{"id":"https://openalex.org/W2919665556","doi":"https://doi.org/10.1186/s12859-019-2665-0","title":"ADS-HCSpark: A scalable HaplotypeCaller leveraging adaptive data segmentation to accelerate variant calling on Spark","display_name":"ADS-HCSpark: A scalable HaplotypeCaller leveraging adaptive data segmentation to accelerate variant calling on Spark","publication_year":2019,"publication_date":"2019-02-14","ids":{"openalex":"https://openalex.org/W2919665556","doi":"https://doi.org/10.1186/s12859-019-2665-0","mag":"2919665556","pmid":"https://pubmed.ncbi.nlm.nih.gov/30764760"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-019-2665-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2665-0","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-2665-0","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/s12859-019-2665-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068977983","display_name":"Anghong Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Anghong Xiao","raw_affiliation_strings":["Communication & Computer Network Lab of Guangdong, School of Computer Science & Engineering, South China University of Technology, Wushan Road, Guangzhou, 510641, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication & Computer Network Lab of Guangdong, School of Computer Science & Engineering, South China University of Technology, Wushan Road, Guangzhou, 510641, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053349477","display_name":"Zongze Wu","orcid":"https://orcid.org/0000-0002-2115-8670"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongze Wu","raw_affiliation_strings":["Communication & Computer Network Lab of Guangdong, School of Computer Science & Engineering, South China University of Technology, Wushan Road, Guangzhou, 510641, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication & Computer Network Lab of Guangdong, School of Computer Science & Engineering, South China University of Technology, Wushan Road, Guangzhou, 510641, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052760299","display_name":"Shoubin Dong","orcid":"https://orcid.org/0000-0003-0153-850X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shoubin Dong","raw_affiliation_strings":["Communication & Computer Network Lab of Guangdong, School of Computer Science & Engineering, South China University of Technology, Wushan Road, Guangzhou, 510641, China. sbdong@scut.edu.cn","Communication & Computer Network Lab of Guangdong, School of Computer Science & Engineering, South China University of Technology, Wushan Road, Guangzhou, 510641, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication & Computer Network Lab of Guangdong, School of Computer Science & Engineering, South China University of Technology, Wushan Road, Guangzhou, 510641, China. sbdong@scut.edu.cn","institution_ids":[]},{"raw_affiliation_string":"Communication & Computer Network Lab of Guangdong, School of Computer Science & Engineering, South China University of Technology, Wushan Road, Guangzhou, 510641, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068977983"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.5399,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71902669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"20","issue":"1","first_page":"76","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.44350001215934753,"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"}},"topics":[{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.44350001215934753,"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":0.4025000035762787,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.029400000348687172,"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":0.8553193807601929},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.824902355670929},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8042101860046387},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.595156192779541},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5876069068908691},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5483381152153015},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4906960725784302},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.485501766204834},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44351521134376526},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.4143664836883545},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37375015020370483},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.346974641084671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1780509650707245},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16471019387245178},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14571335911750793},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1409805417060852},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.09836223721504211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8553193807601929},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.824902355670929},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8042101860046387},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.595156192779541},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5876069068908691},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5483381152153015},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4906960725784302},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.485501766204834},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44351521134376526},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.4143664836883545},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37375015020370483},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.346974641084671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1780509650707245},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16471019387245178},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14571335911750793},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1409805417060852},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.09836223721504211},