{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T04:44:12Z","timestamp":1792471452225,"version":"4.5.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFC2102700, 2019YFA0905700"],"award-info":[{"award-number":["2021YFC2102700, 2019YFA0905700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Protein solubility is a critically important physicochemical property closely related to protein expression. For example, it is one of the main factors to be considered in the design and production of antibody drugs and a prerequisite for realizing various protein functions. Although several solubility prediction models have emerged in recent years, many of these models are limited to capturing information embedded in one-dimensional amino acid sequences, resulting in unsatisfactory predictive performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      In this study, we introduce a novel Graph Attention network-based protein Solubility model, GATSol, which represents the 3D structure of proteins as a protein graph. In addition to the node features of amino acids extracted by the state-of-the-art protein large language model, GATSol utilizes amino acid distance maps generated using the latest AlphaFold technology. Rigorous testing on independent eSOL and the\n                      <jats:italic>Saccharomyces cerevisiae<\/jats:italic>\n                      test datasets has shown that GATSol outperforms most recently introduced models, especially with respect to the coefficient of determination R\n                      <jats:sup>2<\/jats:sup>\n                      , which reaches 0.517 and 0.424, respectively. It outperforms the current state-of-the-art GraphSol by 18.4% on the\n                      <jats:italic>S<\/jats:italic>\n                      .\n                      <jats:italic>cerevisiae<\/jats:italic>\n                      _test set.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>\n                      GATSol captures 3D dimensional features of proteins by building protein graphs, which significantly improves the accuracy of protein solubility prediction. Recent advances in protein structure modeling allow our method to incorporate spatial structure features extracted from predicted structures into the model by relying only on the input of protein sequences, which simplifies the entire graph neural network prediction process, making it more user-friendly and efficient. As a result, GATSol may help prioritize highly soluble proteins, ultimately reducing the cost and effort of experimental work. The source code and data of the GATSol model are freely available at\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/binbinbinv\/GATSol\">https:\/\/github.com\/binbinbinv\/GATSol<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12859-024-05820-8","type":"journal-article","created":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T06:01:24Z","timestamp":1717221684000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["GATSol, an enhanced predictor of protein solubility through the synergy of 3D structure graph and large language modeling"],"prefix":"10.1186","volume":"25","author":[{"given":"Bin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dengming","family":"Ming","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,6,1]]},"reference":[{"key":"5820_CR1","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1615\/CritRevTherDrugCarrierSyst.2013006955","volume":"30","author":"A Jain","year":"2013","unstructured":"Jain A, Jain A, Gulbake A, Shilpi S, Hurkat P, Jain SK. Peptide and protein delivery using new drug delivery systems. Crit Rev Ther Drug Carrier Syst. 2013;30:293\u2013329.","journal-title":"Crit Rev Ther Drug Carrier Syst"},{"key":"5820_CR2","first-page":"45a","volume":"118","author":"M Madani","year":"2020","unstructured":"Madani M, Tarakanova A. Molecular design of soluble zein protein sequences. Biophys J. 2020;118:45a.","journal-title":"Biophys J"},{"key":"5820_CR3","doi-asserted-by":"publisher","first-page":"14085","DOI":"10.1021\/acs.chemrev.1c00757","volume":"122","author":"R Qing","year":"2022","unstructured":"Qing R, Hao S, Smorodina E, Jin D, Zalevsky A, Zhang S. Protein design: from the aspect of water solubility and stability. Chem Rev. 2022;122:14085\u2013179.","journal-title":"Chem Rev"},{"key":"5820_CR4","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1038\/84389","volume":"19","author":"WC Wigley","year":"2001","unstructured":"Wigley WC, Stidham RD, Smith NM, Hunt JF, Thomas PJ. Protein solubility and folding monitored in vivo by structural complementation of a genetic marker protein. Nat Biotechnol. 