{"id":"https://openalex.org/W2171440685","doi":"https://doi.org/10.1186/1471-2105-11-9","title":"PyMix - The Python mixture package - a tool for clustering of heterogeneous biological data","display_name":"PyMix - The Python mixture package - a tool for clustering of heterogeneous biological data","publication_year":2010,"publication_date":"2010-01-06","ids":{"openalex":"https://openalex.org/W2171440685","doi":"https://doi.org/10.1186/1471-2105-11-9","mag":"2171440685","pmid":"https://pubmed.ncbi.nlm.nih.gov/20053276"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-11-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-9","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/10.1186/1471-2105-11-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054499041","display_name":"Benjamin Georgi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142260","display_name":"Max Planck Institute for Molecular Genetics","ror":"https://ror.org/03ate3e03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210142260"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Benjamin Georgi","raw_affiliation_strings":["Max Planck Institute for Molecular Genetics, Dept, of Computational Molecular Biology, Ihnestrasse 73, 14195 Berlin. bgeorgi@mail.med.upenn.edu","Max Planck Institute for Molecular Genetics, Dept. of Computational Molecular Biology, Ihnestrasse 73, 14195, Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Molecular Genetics, Dept, of Computational Molecular Biology, Ihnestrasse 73, 14195 Berlin. bgeorgi@mail.med.upenn.edu","institution_ids":["https://openalex.org/I4210142260"]},{"raw_affiliation_string":"Max Planck Institute for Molecular Genetics, Dept. of Computational Molecular Biology, Ihnestrasse 73, 14195, Berlin","institution_ids":["https://openalex.org/I4210142260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057250270","display_name":"Ivan G. Costa","orcid":"https://orcid.org/0000-0003-2890-8697"},"institutions":[{"id":"https://openalex.org/I25112270","display_name":"Universidade Federal de Pernambuco","ror":"https://ror.org/047908t24","country_code":"BR","type":"education","lineage":["https://openalex.org/I25112270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ivan Gesteira Costa","raw_affiliation_strings":["Center of Informatics, Federal University of Pernambuco, Recife, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Informatics, Federal University of Pernambuco, Recife, Brazil","institution_ids":["https://openalex.org/I25112270"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057266594","display_name":"Alexander Schliep","orcid":"https://orcid.org/0000-0002-3555-3188"},"institutions":[{"id":"https://openalex.org/I4210142260","display_name":"Max Planck Institute for Molecular Genetics","ror":"https://ror.org/03ate3e03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210142260"]},{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Alexander Schliep","raw_affiliation_strings":["Dept. of Computer Science and BioMaPS Institute for Quantitative Biology, Rutgers, The State University of New Jersey, Piscataway, NJ, 08854, USA","Max Planck Institute for Molecular Genetics, Dept. of Computational Molecular Biology, Ihnestrasse 73, 14195, Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and BioMaPS Institute for Quantitative Biology, Rutgers, The State University of New Jersey, Piscataway, NJ, 08854, USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Max Planck Institute for Molecular Genetics, Dept. of Computational Molecular Biology, Ihnestrasse 73, 14195, Berlin","institution_ids":["https://openalex.org/I4210142260"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054499041"],"corresponding_institution_ids":["https://openalex.org/I4210142260"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1105,"currency":"EUR","value_usd":1191},"fwci":6.5236,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.96594422,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"11","issue":"1","first_page":"9","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.5238999724388123,"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"}},"topics":[{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.5238999724388123,"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"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.1550000011920929,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.03660000115633011,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7667281627655029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7147443294525146},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6978450417518616},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6390380859375},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5985949635505676},{"id":"https://openalex.org/keywords/exploratory-data-analysis","display_name":"Exploratory data analysis","score":0.5954828858375549},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.5329267382621765},{"id":"https://openalex.org/keywords/r-package","display_name":"R