{"id":"https://openalex.org/W4210336958","doi":"https://doi.org/10.1093/bioinformatics/btac050","title":"SeqWho: reliable, rapid determination of sequence file identity using<i>k</i>-mer frequencies in Random Forest classifiers","display_name":"SeqWho: reliable, rapid determination of sequence file identity using<i>k</i>-mer frequencies in Random Forest classifiers","publication_year":2022,"publication_date":"2022-01-27","ids":{"openalex":"https://openalex.org/W4210336958","doi":"https://doi.org/10.1093/bioinformatics/btac050","pmid":"https://pubmed.ncbi.nlm.nih.gov/35134110"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac050","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac050","pdf_url":null,"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":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8963323","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035846786","display_name":"Christopher Bennett","orcid":"https://orcid.org/0000-0003-3329-2567"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Bennett","raw_affiliation_strings":["Lyda Hill Department of Bioinformatics, University of Texas Southwestern , Dallas, TX 75390, USA"],"raw_orcid":"https://orcid.org/0000-0003-3329-2567","affiliations":[{"raw_affiliation_string":"Lyda Hill Department of Bioinformatics, University of Texas Southwestern , Dallas, TX 75390, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102910032","display_name":"Micah Thornton","orcid":"https://orcid.org/0000-0002-9093-045X"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Micah Thornton","raw_affiliation_strings":["Lyda Hill Department of Bioinformatics, University of Texas Southwestern , Dallas, TX 75390, USA"],"raw_orcid":"https://orcid.org/0000-0002-9093-045X","affiliations":[{"raw_affiliation_string":"Lyda Hill Department of Bioinformatics, University of Texas Southwestern , Dallas, TX 75390, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091197585","display_name":"Chanhee Park","orcid":"https://orcid.org/0000-0003-2262-8555"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chanhee Park","raw_affiliation_strings":["Lyda Hill Department of Bioinformatics, University of Texas Southwestern , Dallas, TX 75390, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyda Hill Department of Bioinformatics, University of Texas Southwestern , Dallas, TX 75390, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015243761","display_name":"Gervaise H. Henry","orcid":"https://orcid.org/0000-0001-7772-9578"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gervaise Henry","raw_affiliation_strings":["Department of Urology, University of Texas Southwestern , Dallas, TX 75390, USA"],"raw_orcid":"https://orcid.org/0000-0001-7772-9578","affiliations":[{"raw_affiliation_string":"Department of Urology, University of Texas Southwestern , Dallas, TX 75390, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356816","display_name":"Yun Zhang","orcid":"https://orcid.org/0000-0002-6125-6662"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Zhang","raw_affiliation_strings":["Lyda Hill Department of Bioinformatics, University of Texas Southwestern , Dallas, TX 75390, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyda Hill Department of Bioinformatics, University of Texas Southwestern , Dallas, TX 75390, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013449579","display_name":"Venkat S. Malladi","orcid":"https://orcid.org/0000-0002-0144-0564"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkat Malladi","raw_affiliation_strings":["Lyda Hill Department of Bioinformatics, University of Texas Southwestern , Dallas, TX 75390, USA"],"raw_orcid":"https://orcid.org/0000-0002-0144-0564","affiliations":[{"raw_affiliation_string":"Lyda Hill Department of Bioinformatics, University of Texas Southwestern , Dallas, TX 75390, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029419214","display_name":"Daehwan Kim","orcid":"https://orcid.org/0000-0003-1182-629X"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daehwan Kim","raw_affiliation_strings":["Lyda Hill Department of Bioinformatics, University of Texas Southwestern , Dallas, TX 75390, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyda Hill Department of Bioinformatics, University of Texas Southwestern , Dallas, TX 75390, USA","institution_ids":["https://openalex.org/I867280407"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5029419214"],"corresponding_institution_ids":["https://openalex.org/I867280407"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00657996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"7","first_page":"1830","last_page":"1837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.6394000053405762,"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":0.6394000053405762,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.06069999933242798,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.048500001430511475,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.722735583782196},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6899500489234924},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6449111104011536},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5318082571029663},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4588533043861389},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.45544907450675964},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.4187338352203369},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4101904332637787},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.39426109194755554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33312198519706726},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15958401560783386},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.102704256772995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722735583782196},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6899500489234924},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6449111104011536},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5318082571029663},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4588533043861389},