{"id":"https://openalex.org/W2345557302","doi":"https://doi.org/10.7287/peerj.preprints.2015v1","title":"Information theoretic alignment free variant calling","display_name":"Information theoretic alignment free variant calling","publication_year":2016,"publication_date":"2016-05-03","ids":{"openalex":"https://openalex.org/W2345557302","doi":"https://doi.org/10.7287/peerj.preprints.2015v1","mag":"2345557302"},"language":"en","primary_location":{"id":"doi:10.7287/peerj.preprints.2015v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.2015v1","pdf_url":"https://peerj.com/preprints/2015.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://peerj.com/preprints/2015.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064626077","display_name":"Justin Bed\u0151","orcid":"https://orcid.org/0000-0001-5704-0212"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I4210120068","display_name":"IBM Research - Australia","ror":"https://ror.org/027r3nx49","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210120068"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Justin Bedo","raw_affiliation_strings":["Department of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia","IBM Research -- Australia, Carlton, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"IBM Research -- Australia, Carlton, VIC, Australia","institution_ids":["https://openalex.org/I4210120068"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086912690","display_name":"Benjamin Goudey","orcid":"https://orcid.org/0000-0002-2318-985X"},"institutions":[{"id":"https://openalex.org/I4210120068","display_name":"IBM Research - Australia","ror":"https://ror.org/027r3nx49","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210120068"]},{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Benjamin Goudey","raw_affiliation_strings":["Centre For Epidemiology and Biostatistics, The University of Melbourne, Parkville, VIC, Australia","IBM Research -- Australia, Carlton, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Centre For Epidemiology and Biostatistics, The University of Melbourne, Parkville, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"IBM Research -- Australia, Carlton, VIC, Australia","institution_ids":["https://openalex.org/I4210120068"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046963746","display_name":"Jeremy Wazny","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120068","display_name":"IBM Research - Australia","ror":"https://ror.org/027r3nx49","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210120068"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jeremy Wazny","raw_affiliation_strings":["IBM Research -- Australia, Carlton, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"IBM Research -- Australia, Carlton, VIC, Australia","institution_ids":["https://openalex.org/I4210120068"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101777562","display_name":"Zeyu Zhou","orcid":"https://orcid.org/0009-0001-5493-9019"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I4210120068","display_name":"IBM Research - Australia","ror":"https://ror.org/027r3nx49","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210120068"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zeyu Zhou","raw_affiliation_strings":["IBM Research -- Australia, Carlton, VIC, Australia","School of Mathematics and Statistics, The University of Melbourne, Parkville, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"IBM Research -- Australia, Carlton, VIC, Australia","institution_ids":["https://openalex.org/I4210120068"]},{"raw_affiliation_string":"School of Mathematics and Statistics, The University of Melbourne, Parkville, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064626077"],"corresponding_institution_ids":["https://openalex.org/I165779595","https://openalex.org/I4210120068"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02190941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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":0.9995999932289124,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9710999727249146,"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/T10885","display_name":"Gene expression and cancer classification","score":0.970300018787384,"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":0.6696017980575562},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6040983200073242},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.5167309641838074},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5126715898513794},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5103318095207214},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48427075147628784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4585535228252411},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.4456362724304199},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.42249488830566406},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4207892417907715},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4134595990180969},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3760778605937958},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3323512673377991},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.3135739266872406},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.29629185795783997},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22468528151512146},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.20467808842658997},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