{"id":"https://openalex.org/W2158807263","doi":"https://doi.org/10.1093/bioinformatics/btv395","title":"Inference of Markovian properties of molecular sequences from NGS data and applications to comparative genomics","display_name":"Inference of Markovian properties of molecular sequences from NGS data and applications to comparative genomics","publication_year":2015,"publication_date":"2015-06-30","ids":{"openalex":"https://openalex.org/W2158807263","doi":"https://doi.org/10.1093/bioinformatics/btv395","mag":"2158807263","pmid":"https://pubmed.ncbi.nlm.nih.gov/26130573"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btv395","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv395","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/7/993/49018311/bioinformatics_32_7_993.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/32/7/993/49018311/bioinformatics_32_7_993.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100720540","display_name":"Jie Ren","orcid":"https://orcid.org/0000-0003-0464-9096"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Ren","raw_affiliation_strings":["1 Molecular and Computational Biology Program, University of Southern California, Los Angeles, CA, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Molecular and Computational Biology Program, University of Southern California, Los Angeles, CA, USA,","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089528237","display_name":"Kai Song","orcid":"https://orcid.org/0000-0001-6792-7159"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Song","raw_affiliation_strings":["2 School of Mathematical Sciences, Peking University, Beijing, China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"2 School of Mathematical Sciences, Peking University, Beijing, China,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091013880","display_name":"Minghua Deng","orcid":"https://orcid.org/0000-0002-9143-1898"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghua Deng","raw_affiliation_strings":["2 School of Mathematical Sciences, Peking University, Beijing, China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"2 School of Mathematical Sciences, Peking University, Beijing, China,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049954115","display_name":"Gesine Reinert","orcid":"https://orcid.org/0000-0002-0363-9470"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gesine Reinert","raw_affiliation_strings":["3 Department of Statistics, University of Oxford, 1 South Parks Road, Oxford OX1 3TG, UK,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"3 Department of Statistics, University of Oxford, 1 South Parks Road, Oxford OX1 3TG, UK,","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043708529","display_name":"Charles H. Cannon","orcid":"https://orcid.org/0000-0003-1901-0420"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]},{"id":"https://openalex.org/I2801454379","display_name":"Xishuangbanna Tropical Botanical Garden","ror":"https://ror.org/02rz58g17","country_code":"CN","type":"archive","lineage":["https://openalex.org/I19820366","https://openalex.org/I2801454379"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Charles H. Cannon","raw_affiliation_strings":["4 Department of Biological Sciences, Texas Tech University, TX 79409-3131, USA,","5 Xishuangbanna Tropical Botanic Garden, Chinese Academy of Sciences, Yunnan, China and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"4 Department of Biological Sciences, Texas Tech University, TX 79409-3131, USA,","institution_ids":["https://openalex.org/I12315562"]},{"raw_affiliation_string":"5 Xishuangbanna Tropical Botanic Garden, Chinese Academy of Sciences, Yunnan, China and","institution_ids":["https://openalex.org/I2801454379"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022255550","display_name":"Fengzhu Sun","orcid":"https://orcid.org/0000-0002-8552-043X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Fengzhu Sun","raw_affiliation_strings":["1 Molecular and Computational Biology Program, University of Southern California, Los Angeles, CA, USA,","6 Centre for Computational Systems Biology, School of Mathematical Sciences, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Molecular and Computational Biology Program, University of Southern California, Los Angeles, CA, USA,","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"6 Centre for Computational Systems Biology, School of Mathematical Sciences, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5022255550"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I24943067"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.5125,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.89779592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":"7","first_page":"993","last_page":"1000"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.3767000138759613,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.3767000138759613,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.36980000138282776,"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":0.07490000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6482484936714172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6297187805175781},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6019178628921509},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5934610962867737},