{"id":"https://openalex.org/W4200163758","doi":"https://doi.org/10.1142/s0219720021400175","title":"DNN-Boost: Somatic mutation identification of tumor-only whole-exome sequencing data using deep neural network and XGBoost","display_name":"DNN-Boost: Somatic mutation identification of tumor-only whole-exome sequencing data using deep neural network and XGBoost","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4200163758","doi":"https://doi.org/10.1142/s0219720021400175","pmid":"https://pubmed.ncbi.nlm.nih.gov/34895111"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720021400175","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s0219720021400175","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1142/s0219720021400175","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006431177","display_name":"Firda Aminy Maruf","orcid":null},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Firda Aminy Maruf","raw_affiliation_strings":["School of Computer Science and Engineering, Pusan National University, 63 Busandaehak-Ro, Busan 46241, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Pusan National University, 63 Busandaehak-Ro, Busan 46241, Republic of Korea","institution_ids":["https://openalex.org/I4921948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017229179","display_name":"Rian Pratama","orcid":"https://orcid.org/0009-0000-8142-7126"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Rian Pratama","raw_affiliation_strings":["School of Computer Science and Engineering, Pusan National University, 63 Busandaehak-Ro, Busan 46241, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Pusan National University, 63 Busandaehak-Ro, Busan 46241, Republic of Korea","institution_ids":["https://openalex.org/I4921948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012853928","display_name":"Giltae Song","orcid":"https://orcid.org/0000-0001-8796-4678"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Giltae Song","raw_affiliation_strings":["School of Computer Science and Engineering, Pusan National University, 63 Busandaehak-Ro, Busan 46241, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Pusan National University, 63 Busandaehak-Ro, Busan 46241, Republic of Korea","institution_ids":["https://openalex.org/I4921948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012853928"],"corresponding_institution_ids":["https://openalex.org/I4921948"],"apc_list":null,"apc_paid":null,"fwci":0.6951,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.63823512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":"06","first_page":"2140017","last_page":"2140017"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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":0.9977999925613403,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.9955000281333923,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/exome-sequencing","display_name":"Exome sequencing","score":0.8114389181137085},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6640030741691589},{"id":"https://openalex.org/keywords/exome","display_name":"Exome","score":0.6466589570045471},{"id":"https://openalex.org/keywords/mutation","display_name":"Mutation","score":0.5193547010421753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4746865928173065},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4566057026386261},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45548054575920105},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4318523406982422},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.41011637449264526},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.35029420256614685},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2258346676826477},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07785505056381226}],"concepts":[{"id":"https://openalex.org/C16671776","wikidata":"https://www.wikidata.org/wiki/Q5420592","display_name":"Exome sequencing","level":4,"score":0.8114389181137085},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6640030741691589},{"id":"https://openalex.org/C10590036","wikidata":"https://www.wikidata.org/wiki/Q417664","display_name":"Exome","level":5,"score":0.6466589570045471},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.5193547010421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4746865928173065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4566057026386261},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45548054575920105},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4318523406982422},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.41011637449264526},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.35029420256614685},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2258346676826477},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07785505056381226},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000073359","descriptor_name":"Exome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073359","descriptor_name":"Exome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073359","descriptor_name":"Exome Sequencing","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":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059472","descriptor_name":"Exome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059472","descriptor_name":"Exome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059472","descriptor_name":"Exome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720021400175","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s0219720021400175","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:34895111","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34895111","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":"Journal of bioinformatics and computational biology","raw_type":null}],"best_oa_location":{"id":"doi:10.1142/s0219720021400175","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s0219720021400175","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2462963976","display_name":null,"funder_award_id":"2021R1A2C2010775","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6988067448","display_name":null,"funder_award_id":"2020-0-01450","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1983660137","https://openalex.org/W1984068087","https://openalex.org/W2141663748","https://openalex.org/W2155943701","https://openalex.org/W2170551349","https://openalex.org/W2304422002","https://openalex.org/W2323851578","https://openalex.org/W2674532415","https://openalex.org/W2752623939","https://openalex.org/W2769133485","https://openalex.org/W2867868648","https://openalex.org/W2898882839","https://openalex.org/W3014001879","https://openalex.org/W3035647551","https://openalex.org/W3043299403","https://openalex.org/W3131055609"],"related_works":["https://openalex.org/W2093932542","https://openalex.org/W2043256480","https://openalex.org/W2106924416","https://openalex.org/W2772505697","https://openalex.org/W3083501552","https://openalex.org/W2400191746","https://openalex.org/W1983406990","https://openalex.org/W2484239316","https://openalex.org/W3024198590","https://openalex.org/W4367844067"],"abstract_inverted_index":{"Detection":[0],"of":[1,13,49,57,122,142],"somatic":[2,68,94,174],"mutation":[3],"in":[4,96,172],"whole-exome":[5],"sequencing":[6,21,73,99],"data":[7,50,74,100,180],"can":[8],"help":[9],"elucidate":[10],"the":[11,41,55,117,120,132,164,169],"mechanism":[12],"tumor":[14,24,37,71],"progression.":[15],"Most":[16],"computational":[17],"approaches":[18],"require":[19],"exome":[20,72,98,179,183],"for":[22,36,51,66],"both":[23],"and":[25,90,101,125,145,152,181],"normal":[26,43],"samples.":[27,44],"However,":[28],"it":[29,59],"is":[30,60,113],"more":[31],"common":[32],"to":[33,62,92,115],"sequence":[34],"exomes":[35],"samples":[38],"only":[39],"without":[40],"paired":[42,177],"To":[45],"include":[46],"these":[47,126],"types":[48],"extensive":[52],"studies":[53],"on":[54],"process":[56],"tumorigenesis,":[58],"necessary":[61],"develop":[63],"an":[64],"approach":[65,84],"identifying":[67],"mutations":[69,95,175],"using":[70,85],"only.":[75],"In":[76],"this":[77,104],"study,":[78],"we":[79,102],"designed":[80],"a":[81,106],"machine":[82],"learning":[83],"Deep":[86],"Neural":[87],"Network":[88],"(DNN)":[89],"XGBoost":[91,111,138],"identify":[93],"tumor-only":[97,182],"integrated":[103],"into":[105,131],"pipeline":[107],"called":[108],"DNN-Boost.":[109],"The":[110,137],"algorithm":[112,139],"used":[114],"extract":[116],"features":[118,127],"from":[119,176],"results":[121],"variant":[123],"callers":[124],"are":[128],"then":[129],"fed":[130],"DNN":[133],"model":[134,151,167],"as":[135],"input.":[136],"resolves":[140],"issues":[141],"missing":[143],"values":[144],"overfitting.":[146],"We":[147,161],"evaluated":[148],"our":[149],"proposed":[150],"compared":[153],"its":[154],"performance":[155],"with":[156],"other":[157],"existing":[158],"benchmark":[159,170],"methods.":[160],"noted":[162],"that":[163],"DNN-Boost":[165],"classification":[166],"outperformed":[168],"method":[171],"classifying":[173],"tumor-normal":[178],"data.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}