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.45544907450675964},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.4187338352203369},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4101904332637787},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.39426109194755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33312198519706726},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15958401560783386},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.102704256772995},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","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":"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":"D012984","descriptor_name":"Software","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":"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":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","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":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","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":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btac050","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac050","pdf_url":null,"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:35134110","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35134110","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:pubmedcentral.nih.gov:8963323","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8963323","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"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8963323","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8963323","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"},"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G335130813","display_name":null,"funder_award_id":"R01 GM135341","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G3884107769","display_name":"Bioinformatics Core Facility at UT Southwestern Medical Center","funder_award_id":"RP150596","funder_id":"https://openalex.org/F4320308129","funder_display_name":"Cancer Prevention and Research Institute of Texas"},{"id":"https://openalex.org/G6273980934","display_name":"Recruitment of First-Time, Tenure-Track Faculty Members","funder_award_id":"RR170068","funder_id":"https://openalex.org/F4320308129","funder_display_name":"Cancer Prevention and Research Institute of Texas"},{"id":"https://openalex.org/G6981981288","display_name":null,"funder_award_id":"R01-GM135341","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8738160726","display_name":null,"funder_award_id":"U24 DK110814","funder_id":"https://openalex.org/F4320337357","funder_display_name":"National Institute of Diabetes and Digestive and Kidney Diseases"}],"funders":[{"id":"https://openalex.org/F4320308129","display_name":"Cancer Prevention and Research Institute of Texas","ror":"https://ror.org/0003xa228"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337357","display_name":"National Institute of Diabetes and Digestive and Kidney Diseases","ror":"https://ror.org/00adh9b73"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2066103384","https://openalex.org/W2124410686","https://openalex.org/W2143363067","https://openalex.org/W2165446840","https://openalex.org/W2184129002","https://openalex.org/W2254734290","https://openalex.org/W2259938310","https://openalex.org/W2302703011","https://openalex.org/W2323326409","https://openalex.org/W2763759902","https://openalex.org/W2767826728","https://openalex.org/W2898201023","https://openalex.org/W2950687658","https://openalex.org/W2950964375","https://openalex.org/W2951529834","https://openalex.org/W2952136406","https://openalex.org/W2964849163","https://openalex.org/W2982599786","https://openalex.org/W3011957110","https://openalex.org/W6766093519"],"related_works":["https://openalex.org/W4386259002","https://openalex.org/W1546989560","https://openalex.org/W3193043704","https://openalex.org/W3171520305","https://openalex.org/W1924178503","https://openalex.org/W4308716060","https://openalex.org/W4280648719","https://openalex.org/W3135126032","https://openalex.org/W2053421025","https://openalex.org/W2092772380"],"abstract_inverted_index":{"MOTIVATION:":[0],"With":[1],"the":[2,48,56,113,128,133],"vast":[3],"improvements":[4],"in":[5,70,137],"sequencing":[6,13,51,100,134],"technologies":[7],"and":[8,30,53,58,73,90,94,105,110,130],"increased":[9],"number":[10],"of":[11,50,80,112,132],"protocols,":[12],"is":[14,121],"being":[15],"used":[16,136],"to":[17,45],"answer":[18],"complex":[19],"biological":[20],"problems.":[21],"Subsequently,":[22],"analysis":[23],"pipelines":[24],"have":[25],"become":[26],"more":[27],"time":[28],"consuming":[29],"complicated,":[31],"usually":[32],"requiring":[33],"highly":[34],"extensive":[35],"prevalidation":[36],"steps.":[37],"Here,":[38],"we":[39,84,117],"present":[40],"SeqWho,":[41],"a":[42,122],"program":[43],"designed":[44],"assess":[46],"heuristically":[47],"quality":[49,129],"files":[52,135],"reliably":[54,126],"classify":[55],"organism":[57],"protocol":[59],"type":[60],"by":[61,102],"using":[62],"Random":[63],"Forest":[64],"classifiers":[65],"trained":[66],"on":[67],"biases":[68],"native":[69],"k-mer":[71],"frequencies":[72],"repeat":[74],"sequence":[75],"identities.":[76],"RESULTS:":[77],"Using":[78],"one":[79],"our":[81,87],"primary":[82],"models,":[83],"show":[85],"that":[86,119],"method":[88,124],"accurately":[89],"rapidly":[91],"classifies":[92],"human":[93],"mouse":[95],"sequences":[96],"from":[97],"nine":[98],"different":[99],"libraries":[101],"species,":[103],"library":[104],"both":[106],"together,":[107],"98.32%,":[108],"97.86%":[109],"96.38%":[111],"time,":[114],"respectively.":[115],"Ultimately,":[116],"demonstrate":[118],"SeqWho":[120],"powerful":[123],"for":[125],"validating":[127],"identity":[131],"any":[138],"pipeline.":[139],"AVAILABILITY":[140],"AND":[141],"IMPLEMENTATION:":[142],"https://github.com/DaehwanKimLab/seqwho.":[143],"SUPPLEMENTARY":[144],"INFORMATION:":[145],"Supplementary":[146],"data":[147],"are":[148],"available":[149],"at":[150],"Bioinformatics":[151],"online.":[152]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2022-02-08T00:00:00"}