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5921597480773926},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.5181064009666443},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4924972951412201},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.4403228461742401},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4284713864326477},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37569037079811096},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.33799517154693604},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.26150238513946533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23867011070251465},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.15340656042099},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.13799631595611572},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13435235619544983}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6482484936714172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6297187805175781},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6019178628921509},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5934610962867737},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5921597480773926},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5181064009666443},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4924972951412201},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4403228461742401},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4284713864326477},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37569037079811096},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.33799517154693604},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.26150238513946533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23867011070251465},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15340656042099},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.13799631595611572},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13435235619544983},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"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":"D000465","descriptor_name":"Algorithms","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":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014714","descriptor_name":"Vertebrates","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014714","descriptor_name":"Vertebrates","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014714","descriptor_name":"Vertebrates","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014714","descriptor_name":"Vertebrates","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"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":"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":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":6,"locations":[{"id":"doi:10.1093/bioinformatics/btv395","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv395","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/7/993/49018311/bioinformatics_32_7_993.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:26130573","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26130573","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:CiteSeerX.psu:10.1.1.862.4311","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.862.4311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/early/2015/06/29/bioinformatics.btv395.full.pdf","raw_type":"text"},{"id":"pmh:oai:europepmc.org:5127480","is_oa":false,"landing_page_url":"http://europepmc.org/pmc/articles/PMC6169497","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:open-archive.highwire.org:bioinfo:32/7/993","is_oa":false,"landing_page_url":"http://bioinformatics.oxfordjournals.org/cgi/content/short/32/7/993","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"TEXT"},{"id":"pmh:oai:pubmedcentral.nih.gov:6169497","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6169497","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":"doi:10.1093/bioinformatics/btv395","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv395","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/7/993/49018311/bioinformatics_32_7_993.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G127184978","display_name":null,"funder_award_id":"1518001","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1287282707","display_name":null,"funder_award_id":"31428012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1434400711","display_name":null,"funder_award_id":"31471246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G171726519","display_name":null,"funder_award_id":"P50 HG002790","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G180526337","display_name":null,"funder_award_id":"EP/K032402/1","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1853430408","display_name":null,"funder_award_id":"P50 HG 002790","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4895756154","display_name":"Dimensions: Pattern and Process in Marine Bacterial, Archaeal, and Protistan Biodiversity, and Effects of Human Impacts","funder_award_id":"1136818","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G744903794","display_name":null,"funder_award_id":"2015CB910303","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7586172517","display_name":null,"funder_award_id":"DMS 1518001","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7700640841","display_name":null,"funder_award_id":"OCE-1136818","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8328088611","display_name":"Network Comparison","funder_award_id":"EP/K032402/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G851128662","display_name":null,"funder_award_id":"31171262","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8699084357","display_name":null,"funder_award_id":"EP/K032402/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2158807263.pdf","grobid_xml":"https://content.openalex.org/works/W2158807263.