900_vbag233-B45","doi-asserted-by":"crossref","first-page":"bbae404","DOI":"10.1093\/bib\/bbae404","article-title":"PLM_sol: predicting protein solubility by benchmarking multiple protein language models with the updated Escherichia coli protein solubility dataset","volume":"25","author":"Zhang","year":"2024","journal-title":"Brief Bioinform"}],"container-title":["Bioinformatics Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/advance-article-pdf\/doi\/10.1093\/bioadv\/vbag233\/70648266\/vbag233.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article-pdf\/6\/1\/vbag233\/70648266\/vbag233.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article-pdf\/6\/1\/vbag233\/70648266\/vbag233.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T21:36:52Z","timestamp":1789594612000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article\/doi\/10.1093\/bioadv\/vbag233\/8761374"}},"subtitle":[],"editor":[{"given":"Nurcan","family":"Tun\u00e7ba\u011f","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,7]]}},"URL":"https:\/\/doi.org\/10.1093\/bioadv\/vbag233","relation":{},"ISSN":["2635-0041"],"issn-type":[{"value":"2635-0041","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026]]},"published":{"date-parts":[[2026]]},"article-number":"vbag233"}}