{"id":"https://openalex.org/W4226341779","doi":"https://doi.org/10.1093/bioinformatics/btac255","title":"Markov chains improve the significance computation of overlapping genome annotations","display_name":"Markov chains improve the significance computation of overlapping genome annotations","publication_year":2022,"publication_date":"2022-04-14","ids":{"openalex":"https://openalex.org/W4226341779","doi":"https://doi.org/10.1093/bioinformatics/btac255","pmid":"https://pubmed.ncbi.nlm.nih.gov/35758770"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac255","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac255","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1093/bioinformatics/btac255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000329336","display_name":"Askar Gafurov","orcid":"https://orcid.org/0009-0006-5270-831X"},"institutions":[{"id":"https://openalex.org/I74788687","display_name":"Comenius University Bratislava","ror":"https://ror.org/0587ef340","country_code":"SK","type":"education","lineage":["https://openalex.org/I74788687"]}],"countries":["SK"],"is_corresponding":true,"raw_author_name":"Askar Gafurov","raw_affiliation_strings":["Department of Computer Science, Comenius University , Bratislava 84248, Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Comenius University , Bratislava 84248, Slovakia","institution_ids":["https://openalex.org/I74788687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058053699","display_name":"Bro\u0148a Brejov\u00e1","orcid":"https://orcid.org/0000-0002-9483-1766"},"institutions":[{"id":"https://openalex.org/I74788687","display_name":"Comenius University Bratislava","ror":"https://ror.org/0587ef340","country_code":"SK","type":"education","lineage":["https://openalex.org/I74788687"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Bro\u0148a Brejov\u00e1","raw_affiliation_strings":["Department of Computer Science, Comenius University , Bratislava 84248, Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Comenius University , Bratislava 84248, Slovakia","institution_ids":["https://openalex.org/I74788687"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"https://orcid.org/0000-0003-3143-594X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, The Pennsylvania State University , University Park, PA 16802, USA","Department of Computer Science and Engineering, The Pennsylvania State University , University Park, PA 16802, USA","Huck Institutes of the Life Sciences, The Pennsylvania State University , University Park, PA 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, The Pennsylvania State University , University Park, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University , University Park, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Huck Institutes of the Life Sciences, The Pennsylvania State University , University Park, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000329336"],"corresponding_institution_ids":["https://openalex.org/I74788687"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.6725,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7108515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"38","issue":"Supplement_1","first_page":"i203","last_page":"i211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13664","display_name":"Genome Rearrangement Algorithms","score":0.47850000858306885,"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":0.47850000858306885,"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/T11269","display_name":"Algorithms and Data Compression","score":0.2492000013589859,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.15680000185966492,"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/computer-science","display_name":"Computer science","score":0.6878446340560913},{"id":"https://openalex.org/keywords/null","display_name":"Null (SQL)","score":0.5835899710655212},{"id":"https://openalex.org/keywords/null-hypothesis","display_name":"Null hypothesis","score":0.538801908493042},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4865988492965698},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4863010346889496},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.47524309158325195},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4434191882610321},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4177311658859253},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4036279320716858},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3698103427886963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2664610743522644},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2127390205860138},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.20961201190948486},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19450417160987854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1893039345741272},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17645570635795593},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1504097282886505},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08321920037269592}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6878446340560913},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.5835899710655212},{"id":"https://openalex.org/C191988596","wikidata":"https://www.wikidata.org/wiki/Q628374","display_name":"Null hypothesis","level":2,"score":0.538801908493042},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4865988492965698},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4863010346889496},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.47524309158325195},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4434191882610321},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4177311658859253},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4036279320716858},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3698103427886963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2664610743522644},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2127390205860138},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.20961201190948486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19450417160987854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1893039345741272},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17645570635795593},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