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[{"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":"D006239","descriptor_name":"Haplotypes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006239","descriptor_name":"Haplotypes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006239","descriptor_name":"Haplotypes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D012984","descriptor_name":"Software","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":true},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","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":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"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}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12859-019-2665-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2665-0","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-2665-0","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:30764760","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30764760","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:fecdbbf0876148f9b598433e55104308","is_oa":true,"landing_page_url":"https://doaj.org/article/fecdbbf0876148f9b598433e55104308","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:europepmc.org:5380198","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC6376756","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,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:6376756","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6376756","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/s12859-019-2665-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2665-0","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-2665-0","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":[],"awards":[{"id":"https://openalex.org/G8887140105","display_name":null,"funder_award_id":"2015A030308017","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2919665556.pdf","grobid_xml":"https://content.openalex.org/works/W2919665556.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1596062789","https://openalex.org/W2033173420","https://openalex.org/W2108234281","https://openalex.org/W2109701112","https://openalex.org/W2119180969","https://openalex.org/W2131187246","https://openalex.org/W2144320400","https://openalex.org/W2155306111","https://openalex.org/W2159670728","https://openalex.org/W2160363604","https://openalex.org/W2190569576","https://openalex.org/W2504850725","https://openalex.org/W2542459869","https://openalex.org/W2575651982","https://openalex.org/W2584732844","https://openalex.org/W2745862296"],"related_works":["https://openalex.org/W4290802965","https://openalex.org/W4390608645","https://openalex.org/W97789383","https://openalex.org/W4394895745","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W3136989197"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,287],"advance":[2],"of":[3,17,45,65,77,126,133,147,155,209,230,244,284,290],"next":[4],"generation":[5],"sequencing":[6,19],"enables":[7],"higher":[8],"throughput":[9],"with":[10,278],"lower":[11],"price,":[12],"and":[13,32,67,69,74,140,161,180,240,270,281],"as":[14],"the":[15,124,131,145,183,207,228,242,282],"basic":[16],"high-throughput":[18],"data":[20,157,169,187],"analysis,":[21],"variant":[22,38,97,115,127,163,210,220],"calling":[23,98,116,128,164,221],"is":[24,159,171,195,214,235,256,292],"widely":[25],"used":[26],"in":[27,49,88,150,241,251],"disease":[28],"research,":[29],"clinical":[30],"treatment":[31],"medicine":[33],"research.":[34],"However,":[35],"current":[36],"mainstream":[37,134],"caller":[39],"tools":[40],"have":[41,190],"a":[42,81,111,152,162,215],"serious":[43],"problem":[44,146],"computation":[46,148],"bottlenecks,":[47],"resulting":[48],"some":[50],"long":[51,72],"tail":[52],"tasks":[53],"when":[54],"performing":[55],"on":[56,63,99,118,138,167,177,223,237,262,275],"large":[57,100],"datasets.":[58],"This":[59],"prevents":[60],"high":[61,82],"scalability":[62,176,280],"clusters":[64],"multi-node":[66,276],"multi-core,":[68],"leads":[70],"to":[71,95,197,218],"runtime":[73],"inefficient":[75],"usage":[76],"computing":[78],"resources.":[79],"Thus,":[80],"scalable":[83,112,216],"tool":[84,113,217],"which":[85,173],"could":[86,248],"run":[87],"distributed":[89],"environment":[90],"will":[91],"be":[92,249],"highly":[93],"useful":[94],"accelerate":[96],"scale":[101],"genome":[102],"data.":[103],"RESULTS:":[104],"In":[105],"this":[106,252],"paper,":[107],"we":[108],"present":[109],"ADS-HCSpark,":[110],"for":[114],"based":[117,166,222],"Apache":[119,224],"Spark":[120,225],"framework.":[121],"ADS-HCSpark":[122,213,234,255,291],"accelerates":[123],"process":[125],"by":[129],"implementing":[130,227],"parallelization":[132,229],"GATK":[135,231],"HaplotypeCaller":[136,232,261],"algorithm":[137,165],"multi-core":[139],"multi-node.":[141,181],"Aiming":[142],"at":[143,295],"solving":[144],"skew":[149],"HaplotypeCaller,":[151],"parallel":[153],"strategy":[154],"adaptive":[156,168],"segmentation":[158,170],"proposed":[160],"implemented,":[172],"achieves":[174],"good":[175],"both":[178],"single-node":[179,263],"For":[182],"requirement":[184],"that":[185,247],"adjacent":[186],"blocks":[188],"should":[189],"overlapped":[191,203],"boundaries,":[192],"Hadoop-BAM":[193],"library":[194],"customized":[196],"implement":[198],"partitioning":[199],"BAM":[200],"file":[201],"into":[202],"blocks,":[204],"further":[205],"improving":[206],"accuracy":[208,283],"calling.":[211],"CONCLUSIONS:":[212],"achieve":[219],"framework,":[226],"algorithm.":[233],"evaluated":[236],"our":[238],"cluster":[239],"case":[243],"best":[245],"performance":[246],"achieved":[250],"experimental":[253],"platform,":[254],"74%":[257],"faster":[258,266,272],"than":[259,267,273],"GATK3.8":[260],"experiments,":[264,277],"57%":[265],"GATK4.0":[268],"HaplotypeCallerSpark":[269],"27%":[271],"SparkGA":[274],"better":[279],"over":[285],"99%.":[286],"source":[288],"code":[289],"publicly":[293],"available":[294],"https://github.com/SCUT-CCNL/ADS-HCSpark.git":[296],".":[297]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
