{"id":"https://openalex.org/W1520354805","doi":"https://doi.org/10.1089/cmb.2014.0108","title":"Characterizing the Empirical Distribution of Prokaryotic Genome <i>n</i> -mers in the Presence of Nullomers","display_name":"Characterizing the Empirical Distribution of Prokaryotic Genome <i>n</i> -mers in the Presence of Nullomers","publication_year":2014,"publication_date":"2014-07-30","ids":{"openalex":"https://openalex.org/W1520354805","doi":"https://doi.org/10.1089/cmb.2014.0108","mag":"1520354805","pmid":"https://pubmed.ncbi.nlm.nih.gov/25075627"},"language":"en","primary_location":{"id":"doi:10.1089/cmb.2014.0108","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2014.0108","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062791095","display_name":"Loni Philip Tabb","orcid":"https://orcid.org/0000-0002-7601-8368"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Loni Philip Tabb","raw_affiliation_strings":["Department of Epidemiology &amp; Biostatistics, Drexel University, Philadelphia, Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Department of Epidemiology &amp; Biostatistics, Drexel University, Philadelphia, Pennsylvania","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014868299","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0002-8301-9297"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["Division of Translational Medicine and Human Genetics, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Division of Translational Medicine and Human Genetics, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101448554","display_name":"Jingyu Huang","orcid":"https://orcid.org/0000-0001-9591-9981"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyu Huang","raw_affiliation_strings":["Department of Biometrics Services, Frontage Laboratories, Exton, Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Department of Biometrics Services, Frontage Laboratories, Exton, Pennsylvania","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023224900","display_name":"Gail Rosen","orcid":"https://orcid.org/0000-0003-1763-5750"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gail L. Rosen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Drexel University, Philadelphia, Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, Pennsylvania","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062791095"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02922675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"10","first_page":"732","last_page":"740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9991999864578247,"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":0.9991999864578247,"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/T12858","display_name":"Plant Disease Resistance and Genetics","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11470","display_name":"Legume Nitrogen Fixing Symbiosis","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overdispersion","display_name":"Overdispersion","score":0.9113855361938477},{"id":"https://openalex.org/keywords/negative-binomial-distribution","display_name":"Negative binomial distribution","score":0.8755779266357422},{"id":"https://openalex.org/keywords/poisson-distribution","display_name":"Poisson distribution","score":0.8101442456245422},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6023448705673218},{"id":"https://openalex.org/keywords/empirical-distribution-function","display_name":"Empirical distribution function","score":0.5501523613929749},{"id":"https://openalex.org/keywords/count-data","display_name":"Count data","score":0.5282097458839417},{"id":"https://openalex.org/keywords/binomial-distribution","display_name":"Binomial distribution","score":0.5182452201843262},{"id":"https://openalex.org/keywords/binomial","display_name":"Binomial (polynomial)","score":0.4748421311378479},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4724200963973999},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.44448941946029663},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.42498496174812317},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.34721648693084717},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.20098888874053955},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08963721990585327}],"concepts":[{"id":"https://openalex.org/C117236510","wikidata":"https://www.wikidata.org/wiki/Q7113620","display_name":"Overdispersion","level":4,"score":0.9113855361938477},{"id":"https://openalex.org/C199335787","wikidata":"https://www.wikidata.org/wiki/Q743364","display_name":"Negative binomial distribution","level":3,"score":0.8755779266357422},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.8101442456245422},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6023448705673218},{"id":"https://openalex.org/C98385598","wikidata":"https://www.wikidata.org/wiki/Q1339385","display_name":"Empirical distribution function","level":2,"score":0.5501523613929749},{"id":"https://openalex.org/C33643355","wikidata":"https://www.wikidata.org/wiki/Q5176731","display_name":"Count data","level":3,"score":0.5282097458839417},{"id":"https://openalex.org/C41054675","wikidata":"https://www.wikidata.org/wiki/Q185547","display_name":"Binomial distribution","level":2,"score":0.5182452201843262},{"id":"https://openalex.org/C2781315470","wikidata":"https://www.wikidata.org/wiki/Q193623","display_name":"Binomial (polynomial)","level":2,"score":0.4748421311378479},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4724200963973999},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.44448941946029663},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.42498496174812317},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.34721648693084717},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.20098888874053955},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08963721990585327},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D016010","descriptor_name":"Binomial Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016010","descriptor_name":"Binomial Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016010","descriptor_name":"Binomial Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016012","descriptor_name":"Poisson Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016012","descriptor_name":"Poisson Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016012","descriptor_name":"Poisson Distribution","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":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}],"locations_count":2,"locations":[{"id":"doi:10.1089/cmb.2014.0108","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2014.0108","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:25075627","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25075627","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":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310343","display_name":"Drexel University","ror":"https://ror.org/04bdffz58"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W137653784","https://openalex.org/W1597884192","https://openalex.org/W1975525485","https://openalex.org/W2005903772","https://openalex.org/W2018650627","https://openalex.org/W2046113363","https://openalex.org/W2049919946","https://openalex.org/W2053392780","https://openalex.org/W2076983043","https://openalex.org/W2092604303","https://openalex.org/W2097160089","https://openalex.org/W2097927681","https://openalex.org/W2101305949","https://openalex.org/W2108393758","https://openalex.org/W2119634512","https://openalex.org/W2126198043","https://openalex.org/W2142635246","https://openalex.org/W2158196600","https://openalex.org/W2582743722","https://openalex.org/W2751862591","https://openalex.org/W2799002609","https://openalex.org/W4241422942","https://openalex.org/W4248151413","https://openalex.org/W4299432846"],"related_works":["https://openalex.org/W2189104843","https://openalex.org/W2885569989","https://openalex.org/W3134768068","https://openalex.org/W2765416750","https://openalex.org/W3021740479","https://openalex.org/W4390402773","https://openalex.org/W3178810070","https://openalex.org/W4280505828","https://openalex.org/W2081430863","https://openalex.org/W2982191014"],"abstract_inverted_index":{"Characterizing":[0],"the":[1,5,15,27,43,57,67,74,79,83,130,133,144,149,156,166,170,179,204,207],"empirical":[2,80],"distribution":[3,60,81,205],"of":[4,7,45,70,82,85,111,129,155,165,206,209],"frequency":[6,84,208],"n-mers":[8,86],"is":[9],"a":[10,160],"vital":[11],"step":[12],"in":[13,42,92,116,187,197],"understanding":[14],"entire":[16],"genome.":[17],"This":[18],"will":[19,65],"allow":[20],"for":[21,132,151,224],"researchers":[22,211],"to":[23,202],"examine":[24],"how":[25],"complex":[26],"genome":[28],"really":[29],"is,":[30],"and":[31,61,104,119,124,136,175,183,222],"move":[32],"beyond":[33],"simple,":[34],"traditional":[35,180],"modeling":[36],"frameworks":[37],"that":[38,53,113,190,218],"are":[39,184,219],"often":[40],"biased":[41],"presence":[44],"abundant":[46],"and/or":[47],"extremely":[48],"rare":[49],"words.":[50],"We":[51,95],"hypothesize":[52],"models":[54],"based":[55],"on":[56],"negative":[58,100,106,145,173],"binomial":[59,107,146,174],"its":[62],"zero-inflated":[63,102,105],"counterpart":[64],"characterize":[66,203],"n-mer":[68,142],"distributions":[69,177,217],"genomes":[71,112,131,167],"better":[72],"than":[73],"Poisson.":[75],"Our":[76],"study":[77],"examined":[78],"(6":[87],"\u2264":[88,90],"n":[89],"11)":[91],"2,199":[93,157],"genomes.":[94],"considered":[96],"four":[97],"distributions:":[98],"Poisson,":[99,103],"binomial,":[101],"(ZINB).":[108],"The":[109,172],"number":[110],"have":[114],"nullomers":[115],"6-,":[117],"7-,":[118],"8-mers":[120],"was":[121],"150,":[122],"602":[123],"2,012,":[125],"respectively,":[126],"whereas":[127],"all":[128],"9-,":[134],"10-,":[135],"11-mers":[137],"had":[138],"nullomers.":[139,198],"In":[140,199],"each":[141],"considered,":[143],"model":[147],"performed":[148],"best":[150],"at":[152],"least":[153],"93%":[154],"genomes;":[158],"however,":[159],"small":[161],"percentage":[162],"(i.e.,":[163],"<7%)":[164],"did":[168],"prefer":[169],"ZINB.":[171],"zero-inflation":[176],"extend":[178],"Poisson":[181],"setting":[182],"more":[185,220],"flexible":[186,221],"handling":[188],"overdispersion":[189],"can":[191],"be":[192],"caused":[193],"by":[194],"an":[195,200],"increase":[196],"effort":[201],"n-mers,":[210],"should":[212],"also":[213],"consider":[214],"other":[215],"discrete":[216],"adjust":[223],"possible":[225],"overdispersion.":[226]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2016-06-24T00:00:00"}