1504097282886505},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08321920037269592},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006046","descriptor_name":"Gold","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006046","descriptor_name":"Gold","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006046","descriptor_name":"Gold","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":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","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":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btac255","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac255","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35758770","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35758770","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9235476","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9235476","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac255","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac255","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1537326666","display_name":"Nekonven\u010dn\u00e9 aplik\u00e1cie nov\u00fdch sekvena\u010dn\u00fdch technol\u00f3gi\u00ed v komparat\u00edvnej a funk\u010dnej genomike","funder_award_id":"APVV-18-0239","funder_id":"https://openalex.org/F4320323251","funder_display_name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja"},{"id":"https://openalex.org/G174627229","display_name":"Frameworks: Re-Engineering Galaxy for Performance, Scalability and Energy Efficiency","funder_award_id":"1931531","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4106800444","display_name":"CAREER: De Novo Assembly of Large Genomic Data","funder_award_id":"1453527","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"},{"id":"https://openalex.org/F4320323251","display_name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja","ror":"https://ror.org/037nx0e70"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1489273657","https://openalex.org/W1511986666","https://openalex.org/W1966585515","https://openalex.org/W1979594866","https://openalex.org/W2034197594","https://openalex.org/W2036590334","https://openalex.org/W2044826047","https://openalex.org/W2099317248","https://openalex.org/W2099807884","https://openalex.org/W2103630240","https://openalex.org/W2124225056","https://openalex.org/W2127230663","https://openalex.org/W2133938268","https://openalex.org/W2152828142","https://openalex.org/W2162674813","https://openalex.org/W2170830174","https://openalex.org/W2171742939","https://openalex.org/W2184563578","https://openalex.org/W2587686129","https://openalex.org/W2614266827","https://openalex.org/W2724377567","https://openalex.org/W2943766116","https://openalex.org/W2952285719","https://openalex.org/W3195368445","https://openalex.org/W4320300927","https://openalex.org/W4390808053"],"related_works":["https://openalex.org/W4306992803","https://openalex.org/W2979681497","https://openalex.org/W4306992794","https://openalex.org/W4306992806","https://openalex.org/W2590542766","https://openalex.org/W4239137652","https://openalex.org/W1999826675","https://openalex.org/W4306992821","https://openalex.org/W2369782938","https://openalex.org/W2130815278"],"abstract_inverted_index":{"MOTIVATION:":[0],"Genome":[1],"annotations":[2,25],"are":[3,91,190,208,253,261],"a":[4,53,149],"common":[5,61],"way":[6,62],"to":[7,29,42,63,67,127,138,154,216],"represent":[8],"genomic":[9],"features":[10],"such":[11],"as":[12],"genes,":[13],"regulatory":[14],"elements":[15],"or":[16,95],"epigenetic":[17],"modifications.":[18],"The":[19,243],"amount":[20],"of":[21,56,72,103,142,193,227,238],"overlap":[22,49],"between":[23,38,44],"two":[24],"is":[26,33,58,66,83,122,245],"often":[27,92],"used":[28,118],"ascertain":[30],"if":[31,69],"there":[32],"an":[34,166],"underlying":[35],"biological":[36,46],"connection":[37],"them.":[39],"In":[40],"order":[41],"distinguish":[43],"true":[45],"association":[47],"and":[48,183,188,198,205,222],"by":[50,225],"pure":[51],"chance,":[52],"robust":[54],"measure":[55,139],"significance":[57],"required.":[59],"One":[60],"do":[64],"this":[65],"determine":[68],"the":[70,75,80,101,104,113,116,129,140,156,159,173,176,191,196,211,235],"number":[71],"intervals":[73,194],"in":[74,180,195,220],"reference":[76,197],"annotation":[77,82],"that":[78,111,171],"intersect":[79],"query":[81,199],"statistically":[84],"significant.":[85],"However,":[86],"currently":[87],"employed":[88],"statistical":[89],"frameworks":[90],"either":[93],"inefficient":[94],"inaccurate":[96],"when":[97],"computing":[98],"P-values":[99,114,174],"on":[100,229],"scale":[102],"whole":[105],"human":[106,230],"genome.":[107],"RESULTS:":[108],"We":[109,163],"show":[110],"finding":[112],"under":[115,158,175],"typically":[117],"'gold'":[119],"null":[120,130,145,161,178],"hypothesis":[121,131,179],"NP-hard.":[123],"This":[124],"motivates":[125],"us":[126],"reformulate":[128],"using":[132],"Markov":[133],"chains.":[134],"To":[135],"be":[136],"able":[137],"fidelity":[141],"our":[143],"Markovian":[144,177],"hypothesis,":[146],"we":[147],"develop":[148],"fast":[150],"direct":[151],"sampling":[152],"algorithm":[153],"estimate":[155],"P-value":[157],"gold":[160],"hypothesis.":[162],"then":[164],"present":[165],"open-source":[167],"software":[168,244],"tool":[169],"MCDP":[170,203],"computes":[172],"O(m2+n)":[181],"time":[182],"O(m)":[184],"memory,":[185],"where":[186],"m":[187],"n":[189],"numbers":[192],"annotations,":[200,232],"respectively.":[201],"Notably,":[202],"runtime":[204,221],"memory":[206,223],"usage":[207,224],"independent":[209],"from":[210],"genome":[212,231],"length,":[213],"allowing":[214],"it":[215],"outperform":[217],"previous":[218],"approaches":[219],"orders":[226],"magnitude":[228],"while":[233],"maintaining":[234],"same":[236],"level":[237],"accuracy.":[239],"AVAILABILITY":[240],"AND":[241],"IMPLEMENTATION:":[242],"available":[246,254,262],"at":[247,255,263],"https://github.com/fmfi-compbio/mc-overlaps.":[248],"All":[249],"data":[250,260],"for":[251],"reproducibility":[252],"https://github.com/fmfi-compbio/mc-overlaps-reproducibility.":[256],"SUPPLEMENTARY":[257],"INFORMATION:":[258],"Supplementary":[259],"Bioinformatics":[264],"online.":[265]},"counts_by_year":[{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}
