{"id":"https://openalex.org/W3120390914","doi":"https://doi.org/10.1093/bioinformatics/btaa1097","title":"xGAP: a python based efficient, modular, extensible and fault tolerant genomic analysis pipeline for variant discovery","display_name":"xGAP: a python based efficient, modular, extensible and fault tolerant genomic analysis pipeline for variant discovery","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3120390914","doi":"https://doi.org/10.1093/bioinformatics/btaa1097","mag":"3120390914","pmid":"https://pubmed.ncbi.nlm.nih.gov/33416856"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa1097","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa1097","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/1/9/37005861/btaa1097.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,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/37/1/9/37005861/btaa1097.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013395194","display_name":"Aditya Gorla","orcid":"https://orcid.org/0000-0003-0849-7894"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Gorla","raw_affiliation_strings":["Department of Bioengineering, University of California , Los Angeles, CA 90095, USA"],"raw_orcid":"https://orcid.org/0000-0003-0849-7894","affiliations":[{"raw_affiliation_string":"Department of Bioengineering, University of California , Los Angeles, CA 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004736211","display_name":"Brandon Jew","orcid":"https://orcid.org/0000-0002-1848-1880"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brandon Jew","raw_affiliation_strings":["Bioinformatics Interdepartmental Program, University of California , Los Angeles, CA 90095, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Interdepartmental Program, University of California , Los Angeles, CA 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055875104","display_name":"Luke Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luke Zhang","raw_affiliation_strings":["Undergraduate Neuroscience Interdepartmental Program, University of California , Los Angeles, CA 90095, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Undergraduate Neuroscience Interdepartmental Program, University of California , Los Angeles, CA 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102874075","display_name":"Jae Hoon Sul","orcid":"https://orcid.org/0000-0001-8260-2213"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I4210102685","display_name":"Neurobehavioral Systems","ror":"https://ror.org/018d33y89","country_code":"US","type":"other","lineage":["https://openalex.org/I4210102685"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jae Hoon Sul","raw_affiliation_strings":["Department of Psychiatry and Biobehavioral Sciences, University of California , Los Angeles, CA 90095, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychiatry and Biobehavioral Sciences, University of California , Los Angeles, CA 90095, USA","institution_ids":["https://openalex.org/I4210102685","https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102874075"],"corresponding_institution_ids":["https://openalex.org/I161318765","https://openalex.org/I4210102685"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.00627015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"37","issue":"1","first_page":"9","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.5600000023841858,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.5600000023841858,"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":0.32429999113082886,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.06239999830722809,"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/python","display_name":"Python (programming language)","score":0.873613178730011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6828511357307434},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.64293372631073},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.6306833624839783},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6000306606292725},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5533567667007446},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.499605655670166},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4870629608631134},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30022361874580383},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2505428194999695}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.873613178730011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6828511357307434},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.64293372631073},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.6306833624839783},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6000306606292725},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5533567667007446},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.499605655670166},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4870629608631134},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30022361874580383},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2505428194999695}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaa1097","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa1097","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/1/9/37005861/btaa1097.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,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33416856","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33416856","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8034531","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8034531","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaa1097","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa1097","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/1/9/37005861/btaa1097.