{"id":"https://openalex.org/W2108595817","doi":"https://doi.org/10.1186/1471-2105-13-s2-s9","title":"Interpolative multidimensional scaling techniques for the identification of clusters in very large sequence sets","display_name":"Interpolative multidimensional scaling techniques for the identification of clusters in very large sequence sets","publication_year":2012,"publication_date":"2012-03-13","ids":{"openalex":"https://openalex.org/W2108595817","doi":"https://doi.org/10.1186/1471-2105-13-s2-s9","mag":"2108595817","pmid":"https://pubmed.ncbi.nlm.nih.gov/22536872"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-13-s2-s9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-s2-s9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-S2-S9","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/10.1186/1471-2105-13-S2-S9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024636178","display_name":"Adam L. Hughes","orcid":"https://orcid.org/0000-0002-7095-3793"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Hughes","raw_affiliation_strings":["Pervasive Technology Institute, Indiana University, Bloomington, IN 47408, USA","Pervasive Technology Institute, Indiana University, Bloomington, IN, 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pervasive Technology Institute, Indiana University, Bloomington, IN 47408, USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Pervasive Technology Institute, Indiana University, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077273334","display_name":"Yang Ruan","orcid":"https://orcid.org/0000-0002-0178-2484"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Ruan","raw_affiliation_strings":["Pervasive Technology Institute, Indiana University, Bloomington, IN, 47408, USA","School of Informatics and Computing, Indiana University, Bloomington, IN, 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pervasive Technology Institute, Indiana University, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080593862","display_name":"Saliya Ekanayake","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saliya Ekanayake","raw_affiliation_strings":["Pervasive Technology Institute, Indiana University, Bloomington, IN, 47408, USA","School of Informatics and Computing, Indiana University, Bloomington, IN, 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pervasive Technology Institute, Indiana University, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060723215","display_name":"Seunghee Bae","orcid":"https://orcid.org/0000-0001-9114-3063"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seung-Hee Bae","raw_affiliation_strings":["Pervasive Technology Institute, Indiana University, Bloomington, IN, 47408, USA","School of Informatics and Computing, Indiana University, Bloomington, IN, 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pervasive Technology Institute, Indiana University, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088669922","display_name":"Qunfeng Dong","orcid":"https://orcid.org/0000-0002-4610-1670"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qunfeng Dong","raw_affiliation_strings":["Department of Biological Sciences, University of North Texas, Denton, TX, 76203, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, University of North Texas, Denton, TX, 76203, USA","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078928762","display_name":"Mina Rho","orcid":"https://orcid.org/0000-0002-2724-9477"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mina Rho","raw_affiliation_strings":["School of Informatics and Computing, Indiana University, Bloomington, IN, 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108081911","display_name":"Judy Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Judy Qiu","raw_affiliation_strings":["Pervasive Technology Institute, Indiana University, Bloomington, IN, 47408, USA","School of Informatics and Computing, Indiana University, Bloomington, IN, 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pervasive Technology Institute, Indiana University, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078240493","display_name":"Geoffrey Fox","orcid":"https://orcid.org/0000-0003-1017-1391"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Geoffrey Fox","raw_affiliation_strings":["Pervasive Technology Institute, Indiana University, Bloomington, IN, 47408, USA","School of Informatics and Computing, Indiana University, Bloomington, IN, 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pervasive Technology Institute, Indiana University, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5078240493"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.4031,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.62874322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"13","issue":"S2","first_page":"S9","last_page":"S9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.35580000281333923,"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":0.35580000281333923,"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/T10066","display_name":"Gut microbiota and health","score":0.07859999686479568,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.04619999974966049,"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/multidimensional-scaling","display_name":"Multidimensional