{"id":"https://openalex.org/W4389703561","doi":"https://doi.org/10.1093/bioinformatics/btad729","title":"Dupsifter: a lightweight duplicate marking tool for whole genome bisulfite sequencing","display_name":"Dupsifter: a lightweight duplicate marking tool for whole genome bisulfite sequencing","publication_year":2023,"publication_date":"2023-12-01","ids":{"openalex":"https://openalex.org/W4389703561","doi":"https://doi.org/10.1093/bioinformatics/btad729","pmid":"https://pubmed.ncbi.nlm.nih.gov/38092060"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad729","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad729","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad729/54408122/btad729.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad729/54408122/btad729.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088629436","display_name":"Jacob Morrison","orcid":"https://orcid.org/0000-0001-8592-4744"},"institutions":[{"id":"https://openalex.org/I1317189400","display_name":"Van Andel Institute","ror":"https://ror.org/00wm07d60","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1317189400"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jacob Morrison","raw_affiliation_strings":["Department of Epigenetics, Van Andel Institute , Grand Rapids, MI 49503, United States"],"raw_orcid":"https://orcid.org/0000-0001-8592-4744","affiliations":[{"raw_affiliation_string":"Department of Epigenetics, Van Andel Institute , Grand Rapids, MI 49503, United States","institution_ids":["https://openalex.org/I1317189400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010106597","display_name":"Wanding Zhou","orcid":"https://orcid.org/0000-0001-9126-1932"},"institutions":[{"id":"https://openalex.org/I1335321130","display_name":"Children's Hospital of Philadelphia","ror":"https://ror.org/01z7r7q48","country_code":"US","type":"funder","lineage":["https://openalex.org/I1335321130"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wanding Zhou","raw_affiliation_strings":["Center for Computational and Genomic Medicine, Children\u2019s Hospital of Philadelphia , Philadelphia, PA 19104, United States","Department of Pathology and Laboratory Medicine, University of Pennsylvania , Philadelphia, PA 19104, United States"],"raw_orcid":"https://orcid.org/0000-0001-9126-1932","affiliations":[{"raw_affiliation_string":"Center for Computational and Genomic Medicine, Children\u2019s Hospital of Philadelphia , Philadelphia, PA 19104, United States","institution_ids":["https://openalex.org/I1335321130"]},{"raw_affiliation_string":"Department of Pathology and Laboratory Medicine, University of Pennsylvania , Philadelphia, PA 19104, United States","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000135987","display_name":"Benjamin K. Johnson","orcid":"https://orcid.org/0000-0002-1482-1032"},"institutions":[{"id":"https://openalex.org/I1317189400","display_name":"Van Andel Institute","ror":"https://ror.org/00wm07d60","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1317189400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin K Johnson","raw_affiliation_strings":["Department of Epigenetics, Van Andel Institute , Grand Rapids, MI 49503, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Epigenetics, Van Andel Institute , Grand Rapids, MI 49503, United States","institution_ids":["https://openalex.org/I1317189400"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015458809","display_name":"Hui Shen","orcid":"https://orcid.org/0000-0001-9767-4084"},"institutions":[{"id":"https://openalex.org/I1317189400","display_name":"Van Andel Institute","ror":"https://ror.org/00wm07d60","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1317189400"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hui Shen","raw_affiliation_strings":["Department of Epigenetics, Van Andel Institute , Grand Rapids, MI 49503, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Epigenetics, Van Andel Institute , Grand Rapids, MI 49503, United States","institution_ids":["https://openalex.org/I1317189400"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015458809","https://openalex.org/A5088629436"],"corresponding_institution_ids":["https://openalex.org/I1317189400"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.8073,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7412563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"39","issue":"12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.847599983215332,"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":0.847599983215332,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.04490000009536743,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.01119999960064888,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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":0.7739678621292114},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.5709794759750366},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5565337538719177},{"id":"https://openalex.org/keywords/bisulfite","display_name":"Bisulfite","score":0.4851756691932678},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.47699645161628723},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.46742790937423706},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.40903568267822266},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24056130647659302},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.21798241138458252},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.17494314908981323},{"id":"https://openalex.org/keywords/dna-methylation","display_name":"DNA