package","score":0.4891243577003479},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3622872233390808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3325967788696289},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.26725274324417114},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10990491509437561},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08557945489883423}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7667281627655029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147443294525146},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6978450417518616},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6390380859375},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5985949635505676},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.5954828858375549},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.5329267382621765},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.4891243577003479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3622872233390808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3325967788696289},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.26725274324417114},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10990491509437561},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08557945489883423}],"mesh":[{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","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":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-11-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-9","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:20053276","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20053276","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:2f3adc360a3640ecad3b2e89428f4038","is_oa":false,"landing_page_url":"https://doaj.org/article/2f3adc360a3640ecad3b2e89428f4038","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 11, Iss 1, p 9 (2010)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2823712","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2823712","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:10.1186/1471-2105-11-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-9","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":0.49000000953674316,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2171440685.pdf","grobid_xml":"https://content.openalex.org/works/W2171440685.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W119778216","https://openalex.org/W1479807131","https://openalex.org/W1523680690","https://openalex.org/W1579271636","https://openalex.org/W1584866376","https://openalex.org/W1588001317","https://openalex.org/W1593793857","https://openalex.org/W1825362480","https://openalex.org/W1827453818","https://openalex.org/W1987120508","https://openalex.org/W1992419399","https://openalex.org/W2011430131","https://openalex.org/W2011485152","https://openalex.org/W2049633694","https://openalex.org/W2054416990","https://openalex.org/W2062953127","https://openalex.org/W2076146315","https://openalex.org/W2084620487","https://openalex.org/W2113131266","https://openalex.org/W2113828933","https://openalex.org/W2127218421","https://openalex.org/W2130453506","https://openalex.org/W2138550913","https://openalex.org/W2147213963","https://openalex.org/W2150926065","https://openalex.org/W2163166770","https://openalex.org/W2163811214","https://openalex.org/W2167108104","https://openalex.org/W2168817939","https://openalex.org/W2475645889","https://openalex.org/W2488678869","https://openalex.org/W2600906272","https://openalex.org/W4251453717"],"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/W3088642716","https://openalex.org/W2587303152"],"abstract_inverted_index":{"BACKGROUND:":[0],"Cluster":[1],"analysis":[2,10,107,125],"is":[3,16,91,119],"an":[4],"important":[5],"technique":[6],"for":[7,38,68,105,123],"the":[8,41,59,94,106,131,135],"exploratory":[9],"of":[11,43,54,84,108,126,134,145],"biological":[12,109,127],"data.":[13,116,128],"Such":[14],"data":[15,66,148],"often":[17],"high-dimensional,":[18],"inherently":[19],"noisy":[20],"and":[21,31,45,65,72,87,113,147],"contains":[22],"outliers.":[23],"This":[24],"makes":[25],"clustering":[26,39,69],"challenging.":[27],"Mixtures":[28],"are":[29],"versatile":[30],"powerful":[32],"statistical":[33],"models":[34,78],"which":[35],"perform":[36],"robustly":[37],"in":[40,50],"presence":[42],"noise":[44],"have":[46],"been":[47,102],"successfully":[48,103],"applied":[49,140],"a":[51,120,142],"wide":[52,143],"range":[53,144],"applications.":[55],"RESULTS:":[56],"PyMix":[57,90,100,118,137],"-":[58],"Python":[60],"mixture":[61,74],"package":[62],"implements":[63],"algorithms":[64],"structures":[67],"with":[70],"basic":[71],"advanced":[73,77],"models.":[75],"The":[76],"include":[79],"context-specific":[80],"independence":[81],"mixtures,":[82],"mixtures":[83],"dependence":[85],"trees":[86],"semi-supervised":[88],"learning.":[89],"licenced":[92],"under":[93],"GNU":[95],"General":[96],"Public":[97],"licence":[98],"(GPL).":[99],"has":[101],"used":[104],"sequence,":[110],"complex":[111],"disease":[112],"gene":[114],"expression":[115],"CONCLUSIONS:":[117],"useful":[121],"tool":[122],"cluster":[124],"Due":[129],"to":[130,141],"general":[132],"nature":[133],"framework,":[136],"can":[138],"be":[139],"applications":[146],"sets.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}