{"id":"https://openalex.org/W4328143752","doi":"https://doi.org/10.1093/bioinformatics/btad142","title":"OutSingle: a novel method of detecting and injecting outliers in RNA-Seq count data using the optimal hard threshold for singular values","display_name":"OutSingle: a novel method of detecting and injecting outliers in RNA-Seq count data using the optimal hard threshold for singular values","publication_year":2023,"publication_date":"2023-03-22","ids":{"openalex":"https://openalex.org/W4328143752","doi":"https://doi.org/10.1093/bioinformatics/btad142"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad142","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad142","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad142/49589872/btad142.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad142/49589872/btad142.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082427425","display_name":"Edin Salkovic","orcid":"https://orcid.org/0000-0003-0020-8728"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Edin Salkovic","raw_affiliation_strings":["College of Science Engineering, Hamad Bin Khalifa University , Doha, Qatar","College of Science Engineering, Hamad Bin Khalifa University, PO Box 34110, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"College of Science Engineering, Hamad Bin Khalifa University , Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]},{"raw_affiliation_string":"College of Science Engineering, Hamad Bin Khalifa University, PO Box 34110, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658844","display_name":"Mohammad Amin Sadeghi","orcid":"https://orcid.org/0000-0002-6409-7679"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mohammad Amin Sadeghi","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University , Doha, Qatar","Qatar Computing Research Institute, Hamad Bin Khalifa University, PO Box 34110, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University , Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]},{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, PO Box 34110, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059672283","display_name":"Abdelkader Baggag","orcid":"https://orcid.org/0000-0001-8742-5519"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Abdelkader Baggag","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University , Doha, Qatar","Qatar Computing Research Institute, Hamad Bin Khalifa University, PO Box 34110, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University , Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]},{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, PO Box 34110, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067836491","display_name":"Ahmed Gamal Rashed Salem","orcid":null},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ahmed Gamal Rashed Salem","raw_affiliation_strings":["Department of Computer Sciences, College of Engineering, Qatar University , P.O. Box: 2713 , Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, College of Engineering, Qatar University , P.O. Box: 2713 , Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013350725","display_name":"Halima Bensmail","orcid":"https://orcid.org/0000-0001-6700-5752"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Halima Bensmail","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University , Doha, Qatar","Qatar Computing Research Institute, Hamad Bin Khalifa University, PO Box 34110, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University , Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]},{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, PO Box 34110, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013350725"],"corresponding_institution_ids":["https://openalex.org/I4210144839"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.712,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83886529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"39","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.974399983882904,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.974399983882904,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10928","display_name":"Probabilistic and Robust Engineering Design","score":0.9569000005722046,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.7690287232398987},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.6306698322296143},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6292746067047119},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6083875298500061},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5013582706451416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4733334183692932},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46694672107696533},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3555959165096283}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7690287232398987},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.6306698322296143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6292746067047119},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6083875298500061},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5013582706451416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4733334183692932},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46694672107696533},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3555959165096283}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btad142","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad142","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad142/49589872/btad142.