{"id":"https://openalex.org/W4311305969","doi":"https://doi.org/10.1186/s12859-022-05103-0","title":"Evaluation of taxonomic classification and profiling methods for long-read shotgun metagenomic sequencing datasets","display_name":"Evaluation of taxonomic classification and profiling methods for long-read shotgun metagenomic sequencing datasets","publication_year":2022,"publication_date":"2022-12-13","ids":{"openalex":"https://openalex.org/W4311305969","doi":"https://doi.org/10.1186/s12859-022-05103-0","pmid":"https://pubmed.ncbi.nlm.nih.gov/36513983"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-022-05103-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-05103-0","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-05103-0","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-05103-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081119038","display_name":"Daniel M. Portik","orcid":"https://orcid.org/0000-0003-3518-7277"},"institutions":[{"id":"https://openalex.org/I68554272","display_name":"Pacific Biosciences (United States)","ror":"https://ror.org/00fcszb13","country_code":"US","type":"company","lineage":["https://openalex.org/I68554272"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel M. Portik","raw_affiliation_strings":["Pacific Biosciences, 1305 O'Brien Dr, Menlo Park, CA, 93025, USA. dportik@pacb.com","Pacific Biosciences, 1305 O'Brien Dr, Menlo Park, CA, 93025, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Biosciences, 1305 O'Brien Dr, Menlo Park, CA, 93025, USA. dportik@pacb.com","institution_ids":["https://openalex.org/I68554272"]},{"raw_affiliation_string":"Pacific Biosciences, 1305 O'Brien Dr, Menlo Park, CA, 93025, USA","institution_ids":["https://openalex.org/I68554272"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036229691","display_name":"C. Titus Brown","orcid":"https://orcid.org/0000-0001-6001-2677"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Titus Brown","raw_affiliation_strings":["Department of Population Health and Reproduction, University of California Davis, Davis, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Population Health and Reproduction, University of California Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048361007","display_name":"N. Tessa Pierce\u2010Ward","orcid":"https://orcid.org/0000-0002-2942-5331"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Tessa Pierce-Ward","raw_affiliation_strings":["Department of Population Health and Reproduction, University of California Davis, Davis, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Population Health and Reproduction, University of California Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081119038"],"corresponding_institution_ids":["https://openalex.org/I68554272"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":12.8659,"has_fulltext":true,"cited_by_count":138,"citation_normalized_percentile":{"value":0.99381426,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"23","issue":"1","first_page":"541","last_page":"541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9100000262260437,"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":0.9100000262260437,"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/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.05490000173449516,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.00559999980032444,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.8515505790710449},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.8073381185531616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7216547131538391},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.6465168595314026},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6384062767028809},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5099238157272339},{"id":"https://openalex.org/keywords/shotgun-sequencing","display_name":"Shotgun sequencing","score":0.4979531764984131},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49465009570121765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3968593180179596},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3599044382572174},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.33065080642700195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32181477546691895},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.20806670188903809}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.8515505790710449},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.8073381185531616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7216547131538391},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6465168595314026},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6384062767028809},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5099238157272339},{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.4979531764984131},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49465009570121765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3968593180179596},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3599044382572174},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.33065080642700195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32181477546691895},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.20806670188903809},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"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":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","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":5,"locations":[{"id":"doi:10.1186/s12859-022-05103-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-05103-0","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-05103-0","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36513983","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36513983","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:1a20678c1409454b817f8f44efaadd99","is_oa":true,"landing_page_url":"https://doaj.org/article/1a20678c1409454b817f8f44efaadd99","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":"BMC Bioinformatics, Vol 23, Iss 1, Pp 1-39 (2022)","raw_type":"article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt41m7h15x","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/41m7h15x","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"BMC Bioinformatics, vol 23, iss 1","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9749362","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9749362","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-022-05103-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-05103-0","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-05103-0","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311305969.pdf","grobid_xml":"https://content.openalex.org/works/W4311305969.