{"id":"https://openalex.org/W2159906372","doi":"https://doi.org/10.1093/bioinformatics/btv248","title":"Data-dependent bucketing improves reference-free compression of sequencing reads","display_name":"Data-dependent bucketing improves reference-free compression of sequencing reads","publication_year":2015,"publication_date":"2015-04-24","ids":{"openalex":"https://openalex.org/W2159906372","doi":"https://doi.org/10.1093/bioinformatics/btv248","mag":"2159906372","pmid":"https://pubmed.ncbi.nlm.nih.gov/25910696"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btv248","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv248","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/17/2770/49035210/bioinformatics_31_17_2770.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/31/17/2770/49035210/bioinformatics_31_17_2770.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014584023","display_name":"Rob Patro","orcid":"https://orcid.org/0000-0001-8463-1675"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Patro","raw_affiliation_strings":["1 Department of Computer Science, Stony Brook University, Stony Brook, NY 11794-4400, USA and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science, Stony Brook University, Stony Brook, NY 11794-4400, USA and","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113653378","display_name":"Carl Kingsford","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Carl Kingsford","raw_affiliation_strings":["2 Department Computational Biology, School of Computer Science, Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"2 Department Computational Biology, School of Computer Science, Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113653378"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":10.0402,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.98076357,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"31","issue":"17","first_page":"2770","last_page":"2777"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9476000070571899,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9476000070571899,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.013899999670684338,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.003800000064074993,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.8205325603485107},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.601524293422699},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.5886917114257812},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5554561614990234},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5382252931594849},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.49972033500671387},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.48287561535835266},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.4802161157131195},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4291476011276245},{"id":"https://openalex.org/keywords/file-size","display_name":"File size","score":0.42244625091552734},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.41293907165527344},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.30242064595222473},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22769176959991455},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1619369089603424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10897231101989746},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09906008839607239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205325603485107},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.601524293422699},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.5886917114257812},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5554561614990234},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5382252931594849},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.49972033500671387},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.48287561535835266},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.4802161157131195},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4291476011276245},{"id":"https://openalex.org/C2776029614","wikidata":"https://www.wikidata.org/wiki/Q1146367","display_name":"File size","level":2,"score":0.42244625091552734},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.41293907165527344},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30242064595222473},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22769176959991455},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1619369089603424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10897231101989746},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09906008839607239},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","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},{"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":7,"locations":[{"id":"doi:10.1093/bioinformatics/btv248","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv248","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/17/2770/49035210/bioinformatics_31_17_2770.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:25910696","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25910696","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:figshare.com:article/6702062","is_oa":true,"landing_page_url":null,"pdf_url":"https://figshare.com/articles/Data-dependent_bucketing_improves_reference-free_compression_of_sequencing_reads_/6702062","source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:repository.cmu.edu:cbd-1003","is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=1003&context=cbd","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Biology Department","raw_type":"text"},{"id":"pmh:oai:open-archive.highwire.org:bioinfo:31/17/2770","is_oa":false,"landing_page_url":"http://bioinformatics.oxfordjournals.org/cgi/content/short/31/17/2770","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"TEXT"},{"id":"pmh:oai:pubmedcentral.nih.gov:4547610","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4547610","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"},{"id":"doi:10.1184/r1/6702062.