{"id":"https://openalex.org/W7147189718","doi":"https://doi.org/10.1371/journal.pcbi.1014158","title":"ntStat: k-mer characterization using occurrence statistics in raw sequencing data","display_name":"ntStat: k-mer characterization using occurrence statistics in raw sequencing data","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7147189718","doi":"https://doi.org/10.1371/journal.pcbi.1014158","pmid":"https://pubmed.ncbi.nlm.nih.gov/41920843"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1014158","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1014158","pdf_url":null,"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","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1371/journal.pcbi.1014158","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044309076","display_name":"Parham Kazemi","orcid":"https://orcid.org/0000-0002-2126-5644"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Parham Kazemi","raw_affiliation_strings":["BC Cancer Research Institute, Vancouver, Canada","Bioinformatics Graduate Program, Faculty of Science, University of British Columbia, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2126-5644","affiliations":[{"raw_affiliation_string":"BC Cancer Research Institute, Vancouver, Canada","institution_ids":[]},{"raw_affiliation_string":"Bioinformatics Graduate Program, Faculty of Science, University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132655750","display_name":"Lauren Coombe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lauren Coombe","raw_affiliation_strings":["BC Cancer Research Institute, Vancouver, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BC Cancer Research Institute, Vancouver, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132566522","display_name":"Ren\u00e9 L. Warren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren\u00e9 L. Warren","raw_affiliation_strings":["BC Cancer Research Institute, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9890-2293","affiliations":[{"raw_affiliation_string":"BC Cancer Research Institute, Vancouver, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132613490","display_name":"Inanc Birol","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Inanc Birol","raw_affiliation_strings":["BC Cancer Research Institute, Vancouver, Canada","Department of Medical Genetics, University of British Columbia, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0950-7839","affiliations":[{"raw_affiliation_string":"BC Cancer Research Institute, Vancouver, Canada","institution_ids":[]},{"raw_affiliation_string":"Department of Medical Genetics, University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42273653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"4","first_page":"e1014158","last_page":"e1014158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9348999857902527,"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":0.9348999857902527,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.048700001090765,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.002300000051036477,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.614300012588501},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6108999848365784},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.5016999840736389},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.48249998688697815},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.45719999074935913},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.4408000111579895},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.4284000098705292},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.3758000135421753},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.3549000024795532},{"id":"https://openalex.org/keywords/deep-sequencing","display_name":"Deep sequencing","score":0.3499000072479248}],"concepts":[{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.614300012588501},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6108999848365784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5728999972343445},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5016999840736389},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.48249998688697815},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.4408000111579895},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.4284000098705292},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4203000068664551},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3833000063896179},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C132917006","wikidata":"https://www.wikidata.org/wiki/Q5250436","display_name":"Deep sequencing","level":4,"score":0.3499000072479248},{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.3467999994754791},{"id":"https://openalex.org/C166608930","wikidata":"https://www.wikidata.org/wiki/Q5169175","display_name":"Copy number analysis","level":5,"score":0.3467999994754791},{"id":"https://openalex.org/C151020129","wikidata":"https://www.wikidata.org/wiki/Q7625067","display_name":"Structural variation","level":4,"score":0.3402000069618225},{"id":"https://openalex.org/C33643355","wikidata":"https://www.wikidata.org/wiki/Q5176731","display_name":"Count data","level":3,"score":0.3391000032424927},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.33889999985694885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33880001306533813},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.32679998874664307},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.31949999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3190999925136566},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C143589142","wikidata":"https://www.wikidata.org/wiki/Q2617554","display_name":"Loss of heterozygosity","level":4,"score":0.3084000051021576},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C143191323","wikidata":"https://www.wikidata.org/wiki/Q118406","display_name":"Ploidy","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C2779377595","wikidata":"https://www.wikidata.org/wiki/Q21045424","display_name":"Approximate