17800584435462952},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.15513384342193604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6696017980575562},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6040983200073242},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.5167309641838074},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5126715898513794},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5103318095207214},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48427075147628784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4585535228252411},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.4456362724304199},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.42249488830566406},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4207892417907715},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4134595990180969},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3760778605937958},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3323512673377991},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.3135739266872406},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.29629185795783997},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22468528151512146},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.20467808842658997},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17800584435462952},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15513384342193604},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7287/peerj.preprints.2015v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.2015v1","pdf_url":"https://peerj.com/preprints/2015.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.7287/peerj.preprints.2015v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.2015v1","pdf_url":"https://peerj.com/preprints/2015.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7599999904632568,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2345557302.pdf","grobid_xml":"https://content.openalex.org/works/W2345557302.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1488903245","https://openalex.org/W1532744586","https://openalex.org/W1546962148","https://openalex.org/W1554944419","https://openalex.org/W1986115705","https://openalex.org/W2009588715","https://openalex.org/W2010361633","https://openalex.org/W2012457803","https://openalex.org/W2044046058","https://openalex.org/W2105708056","https://openalex.org/W2110381504","https://openalex.org/W2130492588","https://openalex.org/W2138952930","https://openalex.org/W2148687236","https://openalex.org/W2151752966","https://openalex.org/W2153056550","https://openalex.org/W2170035883"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2162923930","https://openalex.org/W1482324242","https://openalex.org/W2133116680","https://openalex.org/W2091678889","https://openalex.org/W2029514038","https://openalex.org/W2149492307","https://openalex.org/W1985408726","https://openalex.org/W2141411672"],"abstract_inverted_index":{"While":[0],"traditional":[1],"methods":[2],"for":[3,54,154,201,206],"calling":[4,39,130],"variants":[5,49,150,197],"across":[6],"whole":[7],"genome":[8],"sequence":[9],"data":[10],"rely":[11],"on":[12,42,91,121,188,195],"alignment":[13,34],"to":[14,47,57,73,161,182,212,216],"an":[15],"appropriate":[16],"reference":[17,26,163,168,174,219],"sequence,":[18],"alternative":[19],"techniques":[20],"are":[21,111,151,209],"needed":[22],"when":[23],"a":[24,32,61,70,77,87,101,118,137,143,217],"suitable":[25,200],"does":[27],"not":[28],"exist.":[29],"We":[30,104,146],"present":[31],"novel":[33],"and":[35,95,114,142,166],"assembly":[36],"free":[37,169],"variant":[38,129],"method":[40,65,131,170,179],"based":[41,120,164,175],"information":[43],"theoretic":[44],"principles":[45],"designed":[46],"detect":[48],"have":[50],"strong":[51],"statistical":[52],"evidence":[53],"their":[55],"ability":[56],"segregate":[58],"samples":[59],"in":[60],"given":[62,88],"dataset.":[63,145,191],"Our":[64],"uses":[66],"the":[67,83,92,122,128,189],"context":[68],"surrounding":[69,93],"particular":[71],"nucleotide":[72,89],"define":[74],"variants.":[75],"Given":[76],"set":[78],"of":[79,85,97,108,127,136,139],"reads,":[80],"we":[81],"model":[82],"probability":[84],"observing":[86],"conditioned":[90],"prefix":[94],"suffixes":[96],"length":[98],"k":[99],"as":[100],"multinomial":[102],"distribution.":[103],"then":[105],"estimate":[106],"which":[107],"these":[109],"contexts":[110],"stable":[112],"intra-sample":[113],"varying":[115],"inter-sample":[116],"using":[117],"statistic":[119],"Kullback\u2013Leibler":[123],"divergence.":[124],"The":[125,192],"utility":[126],"was":[132,180],"evaluated":[133],"through":[134],"analysis":[135,204],"pair":[138],"bacterial":[140,190],"datasets":[141],"mouse":[144],"found":[147],"that":[148,208],"our":[149,178],"highly":[152],"informative":[153],"supervised":[155],"learning":[156],"tasks":[157,205],"with":[158],"performance":[159],"similar":[160,185],"standard":[162],"calls":[165,176],"another":[167],"(DiscoSNP++).":[171],"Comparisons":[172],"against":[173],"showed":[177],"able":[181],"capture":[183],"very":[184],"population":[186],"structure":[187],"algorithm\u2019s":[193],"focus":[194],"discriminatory":[196],"makes":[198],"it":[199],"many":[202],"common":[203],"organisms":[207],"too":[210],"diverse":[211],"be":[213],"mapped":[214],"back":[215],"single":[218],"sequence.":[220]},"counts_by_year":[],"updated_date":"2025-11-25T14:43:58.451035","created_date":"2025-10-10T00:00:00"}