scaling","score":0.6972325444221497},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6768439412117004},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6440489292144775},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.612152099609375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5014913082122803},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.49613580107688904},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.4705161154270172},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32549983263015747},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.31291988492012024},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.28949761390686035},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18600121140480042},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1133165955543518},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09153535962104797}],"concepts":[{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.6972325444221497},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6768439412117004},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6440489292144775},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.612152099609375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5014913082122803},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.49613580107688904},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.4705161154270172},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32549983263015747},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.31291988492012024},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.28949761390686035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18600121140480042},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1133165955543518},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09153535962104797},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"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":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":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":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/1471-2105-13-s2-s9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-s2-s9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-S2-S9","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:22536872","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22536872","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:info:ark/67531/metadc78283","is_oa":false,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc78283/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, 13(2), BioMed Central Ltd., March 13, 2012, pp. 1-6","raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:dae2973f4cc945768a25d4af984d18bc","is_oa":false,"landing_page_url":"https://doaj.org/article/dae2973f4cc945768a25d4af984d18bc","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 13, Iss Suppl 2, p S9 (2012)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:3305784","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3305784","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:10.1186/1471-2105-13-s2-s9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-s2-s9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-S2-S9","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":0.4099999964237213,"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2108595817.pdf","grobid_xml":"https://content.openalex.org/works/W2108595817.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W42763705","https://openalex.org/W1966031848","https://openalex.org/W1976860187","https://openalex.org/W2073548709","https://openalex.org/W2074231493","https://openalex.org/W2115605863","https://openalex.org/W2134007938"],"related_works":["https://openalex.org/W4200285273","https://openalex.org/W2374778813","https://openalex.org/W2012281976","https://openalex.org/W4245539973","https://openalex.org/W4238212629","https://openalex.org/W2003051771","https://openalex.org/W141820298","https://openalex.org/W2494148009","https://openalex.org/W2314854132","https://openalex.org/W4241372895"],"abstract_inverted_index":{"BACKGROUND:":[0],"Modern":[1],"pyrosequencing":[2],"techniques":[3,84],"make":[4],"it":[5],"possible":[6],"to":[7,88,104,169,177,195,208,223,243],"study":[8,162],"complex":[9],"bacterial":[10],"populations,":[11],"such":[12,54],"as":[13],"16S":[14],"rRNA,":[15],"directly":[16],"from":[17,205],"environmental":[18],"or":[19],"clinical":[20],"samples":[21],"without":[22],"the":[23,32,44,67,74,164,190,214,228,250],"need":[24],"for":[25,43,73,148,233],"laboratory":[26],"purification.":[27],"Alignment":[28],"of":[29,40,46,63,69,76,115,137,166,199,216],"sequences":[30,201],"across":[31],"resultant":[33],"large":[34,77],"data":[35,152],"sets":[36,153,248],"(100,000+":[37],"sequences)":[38],"is":[39,66],"particular":[41],"interest":[42],"purpose":[45],"identifying":[47,156],"potential":[48,157],"gene":[49,158],"clusters":[50],"and":[51,100,154],"families,":[52],"but":[53,183],"analysis":[55],"represents":[56],"a":[57,197],"daunting":[58],"computational":[59,237],"task.":[60],"The":[61],"aim":[62],"this":[64],"work":[65,221],"development":[68],"an":[70,145],"efficient":[71],"pipeline":[72],"clustering":[75,171],"sequence":[78,93,122,247],"read":[79],"sets.":[80],"METHODS:":[81],"Pairwise":[82],"alignment":[83,123,131],"are":[85,97,174],"used":[86],"here":[87],"calculate":[89],"genetic":[90,109],"distances":[91,110],"between":[92],"pairs.":[94],"These":[95],"methods":[96],"pleasingly":[98],"parallel":[99],"have":[101,143],"been":[102,203],"shown":[103],"more":[105],"accurately":[106],"reflect":[107],"accurate":[108],"in":[111,132,226,249],"highly":[112],"variable":[113],"regions":[114],"rRNA":[116],"genes":[117],"than":[118,210],"do":[119],"traditional":[120],"multiple":[121],"(MSA)":[124],"approaches.":[125],"By":[126],"utilizing":[127],"Needleman-Wunsch":[128],"(NW)":[129],"pairwise":[130],"conjunction":[133],"with":[134,184],"novel":[135],"implementations":[136],"interpolative":[138,167,217,234],"multidimensional":[139],"scaling":[140],"(MDS),":[141],"we":[142],"developed":[144],"effective":[146],"method":[147],"visualizing":[149],"massive":[150],"biosequence":[151],"quickly":[155],"clusters.":[159],"RESULTS:":[160],"This":[161],"demonstrates":[163],"use":[165,215],"MDS":[168],"obtain":[170],"results":[172],"that":[173],"qualitatively":[175],"similar":[176],"those":[178],"obtained":[179],"through":[180,213],"full":[181],"MDS,":[182,235],"substantial":[185,236],"cost":[186,238],"savings.":[187],"In":[188],"particular,":[189],"wall":[191],"clock":[192],"time":[193],"required":[194],"cluster":[196,244],"set":[198,231],"100,000":[200],"has":[202],"reduced":[204],"seven":[206],"hours":[207],"less":[209],"one":[211],"hour":[212],"MDS.":[218],"CONCLUSIONS:":[219],"Although":[220],"remains":[222],"be":[224],"done":[225],"selecting":[227],"optimal":[229],"training":[230],"size":[232],"savings":[239],"will":[240],"allow":[241],"us":[242],"much":[245],"larger":[246],"future.":[251]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}