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,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G1186668200","display_name":"III: Medium: Detecting Low Dimensional Structures in Genomic Data","funder_award_id":"1705197","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3047920937","display_name":null,"funder_award_id":"NS102371","funder_id":"https://openalex.org/F4320337359","funder_display_name":"National Institute of Neurological Disorders and Stroke"},{"id":"https://openalex.org/G4239438419","display_name":null,"funder_award_id":"#1705197","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4802152530","display_name":null,"funder_award_id":"R01 NS102371","funder_id":"https://openalex.org/F4320337359","funder_display_name":"National Institute of Neurological Disorders and Stroke"},{"id":"https://openalex.org/G5555405555","display_name":null,"funder_award_id":"K01 ES028064","funder_id":"https://openalex.org/F4320337361","funder_display_name":"National Institute of Environmental Health Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337359","display_name":"National Institute of Neurological Disorders and Stroke","ror":"https://ror.org/01s5ya894"},{"id":"https://openalex.org/F4320337361","display_name":"National Institute of Environmental Health Sciences","ror":"https://ror.org/00j4k1h63"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3120390914.pdf","grobid_xml":"https://content.openalex.org/works/W3120390914.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W859230734","https://openalex.org/W1622500880","https://openalex.org/W1996792558","https://openalex.org/W2022603493","https://openalex.org/W2054185647","https://openalex.org/W2103441770","https://openalex.org/W2109402178","https://openalex.org/W2110417468","https://openalex.org/W2111350087","https://openalex.org/W2119180969","https://openalex.org/W2119582595","https://openalex.org/W2128505445","https://openalex.org/W2131016694","https://openalex.org/W2131187246","https://openalex.org/W2150131459","https://openalex.org/W2150506261","https://openalex.org/W2159670728","https://openalex.org/W2168133698","https://openalex.org/W2605897695","https://openalex.org/W2612358188","https://openalex.org/W2770095154","https://openalex.org/W2913417489","https://openalex.org/W2925188014","https://openalex.org/W2929354011","https://openalex.org/W2950586514","https://openalex.org/W2951331911","https://openalex.org/W2951501862","https://openalex.org/W2952870794","https://openalex.org/W2953517386","https://openalex.org/W2988700766","https://openalex.org/W2994531552","https://openalex.org/W4250483256","https://openalex.org/W6746163975"],"related_works":["https://openalex.org/W1948607442","https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W4247766898","https://openalex.org/W2044615423","https://openalex.org/W4244765761","https://openalex.org/W2361584951","https://openalex.org/W2354475557","https://openalex.org/W1918900381","https://openalex.org/W2354832693"],"abstract_inverted_index":{"MOTIVATION:":[0],"Since":[1],"the":[2,17,121,130,205],"first":[3,50],"human":[4],"genome":[5,139],"was":[6],"sequenced":[7],"in":[8,16,84,160],"2001,":[9],"there":[10,67],"has":[11],"been":[12],"a":[13,69,85,138],"rapid":[14],"growth":[15],"number":[18],"of":[19,71,129,165,167,175],"bioinformatic":[20],"methods":[21],"to":[22,37,52,116,147,204,238],"process":[23,153],"and":[24,32,43,96,181,228],"analyze":[25,117],"next-generation":[26],"sequencing":[27,157],"(NGS)":[28],"data":[29,83,119,159,254],"for":[30,177,183],"research":[31],"clinical":[33],"studies":[34],"that":[35,75],"aim":[36],"identify":[38],"genetic":[39,54],"variants":[40,55,180],"influencing":[41],"diseases":[42],"traits.":[44],"To":[45,99],"achieve":[46,148,191],"this":[47],"goal,":[48],"one":[49],"needs":[51],"call":[53],"from":[56],"NGS":[57,82],"data,":[58],"which":[59,87,110],"requires":[60],"multiple":[61,196],"computationally":[62],"intensive":[63],"analysis":[64],"steps.":[65],"Unfortunately,":[66],"is":[68,88,212,226,247],"lack":[70],"an":[72,105],"open-source":[73],"pipeline":[74,135],"can":[76,152,233],"perform":[77],"all":[78],"these":[79],"steps":[80],"on":[81,220],"manner,":[86],"fully":[89],"automated,":[90],"efficient,":[91],"rapid,":[92],"scalable,":[93],"modular,":[94],"user-friendly":[95,227],"fault":[97,229],"tolerant.":[98],"address":[100],"this,":[101],"we":[102],"introduce":[103],"xGAP,":[104],"extensible":[106],"Genome":[107],"Analysis":[108],"Pipeline,":[109],"implements":[111,126],"modified":[112,131],"GATK":[113,132],"best":[114,133],"practice":[115,134],"DNA-seq":[118],"with":[120,144,208],"aforementioned":[122],"functionalities.":[123],"RESULTS:":[124],"xGAP":[125,170,211,225,246],"massive":[127],"parallelization":[128],"by":[136],"splitting":[137],"into":[140],"many":[141],"smaller":[142],"regions":[143],"efficient":[145],"load-balancing":[146],"high":[149],"scalability.":[150],"It":[151],"30\u00d7":[154],"coverage":[155,218],"whole-genome":[156],"(WGS)":[158],"\u223c90":[161],"min.":[162],"In":[163],"terms":[164],"accuracy":[166],"discovered":[168],"variants,":[169],"achieves":[171],"average":[172],"F1":[173],"scores":[174],"99.37%":[176],"single":[178],"nucleotide":[179],"99.20%":[182],"insertion/deletions":[184],"across":[185,195],"seven":[186],"benchmark":[187],"WGS":[188,219],"datasets.":[189],"We":[190],"highly":[192],"consistent":[193],"results":[194],"on-premises":[197],"(SGE":[198],"&":[199],"SLURM)":[200],"high-performance":[201],"clusters.":[202],"Compared":[203],"Churchill":[206],"pipeline,":[207],"similar":[209],"parallelization,":[210],"20%":[213],"faster":[214],"when":[215],"analyzing":[216],"50\u00d7":[217],"Amazon":[221],"Web":[222],"Service.":[223],"Finally,":[224],"tolerant":[230],"where":[231],"it":[232],"automatically":[234],"re-initiate":[235],"failed":[236],"processes":[237],"minimize":[239],"required":[240],"user":[241],"intervention.":[242],"AVAILABILITY":[243],"AND":[244],"IMPLEMENTATION:":[245],"available":[248,256],"at":[249,257],"https://github.com/Adigorla/xgap.":[250],"SUPPLEMENTARY":[251],"INFORMATION:":[252],"Supplementary":[253],"are":[255],"Bioinformatics":[258],"online.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}