2001;19:131\u20136.","journal-title":"Nat Biotechnol"},{"key":"5820_CR5","doi-asserted-by":"publisher","first-page":"2580","DOI":"10.1093\/bioinformatics\/btv162","volume":"31","author":"G De Baets","year":"2015","unstructured":"De Baets G, Van Durme J, van der Kant R, Schymkowitz J, Rousseau F. Solubis: optimize your protein. Bioinformatics. 2015;31:2580\u20132.","journal-title":"Bioinformatics"},{"key":"5820_CR6","doi-asserted-by":"publisher","first-page":"1949","DOI":"10.1007\/s12035-015-9148-8","volume":"53","author":"L Breydo","year":"2016","unstructured":"Breydo L, Morgan D, Uversky VN. Pseudocatalytic antiaggregation activity of antibodies: immunoglobulins can influence \u03b1-synuclein aggregation at substoichiometric concentrations. Mol Neurobiol. 2016;53:1949\u201358.","journal-title":"Mol Neurobiol"},{"key":"5820_CR7","doi-asserted-by":"publisher","first-page":"953","DOI":"10.1093\/bib\/bbt057","volume":"15","author":"CCH Chang","year":"2014","unstructured":"Chang CCH, Song J, Tey BT, Ramanan RN. Bioinformatics approaches for improved recombinant protein production in Escherichia coli: protein solubility prediction. Brief Bioinform. 2014;15:953\u201362.","journal-title":"Brief Bioinform"},{"key":"5820_CR8","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1002\/(SICI)1097-0290(19991120)65:4<382::AID-BIT2>3.0.CO;2-I","volume":"65","author":"GD Davis","year":"1999","unstructured":"Davis GD, Elisee C, Newham DM, Harrison RG. New fusion protein systems designed to give soluble expression in Escherichia coli. Biotechnol Bioeng. 1999;65:382\u20138.","journal-title":"Biotechnol Bioeng"},{"key":"5820_CR9","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1110\/ps.041009005","volume":"14","author":"S Idicula-Thomas","year":"2005","unstructured":"Idicula-Thomas S, Balaji PV. Understanding the relationship between the primary structure of proteins and its propensity to be soluble on overexpression in Escherichia coli. Protein Sci. 2005;14:582\u201392.","journal-title":"Protein Sci"},{"key":"5820_CR10","first-page":"2200","volume":"25","author":"C Magnan","year":"2009","unstructured":"Magnan C, Randall A, Baldi P. SOLpro: accurate sequence-based prediction of protein solubility. Bioinformatics (Oxford, England). 2009;25:2200\u20137.","journal-title":"Bioinformatics (Oxford, England)"},{"key":"5820_CR11","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1080\/17460441.2019.1637413","volume":"14","author":"S Navarro","year":"2019","unstructured":"Navarro S, Ventura S. Computational re-design of protein structures to improve solubility. Expert Opin Drug Discov. 2019;14:1077\u201388.","journal-title":"Expert Opin Drug Discov"},{"key":"5820_CR12","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20:273\u201397.","journal-title":"Mach Learn"},{"key":"5820_CR13","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001;29:1189\u2013232.","journal-title":"Ann Stat"},{"key":"5820_CR14","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1109\/34.494647","volume":"18","author":"GA Babich","year":"1996","unstructured":"Babich GA, Camps OI. Weighted Parzen windows for pattern classification. IEEE Trans Pattern Anal Mach Intell. 1996;18:567\u201370.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5820_CR15","doi-asserted-by":"publisher","first-page":"2192","DOI":"10.1111\/j.1742-4658.2012.08603.x","volume":"279","author":"P Smialowski","year":"2012","unstructured":"Smialowski P, Doose G, Torkler P, Kaufmann S, Frishman D. PROSO II\u2013a new method for protein solubility prediction. FEBS J. 2012;279:2192\u2013200.","journal-title":"FEBS J"},{"key":"5820_CR16","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1093\/bioinformatics\/btaa1102","volume":"37","author":"J Hon","year":"2021","unstructured":"Hon J, Marusiak M, Martinek T, Kunka A, Zendulka J, Bednar D, et al. SoluProt: prediction of soluble protein expression in escherichia coli. Bioinformatics. 