{"id":"https://openalex.org/W2119246926","doi":"https://doi.org/10.1093/bioinformatics/btl623","title":"Protein solubility: sequence based prediction and experimental verification","display_name":"Protein solubility: sequence based prediction and experimental verification","publication_year":2006,"publication_date":"2006-12-06","ids":{"openalex":"https://openalex.org/W2119246926","doi":"https://doi.org/10.1093/bioinformatics/btl623","mag":"2119246926","pmid":"https://pubmed.ncbi.nlm.nih.gov/17150993"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btl623","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl623","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/19/2536/49857430/bioinformatics_23_19_2536.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/23/19/2536/49857430/bioinformatics_23_19_2536.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059153212","display_name":"Pawel Smialowski","orcid":"https://orcid.org/0000-0002-1020-3341"},"institutions":[{"id":"https://openalex.org/I309496635","display_name":"Weihenstephan-Triesdorf University of Applied Sciences","ror":"https://ror.org/00gzkxz88","country_code":"DE","type":"education","lineage":["https://openalex.org/I309496635"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pawel Smialowski","raw_affiliation_strings":["Department of Genome Oriented Bioinformatics, Technische Universit\u00e4t M\u00fcnchen, Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany","Department of Genome Oriented Bioinformatics, Technische Universit\u00e4t M\u00fcnchen Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genome Oriented Bioinformatics, Technische Universit\u00e4t M\u00fcnchen, Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany","institution_ids":["https://openalex.org/I309496635","https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Genome Oriented Bioinformatics, Technische Universit\u00e4t M\u00fcnchen Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059354705","display_name":"Antonio J. Mart\u00edn-Galiano","orcid":"https://orcid.org/0000-0002-6662-329X"},"institutions":[{"id":"https://openalex.org/I309496635","display_name":"Weihenstephan-Triesdorf University of Applied Sciences","ror":"https://ror.org/00gzkxz88","country_code":"DE","type":"education","lineage":["https://openalex.org/I309496635"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Antonio J. Martin-Galiano","raw_affiliation_strings":["Department of Genome Oriented Bioinformatics, Technische Universita \u00a8t Mu \u00a8nchen, Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genome Oriented Bioinformatics, Technische Universita \u00a8t Mu \u00a8nchen, Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany and","institution_ids":["https://openalex.org/I309496635","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001549253","display_name":"Aleksandra Mikolajka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150093","display_name":"Max Planck Institute of Biochemistry","ror":"https://ror.org/04py35477","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210150093"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Aleksandra Mikolajka","raw_affiliation_strings":["1 Department of Genome Oriented Bioinformatics, Technische Universit\u00e4t M\u00fcnchen, Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany and 1Max Planck Institute for Biochemistry, 82152 Martinsried, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Genome Oriented Bioinformatics, Technische Universit\u00e4t M\u00fcnchen, Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany and 1Max Planck Institute for Biochemistry, 82152 Martinsried, Germany","institution_ids":["https://openalex.org/I4210150093","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030634901","display_name":"Tobias Girschick","orcid":null},"institutions":[{"id":"https://openalex.org/I309496635","display_name":"Weihenstephan-Triesdorf University of Applied Sciences","ror":"https://ror.org/00gzkxz88","country_code":"DE","type":"education","lineage":["https://openalex.org/I309496635"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Girschick","raw_affiliation_strings":["Department of Genome Oriented Bioinformatics, Technische Universita \u00a8t Mu \u00a8nchen, Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genome Oriented Bioinformatics, Technische Universita \u00a8t Mu \u00a8nchen, Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany and","institution_ids":["https://openalex.org/I309496635","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051873783","display_name":"Tad A. Holak","orcid":"https://orcid.org/0000-0001-9369-6024"},"institutions":[{"id":"https://openalex.org/I4210150093","display_name":"Max Planck Institute of Biochemistry","ror":"https://ror.org/04py35477","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210150093"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tad A. Holak","raw_affiliation_strings":["1 Department of Genome Oriented Bioinformatics, Technische Universit\u00e4t M\u00fcnchen, Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany and 1Max Planck Institute for Biochemistry, 82152 Martinsried, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Genome Oriented Bioinformatics, Technische Universit\u00e4t M\u00fcnchen, Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany and 1Max Planck Institute for Biochemistry, 82152 