{"id":"https://openalex.org/W2764165465","doi":"https://doi.org/10.1093/bioinformatics/btx639","title":"Compression of genomic sequencing reads via hash-based reordering: algorithm and analysis","display_name":"Compression of genomic sequencing reads via hash-based reordering: algorithm and analysis","publication_year":2017,"publication_date":"2017-10-06","ids":{"openalex":"https://openalex.org/W2764165465","doi":"https://doi.org/10.1093/bioinformatics/btx639","mag":"2764165465","pmid":"https://pubmed.ncbi.nlm.nih.gov/29444237"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btx639","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx639","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/4/558/25117422/btx639.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/34/4/558/25117422/btx639.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086012490","display_name":"Shubham Chandak","orcid":"https://orcid.org/0000-0002-1130-9762"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shubham Chandak","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045177980","display_name":"Kedar Tatwawadi","orcid":"https://orcid.org/0000-0003-3677-4174"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kedar Tatwawadi","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043344688","display_name":"Tsachy Weissman","orcid":"https://orcid.org/0009-0008-1099-691X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsachy Weissman","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086012490"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":4.5586,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.95699377,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"34","issue":"4","first_page":"558","last_page":"567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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":1.0,"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/T11247","display_name":"Plant nutrient uptake and metabolism","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9879000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.8875299692153931},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8116626143455505},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6239993572235107},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6185795068740845},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.552483320236206},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.5455074906349182},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4958542287349701},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4100632965564728},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.39185744524002075},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3582136034965515},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.31983113288879395}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.8875299692153931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116626143455505},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6239993572235107},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6185795068740845},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.552483320236206},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.5455074906349182},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4958542287349701},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4100632965564728},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.39185744524002075},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3582136034965515},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.31983113288879395},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","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":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":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","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":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","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":"D056890","descriptor_name":"Eukaryota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D056890","descriptor_name":"Eukaryota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D056890","descriptor_name":"Eukaryota","qualifier_ui":"Q000235","qualifier_name":"genetics","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":3,"locations":[{"id":"doi:10.1093/bioinformatics/btx639","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx639","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/4/558/25117422/btx639.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:29444237","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29444237","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:europepmc.org:5360589","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5860611","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btx639","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx639","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/4/558/25117422/btx639.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":[],"awards":[{"id":"https://openalex.org/G6452885169","display_name":null,"funder_award_id":"5U01CA198943","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2764165465.pdf","grobid_xml":"https://content.openalex.org/works/W2764165465.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1931027898","https://openalex.org/W2000894445","https://openalex.org/W2092880969","https://openalex.org/W2107745473","https://openalex.org/W2109153336","https://openalex.org/W2111044311","https://openalex.org/W2117608012","https://openalex.org/W2125557405","https://openalex.org/W2131106408","https://openalex.org/W2144560237","https://openalex.org/W2149118757","https://openalex.org/W2149434098","https://openalex.org/W2153707226","https://openalex.org/W2158678815","https://openalex.org/W2159906372","https://openalex.org/W2166588423","https://openalex.org/W2538355508","https://openalex.org/W2598359832","https://openalex.org/W6673812163"],"related_works":["https://openalex.org/W2154749946","https://openalex.org/W1835589799","https://openalex.org/W3095240633","https://openalex.org/W75168880","https://openalex.org/W2144265691","https://openalex.org/W4387216472","https://openalex.org/W3005884313","https://openalex.org/W1605991620","https://openalex.org/W4387251676","https://openalex.org/W2951621017"],"abstract_inverted_index":{"Supplementary":[0],"material":[1],"are":[2],"available":[3,11],"at":[4,14],"Bioinformatics":[5],"online.":[6],"The":[7],"proposed":[8],"algorithm":[9],"is":[10],"for":[12],"download":[13],"https://github.com/shubhamchandak94/HARC.":[15]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}
