{"id":"https://openalex.org/W2969572099","doi":"https://doi.org/10.1186/s12859-019-2967-2","title":"Shared data science infrastructure for genomics data","display_name":"Shared data science infrastructure for genomics data","publication_year":2019,"publication_date":"2019-08-22","ids":{"openalex":"https://openalex.org/W2969572099","doi":"https://doi.org/10.1186/s12859-019-2967-2","mag":"2969572099","pmid":"https://pubmed.ncbi.nlm.nih.gov/31438850"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-019-2967-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2967-2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-019-2967-2","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-019-2967-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024822802","display_name":"Hamid Bagheri","orcid":"https://orcid.org/0000-0003-1540-7797"},"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":"Hamid Bagheri","raw_affiliation_strings":["Department of Computer Science, Iowa State University, 226 Atanasoff Hall, Ames, 50011, USA. hbagheri@iastate.edu","Department of Computer Science, Iowa State University, 226 Atanasoff Hall, Ames, 50011, USA"],"raw_orcid":"https://orcid.org/0000-0003-1540-7797","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Iowa State University, 226 Atanasoff Hall, Ames, 50011, USA. hbagheri@iastate.edu","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Department of Computer Science, Iowa State University, 226 Atanasoff Hall, Ames, 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062338785","display_name":"Usha Muppirala","orcid":"https://orcid.org/0000-0001-7568-509X"},"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":"Usha Muppirala","raw_affiliation_strings":["Genome Informatics Facility, Iowa State University, 206 Science I, Ames, 50011, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genome Informatics Facility, Iowa State University, 206 Science I, Ames, 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002599085","display_name":"Rick E. Masonbrink","orcid":null},"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":"Rick E. Masonbrink","raw_affiliation_strings":["Genome Informatics Facility, Iowa State University, 206 Science I, Ames, 50011, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genome Informatics Facility, Iowa State University, 206 Science I, Ames, 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070520368","display_name":"Andrew Severin","orcid":"https://orcid.org/0000-0002-8015-9665"},"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":"Andrew J. Severin","raw_affiliation_strings":["Genome Informatics Facility, Iowa State University, 206 Science I, Ames, 50011, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genome Informatics Facility, Iowa State University, 206 Science I, Ames, 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059626072","display_name":"Hridesh Rajan","orcid":"https://orcid.org/0000-0002-9410-9562"},"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":"Hridesh Rajan","raw_affiliation_strings":["Department of Computer Science, Iowa State University, 226 Atanasoff Hall, Ames, 50011, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Iowa State University, 226 Atanasoff Hall, Ames, 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024822802"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.2485,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.55244107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"20","issue":"1","first_page":"436","last_page":"436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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":0.9997000098228455,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9866999983787537,"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/computer-science","display_name":"Computer science","score":0.7859268188476562},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5481893420219421},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5015323162078857},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.48487505316734314},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.484657347202301},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.4627660810947418},{"id":"https://openalex.org/keywords/refseq","display_name":"RefSeq","score":0.4416278600692749},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4172988533973694},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3444901704788208},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3406389653682709},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.2946169376373291},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21254438161849976},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.19847986102104187},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15628060698509216},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1161397397518158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7859268188476562},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5481893420219421},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5015323162078857},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.48487505316734314},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.484657347202301},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.4627660810947418},{"id":"https://openalex.org/C151810110","wikidata":"https://www.wikidata.org/wiki/Q7307074","display_name":"RefSeq","level":4,"score":0.4416278600692749},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4172988533973694},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3444901704788208},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3406389653682709},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.2946169376373291},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21254438161849976},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.19847986102104187},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15628060698509216},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1161397397518158},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000077488","descriptor_name":"Data Science","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077488","descriptor_name":"Data Science","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077488","descriptor_name":"Data