{"id":"https://openalex.org/W3216325381","doi":"https://doi.org/10.1093/bioinformatics/btab801","title":"NetSolP: predicting protein solubility in <i>Escherichia coli</i> using language models","display_name":"NetSolP: predicting protein solubility in <i>Escherichia coli</i> using language models","publication_year":2021,"publication_date":"2021-11-23","ids":{"openalex":"https://openalex.org/W3216325381","doi":"https://doi.org/10.1093/bioinformatics/btab801","mag":"3216325381","pmid":"https://pubmed.ncbi.nlm.nih.gov/35088833"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab801","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab801","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/4/941/42319656/btab801.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/38/4/941/42319656/btab801.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090032330","display_name":"Vineet Thumuluri","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vineet Thumuluri","raw_affiliation_strings":["Indian Institute of Technology Madras , India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras , India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075987962","display_name":"Hannah-Marie Martiny","orcid":"https://orcid.org/0000-0001-6733-7888"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Hannah-Marie Martiny","raw_affiliation_strings":["Research Group for Genomic Epidemiology, National Food Institute, Technical University of Denmark , Lyngby 2800, Denmark"],"affiliations":[{"raw_affiliation_string":"Research Group for Genomic Epidemiology, National Food Institute, Technical University of Denmark , Lyngby 2800, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067812333","display_name":"Jos\u00e9 Juan Almagro Armenteros","orcid":"https://orcid.org/0000-0003-0111-1362"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I2801134892","display_name":"Novo Nordisk Foundation","ror":"https://ror.org/04txyc737","country_code":"DK","type":"facility","lineage":["https://openalex.org/I2801134892"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jose J Almagro Armenteros","raw_affiliation_strings":["Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen , 2200 Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen , 2200 Copenhagen, Denmark","institution_ids":["https://openalex.org/I2801134892","https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021661112","display_name":"Jesper Salomon","orcid":"https://orcid.org/0000-0003-2445-6582"},"institutions":[{"id":"https://openalex.org/I106887733","display_name":"Novozymes (Denmark)","ror":"https://ror.org/03ejz0s07","country_code":"DK","type":"company","lineage":["https://openalex.org/I106887733","https://openalex.org/I2801134892","https://openalex.org/I4210159963"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Salomon","raw_affiliation_strings":["Enzyme Research , Novozymes A/S, Lyngby 2800, Denmark"],"affiliations":[{"raw_affiliation_string":"Enzyme Research , Novozymes A/S, Lyngby 2800, Denmark","institution_ids":["https://openalex.org/I106887733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002675555","display_name":"Henrik Nielsen","orcid":"https://orcid.org/0000-0002-9412-9643"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Henrik Nielsen","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark , Lyngby 2800, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark , Lyngby 2800, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044404289","display_name":"Alexander Rosenberg Johansen","orcid":"https://orcid.org/0000-0002-4993-7916"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alexander Rosenberg Johansen","raw_affiliation_strings":["Department of Computer Science, Stanford University , Stanford, CA 94305, USA","Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University , Stanford, CA 94305, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5044404289"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":3.0096,"has_fulltext":true,"cited_by_count":96,"citation_normalized_percentile":{"value":0.92738589,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"38","issue":"4","first_page":"941","last_page":"946"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9937000274658203,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9937000274658203,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9900000095367432,"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/T10028","display_name":"Topic Modeling","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/escherichia-coli","display_name":"Escherichia coli","score":0.7526029348373413},{"id":"https://openalex.org/keywords/solubility","display_name":"Solubility","score":0.6277076601982117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44434836506843567},{"id":"https://openalex.org/keywords/escherichia-coli-proteins","display_name":"Escherichia coli Proteins","score":0.4280083179473877},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.3681960105895996},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3240948021411896},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.29720553755760193},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.24052157998085022},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.09236767888069153}],"concepts":[{"id":"https://openalex.org/C547475151","wikidata":"https://www.wikidata.org/wiki/Q25419","display_name":"Escherichia coli","level":3,"score":0.7526029348373413},{"id":"https://openalex.org/C155574463","wikidata":"https://www.wikidata.org/wiki/Q170731","display_name":"Solubility","level":2,"score":0.6277076601982117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44434836506843567},{"id":"https://openalex.org/C2908821069","wikidata":"https://www.wikidata.org/wiki/Q25419","display_name":"Escherichia coli Proteins","level":4,"score":0.4280083179473877},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3681960105895996},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3240948021411896},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.29720553755760193},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.24052157998085022},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.09236767888069153},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btab801","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab801","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/4/941/42319656/btab801.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35088833","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35088833","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/940f6c71-b1d6-4902-b3f0-6cdec0e877fb","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/940f6c71-b1d6-4902-b3f0-6cdec0e877fb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Thumuluri , V , Martiny , H M , Almagro Armenteros , J J , Salomon , J , Nielsen , H & Johansen , A R 2022 , ' NetSolP : predicting protein solubility in Escherichia coli using language models ' , Bioinformatics , vol. 38 , no. 4 , pp. 941-946 . https://doi.org/10.1093/bioinformatics/btab801","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btab801","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab801","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/4/941/42319656/btab801.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3216325381.pdf","grobid_xml":"https://content.openalex.org/works/W3216325381.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1588724272","https://openalex.org/W1967293793","https://openalex.org/W2015292449","https://openalex.org/W2024970329","https://openalex.org/W2072678801","https://openalex.org/W2075644998","https://openalex.org/W2080057469","https://openalex.org/W2102461176","https://openalex.org/W2103083136","https://openalex.org/W2104756056","https://openalex.org/W2116595386","https://openalex.org/W2124351063","https://openalex.org/W2126258012","https://openalex.org/W2152575748","https://openalex.org/W2171698890","https://openalex.org/W2557595285","https://openalex.org/W2594633041","https://openalex.org/W2613688952","https://openalex.org/W2620185010","https://openalex.org/W2766578745","https://openalex.org/W2794004073","https://openalex.org/W2805241968","https://openalex.org/W2950954328","https://openalex.org/W3022229786","https://openalex.org/W3036344389","https://openalex.org/W3119780302","https://openalex.org/W3121116873","https://openalex.org/W3146944767","https://openalex.org/W3166925323","https://openalex.org/W3208864053","https://openalex.org/W4287724045","https://openalex.org/W6734194636","https://openalex.org/W6780145172"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W2135850184","https://openalex.org/W2252376317","https://openalex.org/W2022891666","https://openalex.org/W2727878429","https://openalex.org/W2469250300","https://openalex.org/W1479745535","https://openalex.org/W3208158820"],"abstract_inverted_index":{"Supplementary":[0],"data":[1],"are":[2],"available":[3],"at":[4],"Bioinformatics":[5],"online.":[6]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":40},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2021-12-06T00:00:00"}
