{"id":"https://openalex.org/W2884983162","doi":"https://doi.org/10.1093/bioinformatics/bty657","title":"The Terabase Search Engine: a large-scale relational database of short-read sequences","display_name":"The Terabase Search Engine: a large-scale relational database of short-read sequences","publication_year":2018,"publication_date":"2018-07-20","ids":{"openalex":"https://openalex.org/W2884983162","doi":"https://doi.org/10.1093/bioinformatics/bty657","mag":"2884983162","pmid":"https://pubmed.ncbi.nlm.nih.gov/30052772","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/6379032"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bty657","doi":"https://doi.org/10.1093/bioinformatics/bty657","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty657","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/4/665/27838499/bty657.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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/35/4/665/27838499/bty657.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055200839","display_name":"Richard N. Wilton","orcid":"https://orcid.org/0000-0003-1263-5532","observed_orcids":["https://orcid.org/0000-0003-1263-5532"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Richard Wilton","raw_affiliation_strings":["Department of Physics and Astronomy, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0003-1263-5532","affiliations":[{"raw_affiliation_string":"Department of Physics and Astronomy, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007007026","display_name":"Sarah J. Wheelan","orcid":"https://orcid.org/0000-0002-9002-0800","observed_orcids":["https://orcid.org/0000-0002-9002-0800"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah J Wheelan","raw_affiliation_strings":["Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA","Department of Oncology, Johns Hopkins University School of Medicine, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Oncology, Johns Hopkins University School of Medicine, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019891335","display_name":"Alexander S. Szalay","orcid":"https://orcid.org/0000-0002-4108-3282","observed_orcids":["https://orcid.org/0000-0002-4108-3282"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander S Szalay","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University School of Medicine, Baltimore, MD, USA","Department of Physics and Astronomy, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University School of Medicine, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]},{"raw_affiliation_string":"Department of Physics and Astronomy, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010384159","display_name":"Steven L. Salzberg","orcid":"https://orcid.org/0000-0002-8859-7432","observed_orcids":["https://orcid.org/0000-0002-8859-7432"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven L Salzberg","raw_affiliation_strings":["Center for Computational Biology, McKusick-Nathans Institute of Genetic Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USA","Department of Biomedical Engineering, Johns Hopkins University School of Medicine, Baltimore, MD, USA","Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA","Department of Computer Science, Johns Hopkins University School of Medicine, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Biology, McKusick-Nathans Institute of Genetic Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]},{"raw_affiliation_string":"Department of Biomedical Engineering, Johns Hopkins University School of Medicine, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University School of Medicine, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055200839"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":{"value":3989,"currency":"USD","value_usd":3989},"fwci":0.1778,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.46402951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"35","issue":"4","first_page":"665","last_page":"670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8593999743461609,"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":0.8593999743461609,"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/T11269","display_name":"Algorithms and Data Compression","score":0.11869999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.003800000064074993,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/relational-databases","display_name":"relational databases","score":0.6990000009536743},{"id":"https://openalex.org/keywords/human-genome","display_name":"human genome","score":0.6940000057220459},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"sequence alignment","score":0.5299999713897705},{"id":"https://openalex.org/keywords/database-indexing","display_name":"database indexing","score":0.6589999794960022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7563401460647583},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.6286935210227966},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5358852744102478},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5336965322494507},{"id":"https://openalex.org/C48000682","wikidata":"https://www.wikidata.org/wiki/Q5227411","display_name":"Database search