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"pmh:oai:pubmedcentral.nih.gov:10089674","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10089674","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10089674/pdf/btad142.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"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"},{"id":"pmh:oai:figshare.com:article/25202120","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/OutSingle_a_novel_method_of_detecting_and_injecting_outliers_in_RNA-Seq_count_data_using_the_optimal_hard_threshold_for_singular_values/25202120","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad142","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad142","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad142/49589872/btad142.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4328143752.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1596515083","https://openalex.org/W1976526581","https://openalex.org/W1980589014","https://openalex.org/W1986911601","https://openalex.org/W2085534751","https://openalex.org/W2110017531","https://openalex.org/W2114104545","https://openalex.org/W2130116522","https://openalex.org/W2137526110","https://openalex.org/W2152239989","https://openalex.org/W2179438025","https://openalex.org/W2949444664","https://openalex.org/W2949982307","https://openalex.org/W2950221693","https://openalex.org/W2950545834","https://openalex.org/W2963780177","https://openalex.org/W2971632170","https://openalex.org/W3003257820","https://openalex.org/W3038072559","https://openalex.org/W3084423418","https://openalex.org/W3091027401","https://openalex.org/W3097562643","https://openalex.org/W3103145119","https://openalex.org/W3122242878","https://openalex.org/W3125383934","https://openalex.org/W3164598425","https://openalex.org/W4210968171","https://openalex.org/W6635617995"],"related_works":["https://openalex.org/W4232638561","https://openalex.org/W3121932492","https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W1997544008","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W3107369729"],"abstract_inverted_index":{"Abstract":[0],"Motivation":[1],"Finding":[2],"outliers":[3,104,172,196,262],"in":[4,12,53,105,263],"RNA-sequencing":[5],"(RNA-Seq)":[6],"gene":[7],"expression":[8],"(GE)":[9],"can":[10,190],"help":[11],"identifying":[13],"genes":[14],"that":[15,57,82,159,233],"are":[16,58,252],"aberrant":[17],"and":[18,61,77,154,218,248,271],"cause":[19],"Mendelian":[20],"disorders.":[21],"Recently":[22],"developed":[23],"models":[24,44],"for":[25,49,115,131,215,275],"this":[26,87],"task":[27],"rely":[28,46,69],"on":[29,47,70,138,165,182,227],"modeling":[30],"RNA-Seq":[31,106,166],"GE":[32,107,167],"data":[33,168],"using":[34,94,213,240],"the":[35,123,177,266],"negative":[36],"binomial":[37],"distribution":[38],"(NBD).":[39],"However,":[40],"some":[41],"of":[42,102,212,230,257,268],"those":[43],"either":[45],"procedures":[48,76],"inferring":[50],"NBD\u2019s":[51],"parameters":[52],"a":[54,111,210],"nonbiased":[55],"way":[56,101,211],"computationally":[59,72],"demanding":[60,73],"thus":[62],"make":[63],"confounder":[64,79,119],"control":[65,80],"challenging,":[66],"while":[67],"others":[68],"less":[71],"but":[74],"biased":[75],"convoluted":[78],"approaches":[81],"hinder":[83],"interpretability.":[84],"Results":[85],"In":[86],"article,":[88],"we":[89],"present":[90],"OutSingle":[91,189,214,223,276],"(Outlier":[92],"detection":[93],"Singular":[95],"Value":[96],"Decomposition),":[97],"an":[98,183],"almost":[99],"instantaneous":[100],"detecting":[103],"data.":[108],"It":[109],"uses":[110,122],"simple":[112],"log-normal":[113],"approach":[114],"count":[116],"modeling.":[117],"For":[118],"control,":[120],"it":[121],"recently":[124],"discovered":[125],"optimal":[126],"hard":[127],"threshold":[128],"(OHT)":[129],"method":[130],"noise":[132],"detection,":[133],"which":[134,200],"itself":[135],"is":[136,150,201,277],"based":[137,181],"singular":[139],"value":[140],"decomposition":[141],"(SVD).":[142],"Due":[143],"to":[144,152,193,203,220,254],"its":[145,225],"SVD/OHT":[146],"utilization,":[147],"OutSingle\u2019s":[148,241],"model":[149,180],"straightforward":[151],"understand":[153],"interpret.":[155],"We":[156,208],"then":[157],"show":[158,221],"our":[160],"novel":[161],"method,":[162],"when":[163],"used":[164,192],"with":[169,205,244],"real":[170,238],"biological":[171],"masked":[173,197],"by":[174,198],"confounders,":[175,199],"outcompetes":[176],"previous":[178,206],"state-of-the-art":[179],"ad":[184],"hoc":[185],"denoising":[186],"autoencoder.":[187],"Additionally,":[188],"be":[191],"inject":[194],"artificial":[195],"difficult":[202],"achieve":[204],"approaches.":[207],"describe":[209],"outlier":[216,246],"injection":[217,242],"proceed":[219],"how":[222],"outperforms":[224],"competition":[226],"16":[228],"out":[229],"18":[231],"datasets":[232,239],"were":[234],"generated":[235],"from":[236],"three":[237],"procedure":[243],"different":[245],"types":[247,256],"magnitudes.":[249],"Our":[250],"methods":[251],"applicable":[253],"other":[255],"similar":[258],"problems":[259],"involving":[260],"finding":[261],"matrices":[264],"under":[265],"presence":[267],"confounders.":[269],"Availability":[270],"implementation":[272],"The":[273],"code":[274],"available":[278],"at":[279],"https://github.com/esalkovic/outsingle.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
