{"id":"https://openalex.org/W4413339723","doi":"https://doi.org/10.1186/s12859-025-06242-w","title":"Learning-based parallel acceleration for HaplotypeCaller","display_name":"Learning-based parallel acceleration for HaplotypeCaller","publication_year":2025,"publication_date":"2025-08-20","ids":{"openalex":"https://openalex.org/W4413339723","doi":"https://doi.org/10.1186/s12859-025-06242-w","pmid":"https://pubmed.ncbi.nlm.nih.gov/40835904"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-025-06242-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06242-w","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06242-w","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06242-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiangxing Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxing Lai","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Waihuan Dong Road, Guangzhou, 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Waihuan Dong Road, Guangzhou, 510006, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Minguang Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112812","display_name":"National Supercomputing Center in Shenzhen","ror":"https://ror.org/02291hh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210112812"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minguang Xiao","raw_affiliation_strings":["National Supercomputer Center in Guangzhou, Xiaoyuan Dong Road, Guangzhou, 510330, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Supercomputer Center in Guangzhou, Xiaoyuan Dong Road, Guangzhou, 510330, China","institution_ids":["https://openalex.org/I4210112812"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075384001","display_name":"Lichun Weng","orcid":"https://orcid.org/0009-0003-3414-1688"},"institutions":[{"id":"https://openalex.org/I4210112812","display_name":"National Supercomputing Center in Shenzhen","ror":"https://ror.org/02291hh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210112812"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingling Weng","raw_affiliation_strings":["National Supercomputer Center in Guangzhou, Xiaoyuan Dong Road, Guangzhou, 510330, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Supercomputer Center in Guangzhou, Xiaoyuan Dong Road, Guangzhou, 510330, China","institution_ids":["https://openalex.org/I4210112812"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101483479","display_name":"Zhiguang Chen","orcid":"https://orcid.org/0000-0002-9318-5715"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiguang Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Waihuan Dong Road, Guangzhou, 510006, China. chenzhg29@mail.sysu.edu.cn","School of Computer Science and Engineering, Sun Yat-sen University, Waihuan Dong Road, Guangzhou, 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Waihuan Dong Road, Guangzhou, 510006, China. chenzhg29@mail.sysu.edu.cn","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Waihuan Dong Road, Guangzhou, 510006, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16149578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"1","first_page":"217","last_page":"217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.998199999332428,"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/T10885","display_name":"Gene expression and cancer classification","score":0.998199999332428,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9941999912261963,"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":0.9918000102043152,"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/acceleration","display_name":"Acceleration","score":0.5954121351242065},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5732309818267822},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3959452211856842},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3416481614112854},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3133087456226349},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1653490960597992}],"concepts":[{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5954121351242065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5732309818267822},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3959452211856842},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3416481614112854},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3133087456226349},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1653490960597992},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098436","descriptor_name":"Parallel Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006239","descriptor_name":"Haplotypes","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":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D054643","descriptor_name":"INDEL Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-025-06242-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06242-w","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06242-w","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:40835904","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40835904","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:5715c691519b439c9adc60db587f6a77","is_oa":true,"landing_page_url":"https://doaj.org/article/5715c691519b439c9adc60db587f6a77","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 26, Iss 1, Pp 1-17 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12366067","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12366067","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/s12859-025-06242-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06242-w","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06242-w","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":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.6299999952316284}],"awards":[{"id":"https://openalex.org/G6651040689","display_name":null,"funder_award_id":"62332021","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G687123064","display_name":null,"funder_award_id":"62272499","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413339723.pdf","grobid_xml":"https://content.openalex.org/works/W4413339723.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1967239133","https://openalex.org/W1996641286","https://openalex.org/W2090705041","https://openalex.org/W2101305463","https://openalex.org/W2103184242","https://openalex.org/W2118246164","https://openalex.org/W2575651982","https://openalex.org/W2584732844","https://openalex.org/W2745862296","https://openalex.org/W2784244711","https://openalex.org/W2794135466","https://openalex.org/W2910124299","https://openalex.org/W2919665556","https://openalex.org/W2922894427","https://openalex.org/W2938304012","https://openalex.org/W2994531552","https://openalex.org/W2996844906","https://openalex.org/W3005136035","https://openalex.org/W3021001696","https://openalex.org/W3100908593","https://openalex.org/W3188605633","https://openalex.org/W4210602415","https://openalex.org/W4283819568","https://openalex.org/W4378907379","https://openalex.org/W4383554057","https://openalex.org/W4389525196","https://openalex.org/W4392364378","https://openalex.org/W4402626459","https://openalex.org/W4403312475"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W2082860237","https://openalex.org/W2119695867","https://openalex.org/W2130076355","https://openalex.org/W1990804418","https://openalex.org/W1993764875","https://openalex.org/W2046158694","https://openalex.org/W2788277189"],"abstract_inverted_index":{"In":[0],"the":[1,38,61,88,152],"genome":[2],"analysis":[3],"workflow,":[4],"Genome":[5],"Analysis":[6],"Toolkit":[7],"(GATK)":[8],"HaplotypeCaller":[9,35,46,126],"is":[10,50,122,164],"a":[11,76,134,145],"widely":[12],"used":[13],"variant":[14,157],"calling":[15],"tool":[16],"designed":[17],"to":[18,58,69,85,139],"accurately":[19,59,86],"identify":[20],"single":[21],"nucleotide":[22],"polymorphisms":[23],"(SNPs)":[24],"and":[25,99,127,154],"insertions/deletions":[26],"(Indels)":[27],"in":[28,114],"samples.":[29],"However,":[30],"when":[31],"processing":[32],"large-scale":[33],"datasets,":[34,116],"often":[36],"faces":[37],"challenge":[39],"of":[40,64,91,136,156,162],"excessively":[41],"long":[42],"runtime.":[43],"Parallelizing":[44],"GATK":[45],"with":[47,148],"data":[48,66,96],"segmentation":[49,97],"an":[51],"effective":[52],"solution,":[53],"but":[54],"existing":[55],"methods":[56],"struggle":[57],"estimate":[60],"computational":[62,71,89,109],"complexity":[63,90],"each":[65],"block,":[67],"leading":[68],"severe":[70],"skew.":[72,110],"This":[73],"paper":[74],"introduces":[75],"learning-based":[77],"framework":[78],"LPA":[79,106,113,132,143,163],"(learning-based":[80],"parallel":[81],"acceleration),":[82],"leveraging":[83],"model":[84],"predict":[87],"data.":[92],"By":[93],"employing":[94],"adaptive":[95],"algorithms":[98],"Multi-Knapsack":[100],"Problem":[101],"(MKP)":[102],"based":[103],"task":[104],"scheduling,":[105],"significantly":[107],"alleviates":[108],"We":[111],"evaluated":[112],"multiple":[115],"demonstrating":[117],"that":[118],"its":[119],"execution":[120],"speed":[121],"30x\u201340x":[123],"faster":[124,129],"than":[125,130],"2x\u20135x":[128],"HaplotypeCallerSpark.":[131],"achieves":[133],"speedup":[135],"1.3x\u20132x":[137],"compared":[138],"similar":[140],"methods.":[141],"And":[142],"maintaining":[144],"high":[146],"accuracy":[147],"over":[149],"99.9%,":[150],"enhancing":[151],"efficiency":[153],"reliability":[155],"calling.":[158],"The":[159],"source":[160],"code":[161],"publicly":[165],"available":[166],"at":[167],"https://github.com/laixx9/LPA":[168],".":[169]},"counts_by_year":[],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-10-10T00:00:00"}