Bayesian computation","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C60782215","wikidata":"https://www.wikidata.org/wiki/Q3333679","display_name":"Probabilistic method","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.257999986410141}],"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":"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":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","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":"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":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","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":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":4,"locations":[{"id":"doi:10.1371/journal.pcbi.1014158","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1014158","pdf_url":null,"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":"pmid:41920843","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41920843","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:doaj.org/article:bfe9dd4594a545418e3916d5c583e8b1","is_oa":true,"landing_page_url":"https://doaj.org/article/bfe9dd4594a545418e3916d5c583e8b1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 22, Iss 4, p e1014158 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13056179","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13056179/","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.1014158","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1014158","pdf_url":null,"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/G3602867403","display_name":null,"funder_award_id":"PJT-183608","funder_id":"https://openalex.org/F4320334506","funder_display_name":"Canadian Institutes of Health Research"}],"funders":[{"id":"https://openalex.org/F4320334506","display_name":"Canadian Institutes of Health Research","ror":"https://ror.org/01gavpb45"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1595159159","https://openalex.org/W2005136695","https://openalex.org/W2038210983","https://openalex.org/W2078409719","https://openalex.org/W2096128575","https://openalex.org/W2103111465","https://openalex.org/W2103962160","https://openalex.org/W2123845384","https://openalex.org/W2128591967","https://openalex.org/W2133956160","https://openalex.org/W2134153749","https://openalex.org/W2163584430","https://openalex.org/W2570372911","https://openalex.org/W2583363792","https://openalex.org/W2762777574","https://openalex.org/W2949074212","https://openalex.org/W2949086752","https://openalex.org/W2950266744","https://openalex.org/W2950354111","https://openalex.org/W2952136406","https://openalex.org/W2953326935","https://openalex.org/W3012094285","https://openalex.org/W3202547677","https://openalex.org/W4220999759","https://openalex.org/W4308353607","https://openalex.org/W4311473687","https://openalex.org/W4321112378","https://openalex.org/W4387743254","https://openalex.org/W4398177119","https://openalex.org/W4416098230"],"related_works":[],"abstract_inverted_index":{"K-mer":[0],"counts":[1,49],"are":[2,197],"fundamental":[3],"in":[4,50,77,105,141,244],"many":[5],"genomic":[6,56],"data":[7,32,93,153],"analysis":[8,202,231],"tasks,":[9],"providing":[10],"valuable":[11,119],"information":[12,102],"for":[13,151,210],"genome":[14,60,78,218],"assembly,":[15],"error":[16,240],"correction,":[17],"and":[18,34,63,80,100,103,117,126,139,175,188,207,223],"variant":[19],"detection.":[20],"State-of-the-art":[21],"k-mer":[22,40,48,72,98,111,186,208,245],"counting":[23],"tools":[24],"employ":[25],"various":[26],"techniques,":[27],"such":[28,58],"as":[29,59],"parallelism,":[30],"probabilistic":[31],"structures,":[33],"disk":[35,173],"utilization,":[36],"to":[37,95,226],"efficiently":[38],"extract":[39],"frequencies":[41],"from":[42,214],"large":[43],"datasets.":[44],"The":[45,66,230],"distribution":[46],"of":[47,68,143,191,232,241],"raw":[51],"sequencing":[52,124],"reads":[53,69],"reveals":[54],"key":[55],"characteristics":[57],"size,":[61],"heterozygosity,":[62],"basecalling":[64],"quality.":[65],"number":[67],"containing":[70],"a":[71,86,171,215],"has":[73],"also":[74,179],"shown":[75],"application":[76],"assembly":[79],"sequence":[81],"analysis.":[82],"We":[83],"present":[84],"ntStat,":[85],"toolkit":[87],"that":[88],"employs":[89],"succinct":[90],"Bloom":[91],"filter":[92],"structures":[94],"track":[96],"both":[97],"count":[99,112],"depth":[101],"use":[104],"downstream":[106],"applications.":[107],"ntStat":[108,131,150,178,196],"models":[109],"the":[110,122,192,227],"histogram":[113,201],"using":[114],"evolutionary":[115],"computation,":[116],"infers":[118],"insights":[120],"about":[121],"genome,":[123],"data,":[125],"individual":[127],"k-mers,":[128],"de":[129],"novo.":[130],"consistently":[132],"ran":[133],"faster":[134,148,167],"than":[135,149,183,221],"DSK,":[136],"BFCounter,":[137],"hackgap,":[138],"Squeakr":[140],"all":[142],"our":[144],"tests.":[145],"Jellyfish":[146],"performed":[147],"human":[152,217],"with":[154,161,219],"k":[155,162],"=":[156,163],"25":[157],"but":[158,169],"fell":[159],"behind":[160],"64.":[164],"KMC3":[165],"was":[166],"overall":[168],"at":[170],"high":[172],"usage":[174],"memory":[176,182],"cost.":[177],"used":[180],"less":[181,220],"other":[184],"non-disk-based":[185],"counters":[187],"typically,":[189],"99.5-99.9%":[190],"k-mers":[193],"processed":[194],"by":[195],"counted":[198],"correctly.":[199],"ntStat's":[200],"module":[203],"detected":[204],"heterozygosity":[205],"percentages":[206],"coverage":[209],"long-read":[211],"datasets":[212,236],"simulated":[213,233],"diploid":[216],"1%":[222],"0.5-fold":[224],"difference":[225],"ground":[228],"truth.":[229],"long":[234],"read":[235],"showed":[237],"an":[238],"average":[239],"just":[242],"2%":[243],"robustness":[246],"estimates.":[247]},"counts_by_year":[],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2026-04-02T00:00:00"}