{"id":"https://openalex.org/W4416889045","doi":"https://doi.org/10.1093/bioinformatics/btaf633","title":"FastDup: a scalable duplicate marking tool using speculation-and-test mechanism","display_name":"FastDup: a scalable duplicate marking tool using speculation-and-test mechanism","publication_year":2025,"publication_date":"2025-11-26","ids":{"openalex":"https://openalex.org/W4416889045","doi":"https://doi.org/10.1093/bioinformatics/btaf633","pmid":"https://pubmed.ncbi.nlm.nih.gov/41324559"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf633","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf633","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/12/btaf633/65667076/btaf633.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/article-pdf/41/12/btaf633/65667076/btaf633.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhonghai Zhang","orcid":"https://orcid.org/0009-0003-5695-0056"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhonghai Zhang","raw_affiliation_strings":["Institute of Computing Technology , Haidian District , Beijing 100190,","School of Computer Science, University of Chinese Academy of Sciences , Haidian District , Beijing 100049,","University of Chinese Academy of Sciences School of Computer Science, , Haidian District, 100049, China Beijing","Institute of Computing Technology, Haidian District, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Haidian District , Beijing 100190,","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"School of Computer Science, University of Chinese Academy of Sciences , Haidian District , Beijing 100049,","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences School of Computer Science, , Haidian District, 100049, China Beijing","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology, Haidian District, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063575625","display_name":"Yewen Li","orcid":"https://orcid.org/0000-0001-8406-0606"},"institutions":[{"id":"https://openalex.org/I2800906782","display_name":"Hong Kong Science and Technology Parks Corporation","ror":"https://ror.org/05q8mqd91","country_code":"HK","type":"nonprofit","lineage":["https://openalex.org/I2800906782"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yewen Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology , Sai Kung District , New Territories, Hong Kong 999077,","The Hong Kong University of Science and Technology, Sai Kung District, 999077, New Territories, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology , Sai Kung District , New Territories, Hong Kong 999077,","institution_ids":["https://openalex.org/I2800906782","https://openalex.org/I889458895"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Sai Kung District, 999077, New Territories, Hong Kong, China","institution_ids":["https://openalex.org/I2800906782","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100650527","display_name":"Ke Meng","orcid":"https://orcid.org/0000-0002-3629-7892"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Meng","raw_affiliation_strings":["Institute of Computing Technology , Haidian District , Beijing 100190,","Institute of Computing Technology, Haidian District, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Haidian District , Beijing 100190,","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Institute of Computing Technology, Haidian District, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102005126","display_name":"Chunming Zhang","orcid":"https://orcid.org/0000-0001-7871-6170"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunming Zhang","raw_affiliation_strings":["Institute of Computing Technology , Haidian District , Beijing 100190,","Institute of Computing Technology, Haidian District, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Haidian District , Beijing 100190,","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Institute of Computing Technology, Haidian District, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006750799","display_name":"Guangming Tan","orcid":"https://orcid.org/0000-0002-6361-5948"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Tan","raw_affiliation_strings":["Institute of Computing Technology , Haidian District , Beijing 100190,","School of Computer Science, University of Chinese Academy of Sciences , Haidian District , Beijing 100049,","Institute of Computing Technology, Haidian District, Beijing, 100190, China","University of Chinese Academy of Sciences School of Computer Science, , Haidian District, 100049, China Beijing"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Haidian District , Beijing 100190,","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"School of Computer Science, University of Chinese Academy of Sciences , Haidian District , Beijing 100049,","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology, Haidian District, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences School of Computer Science, , Haidian District, 100049, China Beijing","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36588832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"41","issue":"12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.17669999599456787,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.17669999599456787,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.11569999903440475,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.08810000121593475,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6485000252723694},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5794000029563904},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4819999933242798},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3716999888420105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148000240325928},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6485000252723694},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5794000029563904},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4819999933242798},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40149998664855957},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3314000070095062},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25609999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24729999899864197},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.24469999969005585}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"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":"D000465","descriptor_name":"Algorithms","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":"D016133","descriptor_name":"Polymerase Chain Reaction","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016133","descriptor_name":"Polymerase Chain Reaction","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016133","descriptor_name":"Polymerase Chain Reaction","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":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaf633","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf633","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/12/btaf633/65667076/btaf633.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:41324559","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41324559","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:12718101","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12718101/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"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/btaf633","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf633","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/12/btaf633/65667076/btaf633.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/G1575492544","display_name":null,"funder_award_id":"T2125013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3096139269","display_name":null,"funder_award_id":"T2125013","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5832729736","display_name":null,"funder_award_id":"62032023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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"},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416889045.pdf","grobid_xml":"https://content.openalex.org/works/W4416889045.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2128505445","https://openalex.org/W2132378736","https://openalex.org/W3131443014","https://openalex.org/W4362693116"],"related_works":[],"abstract_inverted_index":{"FastDup":[0],"is":[1],"a":[2],"C++":[3],"program":[4],"available":[5],"from":[6],"Zenodo":[7],"https://zenodo.org/records/15727829,":[8],"Bioconda":[9],"https://anaconda.org/bioconda/fastdup":[10],"and":[11],"GitHub":[12],"https://github.com/zzhofict/FastDup.git":[13],"under":[14],"the":[15],"MIT":[16],"license.":[17]},"counts_by_year":[],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-12-02T00:00:00"}
