{"id":"https://openalex.org/W2296336302","doi":"https://doi.org/10.1186/1471-2105-16-s17-s3","title":"How genome complexity can explain the difficulty of aligning reads to genomes","display_name":"How genome complexity can explain the difficulty of aligning reads to genomes","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2296336302","doi":"https://doi.org/10.1186/1471-2105-16-s17-s3","mag":"2296336302","pmid":"https://pubmed.ncbi.nlm.nih.gov/26678826"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-16-s17-s3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-16-s17-s3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-16-S17-S3","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/10.1186/1471-2105-16-S17-S3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019979430","display_name":"Vinhthuy Phan","orcid":"https://orcid.org/0000-0001-6108-1228"},"institutions":[{"id":"https://openalex.org/I94658018","display_name":"University of Memphis","ror":"https://ror.org/01cq23130","country_code":"US","type":"education","lineage":["https://openalex.org/I94658018"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinhthuy Phan","raw_affiliation_strings":["Department of Computer Science, University of Memphis, Memphis, TN, 38152, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Memphis, Memphis, TN, 38152, USA","institution_ids":["https://openalex.org/I94658018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064788213","display_name":"Shanshan Gao","orcid":"https://orcid.org/0000-0003-3920-3713"},"institutions":[{"id":"https://openalex.org/I94658018","display_name":"University of Memphis","ror":"https://ror.org/01cq23130","country_code":"US","type":"education","lineage":["https://openalex.org/I94658018"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanshan Gao","raw_affiliation_strings":["Department of Computer Science, University of Memphis, Memphis, TN, 38152, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Memphis, Memphis, TN, 38152, USA","institution_ids":["https://openalex.org/I94658018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021784087","display_name":"Quang Tran","orcid":"https://orcid.org/0000-0002-9263-0733"},"institutions":[{"id":"https://openalex.org/I94658018","display_name":"University of Memphis","ror":"https://ror.org/01cq23130","country_code":"US","type":"education","lineage":["https://openalex.org/I94658018"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quang Tran","raw_affiliation_strings":["Department of Computer Science, University of Memphis, Memphis, TN, 38152, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Memphis, Memphis, TN, 38152, USA","institution_ids":["https://openalex.org/I94658018"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043745628","display_name":"Nam S. Vo","orcid":"https://orcid.org/0000-0002-5454-9176"},"institutions":[{"id":"https://openalex.org/I94658018","display_name":"University of Memphis","ror":"https://ror.org/01cq23130","country_code":"US","type":"education","lineage":["https://openalex.org/I94658018"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam S Vo","raw_affiliation_strings":["Department of Computer Science, University of Memphis, Memphis, TN, 38152, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Memphis, Memphis, TN, 38152, USA","institution_ids":["https://openalex.org/I94658018"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94658018"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.0,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.11111755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"16","issue":"S17","first_page":"S3","last_page":"S3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13664","display_name":"Genome Rearrangement Algorithms","score":0.38960000872612,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.38960000872612,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3264000117778778,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.21160000562667847,"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/genome","display_name":"Genome","score":0.7494867444038391},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6188445091247559},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.579839825630188},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.4909391701221466},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.4555540978908539},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.4231809973716736},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.21826037764549255}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7494867444038391},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6188445091247559},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.579839825630188},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.4909391701221466},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4555540978908539},