{"id":"https://openalex.org/W4367834493","doi":"https://doi.org/10.1186/s12859-023-05305-0","title":"ERStruct: a fast Python package for inferring the number of top principal components from whole genome sequencing data","display_name":"ERStruct: a fast Python package for inferring the number of top principal components from whole genome sequencing data","publication_year":2023,"publication_date":"2023-05-02","ids":{"openalex":"https://openalex.org/W4367834493","doi":"https://doi.org/10.1186/s12859-023-05305-0","pmid":"https://pubmed.ncbi.nlm.nih.gov/37131141"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-023-05305-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05305-0","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05305-0","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/s12859-023-05305-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076569509","display_name":"Jinghan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jinghan Yang","raw_affiliation_strings":["Department of Statistics and Actuarial Science, The University of Hong Kong, Pokfulam, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and Actuarial Science, The University of Hong Kong, Pokfulam, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074623897","display_name":"Yuyang Xu","orcid":"https://orcid.org/0000-0002-3962-3526"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuyang Xu","raw_affiliation_strings":["Department of Statistics and Actuarial Science, The University of Hong Kong, Pokfulam, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and Actuarial Science, The University of Hong Kong, Pokfulam, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081104417","display_name":"Minhao Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Minhao Yao","raw_affiliation_strings":["Department of Statistics and Actuarial Science, The University of Hong Kong, Pokfulam, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and Actuarial Science, The University of Hong Kong, Pokfulam, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648728","display_name":"Gao Wang","orcid":"https://orcid.org/0000-0001-9336-402X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gao Wang","raw_affiliation_strings":["Department of Neurology, Gertrude. H. Sergievsky Center, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Neurology, Gertrude. H. Sergievsky Center, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100413280","display_name":"Zhonghua Liu","orcid":"https://orcid.org/0000-0003-3048-9823"},"institutions":[{"id":"https://openalex.org/I2799503643","display_name":"Columbia University Irving Medical Center","ror":"https://ror.org/01esghr10","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799503643"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhonghua Liu","raw_affiliation_strings":["Department of Biostatistics, Columbia University, New York, NY, USA. zl2509@cumc.columbia.edu","Department of Biostatistics, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Columbia University, New York, NY, USA. zl2509@cumc.columbia.edu","institution_ids":["https://openalex.org/I2799503643","https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Biostatistics, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100413280"],"corresponding_institution_ids":["https://openalex.org/I2799503643","https://openalex.org/I78577930"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13404646,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"1","first_page":"180","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9993000030517578,"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/T10269","display_name":"Epigenetics and DNA Methylation","score":0.9907000064849854,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.8357285261154175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6694998741149902},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5698356032371521},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5185390114784241},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4712013900279999},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.4640035033226013},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.45894116163253784},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4538191854953766},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4330858588218689},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.36256644129753113},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2814476490020752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21726453304290771},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1967785656452179},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.08019676804542542}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8357285261154175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6694998741149902},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5698356032371521},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5185390114784241},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4712013900279999},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.4640035033226013},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.45894116163253784},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4538191854953766},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4330858588218689},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.36256644129753113},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2814476490020752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21726453304290771},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1967785656452179},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.08019676804542542},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","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":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-023-05305-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05305-0","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05305-0","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:37131141","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37131141","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:pubmedcentral.nih.gov:10155328","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10155328","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10155328/pdf/12859_2023_Article_5305.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"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"},{"id":"pmh:oai:doaj.org/article:76279a21ddcf4095ba4c61d5beb6ad0f","is_oa":true,"landing_page_url":"https://doaj.org/article/76279a21ddcf4095ba4c61d5beb6ad0f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"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 24, Iss 1, Pp 1-9 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-023-05305-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05305-0","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05305-0","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":[],"awards":[{"id":"https://openalex.org/G6101984482","display_name":null,"funder_award_id":"R01 AG076901","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320322170","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4367834493.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1034866458","https://openalex.org/W1520752838","https://openalex.org/W2022481980","https://openalex.org/W2072706575","https://openalex.org/W2084347413","https://openalex.org/W2093636770","https://openalex.org/W2099551908","https://openalex.org/W2104549677","https://openalex.org/W2107916366","https://openalex.org/W2108169091","https://openalex.org/W2157752701","https://openalex.org/W2159247370","https://openalex.org/W2328187444","https://openalex.org/W3100735222","https://openalex.org/W4229371180"],"related_works":["https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W4287027380","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W3116064965","https://openalex.org/W3193760048","https://openalex.org/W4285822516","https://openalex.org/W2551200859"],"abstract_inverted_index":{"Our":[0],"Python":[1],"package":[2],"ERStruct":[3],"is":[4],"an":[5],"efficient":[6],"and":[7],"user-friendly":[8],"tool":[9],"for":[10],"estimating":[11],"the":[12],"number":[13],"of":[14],"top":[15],"informative":[16],"principal":[17],"components":[18],"that":[19],"capture":[20],"population":[21],"structure":[22],"from":[23],"whole":[24],"genome":[25],"sequencing":[26],"data.":[27]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