Science","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005091","descriptor_name":"Exons","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005091","descriptor_name":"Exons","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005091","descriptor_name":"Exons","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","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":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":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D033181","descriptor_name":"Information Dissemination","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D033181","descriptor_name":"Information Dissemination","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D033181","descriptor_name":"Information Dissemination","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-019-2967-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2967-2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-019-2967-2","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31438850","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31438850","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:27d4592a4a08475a9dbdceb30f6a8c91","is_oa":true,"landing_page_url":"https://doaj.org/article/27d4592a4a08475a9dbdceb30f6a8c91","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 20, Iss 1, Pp 1-13 (2019)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:6704658","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6704658","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-019-2967-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2967-2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-019-2967-2","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1433996340","display_name":null,"funder_award_id":"CCF-15-18897","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4058398719","display_name":null,"funder_award_id":"(CNS-15-13263)","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7770872176","display_name":null,"funder_award_id":"CNS-15-13263","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2969572099.pdf","grobid_xml":"https://content.openalex.org/works/W2969572099.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W821933395","https://openalex.org/W2011411346","https://openalex.org/W2014596857","https://openalex.org/W2017046042","https://openalex.org/W2024872854","https://openalex.org/W2053135018","https://openalex.org/W2055043387","https://openalex.org/W2100827887","https://openalex.org/W2105803236","https://openalex.org/W2107903949","https://openalex.org/W2109701112","https://openalex.org/W2114850508","https://openalex.org/W2150772374","https://openalex.org/W2150934173","https://openalex.org/W2153091158","https://openalex.org/W2160363604","https://openalex.org/W2161762698","https://openalex.org/W2163598668","https://openalex.org/W2173213060","https://openalex.org/W2412192467","https://openalex.org/W2575568020","https://openalex.org/W2585711475","https://openalex.org/W2799324424","https://openalex.org/W2883786072","https://openalex.org/W2949375137","https://openalex.org/W2963580824"],"related_works":["https://openalex.org/W3023169329","https://openalex.org/W4389470870","https://openalex.org/W2782165897","https://openalex.org/W4300438041","https://openalex.org/W2054104202","https://openalex.org/W2139703748","https://openalex.org/W2761254753","https://openalex.org/W1024825291","https://openalex.org/W2188981919","https://openalex.org/W3084909426"],"abstract_inverted_index":{"Creating":[0],"a":[1,73,100,112,120,185,196,244,261,286],"scalable":[2],"computational":[3],"infrastructure":[4,118,215],"to":[5,18,37,86,139,203,208,220,226,247,249,272],"analyze":[6,87],"the":[7,143,149,163,192,258,262,269],"wealth":[8],"of":[9,51,75,131,191,213,260,289],"information":[10],"contained":[11,43],"in":[12,21,44,145,188,200,253],"data":[13,29,42,46,60,67,70,194,252],"repositories":[14],"is":[15,35,285],"difficult":[16],"due":[17,207],"significant":[19,186,197],"barriers":[20],"organizing,":[22],"extracting":[23],"and":[24,40,63,92,108,127,151,171,195,211,278],"analyzing":[25],"relevant":[26],"data.":[27],"Shared":[28,235],"science":[30],"infrastructures":[31],"like":[32,106],"Boa":[33,52,77,80,97,137,181,239,266,291],"g":[34,53,81,98,138,182,240,267,292],"needed":[36],"efficiently":[38,250],"process":[39],"parse":[41],"large":[45,205,297],"repositories.":[47,71],"The":[48,234],"main":[49],"features":[50],"are":[54,232,280],"inspired":[55],"from":[56,68,103],"existing":[57,104],"languages":[58],"for":[59,78,119,158],"intensive":[61],"computing":[62],"can":[64],"easily":[65],"integrate":[66],"biological":[69,228,298],"As":[72],"proof":[74],"concept,":[76],"genomics,":[79],",":[82,241],"has":[83],"been":[84],"implemented":[85],"RefSeq\u2019s":[88],"153,848":[89],"annotation":[90],"(GFF)":[91],"assembly":[93,169],"(FASTA)":[94],"file":[95],"metadata.":[96],"provides":[99,242],"massive":[101],"improvement":[102],"solutions":[105],"Python":[107],"MongoDB,":[109],"by":[110],"utilizing":[111],"domain-specific":[113],"language":[114,265],"that":[115,124],"uses":[116],"Hadoop":[117,214],"smaller":[121],"storage":[122,190],"footprint":[123],"scales":[125],"well":[126],"requires":[128],"fewer":[129],"lines":[130],"code.":[132],"We":[133,147,256],"execute":[134],"scripts":[135],"through":[136],"answer":[140],"questions":[141],"about":[142],"genomes":[144,153],"RefSeq.":[146],"identify":[148,162],"largest":[150],"smallest":[152],"deposited,":[154],"explore":[155,251,273],"exon":[156],"frequencies":[157],"assemblies":[159,176,277],"after":[160],"2016,":[161],"most":[164],"commonly":[165],"used":[166,295],"bacterial":[167],"genome":[168,175,276],"program,":[170],"address":[172],"how":[173,274,290],"animal":[174],"have":[177],"improved":[178],"since":[179],"2016.":[180],"databases":[183],"provide":[184],"reduction":[187],"required":[189],"raw":[193],"speed":[198],"up":[199],"its":[201],"ability":[202,225],"query":[204],"datasets":[206],"automated":[209],"parallelization":[210],"distribution":[212],"during":[216],"computations.":[217],"In":[218],"order":[219],"keep":[221],"pace":[222],"with":[223,296],"our":[224],"produce":[227],"data,":[229],"innovative":[230],"methods":[231],"required.":[233],"Data":[236],"Science":[237],"Infrastructure,":[238],"researchers":[243,248],"greater":[245],"access":[246],"new":[254],"ways.":[255],"demonstrate":[257],"potential":[259],"domain":[263],"specific":[264],"using":[268],"RefSeq":[270],"database":[271],"deposited":[275],"annotations":[279],"changing":[281],"over":[282],"time.":[283],"This":[284],"small":[287],"example":[288],"could":[293],"be":[294],"datasets.":[299]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}
