{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T09:08:01Z","timestamp":1776416881898,"version":"3.51.2"},"reference-count":19,"publisher":"Oxford University Press (OUP)","issue":"19","license":[{"start":{"date-parts":[[2017,5,29]],"date-time":"2017-05-29T00:00:00Z","timestamp":1496016000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Protein solubility is an important property in industrial and therapeutic applications. Prediction is a challenge, despite a growing understanding of the relevant physicochemical properties.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Protein\u2013Sol is a web server for predicting protein solubility. Using available data for Escherichia coli protein solubility in a cell-free expression system, 35 sequence-based properties are calculated. Feature weights are determined from separation of low and high solubility subsets. The model returns a predicted solubility and an indication of the features which deviate most from average values. Two other properties are profiled in windowed calculation along the sequence: fold propensity, and net segment charge. The utility of these additional features is demonstrated with the example of thioredoxin.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The Protein\u2013Sol webserver is available at http:\/\/protein-sol.manchester.ac.uk.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btx345","type":"journal-article","created":{"date-parts":[[2017,5,26]],"date-time":"2017-05-26T19:14:08Z","timestamp":1495826048000},"page":"3098-3100","source":"Crossref","is-referenced-by-count":728,"title":["Protein\u2013Sol: a web tool for predicting protein solubility from sequence"],"prefix":"10.1093","volume":"33","author":[{"given":"Max","family":"Hebditch","sequence":"first","affiliation":[{"name":"School of Chemical Engineering and Analytical Science, Manchester Institute of Biotechnology, University of Manchester, Manchester, UK"}]},{"given":"M Alejandro","family":"Carballo-Amador","sequence":"additional","affiliation":[{"name":"School of Chemistry, Manchester Institute of Biotechnology, University of Manchester, Manchester, UK"}]},{"given":"Spyros","family":"Charonis","sequence":"additional","affiliation":[{"name":"School of Chemical Engineering and Analytical Science, Manchester Institute of Biotechnology, University of Manchester, Manchester, UK"}]},{"given":"Robin","family":"Curtis","sequence":"additional","affiliation":[{"name":"School of Chemical Engineering and Analytical Science, Manchester Institute of Biotechnology, University of Manchester, Manchester, UK"}]},{"given":"Jim","family":"Warwicker","sequence":"additional","affiliation":[{"name":"School of Chemistry, Manchester Institute of Biotechnology, University of Manchester, Manchester, UK"}]}],"member":"286","published-online":{"date-parts":[[2017,5,29]]},"reference":[{"key":"2023020206472843500_btx345-B1","doi-asserted-by":"crossref","first-page":"2975","DOI":"10.1093\/bioinformatics\/btu420","article-title":"ccSOL omics: a webserver for large-scale prediction of endogenous and heterologous solubility in E. coli","volume":"30","author":"Agostini","year":"2014","journal-title":"Bioinformatics"},{"key":"2023020206472843500_btx345-B2","doi-asserted-by":"crossref","first-page":"5081","DOI":"10.1002\/jps.22705","article-title":"Aggregation in protein-based biotherapeutics: computational studies and tools to identify aggregation-prone regions","volume":"100","author":"Agrawal","year":"2011","journal-title":"J. Pharm. Sci"},{"key":"2023020206472843500_btx345-B3","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.bbrc.2006.01.159","article-title":"Amino acid propensities for secondary structures are influenced by the protein structural class","volume":"342","author":"Costantini","year":"2006","journal-title":"Biochem. Bioph. Res. Commun"},{"key":"2023020206472843500_btx345-B4","doi-asserted-by":"crossref","first-page":"18.","DOI":"10.1186\/1472-6807-7-18","article-title":"Mechanisms for stabilisation and the maintenance of solubility in proteins from thermophiles","volume":"7","author":"Greaves","year":"2007","journal-title":"BMC Struct. Biol"},{"key":"2023020206472843500_btx345-B5","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/0022-2836(90)90313-B","article-title":"Crystal structure of thioredoxin from Escherichia coli at 1.68 \u00c5 resolution","volume":"212","author":"Katti","year":"1990","journal-title":"J. Mol. Biol"},{"key":"2023020206472843500_btx345-B6","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/0022-2836(82)90515-0","article-title":"A simple method for displaying the hydropathic character of a