{"id":"https://openalex.org/W2014201485","doi":"https://doi.org/10.1109/escience.2012.6404416","title":"Prediction of protein solubility in E. coli","display_name":"Prediction of protein solubility in E. coli","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W2014201485","doi":"https://doi.org/10.1109/escience.2012.6404416","mag":"2014201485"},"language":"en","primary_location":{"id":"doi:10.1109/escience.2012.6404416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2012.6404416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 8th International Conference on E-Science","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082534966","display_name":"Taghrid Samak","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Taghrid Samak","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027568646","display_name":"Dan Gunter","orcid":"https://orcid.org/0000-0002-2779-2744"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Gunter","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100781872","display_name":"Zhong Wang","orcid":"https://orcid.org/0000-0002-6307-0458"},"institutions":[{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Wang","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA","Department of Energy, Joint Genome Institute, Walnut Creek, CA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Department of Energy, Joint Genome Institute, Walnut Creek, CA","institution_ids":["https://openalex.org/I196679689"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082534966"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":0.1341,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.51515022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/solubility","display_name":"Solubility","score":0.8570965528488159},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5837603211402893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5201597213745117},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49455639719963074},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.47291597723960876},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.43927302956581116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39467909932136536},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38440605998039246},{"id":"https://openalex.org/keywords/biological-system","display_name":"Biological system","score":0.37745505571365356},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2989846467971802},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.2871605157852173},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.28477293252944946},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.23840904235839844},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.20505419373512268}],"concepts":[{"id":"https://openalex.org/C155574463","wikidata":"https://www.wikidata.org/wiki/Q170731","display_name":"Solubility","level":2,"score":0.8570965528488159},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5837603211402893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5201597213745117},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49455639719963074},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.47291597723960876},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.43927302956581116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39467909932136536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38440605998039246},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.37745505571365356},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2989846467971802},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.2871605157852173},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.28477293252944946},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.23840904235839844},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.20505419373512268},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/escience.2012.6404416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2012.6404416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 8th International Conference on E-Science","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1548911371","https://openalex.org/W1993282040","https://openalex.org/W1996423252","https://openalex.org/W2067602907","https://openalex.org/W2090909522","https://openalex.org/W2109449939","https://openalex.org/W2119246926","https://openalex.org/W2133458779","https://openalex.org/W2147189708","https://openalex.org/W2164511624","https://openalex.org/W2171533950"],"related_works":["https://openalex.org/W1990608904","https://openalex.org/W1539400370","https://openalex.org/W2007219878","https://openalex.org/W1934224411","https://openalex.org/W1561807720","https://openalex.org/W2005109573","https://openalex.org/W2393951301","https://openalex.org/W2006697860","https://openalex.org/W2080187647","https://openalex.org/W1564792705"],"abstract_inverted_index":{"Gene":[0],"synthesis":[1,39],"is":[2,16,134,148,181],"a":[3,17,41,67,120,205],"key":[4],"step":[5],"to":[6,11,56,85,93,113,128,136,187,193],"convert":[7],"digitally":[8],"predicted":[9,158],"proteins":[10,28],"functional":[12],"proteins.":[13,116,154],"However,":[14],"it":[15],"relatively":[18],"expensive":[19],"and":[20,166,183,212],"labor-intensive":[21],"process.":[22],"About":[23],"30-50%":[24],"of":[25,37,61,72,82,171,190],"the":[26,35,54,59,78,83,104,141,159,172,202],"synthesized":[27],"are":[29,110],"not":[30],"soluble,":[31],"thereby":[32],"further":[33],"reduces":[34],"efficacy":[36],"gene":[38,62],"as":[40],"method":[42],"for":[43,97],"protein":[44,51,80,130,138],"function":[45],"characterization.":[46],"Solubility":[47],"prediction":[48],"from":[49,74],"primary":[50,79],"sequences":[52,81],"holds":[53],"promise":[55],"dramatically":[57],"reduce":[58],"cost":[60],"synthesis.":[63],"This":[64,99],"work":[65],"presents":[66],"framework":[68,121,133,199],"that":[69,109,122],"creates":[70],"models":[71,96],"solubility":[73,139,160],"sequence":[75,88,191],"information.":[76],"From":[77],"genes":[84,108],"be":[86,91,185],"synthesized,":[87],"features":[89,175,192],"can":[90,102,184],"used":[92,135],"build":[94],"computational":[95],"solubility.":[98,131,177],"way,":[100],"biologists":[101],"focus":[103],"effort":[105],"on":[106,150],"synthesizing":[107],"highly":[111],"likely":[112],"generate":[114],"soluble":[115],"We":[117],"have":[118],"developed":[119],"employs":[123],"several":[124],"machine":[125],"learning":[126,210],"algorithms":[127],"model":[129],"The":[132,146,155,178,198],"predict":[137,194],"in":[140,168],"Escherichia":[142],"coli":[143],"expression":[144],"system.":[145],"analysis":[147,170,179],"performed":[149],"over":[151],"1,600":[152],"quantified":[153],"approach":[156],"successfully":[157],"with":[161,204],"more":[162],"than":[163],"80%":[164],"accuracy,":[165],"enabled":[167],"depth":[169],"most":[173],"important":[174],"affecting":[176],"pipeline":[180],"general":[182],"applied":[186],"any":[188,195],"set":[189],"binary":[196],"measure.":[197],"also":[200],"provides":[201],"biologist":[203],"comprehensive":[206],"comparison":[207],"between":[208],"different":[209],"algorithms,":[211],"insightful":[213],"feature":[214],"analysis.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
