{"id":"https://openalex.org/W4406460816","doi":"https://doi.org/10.1109/bigdata62323.2024.10825037","title":"A Novel Pipeline for Virus Integration Sites Detection in Tumor Genomes Using Deep Learning","display_name":"A Novel Pipeline for Virus Integration Sites Detection in Tumor Genomes Using Deep Learning","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406460816","doi":"https://doi.org/10.1109/bigdata62323.2024.10825037"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lorrayya Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I118073183","display_name":"Meharry Medical College","ror":"https://ror.org/00k63dq23","country_code":"US","type":"education","lineage":["https://openalex.org/I118073183"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lorrayya Williams","raw_affiliation_strings":["Meharry Medical College,School of Applied Computational Sciences,Department of Computer Science &amp; Data Science,Nashville,TN,USA"],"affiliations":[{"raw_affiliation_string":"Meharry Medical College,School of Applied Computational Sciences,Department of Computer Science &amp; Data Science,Nashville,TN,USA","institution_ids":["https://openalex.org/I118073183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077153628","display_name":"Vibhuti Gupta","orcid":"https://orcid.org/0000-0002-6221-4712"},"institutions":[{"id":"https://openalex.org/I118073183","display_name":"Meharry Medical College","ror":"https://ror.org/00k63dq23","country_code":"US","type":"education","lineage":["https://openalex.org/I118073183"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vibhuti Gupta","raw_affiliation_strings":["Meharry Medical College,School of Applied Computational Sciences,Department of Computer Science &amp; Data Science,Nashville,TN,USA"],"affiliations":[{"raw_affiliation_string":"Meharry Medical College,School of Applied Computational Sciences,Department of Computer Science &amp; Data Science,Nashville,TN,USA","institution_ids":["https://openalex.org/I118073183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118073183"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24119863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4946","last_page":"4951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10494","display_name":"Plant Virus Research Studies","score":0.9934999942779541,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.992900013923645,"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/pipeline","display_name":"Pipeline (software)","score":0.7229757308959961},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6544219255447388},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5424680113792419},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5176118612289429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46772658824920654},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3809840679168701},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.21794793009757996},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.09951701760292053},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09610572457313538},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0943005383014679}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7229757308959961},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6544219255447388},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5424680113792419},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5176118612289429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46772658824920654},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3809840679168701},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21794793009757996},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.09951701760292053},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09610572457313538},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0943005383014679}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2035322315","https://openalex.org/W2076038974","https://openalex.org/W2081116295","https://openalex.org/W2092987969","https://openalex.org/W2140481064","https://openalex.org/W2141860194","https://openalex.org/W2143080883","https://openalex.org/W2158274053","https://openalex.org/W2273396394","https://openalex.org/W2310001042","https://openalex.org/W2566412048","https://openalex.org/W2789624890","https://openalex.org/W2884116871","https://openalex.org/W2887469830","https://openalex.org/W2887748806","https://openalex.org/W2889664156","https://openalex.org/W2906848853","https://openalex.org/W2913426519","https://openalex.org/W2949535114","https://openalex.org/W2996021891","https://openalex.org/W3005400930","https://openalex.org/W3093048084","https://openalex.org/W3118380717","https://openalex.org/W3118630218","https://openalex.org/W3126121283","https://openalex.org/W3163537448","https://openalex.org/W3182709031","https://openalex.org/W4319919562","https://openalex.org/W6730511303"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W3086377361"],"abstract_inverted_index":{"Cancer":[0],"is":[1,58,71,109],"one":[2],"of":[3,7,19,43,54,78,86,99,190,222],"the":[4,37,41,51,74,84,97,104,156,161,188,220,223],"leading":[5],"causes":[6],"death":[8],"worldwide.":[9],"Pathogenic":[10],"viruses":[11],"are":[12,143,217],"estimated":[13],"to":[14,28,60,103,111,130,181],"be":[15],"responsible":[16],"for":[17,116,194],"15%":[18],"all":[20],"human":[21],"cancers":[22],"globally":[23],"and":[24,96,148,163,186,202,209],"pose":[25],"significant":[26],"threats":[27],"public":[29],"health.":[30],"Viruses":[31],"integrate":[32,149],"their":[33,167],"genetic":[34],"material":[35],"into":[36,155],"host":[38,162],"genome,":[39],"increasing":[40,76],"risk":[42],"cancer":[44,66],"promoting":[45],"changes":[46],"in":[47,65,121,226],"it.":[48],"To":[49],"understand":[50],"molecular":[52],"mechanisms":[53],"virus-mediated":[55],"cancers,":[56],"it":[57,108],"crucial":[59,110],"identify":[61,131],"viral":[62,93,132,164,183,228],"insertion":[63],"sites":[64,134,185],"genomes.":[67,123],"However,":[68],"this":[69],"effort":[70],"hindered":[72],"by":[73,91],"rapidly":[75],"volume":[77],"tumor":[79,122],"sequencing":[80,211],"data,":[81],"along":[82],"with":[83,166,177],"challenges":[85],"accurate":[87],"data":[88],"analysis":[89],"caused":[90],"high":[92],"mutation":[94],"rates":[95],"difficulty":[98],"aligning":[100,160],"short":[101],"reads":[102],"reference":[105,169],"genome.":[106],"Thus":[107],"develop":[112],"an":[113],"efficient":[114],"method":[115],"virus":[117],"integration":[118,133,184,229],"site":[119],"detection":[120],"This":[124],"paper":[125,197],"proposes":[126],"a":[127],"novel":[128,151],"pipeline":[129],"leveraging":[135],"deep":[136],"Convolutional":[137],"Neural":[138],"Networks":[139],"(CNN).":[140],"Our":[141,213],"contributions":[142],"twofold:":[144],"(i)":[145],"We":[146,172],"propose":[147],"three":[150],"matrix":[152],"generation":[153],"methods":[154,225],"pipeline,":[157],"developed":[158],"after":[159],"genomes":[165],"respective":[168],"genomes.;":[170],"(ii)":[171],"employ":[173],"one-hot":[174],"encoded":[175],"images":[176],"reduced":[178],"computational":[179],"complexity":[180],"represent":[182],"harness":[187],"capabilities":[189],"Deep":[191],"CNN":[192],"networks":[193],"detection.":[195],"The":[196],"illustrates":[198],"our":[199],"proposed":[200,224],"approach":[201],"presents":[203],"experiments":[204],"conducted":[205],"using":[206],"both":[207],"synthetic":[208],"real":[210],"data.":[212],"preliminary":[214],"experimental":[215],"results":[216],"promising,":[218],"showcasing":[219],"effectiveness":[221],"detecting":[227],"sites.":[230]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}
