{"id":"https://openalex.org/W4317779747","doi":"https://doi.org/10.1093/bioinformatics/btad048","title":"GOThresher: a program to remove annotation biases from protein function annotation datasets","display_name":"GOThresher: a program to remove annotation biases from protein function annotation datasets","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4317779747","doi":"https://doi.org/10.1093/bioinformatics/btad048","pmid":"https://pubmed.ncbi.nlm.nih.gov/36688705"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad048","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad048","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad048/48957207/btad048.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad048/48957207/btad048.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047013340","display_name":"Parnal Joshi","orcid":"https://orcid.org/0000-0001-6689-3858"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parnal Joshi","raw_affiliation_strings":["Bioinformatics and Computational Biology Program, Iowa State University , Ames, IA 50011, USA","Department of Veterinary Microbiology and Preventive Medicine, Iowa State University , Ames, IA 50011, USA"],"affiliations":[{"raw_affiliation_string":"Bioinformatics and Computational Biology Program, Iowa State University , Ames, IA 50011, USA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Department of Veterinary Microbiology and Preventive Medicine, Iowa State University , Ames, IA 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004906719","display_name":"Sagnik Banerjee","orcid":"https://orcid.org/0000-0002-2052-7577"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sagnik Banerjee","raw_affiliation_strings":["Bioinformatics and Computational Biology Program, Iowa State University , Ames, IA 50011, USA","Department of Statistics, Iowa State University , Ames, IA 50011, USA"],"affiliations":[{"raw_affiliation_string":"Bioinformatics and Computational Biology Program, Iowa State University , Ames, IA 50011, USA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Department of Statistics, Iowa State University , Ames, IA 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057994049","display_name":"Xiao Hu","orcid":"https://orcid.org/0000-0002-3309-9575"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Hu","raw_affiliation_strings":["Department of Veterinary Microbiology and Preventive Medicine, Iowa State University , Ames, IA 50011, USA"],"affiliations":[{"raw_affiliation_string":"Department of Veterinary Microbiology and Preventive Medicine, Iowa State University , Ames, IA 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080089792","display_name":"Pranav M. Khade","orcid":"https://orcid.org/0000-0002-0756-9828"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pranav M Khade","raw_affiliation_strings":["Bioinformatics and Computational Biology Program, Iowa State University , Ames, IA 50011, USA","Roy J. Carver Department of Biochemistry, Biophysics and Molecular Biology, Iowa State University , Ames, IA 50011, USA"],"affiliations":[{"raw_affiliation_string":"Bioinformatics and Computational Biology Program, Iowa State University , Ames, IA 50011, USA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Roy J. Carver Department of Biochemistry, Biophysics and Molecular Biology, Iowa State University , Ames, IA 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041597050","display_name":"Iddo Friedberg","orcid":"https://orcid.org/0000-0002-1789-8000"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Iddo Friedberg","raw_affiliation_strings":["Bioinformatics and Computational Biology Program, Iowa State University , Ames, IA 50011, USA","Department of Veterinary Microbiology and Preventive Medicine, Iowa State University , Ames, IA 50011, USA"],"affiliations":[{"raw_affiliation_string":"Bioinformatics and Computational Biology Program, Iowa State University , Ames, IA 50011, USA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Department of Veterinary Microbiology and Preventive Medicine, Iowa State University , Ames, IA 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041597050"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.4771,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65746127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"39","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9998000264167786,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9998000264167786,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9959999918937683,"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":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.907197117805481},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.8569576740264893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7537460327148438},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6181904077529907},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.567658543586731},{"id":"https://openalex.org/keywords/gene-annotation","display_name":"Gene Annotation","score":0.5295903086662292},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.49839091300964355},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.4576849043369293},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.4224017858505249},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3535084128379822},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32417774200439453},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.25228220224380493},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.23091673851013184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19896426796913147},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15797358751296997},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1536136269569397},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.10021340847015381},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0683947205543518}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.907197117805481},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8569576740264893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537460327148438},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6181904077529907},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.567658543586731},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.5295903086662292},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.49839091300964355},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.4576849043369293},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.4224017858505249},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3535084128379822},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32417774200439453},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.25228220224380493},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.23091673851013184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19896426796913147},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15797358751296997},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1536136269569397},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.10021340847015381},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0683947205543518}],"mesh":[{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btad048","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad048","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad048/48957207/btad048.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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:36688705","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36688705","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}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad048","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad048","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad048/48957207/btad048.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":[{"id":"https://metadata.un.org/sdg/1","score":0.4699999988079071,"display_name":"No poverty"}],"awards":[{"id":"https://openalex.org/G7285318607","display_name":null,"funder_award_id":"DBI-1458359","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311090","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4317779747.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1806630989","https://openalex.org/W2008830098","https://openalex.org/W2060797027","https://openalex.org/W2084168100","https://openalex.org/W2098432760","https://openalex.org/W2099364528","https://openalex.org/W2103017472","https://openalex.org/W2108491719","https://openalex.org/W2127563440","https://openalex.org/W2128049108","https://openalex.org/W2138776746","https://openalex.org/W2159348493","https://openalex.org/W2169059428","https://openalex.org/W2799828084","https://openalex.org/W2913143675","https://openalex.org/W3042951841"],"related_works":["https://openalex.org/W2132241624","https://openalex.org/W4311683883","https://openalex.org/W4221030787","https://openalex.org/W4212902261","https://openalex.org/W2790811106","https://openalex.org/W2789551765","https://openalex.org/W3097598351","https://openalex.org/W3170192653","https://openalex.org/W4287775886","https://openalex.org/W4391006377"],"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":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