engine","level":3,"score":0.5278318524360657},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5264397859573364},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5193325281143188},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5092700719833374},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4576645493507385},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4224246144294739},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15151166915893555},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.1357547640800476},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.12075173854827881},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10307171940803528},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07867419719696045}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","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":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","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":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/bty657","doi":"https://doi.org/10.1093/bioinformatics/bty657","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty657","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/4/665/27838499/bty657.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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:5963102","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6379032","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:6379032","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6379032","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,"listed_in":[],"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","raw_type":"Text"},{"id":"pmid:30052772","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30052772","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,"listed_in":[],"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":"Journal Article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bty657","doi":"https://doi.org/10.1093/bioinformatics/bty657","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty657","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/4/665/27838499/bty657.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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5718903770","display_name":"The Terabase Search Engine","funder_award_id":"R01HG007196","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G8536629262","display_name":"A Software Framework for Exploring 1,000 Genomes of African Descent","funder_award_id":"R01HL129239","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2884983162.pdf","grobid_xml":"https://content.openalex.org/works/W2884983162.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1838635991","https://openalex.org/W2069066547","https://openalex.org/W2070102345","https://openalex.org/W2103441770","https://openalex.org/W2104549677","https://openalex.org/W2117131162","https://openalex.org/W2129504003","https://openalex.org/W2134840052","https://openalex.org/W2158714788","https://openalex.org/W2159084616","https://openalex.org/W2170551349","https://openalex.org/W2522993044","https://openalex.org/W2953263404"],"related_works":["https://openalex.org/W7101100816","https://openalex.org/W2266239166","https://openalex.org/W4414938270","https://openalex.org/W2083475546","https://openalex.org/W2058423261","https://openalex.org/W2884435343","https://openalex.org/W4383819045","https://openalex.org/W3090493712","https://openalex.org/W4379379188","https://openalex.org/W2523202588"],"abstract_inverted_index":{"MOTIVATION:":[0],"DNA":[1],"sequencing":[2,63],"archives":[3],"have":[4,17,67],"grown":[5],"to":[6,43,54,94,137,148],"enormous":[7],"scales":[8],"in":[9,98,117],"recent":[10],"years,":[11],"and":[12,53,90],"thousands":[13],"of":[14,23,47,86,88,109,120,128],"human":[15,82],"genomes":[16],"already":[18],"been":[19],"sequenced.":[20],"The":[21,100],"size":[22],"these":[24,96],"data":[25,33,49,78,97,161],"sets":[26],"has":[27],"made":[28],"searching":[29],"the":[30,75,111,138,141,149],"raw":[31,76],"read":[32,77],"infeasible":[34],"without":[35],"high-performance":[36],"data-query":[37],"technology.":[38],"Additionally,":[39],"it":[40],"is":[41,135,154],"challenging":[42],"search":[44,95,124],"a":[45,69,118,126,131],"repository":[46],"short-read":[48],"using":[50,125],"relational":[51],"logic":[52,57],"apply":[55],"that":[56,73,91,134],"across":[58],"samples":[59],"from":[60,106],"multiple":[61],"whole-genome":[62],"samples.":[64],"RESULTS:":[65],"We":[66],"built":[68],"compact,":[70],"efficiently-indexed":[71],"database":[72,108,153],"contains":[74],"for":[79,113],"over":[80],"250":[81],"genomes,":[83],"encompassing":[84],"trillions":[85],"bases":[87],"DNA,":[89],"allows":[92],"users":[93],"real-time.":[99],"Terabase":[101,150],"Search":[102,151],"Engine":[103,152],"enables":[104],"retrieval":[105],"this":[107],"all":[110],"reads":[112],"any":[114],"genomic":[115],"location":[116],"matter":[119],"seconds.":[121],"Users":[122],"can":[123],"range":[127],"positions":[129],"or":[130],"specific":[132],"sequence":[133],"aligned":[136],"genome":[139],"on":[140],"fly.":[142],"AVAILABILITY":[143],"AND":[144],"IMPLEMENTATION:":[145],"Public":[146],"access":[147],"available":[155,163],"at":[156,164],"http://tse.idies.jhu.edu.":[157],"SUPPLEMENTARY":[158],"INFORMATION:":[159],"Supplementary":[160],"are":[162],"Bioinformatics":[165],"online.":[166]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2018-08-03T00:00:00"}