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6702062.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btv248","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv248","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/17/2770/49035210/bioinformatics_31_17_2770.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1080157019","display_name":null,"funder_award_id":"R21HG006913","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G1325684988","display_name":null,"funder_award_id":"CCF-1256087","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1671837195","display_name":null,"funder_award_id":"R21HG006913","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G2933222473","display_name":"AF: Small: Multiscale Spectral Signatures for Local and Multi-objective Biological Network Alignment","funder_award_id":"1319998","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3068176952","display_name":null,"funder_award_id":"R01HG007104","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3235315301","display_name":null,"funder_award_id":"R21 HG006913","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G3355402586","display_name":"Carl Kingsford Investigator Award","funder_award_id":"GBMF4554","funder_id":"https://openalex.org/F4320306202","funder_display_name":"Gordon and Betty Moore Foundation"},{"id":"https://openalex.org/G3641969089","display_name":"CAREER: Model-based Reconstruction of Ancient Biological Networks","funder_award_id":"1256087","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7958957864","display_name":null,"funder_award_id":"CCF-1256087, CCF-1319998","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8913690421","display_name":null,"funder_award_id":"R01 HG007104","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G8978740379","display_name":null,"funder_award_id":"R01HG007104","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2159906372.pdf","grobid_xml":"https://content.openalex.org/works/W2159906372.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1025014104","https://openalex.org/W1970218893","https://openalex.org/W1978939618","https://openalex.org/W2000466469","https://openalex.org/W2010928148","https://openalex.org/W2020255088","https://openalex.org/W2050374641","https://openalex.org/W2051929999","https://openalex.org/W2065128082","https://openalex.org/W2069066547","https://openalex.org/W2092880969","https://openalex.org/W2095680943","https://openalex.org/W2100076391","https://openalex.org/W2101247207","https://openalex.org/W2109153336","https://openalex.org/W2110553099","https://openalex.org/W2111044311","https://openalex.org/W2112509895","https://openalex.org/W2117953160","https://openalex.org/W2123445896","https://openalex.org/W2131106408","https://openalex.org/W2137892587","https://openalex.org/W2142003566","https://openalex.org/W2144560237","https://openalex.org/W2159084616","https://openalex.org/W2159683766","https://openalex.org/W2166588423","https://openalex.org/W2167943254","https://openalex.org/W2169456326","https://openalex.org/W2171057071","https://openalex.org/W4210767115","https://openalex.org/W4394666350","https://openalex.org/W6674561012","https://openalex.org/W6806875027"],"related_works":["https://openalex.org/W4383723869","https://openalex.org/W4384298135","https://openalex.org/W4383722264","https://openalex.org/W2388481516","https://openalex.org/W2161302774","https://openalex.org/W1723410974","https://openalex.org/W3007688875","https://openalex.org/W2152893502","https://openalex.org/W4386918011","https://openalex.org/W3209669196"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1],"storage":[2,31],"and":[3,32,80,104,141],"transmission":[4,33],"of":[5,51,59,84],"high-throughput":[6],"sequencing":[7,39,52],"data":[8,18,160],"consumes":[9],"significant":[10],"resources.":[11],"As":[12],"our":[13],"capacity":[14],"to":[15,20,29,36,47,112],"produce":[16],"such":[17],"continues":[19],"increase,":[21],"this":[22,38],"burden":[23],"will":[24],"only":[25],"grow.":[26],"One":[27],"approach":[28],"reduce":[30],"requirements":[34],"is":[35,54,134,138,151],"compress":[37],"data.":[40],"RESULTS:":[41],"We":[42,71],"present":[43],"a":[44,76,82,113],"novel":[45],"technique":[46],"boost":[48],"the":[49,57,69,147],"compression":[50,92,99,128],"that":[53,64],"based":[55],"on":[56,120],"concept":[58],"bucketing":[60,78,103],"similar":[61],"reads":[62],"so":[63],"they":[65],"appear":[66],"nearby":[67],"in":[68,116,136],"file.":[70],"demonstrate":[72],"that,":[73],"by":[74],"adopting":[75],"data-dependent":[77],"scheme":[79],"employing":[81],"number":[83],"encoding":[85],"ideas,":[86],"we":[87],"can":[88],"achieve":[89],"substantially":[90],"better":[91],"ratios":[93],"than":[94],"existing":[95,124],"de":[96,126],"novo":[97,127],"sequence":[98],"tools,":[100],"including":[101],"other":[102],"reordering":[105],"schemes.":[106,129],"Our":[107],"method,":[108],"Mince,":[109],"achieves":[110],"up":[111],"45%":[114],"reduction":[115],"file":[117],"sizes":[118],"(28%":[119],"average)":[121],"compared":[122],"with":[123],"state-of-the-art":[125],"AVAILABILITY":[130],"AND":[131],"IMPLEMENTATION:":[132],"Mince":[133],"written":[135],"C++11,":[137],"open":[139],"source":[140],"has":[142],"been":[143],"made":[144],"available":[145,152,162],"under":[146],"GPLv3":[148],"license.":[149],"It":[150],"at":[153,163],"http://www.cs.cmu.edu/\u223cckingsf/software/mince.":[154],"CONTACT:":[155],"carlk@cs.cmu.edu":[156],"SUPPLEMENTARY":[157],"INFORMATION:":[158],"Supplementary":[159],"are":[161],"Bioinformatics":[164],"online.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}
