{"id":"https://openalex.org/W3042317134","doi":"https://doi.org/10.1093/bioinformatics/btaa647","title":"GeoBoost2: a natural languageprocessing pipeline for GenBank metadata enrichment for virus phylogeography","display_name":"GeoBoost2: a natural languageprocessing pipeline for GenBank metadata enrichment for virus phylogeography","publication_year":2020,"publication_date":"2020-07-14","ids":{"openalex":"https://openalex.org/W3042317134","doi":"https://doi.org/10.1093/bioinformatics/btaa647","mag":"3042317134","pmid":"https://pubmed.ncbi.nlm.nih.gov/32683454"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa647","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa647","pdf_url":null,"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":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7755405","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068908108","display_name":"Arjun Magge","orcid":"https://orcid.org/0000-0002-4109-1346"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]},{"id":"https://openalex.org/I2802821144","display_name":"Center for Environmental Health","ror":"https://ror.org/03k84rm07","country_code":"US","type":"facility","lineage":["https://openalex.org/I2802821144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arjun Magge","raw_affiliation_strings":["Biodesign Center for Environmental Health Engineering, Biodesign Institute, Arizona State University , Tempe, AZ 85287, USA","College of Health Solutions, Arizona State University , Phoenix, AZ 85004, USA","University of Pennsylvania Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, , Philadelphia, PA 19104, USA"],"affiliations":[{"raw_affiliation_string":"Biodesign Center for Environmental Health Engineering, Biodesign Institute, Arizona State University , Tempe, AZ 85287, USA","institution_ids":["https://openalex.org/I55732556","https://openalex.org/I2802821144"]},{"raw_affiliation_string":"College of Health Solutions, Arizona State University , Phoenix, AZ 85004, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"University of Pennsylvania Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, , Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040948702","display_name":"Davy Weissenbacher","orcid":"https://orcid.org/0000-0001-8331-3675"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Davy Weissenbacher","raw_affiliation_strings":["University of Pennsylvania Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, , Philadelphia, PA 19104, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, , Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025763545","display_name":"Karen O\u2019Connor","orcid":"https://orcid.org/0000-0001-7709-3813"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen O\u2019Connor","raw_affiliation_strings":["University of Pennsylvania Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, , Philadelphia, PA 19104, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, , Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038933482","display_name":"Tasnia Tahsin","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tasnia Tahsin","raw_affiliation_strings":["College of Health Solutions, Arizona State University , Phoenix, AZ 85004, USA"],"affiliations":[{"raw_affiliation_string":"College of Health Solutions, Arizona State University , Phoenix, AZ 85004, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022014033","display_name":"Graciela Gonzalez\u2010Hernandez","orcid":"https://orcid.org/0000-0002-6416-9556"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graciela Gonzalez-Hernandez","raw_affiliation_strings":["University of Pennsylvania Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, , Philadelphia, PA 19104, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, , Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050090926","display_name":"Matthew Scotch","orcid":"https://orcid.org/0000-0001-5100-9724"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]},{"id":"https://openalex.org/I2802821144","display_name":"Center for Environmental Health","ror":"https://ror.org/03k84rm07","country_code":"US","type":"facility","lineage":["https://openalex.org/I2802821144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Scotch","raw_affiliation_strings":["Biodesign Center for Environmental Health Engineering, Biodesign Institute, Arizona State University , Tempe, AZ 85287, USA","College of Health Solutions, Arizona State University , Phoenix, AZ 85004, USA"],"affiliations":[{"raw_affiliation_string":"Biodesign Center for Environmental Health Engineering, Biodesign Institute, Arizona State University , Tempe, AZ 85287, USA","institution_ids":["https://openalex.org/I55732556","https://openalex.org/I2802821144"]},{"raw_affiliation_string":"College of Health Solutions, Arizona State University , Phoenix, AZ 85004, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5068908108"],"corresponding_institution_ids":["https://openalex.org/I2802821144","https://openalex.org/I55732556","https://openalex.org/I79576946"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.67058194,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"36","issue":"20","first_page":"5120","last_page":"5121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9983999729156494,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9983999729156494,"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/T11688","display_name":"Microbial infections and disease research","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2404","display_name":"Microbiology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/genbank","display_name":"GenBank","score":0.8195254802703857},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7957711219787598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.717287540435791},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6541893482208252},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5576667785644531},{"id":"https://openalex.org/keywords/phylogeography","display_name":"Phylogeography","score":0.5282220840454102},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.516567587852478},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40143686532974243},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37814217805862427},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.21282511949539185},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1998395323753357},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.1377812922000885}],"concepts":[{"id":"https://openalex.org/C79029880","wikidata":"https://www.wikidata.org/wiki/Q901755","display_name":"GenBank","level":3,"score":0.8195254802703857},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7957711219787598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717287540435791},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6541893482208252},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5576667785644531},{"id":"https://openalex.org/C94043034","wikidata":"https://www.wikidata.org/wiki/Q377756","display_name":"Phylogeography","level":4,"score":0.5282220840454102},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.516567587852478},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40143686532974243},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37814217805862427},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21282511949539185},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1998395323753357},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.1377812922000885},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058974","descriptor_name":"Phylogeography","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058974","descriptor_name":"Phylogeography","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058974","descriptor_name":"Phylogeography","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaa647","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa647","pdf_url":null,"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:32683454","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32683454","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:pubmedcentral.nih.gov:7755405","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7755405","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:7755405","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7755405","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6474139209","display_name":null,"funder_award_id":"R01AI117011","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G8677649668","display_name":null,"funder_award_id":"R01LM012080","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W189548156","https://openalex.org/W2017979743","https://openalex.org/W2057434754","https://openalex.org/W2156804059","https://openalex.org/W2278764098","https://openalex.org/W2516104505","https://openalex.org/W2774353266","https://openalex.org/W2807308836","https://openalex.org/W2808473449","https://openalex.org/W2902701726","https://openalex.org/W2918316203","https://openalex.org/W2947102967","https://openalex.org/W3006645647","https://openalex.org/W4256333965","https://openalex.org/W6757064504","https://openalex.org/W6762936208"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W1993070549","https://openalex.org/W4250169950","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1906885765","https://openalex.org/W1985426483"],"abstract_inverted_index":{"Supplementary":[0],"data":[1],"are":[2],"available":[3],"at":[4],"Bioinformatics":[5],"online.":[6]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