protein","volume":"157","author":"Kyte","year":"1982","journal-title":"J. Mol. Biol"},{"key":"2023020206472843500_btx345-B7","doi-asserted-by":"crossref","first-page":"3701","DOI":"10.1093\/nar\/gkg519","article-title":"GlobPlot: exploring protein sequences for globularity and disorder","volume":"31","author":"Linding","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"2023020206472843500_btx345-B8","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":"2023020206472843500_btx345-B9","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1038\/nbt.1514","article-title":"Understanding the physical properties controlling protein crystallization","volume":"27","author":"Price","year":"2009","journal-title":"Nature Biotechnol"},{"key":"2023020206472843500_btx345-B10","doi-asserted-by":"crossref","first-page":"4201","DOI":"10.1073\/pnas.0811922106","article-title":"Bimodal protein solubility distribution revealed by an aggregation analysis of the entire ensemble of Escherichia coli proteins","volume":"106","author":"Niwa","year":"2009","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023020206472843500_btx345-B11","doi-asserted-by":"crossref","first-page":"4644","DOI":"10.1073\/pnas.032671499","article-title":"The complete genome of hyperthermophile Methanopyrus kandleri AV19 and monophyly of archaeal methanogens","volume":"99","author":"Slesarev","year":"2002","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023020206472843500_btx345-B12","doi-asserted-by":"crossref","first-page":"1395","DOI":"10.1039\/b706784b","article-title":"The Zyggregator method for predicting protein aggregation propensities","volume":"37","author":"Tartaglia","year":"2008","journal-title":"Chem. Soc. Rev"},{"key":"2023020206472843500_btx345-B13","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.tibs.2007.03.005","article-title":"Life on the edge: a link between gene expression levels and aggregation rates of human proteins","volume":"32","author":"Tartaglia","year":"2007","journal-title":"Trends Biochem. Sci"},{"key":"2023020206472843500_btx345-B14","doi-asserted-by":"crossref","first-page":"D158.","DOI":"10.1093\/nar\/gkw1099","article-title":"UniProt: the universal protein knowledgebase","volume":"45","author":"UniProt Consortium","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2023020206472843500_btx345-B15","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1002\/1097-0134(20001115)41:3<415::AID-PROT130>3.0.CO;2-7","article-title":"Why are \u201cnatively unfolded\u201d proteins unstructured under physiologic conditions?","volume":"41","author":"Uversky","year":"2000","journal-title":"Proteins"},{"key":"2023020206472843500_btx345-B16","doi-asserted-by":"crossref","first-page":"3163","DOI":"10.1002\/pmic.201400441","article-title":"Version 4.0 of PaxDb: protein abundance data, integrated across model organisms, tissues, and cell-lines","volume":"15","author":"Wang","year":"2015","journal-title":"Proteomics"},{"key":"2023020206472843500_btx345-B17","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1021\/mp4004749","article-title":"Lysine and arginine content of proteins: computational analysis suggests a new tool for solubility design","volume":"11","author":"Warwicker","year":"2014","journal-title":"Mol. Pharm"},{"key":"2023020206472843500_btx345-B18","first-page":"443","article-title":"Predicting the solubility of recombinant proteins in Escherichia coli","volume":"9","author":"Wilkinson","year":"1991","journal-title":"Bio\/Technology"},{"key":"2023020206472843500_btx345-B19","doi-asserted-by":"crossref","first-page":"25328","DOI":"10.1074\/jbc.270.43.25328","article-title":"Increase of solubility of foreign proteins in Escherichia coli by coproduction of the bacterial thioredoxin. Increase of solubility of foreign proteins in Escherichia coli by coproduction of the bacterial thioredoxin","volume":"270","author":"Yasukawa","year":"1995","journal-title":"J. Biol. Chem"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/19\/3098\/49041604\/bioinformatics_33_19_3098.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/19\/3098\/49041604\/bioinformatics_33_19_3098.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T06:48:10Z","timestamp":1675320490000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/19\/3098\/3857748"}},"subtitle":[],"editor":[{"given":"Alfonso","family":"Valencia","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2017,5,29]]},"references-count":19,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2017,10,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx345","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,10,1]]},"published":{"date-parts":[[2017,5,29]]}}}