2021;37:23\u20138.","journal-title":"Bioinformatics"},{"key":"5820_CR17","doi-asserted-by":"publisher","first-page":"2605","DOI":"10.1093\/bioinformatics\/bty166","volume":"34","author":"S Khurana","year":"2018","unstructured":"Khurana S, Rawi R, Kunji K, Chuang G-Y, Bensmail H, Mall R. DeepSol: a deep learning framework for sequence-based protein solubility prediction. Bioinformatics. 2018;34:2605\u201313.","journal-title":"Bioinformatics"},{"key":"5820_CR18","unstructured":"LeCun Y, Bengio Y. Convolutional networks for images, speech, and time series. In: The handbook of brain theory and neural networks. Cambridge, MA, USA: MIT Press; 1998. p. 255\u20138."},{"key":"5820_CR19","doi-asserted-by":"publisher","first-page":"402","DOI":"10.2174\/138920209789177575","volume":"10","author":"B-J Yoon","year":"2009","unstructured":"Yoon B-J. Hidden markov models and their applications in biological sequence analysis. Curr Genomics. 2009;10:402\u201315.","journal-title":"Curr Genomics"},{"key":"5820_CR20","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s13321-021-00488-1","volume":"13","author":"J Chen","year":"2021","unstructured":"Chen J, Zheng S, Zhao H, Yang Y. Structure-aware protein solubility prediction from sequence through graph convolutional network and predicted contact map. J Cheminformatics. 2021;13:7.","journal-title":"J Cheminformatics"},{"key":"5820_CR21","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/s11538-017-0380-4","volume":"80","author":"Q-H Guo","year":"2018","unstructured":"Guo Q-H, Sun LH. Combinatorics of contacts in protein contact maps. Bull Math Biol. 2018;80:385\u2013403.","journal-title":"Bull Math Biol"},{"key":"5820_CR22","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","volume":"596","author":"J Jumper","year":"2021","unstructured":"Jumper J, Evans R, Pritzel A, Green T, Figurnov M, Ronneberger O, et al. Highly accurate protein structure prediction with AlphaFold. Nature. 2021;596:583\u20139.","journal-title":"Nature"},{"key":"5820_CR23","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1038\/d41573-021-00161-0","volume":"20","author":"A Mullard","year":"2021","unstructured":"Mullard A. What does AlphaFold mean for drug discovery? Nat Rev Drug Discovery. 2021;20:725\u20137.","journal-title":"Nat Rev Drug Discovery"},{"key":"5820_CR24","doi-asserted-by":"crossref","unstructured":"Nussinov R, Zhang M, Liu Y, Jang H. Alphafold, artificial intelligence (AI), and allostery. J Phys Chem B. 2022;126:6372\u201382","DOI":"10.1021\/acs.jpcb.2c04346"},{"key":"5820_CR25","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118","volume":"118","author":"A Rives","year":"2021","unstructured":"Rives A, Meier J, Sercu T, Goyal S, Lin Z, Liu J, et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc Natl Acad Sci. 2021;118: e2016239118.","journal-title":"Proc Natl Acad Sci"},{"key":"5820_CR26","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","volume":"44","author":"A Elnaggar","year":"2022","unstructured":"Elnaggar A, Heinzinger M, Dallago C, Rehawi G, Wang Y, Jones L, et al. ProtTrans: toward understanding the language of life through self-supervised learning. IEEE Trans Pattern Anal Mach Intell. 2022;44:7112\u201327.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5820_CR27","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Li\u00f2 P, Bengio Y. Graph attention networks. Preprint at https:\/\/arxiv.org\/abs\/1710.10903 (2018)."},{"key":"5820_CR28","doi-asserted-by":"publisher","first-page":"7624","DOI":"10.1038\/s41598-022-10418-2","volume":"12","author":"C Knutson","year":"2022","unstructured":"Knutson C, Bontha M, Bilbrey JA, Kumar N. Decoding the protein\u2013ligand interactions using parallel graph neural networks. Sci Rep. 2022;12:7624.","journal-title":"Sci Rep"},{"key":"5820_CR29","doi-asserted-by":"crossref","unstructured":"Abdine H, Chatzianastasis M, Bouyioukos C, Vazirgiannis M. Prot2Text: multimodal protein\u2019s function generation with GNNs and transformers. Preprint at https:\/\/arxiv.org\/abs\/2307.14367 (2024).","DOI":"10.1609\/aaai.v38i10.28948"},{"key":"5820_CR30","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1021\/ci034243x","volume":"44","author":"JS Delaney","year":"2004","unstructured":"Delaney JS. ESOL: estimating aqueous solubility directly from molecular structure. J Chem Inf Comput Sci. 2004;44:1000\u20135.","journal-title":"J Chem Inf Comput Sci"},{"key":"5820_CR31","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1016\/j.ymeth.2005.04.006","volume":"36","author":"Y Shimizu","year":"2005","unstructured":"Shimizu Y, Kanamori T, Ueda T. Protein synthesis by pure translation systems. Methods. 