methylation","score":0.09542974829673767},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07307031750679016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739678621292114},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.5709794759750366},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5565337538719177},{"id":"https://openalex.org/C2775959680","wikidata":"https://www.wikidata.org/wiki/Q2718222","display_name":"Bisulfite","level":5,"score":0.4851756691932678},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.47699645161628723},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.46742790937423706},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.40903568267822266},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24056130647659302},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21798241138458252},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.17494314908981323},{"id":"https://openalex.org/C190727270","wikidata":"https://www.wikidata.org/wiki/Q874745","display_name":"DNA methylation","level":4,"score":0.09542974829673767},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07307031750679016},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":false},{"descriptor_ui":"D013447","descriptor_name":"Sulfites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013447","descriptor_name":"Sulfites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013447","descriptor_name":"Sulfites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013447","descriptor_name":"Sulfites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019175","descriptor_name":"DNA Methylation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019175","descriptor_name":"DNA Methylation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019175","descriptor_name":"DNA Methylation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019175","descriptor_name":"DNA Methylation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btad729","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad729","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad729/54408122/btad729.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:38092060","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38092060","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:10724848","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10724848","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10724848/pdf/btad729.pdf","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad729","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad729","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad729/54408122/btad729.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5428081548","display_name":null,"funder_award_id":"R37 CA230748","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"}],"funders":[{"id":"https://openalex.org/F4320308551","display_name":"Van Andel Research Institute","ror":"https://ror.org/00wm07d60"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4389703561.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2097895258","https://openalex.org/W2106889224","https://openalex.org/W2128505445","https://openalex.org/W2131374955","https://openalex.org/W2132378736","https://openalex.org/W2259938310","https://openalex.org/W2888047927","https://openalex.org/W2950909085","https://openalex.org/W3131055609","https://openalex.org/W3131443014","https://openalex.org/W3157044858","https://openalex.org/W4366083229"],"related_works":["https://openalex.org/W4309247532","https://openalex.org/W3096946169","https://openalex.org/W2113128227","https://openalex.org/W2144610372","https://openalex.org/W4312114021","https://openalex.org/W2121840477","https://openalex.org/W4311938462","https://openalex.org/W2515936044","https://openalex.org/W3123068371","https://openalex.org/W1518632238"],"abstract_inverted_index":{"SUMMARY:":[0],"In":[1],"whole":[2,28],"genome":[3,29],"sequencing":[4,31],"data,":[5],"polymerase":[6],"chain":[7],"reaction":[8],"amplification":[9],"results":[10],"in":[11,20,127],"duplicate":[12,57,95],"DNA":[13,41],"fragments":[14,42],"coming":[15],"from":[16,43,68],"the":[17,21,35,44,66,88,121],"same":[18,45],"location":[19,46],"genome.":[22],"The":[23],"process":[24],"of":[25,84],"preparing":[26],"a":[27,69,81],"bisulfite":[30],"(WGBS)":[32],"library,":[33],"on":[34,132],"other":[36],"hand,":[37],"can":[38],"create":[39],"two":[40],"that":[47,98],"should":[48],"not":[49,73],"be":[50],"considered":[51],"duplicates.":[52],"Currently,":[53],"only":[54,63],"one":[55],"WGBS-aware":[56],"marking":[58,96],"tool":[59,97],"exists.":[60],"However,":[61],"it":[62],"works":[64],"with":[65],"output":[67],"single":[70],"tool,":[71],"does":[72],"accept":[74],"streaming":[75,102],"input":[76,89],"or":[77],"output,":[78],"and":[79,104,113,129,134],"requires":[80],"substantial":[82],"amount":[83],"memory":[85,106],"relative":[86],"to":[87],"size.":[90],"Dupsifter":[91,124],"provides":[92],"an":[93],"aligner-agnostic":[94],"is":[99,105,125,130],"lightweight,":[100],"has":[101],"capabilities,":[103],"efficient.":[107],"AVAILABILITY":[108],"AND":[109],"IMPLEMENTATION:":[110],"Source":[111],"code":[112],"binaries":[114],"are":[115],"freely":[116],"available":[117],"at":[118],"https://github.com/huishenlab/dupsifter":[119],"under":[120],"MIT":[122],"license.":[123],"implemented":[126],"C":[128],"supported":[131],"macOS":[133],"Linux.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