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2045204781","https://openalex.org/W2159954944","https://openalex.org/W2282583203","https://openalex.org/W2345658906","https://openalex.org/W2465681871","https://openalex.org/W2519890620","https://openalex.org/W2758005814","https://openalex.org/W2773939681","https://openalex.org/W2789843538","https://openalex.org/W2885972398","https://openalex.org/W2908149669","https://openalex.org/W2920716817","https://openalex.org/W2949968272","https://openalex.org/W2950671516","https://openalex.org/W2951160681","https://openalex.org/W2951176108","https://openalex.org/W2951278111","https://openalex.org/W2951676949","https://openalex.org/W2952152744","https://openalex.org/W2955167895","https://openalex.org/W2958388979","https://openalex.org/W2968450569","https://openalex.org/W2968499116","https://openalex.org/W2990618091","https://openalex.org/W2996645820","https://openalex.org/W3011982747","https://openalex.org/W3031621849","https://openalex.org/W3032367065","https://openalex.org/W3107569415","https://openalex.org/W3108225425","https://openalex.org/W3137047737","https://openalex.org/W3138971169","https://openalex.org/W3156763462","https://openalex.org/W3159504416","https://openalex.org/W4206102744","https://openalex.org/W4206152354","https://openalex.org/W4225258284","https://openalex.org/W4307033441"],"related_works":["https://openalex.org/W3043668926","https://openalex.org/W3036436206","https://openalex.org/W4238948313","https://openalex.org/W4389452281","https://openalex.org/W3111832393","https://openalex.org/W3000916974","https://openalex.org/W3183189600","https://openalex.org/W3134948850","https://openalex.org/W2573498001","https://openalex.org/W2987572536"],"abstract_inverted_index":{"BACKGROUND:":[0],"Long-read":[1],"shotgun":[2],"metagenomic":[3,296],"sequencing":[4],"is":[5,23,45,49],"gaining":[6],"in":[7,20,176,263],"popularity":[8],"and":[9,34,96,106,123,147,161,169,201,214,236,266,314],"offers":[10],"many":[11,127],"advantages":[12,293],"over":[13],"short-read":[14,121,289],"sequencing.":[15,297],"The":[16,36],"higher":[17],"information":[18,53],"content":[19],"long":[21,74,312],"reads":[22,257,313],"useful":[24],"for":[25,42,73,226,275,294,308,318],"a":[26,50,61,252,316],"variety":[27],"of":[28,38,52,144,216,255,302],"metagenomics":[29],"analyses,":[30],"including":[31,68],"taxonomic":[32,43],"classification":[33,44,122,276],"profiling.":[35],"development":[37],"long-read":[39,115,155,196,249,282,295],"specific":[40],"tools":[41,79],"accelerating,":[46],"yet":[47],"there":[48],"lack":[51],"regarding":[54],"their":[55,98],"relative":[56,107,270],"performance.":[57],"Here,":[58],"we":[59,278],"perform":[60],"critical":[62,300],"benchmarking":[63,320],"study":[64],"using":[65,86,311],"11":[66],"methods,":[67,197,277],"five":[69],"methods":[70,125,156,182,227,238,304],"designed":[71],"specifically":[72],"reads.":[75],"We":[76,220,245],"applied":[77],"these":[78,181,237],"to":[80,137,187,206,210,271],"several":[81],"mock":[82],"community":[83],"datasets":[84,180,250,283],"generated":[85],"Pacific":[87],"Biosciences":[88],"(PacBio)":[89],"HiFi":[90,179,243],"or":[91,232],"Oxford":[92],"Nanopore":[93],"Technology":[94],"sequencing,":[95],"evaluated":[97],"performance":[99,225],"based":[100],"on":[101,229],"read":[102,222],"utilization,":[103],"detection":[104],"metrics,":[105],"abundance":[108,150,190,268],"estimates.":[109,151],"RESULTS:":[110],"Our":[111,299],"results":[112,287],"show":[113],"that":[114,248,280],"classifiers":[116],"generally":[117],"performed":[118,239],"best.":[119],"Several":[120],"profiling":[124],"produced":[126,148,284],"false":[128,208],"positives":[129,209],"(particularly":[130],"at":[131],"lower":[132,264],"abundances),":[133],"required":[134,203],"heavy":[135],"filtering":[136,173,205],"achieve":[138],"acceptable":[139],"precision":[140,168,213,265],"(at":[141],"the":[142,177,188,212,217,281],"cost":[143],"reduced":[145],"recall),":[146],"inaccurate":[149],"By":[152],"contrast,":[153],"two":[154],"(BugSeq,":[157],"MEGAN-LR":[158],"&":[159],"DIAMOND)":[160],"one":[162],"generalized":[163],"method":[164],"(sourmash)":[165],"displayed":[166],"high":[167,193],"recall":[170,215],"without":[171],"any":[172],"required.":[174],"Furthermore,":[175],"PacBio":[178,242],"detected":[183],"all":[184],"species":[185],"down":[186],"0.1%":[189],"level":[191],"with":[192,241,251],"precision.":[194],"Some":[195],"such":[198],"as":[199],"MetaMaps":[200],"MMseqs2,":[202],"moderate":[204],"reduce":[207],"resemble":[211],"top-performing":[218],"methods.":[219],"found":[221,247,279],"quality":[223],"affected":[224],"relying":[228],"protein":[230],"prediction":[231],"exact":[233],"k-mer":[234],"matching,":[235],"better":[240,286],"datasets.":[244,273],"also":[246],"large":[253],"proportion":[254],"shorter":[256],"(<":[258],"2":[259],"kb":[260],"length)":[261],"resulted":[262],"worse":[267],"estimates,":[269],"length-filtered":[272],"Finally,":[274],"significantly":[285],"than":[288],"datasets,":[290],"demonstrating":[291],"clear":[292],"CONCLUSIONS:":[298],"assessment":[301],"available":[303],"provides":[305],"best-practice":[306],"recommendations":[307],"current":[309],"research":[310],"establishes":[315],"baseline":[317],"future":[319],"studies.":[321]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":41},{"year":2024,"cited_by_count":60},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}
