{"id":"https://openalex.org/W2979727888","doi":"https://doi.org/10.1186/s12859-019-3108-7","title":"DECA: scalable XHMM exome copy-number variant calling with ADAM and Apache Spark","display_name":"DECA: scalable XHMM exome copy-number variant calling with ADAM and Apache Spark","publication_year":2019,"publication_date":"2019-10-11","ids":{"openalex":"https://openalex.org/W2979727888","doi":"https://doi.org/10.1186/s12859-019-3108-7","mag":"2979727888","pmid":"https://pubmed.ncbi.nlm.nih.gov/31604420"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-019-3108-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-3108-7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-3108-7","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/track/pdf/10.1186/s12859-019-3108-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027174942","display_name":"Michael D. Linderman","orcid":"https://orcid.org/0000-0002-9643-7148"},"institutions":[{"id":"https://openalex.org/I195575238","display_name":"Middlebury College","ror":"https://ror.org/0217hb928","country_code":"US","type":"education","lineage":["https://openalex.org/I195575238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael D. Linderman","raw_affiliation_strings":["Department of Computer Science, Middlebury College, 75 Shannon St, Middlebury, VT, 05753, USA. mlinderman@middlebury.edu","Department of Computer Science, Middlebury College, 75 Shannon St, Middlebury, VT, 05753, USA"],"raw_orcid":"https://orcid.org/0000-0002-9643-7148","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Middlebury College, 75 Shannon St, Middlebury, VT, 05753, USA. mlinderman@middlebury.edu","institution_ids":["https://openalex.org/I195575238"]},{"raw_affiliation_string":"Department of Computer Science, Middlebury College, 75 Shannon St, Middlebury, VT, 05753, USA","institution_ids":["https://openalex.org/I195575238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084164103","display_name":"Davin Chia","orcid":null},"institutions":[{"id":"https://openalex.org/I195575238","display_name":"Middlebury College","ror":"https://ror.org/0217hb928","country_code":"US","type":"education","lineage":["https://openalex.org/I195575238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Davin Chia","raw_affiliation_strings":["Department of Computer Science, Middlebury College, 75 Shannon St, Middlebury, VT, 05753, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Middlebury College, 75 Shannon St, Middlebury, VT, 05753, USA","institution_ids":["https://openalex.org/I195575238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026849592","display_name":"Forrest Wallace","orcid":null},"institutions":[{"id":"https://openalex.org/I195575238","display_name":"Middlebury College","ror":"https://ror.org/0217hb928","country_code":"US","type":"education","lineage":["https://openalex.org/I195575238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Forrest Wallace","raw_affiliation_strings":["Department of Computer Science, Middlebury College, 75 Shannon St, Middlebury, VT, 05753, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Middlebury College, 75 Shannon St, Middlebury, VT, 05753, USA","institution_ids":["https://openalex.org/I195575238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008077599","display_name":"Frank Austin Nothaft","orcid":"https://orcid.org/0000-0002-7729-7055"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank A. Nothaft","raw_affiliation_strings":["AMPLab, University of California, Berkeley, Berkeley, CA, USA","Databricks, Inc., San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMPLab, University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Databricks, Inc., San Francisco, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027174942"],"corresponding_institution_ids":["https://openalex.org/I195575238"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.1709,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53414728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"20","issue":"1","first_page":"493","last_page":"493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7578999996185303,"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":0.7578999996185303,"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/T11213","display_name":"Genomic variations and chromosomal abnormalities","score":0.08410000056028366,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.04039999842643738,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/spark","display_name":"SPARK (programming language)","score":0.6482634544372559},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.542980432510376},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5356848239898682},{"id":"https://openalex.org/keywords/exome-sequencing","display_name":"Exome sequencing","score":0.5104178786277771},{"id":"https://openalex.org/keywords/exome","display_name":"Exome","score":0.5052009224891663},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.4777785539627075},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4674561619758606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4465055465698242},{"id":"https://openalex.org/keywords/copy-number-variation","display_name":"Copy-number variation","score":0.4208245873451233},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.40292060375213623},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.339842826128006},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2142057716846466},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.19584479928016663},{"id":"https://openalex.org/keywords/mutation","display_name":"Mutation","score":0.1719384789466858},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.169928640127182},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16687420010566711}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6482634544372559},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.542980432510376},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5356848239898682},{"id":"https://openalex.org/C16671776","wikidata":"https://www.wikidata.org/wiki/Q5420592","display_name":"Exome sequencing","level":4,"score":0.5104178786277771},{"id":"https://openalex.org/C10590036","wikidata":"https://www.wikidata.org/wiki/Q417664","display_name":"Exome","level":5,"score":0.5052009224891663},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.4777785539627075},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4674561619758606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4465055465698242},{"id":"https://openalex.org/C120821319","wikidata":"https://www.wikidata.org/wiki/Q1501491","display_name":"Copy-number variation","level":4,"score":0.4208245873451233},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.40292060375213623},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.339842826128006},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2142057716846466},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.19584479928016663},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.1719384789466858},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.169928640127182},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16687420010566711},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000073359","descriptor_name":"Exome Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000073359","descriptor_name":"Exome Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000073359","descriptor_name":"Exome Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000073359","descriptor_name":"Exome Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056915","descriptor_name":"DNA