{"id":"https://openalex.org/W4307475426","doi":"https://doi.org/10.1371/journal.pcbi.1010638","title":"Parameterized syncmer schemes improve long-read mapping","display_name":"Parameterized syncmer schemes improve long-read mapping","publication_year":2022,"publication_date":"2022-10-28","ids":{"openalex":"https://openalex.org/W4307475426","doi":"https://doi.org/10.1371/journal.pcbi.1010638"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1010638","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1010638","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010638&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010638&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068525077","display_name":"Abhinav Dutta","orcid":"https://orcid.org/0000-0001-6519-9581"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Abhinav Dutta","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India,","Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India"],"raw_orcid":"https://orcid.org/0000-0001-6519-9581","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India,","institution_ids":["https://openalex.org/I132153292"]},{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008335823","display_name":"David Pellow","orcid":"https://orcid.org/0000-0002-6296-5209"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"David Pellow","raw_affiliation_strings":["Blavatnik School of Computer Science, Tel-Aviv University, Tel-Aviv Israel"],"raw_orcid":"https://orcid.org/0000-0002-6296-5209","affiliations":[{"raw_affiliation_string":"Blavatnik School of Computer Science, Tel-Aviv University, Tel-Aviv Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038806020","display_name":"Ron Shamir","orcid":"https://orcid.org/0000-0003-1889-9870"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Ron Shamir","raw_affiliation_strings":["Blavatnik School of Computer Science, Tel-Aviv University, Tel-Aviv Israel"],"raw_orcid":"https://orcid.org/0000-0003-1889-9870","affiliations":[{"raw_affiliation_string":"Blavatnik School of Computer Science, Tel-Aviv University, Tel-Aviv Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008335823","https://openalex.org/A5038806020","https://openalex.org/A5068525077"],"corresponding_institution_ids":["https://openalex.org/I132153292","https://openalex.org/I16391192"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":2.4303,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.90010341,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"18","issue":"10","first_page":"e1010638","last_page":"e1010638"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994999766349792,"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":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9922999739646912,"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9902999997138977,"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":0.6218600869178772},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5966174602508545},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5525684952735901},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5175613760948181},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.45318174362182617},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4430708885192871},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4289287030696869},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.41511696577072144},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.4143882393836975},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.4112205505371094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32835423946380615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2447296380996704},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1604708433151245},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1553530991077423},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1277570128440857}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6218600869178772},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5966174602508545},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5525684952735901},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5175613760948181},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.45318174362182617},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4430708885192871},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4289287030696869},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.41511696577072144},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.4143882393836975},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.4112205505371094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32835423946380615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2447296380996704},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1604708433151245},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1553530991077423},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1277570128440857},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1371/journal.pcbi.1010638","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1010638","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010638&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:plo:pcbi00:1010638","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010638","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9645665","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9645665","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":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1010638","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1010638","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010638&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3711085794","display_name":null,"funder_award_id":"1339/18","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"},{"id":"https://openalex.org/G6519853539","display_name":null,"funder_award_id":"3165/19","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320312914","display_name":"Blavatnik Family Foundation","ror":null},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4307475426.pdf","grobid_xml":"https://content.openalex.org/works/W4307475426.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2111295912","https://openalex.org/W2134153749","https://openalex.org/W2141978199","https://openalex.org/W2438121987","https://openalex.org/W2583363792","https://openalex.org/W2789843538","https://openalex.org/W2950121474","https://openalex.org/W2950266744","https://openalex.org/W2953263404","https://openalex.org/W2990618091","https://openalex.org/W3029256690","https://openalex.org/W3042377559","https://openalex.org/W3128964673","https://openalex.org/W3164362182","https://openalex.org/W3202634790","https://openalex.org/W4220999759","https://openalex.org/W4225293672","https://openalex.org/W4243450674","https://openalex.org/W6767601804"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2051058708","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W2591066345","https://openalex.org/W2107233609"],"abstract_inverted_index":{"Motivation":[0],"Sequencing":[1],"long":[2,238],"reads":[3,18,155,196,214,239],"presents":[4],"novel":[5],"challenges":[6],"to":[7,23,39,54,73],"mapping.":[8],"One":[9],"such":[10],"challenge":[11],"is":[12,53,70],"low":[13,172],"sequence":[14,173,176],"similarity":[15],"between":[16,41],"the":[17,20,115,120,139,147,195,216,225],"and":[19,27,75,89,110,123,130,180,191,207],"reference,":[21],"due":[22,38],"high":[24,159],"sequencing":[25,76],"error":[26,208],"mutation":[28],"rates.":[29],"This":[30],"occurs,":[31],"e.g.,":[32],"in":[33,50,119,240],"a":[34,85,91,135,241],"cancer":[35],"tumor,":[36],"or":[37,45,102],"differences":[40],"strains":[42],"of":[43,87,117,137,149,178,194,237,244],"viruses":[44],"bacteria.":[46],"A":[47],"key":[48],"idea":[49],"mapping":[51,211,236],"algorithms":[52],"sketch":[55],"sequences":[56],"with":[57,100,142],"their":[58],"minimizers.":[59],"Recently,":[60],"syncmers":[61],"were":[62,200],"introduced":[63],"as":[64,187,220,222],"an":[65],"alternative":[66],"sketching":[67],"method":[68],"that":[69,197,231],"more":[71,169,213],"robust":[72],"mutations":[74],"errors.":[77],"Results":[78],"We":[79,113,229],"introduce":[80],"parameterized":[81],"syncmer":[82,227],"schemes":[83],"(PSS),":[84],"generalization":[86],"syncmers,":[88],"provide":[90],"theoretical":[92,151],"analysis":[93],"for":[94],"multi-parameter":[95],"schemes.":[96,228],"By":[97],"combining":[98],"PSS":[99,118,233],"downsampling":[101],"minimizers":[103],"we":[104],"can":[105,234],"achieve":[106],"any":[107],"desired":[108],"compression":[109,160,206],"window":[111],"guarantee.":[112],"implemented":[114],"use":[116],"popular":[121],"minimap2":[122],"Winnowmap2":[124],"mappers.":[125],"In":[126],"tests":[127],"on":[128,146],"simulated":[129],"real":[131],"long-read":[132],"data":[133],"from":[134],"variety":[136],"genomes,":[138],"PSS-based":[140,210],"algorithms,":[141],"scheme":[143],"parameters":[144],"selected":[145],"basis":[148],"our":[150],"analysis,":[152],"reduced":[153],"unmapped":[154,189],"by":[156],"20-60%":[157],"at":[158,171,204],"while":[161],"usually":[162],"using":[163,224,232],"less":[164],"memory.":[165],"The":[166],"advantage":[167],"was":[168],"pronounced":[170],"identity.":[174],"At":[175],"identity":[177],"75%":[179],"medium":[181],"compression,":[182],"PSS-minimap":[183],"had":[184],"only":[185],"37%":[186],"many":[188],"reads,":[190],"8%":[192],"fewer":[193],"did":[198],"map":[199],"incorrectly":[201],"mapped.":[202],"Even":[203],"lower":[205],"rates,":[209],"mapped":[212],"than":[215],"original":[217,226],"minimizer-based":[218],"mappers":[219,223],"well":[221],"conclude":[230],"improve":[235],"wide":[242],"range":[243],"settings.":[245]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5}],"updated_date":"2025-11-23T05:10:03.516525","created_date":"2022-11-02T00:00:00"}