Martinsried, Germany","institution_ids":["https://openalex.org/I4210150093","https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103088733","display_name":"Dmitrij Frishman","orcid":"https://orcid.org/0000-0001-7744-9402"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Dmitrij Frishman","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103088733"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.1611,"has_fulltext":true,"cited_by_count":170,"citation_normalized_percentile":{"value":0.86742443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"23","issue":"19","first_page":"2536","last_page":"2542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9993000030517578,"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":0.9993000030517578,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9987999796867371,"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/T11162","display_name":"Enzyme Structure and Function","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/solubility","display_name":"Solubility","score":0.7933211922645569},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6952080726623535},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6102241277694702},{"id":"https://openalex.org/keywords/pseudo-amino-acid-composition","display_name":"Pseudo amino acid composition","score":0.5334981083869934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5226259827613831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5053146481513977},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4844062924385071},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.45583227276802063},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.45338332653045654},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3833630681037903},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34706413745880127},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.2898944020271301},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2825887203216553},{"id":"https://openalex.org/keywords/amino-acid","display_name":"Amino acid","score":0.2319280207157135},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.19142848253250122},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.1324400007724762}],"concepts":[{"id":"https://openalex.org/C155574463","wikidata":"https://www.wikidata.org/wiki/Q170731","display_name":"Solubility","level":2,"score":0.7933211922645569},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6952080726623535},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6102241277694702},{"id":"https://openalex.org/C2780362125","wikidata":"https://www.wikidata.org/wiki/Q7254464","display_name":"Pseudo amino acid composition","level":4,"score":0.5334981083869934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5226259827613831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5053146481513977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4844062924385071},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.45583227276802063},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.45338332653045654},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3833630681037903},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34706413745880127},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.2898944020271301},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2825887203216553},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.2319280207157135},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.19142848253250122},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.1324400007724762},{"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/C2779138802","wikidata":"https://www.wikidata.org/wiki/Q418602","display_name":"Dipeptide","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","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},{"descriptor_ui":"D012997","descriptor_name":"Solvents","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012997","descriptor_name":"Solvents","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012997","descriptor_name":"Solvents","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/btl623","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl623","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/19/2536/49857430/bioinformatics_23_19_2536.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:17150993","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17150993","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:CiteSeerX.psu:10.1.1.104.5758","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.5758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/cgi/reprint/btl623v1.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:328054","is_oa":false,"landing_page_url":"http://edoc.mpg.de/328054","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, v.23, 2536-2542 (2007)","raw_type":"Article"},{"id":"pmh:oai:pure.mpg.de:item_1579994","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0010-5EF3-5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btl623","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl623","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/19/2536/49857430/bioinformatics_23_19_2536.