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4231809973716736},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.21826037764549255},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"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":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","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},{"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}],"locations_count":3,"locations":[{"id":"doi:10.1186/1471-2105-16-s17-s3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-16-s17-s3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-16-S17-S3","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:26678826","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26678826","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:4674900","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4674900","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:10.1186/1471-2105-16-s17-s3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-16-s17-s3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-16-S17-S3","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/G7491170140","display_name":"Analysis of gene expression data using transitive directed graphs","funder_award_id":"1320297","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2296336302.pdf","grobid_xml":"https://content.openalex.org/works/W2296336302.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1489909987","https://openalex.org/W1649017551","https://openalex.org/W1751520913","https://openalex.org/W2037444377","https://openalex.org/W2066846592","https://openalex.org/W2067974452","https://openalex.org/W2078711260","https://openalex.org/W2093931624","https://openalex.org/W2097160089","https://openalex.org/W2098291606","https://openalex.org/W2103441770","https://openalex.org/W2108234281","https://openalex.org/W2128524432","https://openalex.org/W2129295606","https://openalex.org/W2129714591","https://openalex.org/W2139523073","https://openalex.org/W2139747296","https://openalex.org/W2139760555","https://openalex.org/W2140154634","https://openalex.org/W2170551349","https://openalex.org/W4247053599"],"related_works":["https://openalex.org/W2086525401","https://openalex.org/W2006735166","https://openalex.org/W2079327011","https://openalex.org/W2053325634","https://openalex.org/W3178279768","https://openalex.org/W193851735","https://openalex.org/W2773861473","https://openalex.org/W1971903861","https://openalex.org/W3047903919","https://openalex.org/W2053972265"],"abstract_inverted_index":{"BACKGROUND:":[0],"Although":[1],"it":[2,118],"is":[3,88],"frequently":[4],"observed":[5],"that":[6,63,153,199],"aligning":[7],"short":[8,220],"reads":[9,136,221],"to":[10,26,72,90,97,109,122,134,137,222],"genomes":[11,33,131,203],"becomes":[12],"harder":[13],"if":[14],"they":[15],"contain":[16],"complex":[17],"repeat":[18],"patterns,":[19],"there":[20],"has":[21],"not":[22],"been":[23],"much":[24],"effort":[25],"quantify":[27],"the":[28,47,69,78,91,125,143,171,200,217],"relationship":[29,177],"between":[30,167,178],"complexity":[31,43,60,67,169,180,201],"of":[32,36,41,51,59,66,74,80,83,102,127,173,202,208,211,219],"and":[34,49,61,104,170,181],"difficulty":[35,126],"short-read":[37,174],"alignment.":[38,75],"Existing":[39],"measures":[40,58,65,145],"sequence":[42],"seem":[44],"unsuitable":[45],"for":[46,129,150,188,192],"understanding":[48],"quantification":[50],"this":[52,111,196],"relationship.":[53],"RESULTS:":[54],"We":[55,106,140,162],"investigated":[56],"several":[57],"found":[62],"length-sensitive":[64,144],"had":[68],"highest":[70],"correlation":[71],"accuracy":[73,172,183],"In":[76],"particular,":[77],"rate":[79],"distinct":[81],"substrings":[82],"length":[84],"k,":[85],"where":[86],"k":[87],"similar":[89],"read":[92],"length,":[93],"correlated":[94],"very":[95],"highly":[96],"alignment":[98,128,182,218],"performance":[99],"in":[100,114,120,209],"terms":[101,210],"precision":[103],"recall.":[105],"showed":[107,141],"how":[108,142],"compute":[110],"measure":[112],"efficiently":[113],"linear":[115],"time,":[116],"making":[117],"useful":[119,186],"practice":[121],"estimate":[123],"quickly":[124],"new":[130,159,193],"without":[132],"having":[133],"align":[135,155],"them":[138],"first.":[139],"could":[146],"provide":[147],"additional":[148,185],"information":[149,187],"choosing":[151],"aligners":[152,191],"would":[154],"consistently":[156],"accurately":[157],"on":[158],"genomes.":[160,194,223],"CONCLUSIONS:":[161],"formally":[163],"established":[164],"a":[165],"connection":[166],"genome":[168,179],"aligners.":[175],"The":[176],"provides":[184],"selecting":[189],"suitable":[190],"Further,":[195],"work":[197],"suggests":[198],"sometimes":[204],"should":[205],"be":[206],"thought":[207],"specific":[212],"computational":[213],"problems,":[214],"such":[215],"as":[216]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}