2005;36:299\u2013304.","journal-title":"Methods"},{"key":"5820_CR32","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.crbiot.2021.01.001","volume":"3","author":"MH G\u00edslason","year":"2021","unstructured":"G\u00edslason MH, Nielsen H, Almagro Armenteros JJ, Johansen AR. Prediction of GPI-anchored proteins with pointer neural networks. Current Research in Biotechnology. 2021;3:6\u201313.","journal-title":"Current Research in Biotechnology"},{"key":"5820_CR33","doi-asserted-by":"publisher","first-page":"2444","DOI":"10.1073\/pnas.85.8.2444","volume":"85","author":"WR Pearson","year":"1988","unstructured":"Pearson WR, Lipman DJ. Improved tools for biological sequence comparison. Proc Natl Acad Sci USA. 1988;85:2444\u20138.","journal-title":"Proc Natl Acad Sci USA"},{"key":"5820_CR34","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.1093\/bioinformatics\/btz773","volume":"36","author":"Q Hou","year":"2020","unstructured":"Hou Q, Kwasigroch JM, Rooman M, Pucci F. SOLart: a structure-based method to predict protein solubility and aggregation. Bioinformatics. 2020;36:1445\u201352.","journal-title":"Bioinformatics"},{"key":"5820_CR35","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1016\/j.patcog.2019.06.012","volume":"95","author":"Q Zhang","year":"2019","unstructured":"Zhang Q, Chang J, Meng G, Xu S, Xiang S, Pan C. Learning graph structure via graph convolutional networks. Pattern Recogn. 2019;95:308\u201318.","journal-title":"Pattern Recogn"},{"key":"5820_CR36","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1038\/nbt0804-1035","volume":"22","author":"SR Eddy","year":"2004","unstructured":"Eddy SR. Where did the BLOSUM62 alignment score matrix come from? Nat Biotechnol. 2004;22:1035\u20136.","journal-title":"Nat Biotechnol"},{"key":"5820_CR37","doi-asserted-by":"crossref","unstructured":"Rahmani A, Mirakabad FZ. An extension of Wang\u2019s protein design model using Blosum62 substitution matrix. 2021;2021.06.07.447415.","DOI":"10.1101\/2021.06.07.447415"},{"key":"5820_CR38","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1038\/s41586-023-06415-8","volume":"620","author":"JL Watson","year":"2023","unstructured":"Watson JL, Juergens D, Bennett NR, Trippe BL, Yim J, Eisenach HE, et al. De novo design of protein structure and function with RFdiffusion. Nature. 2023;620:1089\u2013100.","journal-title":"Nature"},{"key":"5820_CR39","first-page":"1","volume":"35","author":"R Lin","year":"2022","unstructured":"Lin R, Zhou Z, You S, Rao R, Kuo C-CJ. Geometrical interpretation and design of multilayer perceptrons. IEEE Trans Neural Netw Learn Syst. 2022;35:1\u201315.","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"5820_CR40","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2023.2197686","author":"S Bates","year":"2023","unstructured":"Bates S, Hastie T, Tibshirani R. Cross-validation: what does it estimate and how well does it do it? J Am Stat Assoc. 2023. https:\/\/doi.org\/10.1080\/01621459.2023.2197686.","journal-title":"J Am Stat Assoc"},{"key":"5820_CR41","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s12915-023-01510-8","volume":"21","author":"C Wang","year":"2023","unstructured":"Wang C, Zou Q. Prediction of protein solubility based on sequence physicochemical patterns and distributed representation information with DeepSoluE. BMC Biol. 2023;21:12.","journal-title":"BMC Biol"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-024-05820-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-024-05820-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-024-05820-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T08:03:11Z","timestamp":1731052991000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-024-05820-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,1]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["5820"],"URL":"https:\/\/doi.org\/10.1186\/s12859-024-05820-8","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,1]]},"assertion":[{"value":"20 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"204"}}