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1600463518","https://openalex.org/W1966711026","https://openalex.org/W1968363797","https://openalex.org/W1982443365","https://openalex.org/W1988827980","https://openalex.org/W2001753819","https://openalex.org/W2006075770","https://openalex.org/W2006772779","https://openalex.org/W2007321142","https://openalex.org/W2018604728","https://openalex.org/W2023091911","https://openalex.org/W2024500224","https://openalex.org/W2025166640","https://openalex.org/W2032845906","https://openalex.org/W2041397659","https://openalex.org/W2048818637","https://openalex.org/W2053392780","https://openalex.org/W2056859449","https://openalex.org/W2057215967","https://openalex.org/W2077299429","https://openalex.org/W2085315537","https://openalex.org/W2085667778","https://openalex.org/W2086291326","https://openalex.org/W2087686387","https://openalex.org/W2094890728","https://openalex.org/W2096116532","https://openalex.org/W2111367247","https://openalex.org/W2111798311","https://openalex.org/W2116790427","https://openalex.org/W2124163981","https://openalex.org/W2126953550","https://openalex.org/W2131171044","https://openalex.org/W2132996374","https://openalex.org/W2133530448","https://openalex.org/W2138842363","https://openalex.org/W2155430004","https://openalex.org/W2168031553","https://openalex.org/W2168451430","https://openalex.org/W2168546919","https://openalex.org/W2329077652","https://openalex.org/W2333466645","https://openalex.org/W2740984310","https://openalex.org/W2914081640","https://openalex.org/W3142026388","https://openalex.org/W4230450987","https://openalex.org/W4297948819","https://openalex.org/W6843858941"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W3145575561","https://openalex.org/W2164162849"],"abstract_inverted_index":{"MOTIVATION:":[0],"Next-generation":[1],"sequencing":[2],"(NGS)":[3],"technologies":[4],"generate":[5],"large":[6],"amounts":[7],"of":[8,70,97,122,178,194,201,222,244,252,260],"short":[9,23,135],"read":[10,136],"data":[11,109,278],"for":[12,54,66,104,133,145,167],"many":[13],"different":[14],"organisms.":[15],"The":[16],"fact":[17],"that":[18,152,218,235,239],"NGS":[19,42,108,134,183,209],"reads":[20,30,184,210],"are":[21,62,91,279],"generally":[22],"makes":[24],"it":[25],"challenging":[26],"to":[27,93,174],"assemble":[28],"the":[29,33,57,77,95,100,105,153,164,176,179,192,219,223,230,236,245,253,261],"and":[31,99,185,204,234],"reconstruct":[32],"original":[34],"genome":[35],"sequence.":[36],"For":[37,85],"clustering":[38,198,231,237,251],"genomes":[39],"using":[40,163,188,211],"such":[41,146],"data,":[43],"word-count":[44],"based":[45,124,181,207],"alignment-free":[46,212],"sequence":[47,79,213],"comparison":[48],"is":[49,73,265],"a":[50,81,113,142,226,241,249],"promising":[51],"approach,":[52,56],"but":[53],"this":[55,67],"underlying":[58,68],"expected":[59],"word":[60,71,147],"counts":[61,72],"essential.A":[63],"plausible":[64,250],"model":[65,166],"distribution":[69,161],"given":[74],"through":[75],"modeling":[76],"DNA":[78],"as":[80,267],"Markov":[82],"chain":[83],"(MC).":[84],"single":[86,114,126],"long":[87,115,127],"sequences,":[88],"efficient":[89],"statistics":[90,262],"available":[92,266,280],"estimate":[94,175],"order":[96,177,221,247],"MCs":[98],"transition":[101],"probability":[102],"matrix":[103],"sequences.":[106],"As":[107],"do":[110],"not":[111],"provide":[112],"sequence,":[116],"inference":[117],"methods":[118,173],"on":[119,125,182,208,229],"Markovian":[120],"properties":[121],"sequences":[123,128,200],"cannot":[129],"be":[130],"directly":[131],"used":[132],"data.":[137],"RESULTS:":[138],"Here":[139],"we":[140],"derive":[141],"normal":[143],"approximation":[144],"counts.":[148],"We":[149,170,190,216],"also":[150],"show":[151],"traditional":[154],"Chi-square":[155],"statistic":[156],"has":[157,225],"an":[158],"approximate":[159],"gamma":[160],",:":[162,233],"Lander-Waterman":[165],"physical":[168],"mapping.":[169],"propose":[171],"several":[172,202],"MC":[180,224,243],"evaluate":[186],"those":[187],"simulations.":[189],"illustrate":[191],"applications":[193],"our":[195],"results":[196,232,238],"by":[197],"genomic":[199],"vertebrate":[203],"tree":[205],"species":[206],"dissimilarity":[214],"measures.":[215],"find":[217],"estimated":[220,246],"considerable":[227],"effect":[228],"use":[240],"N:":[242],"give":[248],"species.":[254],"AVAILABILITY":[255],"AND":[256],"IMPLEMENTATION:":[257],"Our":[258],"implementation":[259],"developed":[263],"here":[264],"R":[268],"package":[269],"'NGS.MC'":[270],"at":[271,281],"http://www-rcf.usc.edu/\u223cfsun/Programs/NGS-MC/NGS-MC.html":[272],"CONTACT:":[273],"fsun@usc.edu":[274],"SUPPLEMENTARY":[275],"INFORMATION:":[276],"Supplementary":[277],"Bioinformatics":[282],"online.":[283]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}