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2119246926.pdf","grobid_xml":"https://content.openalex.org/works/W2119246926.grobid-xml"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W243303449","https://openalex.org/W1504719146","https://openalex.org/W1507029541","https://openalex.org/W1512098439","https://openalex.org/W1536886974","https://openalex.org/W1558974213","https://openalex.org/W1574206268","https://openalex.org/W1588000118","https://openalex.org/W1604938182","https://openalex.org/W1847611580","https://openalex.org/W1863266496","https://openalex.org/W1963523582","https://openalex.org/W1968218728","https://openalex.org/W1975304761","https://openalex.org/W1985118646","https://openalex.org/W1994322185","https://openalex.org/W2002692958","https://openalex.org/W2004346851","https://openalex.org/W2005986251","https://openalex.org/W2014731953","https://openalex.org/W2017337590","https://openalex.org/W2019210215","https://openalex.org/W2023071489","https://openalex.org/W2039388179","https://openalex.org/W2047186187","https://openalex.org/W2049633694","https://openalex.org/W2057021995","https://openalex.org/W2060287713","https://openalex.org/W2067602907","https://openalex.org/W2074369001","https://openalex.org/W2097152121","https://openalex.org/W2097423696","https://openalex.org/W2108211735","https://openalex.org/W2109449939","https://openalex.org/W2109676405","https://openalex.org/W2118619377","https://openalex.org/W2125769071","https://openalex.org/W2127042504","https://openalex.org/W2129499385","https://openalex.org/W2130479394","https://openalex.org/W2131965976","https://openalex.org/W2135083016","https://openalex.org/W2135737874","https://openalex.org/W2137450588","https://openalex.org/W2137490166","https://openalex.org/W2138816428","https://openalex.org/W2144587714","https://openalex.org/W2148676725","https://openalex.org/W2151040995","https://openalex.org/W2151430326","https://openalex.org/W2151548440","https://openalex.org/W2152770371","https://openalex.org/W2155144535","https://openalex.org/W2156494890","https://openalex.org/W2160675155","https://openalex.org/W2160721947","https://openalex.org/W2164511624","https://openalex.org/W2166204890","https://openalex.org/W2235129190","https://openalex.org/W2239384431","https://openalex.org/W2255304239","https://openalex.org/W3129711340","https://openalex.org/W4213345021","https://openalex.org/W4244736178","https://openalex.org/W4247571305","https://openalex.org/W4250555591","https://openalex.org/W4319425375","https://openalex.org/W4320300861","https://openalex.org/W6630233695","https://openalex.org/W6630527977","https://openalex.org/W6639093311","https://openalex.org/W6671376181"],"related_works":["https://openalex.org/W2537862391","https://openalex.org/W2417174640","https://openalex.org/W1987193419","https://openalex.org/W2123706975","https://openalex.org/W2574994322","https://openalex.org/W2046691535","https://openalex.org/W2008162067","https://openalex.org/W576256462","https://openalex.org/W1996989509","https://openalex.org/W4389980359"],"abstract_inverted_index":{"MOTIVATION:":[0],"Obtaining":[1],"soluble":[2,73],"proteins":[3,22],"in":[4,12,52,77,95],"sufficient":[5],"concentrations":[6],"is":[7,17,31,45,89],"a":[8,25,59,69,92,110],"recurring":[9],"limiting":[10],"factor":[11],"various":[13],"experimental":[14,29,183],"studies.":[15],"Solubility":[16],"an":[18],"individual":[19],"trait":[20],"of":[21,28,41,68,99,133,156,169,185,195],"which,":[23],"under":[24],"given":[26],"set":[27],"conditions,":[30],"determined":[32],"by":[33,150],"their":[34],"amino":[35,83],"acid":[36,84],"sequence.":[37],"Accurate":[38],"theoretical":[39],"prediction":[40,167],"solubility":[42,162,189],"from":[43,118],"sequence":[44],"instrumental":[46],"for":[47,109,174,191],"setting":[48],"priorities":[49],"on":[50,81],"targets":[51],"large-scale":[53],"proteomics":[54],"projects.":[55],"RESULTS:":[56],"We":[57,180],"present":[58],"machine-learning":[60],"approach":[61],"called":[62],"PROSO":[63],"to":[64,71],"assess":[65],"the":[66,97,119,131,151,165],"chance":[67],"protein":[70],"be":[72],"upon":[74],"heterologous":[75],"expression":[76],"Escherichia":[78],"coli":[79],"based":[80],"its":[82],"composition.":[85],"The":[86],"classification":[87,143],"algorithm":[88,144],"organized":[90],"as":[91,107,122,124,130],"two-layered":[93],"structure":[94],"which":[96],"output":[98],"primary":[100],"support":[101],"vector":[102],"machine":[103],"(SVM)":[104],"classifiers":[105],"serves":[106],"input":[108],"secondary":[111],"Naive":[112],"Bayes":[113],"classifier.":[114],"Experimental":[115],"progress":[116],"information":[117],"TargetDB":[120],"database":[121],"well":[123],"previously":[125,139],"published":[126,140],"datasets":[127],"were":[128],"used":[129],"source":[132],"training":[134],"data.":[135],"In":[136],"comparison":[137],"with":[138],"methods":[141],"our":[142,186],"possesses":[145],"improved":[146],"discriminatory":[147],"capacity":[148],"characterized":[149],"Matthews":[152],"Correlation":[153],"Coefficient":[154],"(MCC)":[155],"0.434":[157],"between":[158],"predicted":[159],"and":[160,164,172,176],"known":[161],"states":[163],"overall":[166],"accuracy":[168],"72%":[170],"(75":[171],"68%":[173],"positive":[175],"negative":[177],"class,":[178],"respectively).":[179],"also":[181],"provide":[182],"verification":[184],"predictions":[187],"using":[188],"measurements":[190],"31":[192],"mutational":[193],"variants":[194],"two":[196],"different":[197],"proteins.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":9}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}