Copy Number Variations","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056915","descriptor_name":"DNA Copy Number Variations","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056915","descriptor_name":"DNA Copy Number Variations","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056915","descriptor_name":"DNA Copy Number Variations","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059472","descriptor_name":"Exome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059472","descriptor_name":"Exome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059472","descriptor_name":"Exome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059472","descriptor_name":"Exome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12859-019-3108-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-3108-7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-3108-7","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:31604420","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31604420","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:b55e1c6b882243a3b2795b33ab10e78c","is_oa":false,"landing_page_url":"https://doaj.org/article/b55e1c6b882243a3b2795b33ab10e78c","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 20, Iss 1, Pp 1-8 (2019)","raw_type":"article"},{"id":"pmh:oai:osti.gov:1618535","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1618535","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:6787990","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6787990","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/s12859-019-3108-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-3108-7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-3108-7","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":0.4699999988079071,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G186087738","display_name":null,"funder_award_id":"U54HG007990-01","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G4417639437","display_name":null,"funder_award_id":"U54HG007990","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6398089940","display_name":"Making Sense at Scale with Algorithms, Machines, and People","funder_award_id":"1139158","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7103680314","display_name":null,"funder_award_id":"FA8750-12-2-0331","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7343583039","display_name":null,"funder_award_id":"HHSN261201400006C","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8560804567","display_name":null,"funder_award_id":"7076018","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G900736768","display_name":null,"funder_award_id":"CCF-1139158","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/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332814","display_name":"UC Berkeley College of Chemistry","ror":"https://ror.org/01an7q238"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320338292","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2979727888.pdf","grobid_xml":"https://content.openalex.org/works/W2979727888.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1707809421","https://openalex.org/W1905244645","https://openalex.org/W1989017925","https://openalex.org/W2012151892","https://openalex.org/W2104549677","https://openalex.org/W2114034064","https://openalex.org/W2119180969","https://openalex.org/W2125838338","https://openalex.org/W2131975293","https://openalex.org/W2147869723","https://openalex.org/W2160363604","https://openalex.org/W2189371416","https://openalex.org/W2191556466","https://openalex.org/W2485107572","https://openalex.org/W2512464499","https://openalex.org/W2523288541","https://openalex.org/W2579188339","https://openalex.org/W2734317952","https://openalex.org/W2740824981","https://openalex.org/W2886161096","https://openalex.org/W2912516925","https://openalex.org/W2963288913","https://openalex.org/W2963891150","https://openalex.org/W6614148910"],"related_works":["https://openalex.org/W2093932542","https://openalex.org/W2043256480","https://openalex.org/W4242893802","https://openalex.org/W2772505697","https://openalex.org/W3083501552","https://openalex.org/W2400191746","https://openalex.org/W1983406990","https://openalex.org/W2542213537","https://openalex.org/W2484239316","https://openalex.org/W2584621370"],"abstract_inverted_index":{"BACKGROUND:":[0],"XHMM":[1,64,84,175],"is":[2,57],"a":[3,58,111,125,161,185,199],"widely":[4],"used":[5],"tool":[6],"for":[7,25,36,204],"copy-number":[8],"variant":[9],"(CNV)":[10],"discovery":[11,99,147],"from":[12,100,148],"whole":[13],"exome":[14],"sequencing":[15],"data":[16],"but":[17,209],"can":[18,214],"require":[19,215],"hours":[20],"to":[21,23,49,78,174,176,190,221],"days":[22],"run":[24],"large":[26,92,212],"cohorts.":[27],"A":[28],"more":[29],"scalable":[30,60],"implementation":[31,61,172],"would":[32],"reduce":[33],"the":[34,45,51,63,67,101,149],"need":[35],"specialized":[37],"computational":[38],"resources":[39],"and":[40,70,91,132,171,180,192,195,201,218],"enable":[41],"increased":[42],"exploration":[43],"of":[44,62],"configuration":[46,223],"parameter":[47],"space":[48],"obtain":[50,177],"best":[52],"possible":[53],"results.":[54],"RESULTS:":[55],"DECA":[56,82],"horizontally":[59],"algorithm":[65],"using":[66,120,135,156],"ADAM":[68,191,194],"framework":[69],"Apache":[71,196],"Spark":[72,94,126,162,197],"that":[73,178],"incorporates":[74],"novel":[75],"algorithmic":[76,170,216],"optimizations":[77,217],"eliminate":[79],"unneeded":[80],"computation.":[81],"parallelizes":[83],"on":[85,110,124,139,160],"both":[86],"multi-core":[87],"shared":[88],"memory":[89],"computers":[90],"shared-nothing":[93],"clusters.":[95],"We":[96,144,165],"performed":[97,145],"CNV":[98,146],"read-depth":[102],"matrix":[103],"in":[104,107,153],"2535":[105],"exomes":[106],"9.3":[108],"min":[109,119,134,155],"16-core":[112],"workstation":[113],"(35.3\u00d7":[114],"speedup":[115,129],"vs.":[116,130],"XHMM),":[117,131],"12.7":[118],"10":[121],"executor":[122,137,158],"cores":[123,138,159],"cluster":[127],"(18.8\u00d7":[128],"9.8":[133],"32":[136],"Amazon":[140],"AWS'":[141],"Elastic":[142],"MapReduce.":[143],"original":[150],"BAM":[151],"files":[152],"292":[154],"640":[157],"cluster.":[163],"CONCLUSIONS:":[164],"describe":[166],"DECA's":[167],"performance,":[168,179],"our":[169,181],"enhancements":[173],"lessons":[182],"learned":[183],"porting":[184],"complex":[186],"genome":[187,207],"analysis":[188],"application":[189],"Spark.":[193],"are":[198],"performant":[200],"productive":[202],"platform":[203],"implementing":[205],"large-scale":[206],"analyses,":[208],"efficiently":[210],"utilizing":[211],"clusters":[213],"careful":[219],"attention":[220],"Spark's":[222],"parameters.":[224]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}
