{"id":"https://openalex.org/W4315928526","doi":"https://doi.org/10.1093/bioinformatics/btac828","title":"DeepSom: a CNN-based approach to somatic variant calling in WGS samples without a matched normal","display_name":"DeepSom: a CNN-based approach to somatic variant calling in WGS samples without a matched normal","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4315928526","doi":"https://doi.org/10.1093/bioinformatics/btac828","pmid":"https://pubmed.ncbi.nlm.nih.gov/36637201"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac828","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac828","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac828/48731812/btac828.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","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac828/48731812/btac828.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053673361","display_name":"Sergey Vilov","orcid":"https://orcid.org/0000-0002-2609-1356"},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Munich","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sergey Vilov","raw_affiliation_strings":["Institute of Computational Biology, Computational Health Center, Helmholtz Zentrum M\u00fcnchen Deutsches Forschungszentrum f\u00fcr Gesundheit und Umwelt (GmbH) , 85764 Neuherberg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2609-1356","affiliations":[{"raw_affiliation_string":"Institute of Computational Biology, Computational Health Center, Helmholtz Zentrum M\u00fcnchen Deutsches Forschungszentrum f\u00fcr Gesundheit und Umwelt (GmbH) , 85764 Neuherberg, Germany","institution_ids":["https://openalex.org/I3018134672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012712519","display_name":"Matthias Heinig","orcid":"https://orcid.org/0000-0002-5612-1720"},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Munich","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I4210127591","display_name":"German Centre for Cardiovascular Research","ror":"https://ror.org/031t5w623","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127591","https://openalex.org/I4405256427"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Matthias Heinig","raw_affiliation_strings":["DZHK (German Centre for Cardiovascular Research), Munich Heart Association, Partner Site Munich , 10785 Berlin , Germany","Department of Computer Science, TUM School of Computation, Information and Technology, Technical University Munich , 85748 Garching, Germany","Institute of Computational Biology, Computational Health Center, Helmholtz Zentrum M\u00fcnchen Deutsches Forschungszentrum f\u00fcr Gesundheit und Umwelt (GmbH) , 85764 Neuherberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DZHK (German Centre for Cardiovascular Research), Munich Heart Association, Partner Site Munich , 10785 Berlin , Germany","institution_ids":["https://openalex.org/I4210127591"]},{"raw_affiliation_string":"Department of Computer Science, TUM School of Computation, Information and Technology, Technical University Munich , 85748 Garching, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute of Computational Biology, Computational Health Center, Helmholtz Zentrum M\u00fcnchen Deutsches Forschungszentrum f\u00fcr Gesundheit und Umwelt (GmbH) , 85764 Neuherberg, Germany","institution_ids":["https://openalex.org/I3018134672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012712519"],"corresponding_institution_ids":["https://openalex.org/I3018134672","https://openalex.org/I4210127591","https://openalex.org/I62916508"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3171,"currency":"EUR","value_usd":3419},"fwci":1.1522,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.76182836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"39","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.8414999842643738,"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":0.8414999842643738,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.04899999871850014,"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/T10862","display_name":"AI in cancer detection","score":0.027799999341368675,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/somatic-cell","display_name":"Somatic cell","score":0.7290748357772827},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5043114423751831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48762527108192444},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4304412305355072},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42066794633865356},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3428327441215515},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.27532342076301575},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23620879650115967},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13730311393737793},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06547880172729492}],"concepts":[{"id":"https://openalex.org/C134305767","wikidata":"https://www.wikidata.org/wiki/Q725508","display_name":"Somatic cell","level":3,"score":0.7290748357772827},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5043114423751831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48762527108192444},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4304412305355072},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42066794633865356},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3428327441215515},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.27532342076301575},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23620879650115967},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13730311393737793},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06547880172729492}],"mesh":[{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome 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":"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":"D012189","descriptor_name":"Retrospective Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012189","descriptor_name":"Retrospective Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012189","descriptor_name":"Retrospective Studies","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":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btac828","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac828","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac828/48731812/btac828.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":"pmid:36637201","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36637201","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:9843587","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9843587","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9843587/pdf/btac828.pdf","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"},{"id":"pmh:oai:push-zb.helmholtz-munich.de:67203","is_oa":true,"landing_page_url":"https://push-zb.helmholtz-munich.de/frontdoor.php?source_opus=67203","pdf_url":null,"source":{"id":"https://openalex.org/S7407055352","display_name":"PuSH - Publication Server of Helmholtz Zentrum M\u00fcnchen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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 39:9 (2023)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac828","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac828","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac828/48731812/btac828.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":[{"id":"https://openalex.org/G384249178","display_name":null,"funder_award_id":"031L0203A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4315928526.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1255676896","https://openalex.org/W1919257374","https://openalex.org/W1980323101","https://openalex.org/W2034269086","https://openalex.org/W2054606083","https://openalex.org/W2059437408","https://openalex.org/W2076118871","https://openalex.org/W2097113581","https://openalex.org/W2097998348","https://openalex.org/W2106578986","https://openalex.org/W2108643617","https://openalex.org/W2119180969","https://openalex.org/W2121906867","https://openalex.org/W2146290346","https://openalex.org/W2152061559","https://openalex.org/W2158698691","https://openalex.org/W2168133698","https://openalex.org/W2202187342","https://openalex.org/W2399777075","https://openalex.org/W2674532415","https://openalex.org/W2759930271","https://openalex.org/W2766874495","https://openalex.org/W2786268518","https://openalex.org/W2794000666","https://openalex.org/W2887469830","https://openalex.org/W2889664156","https://openalex.org/W2890909649","https://openalex.org/W2894573839","https://openalex.org/W2898789672","https://openalex.org/W2912626193","https://openalex.org/W2921650138","https://openalex.org/W2936861442","https://openalex.org/W2950493549","https://openalex.org/W2995057955","https://openalex.org/W3006716981","https://openalex.org/W3029661147","https://openalex.org/W3099717514","https://openalex.org/W3138857030","https://openalex.org/W3160595474","https://openalex.org/W3207769218","https://openalex.org/W4283271244","https://openalex.org/W6674385629","https://openalex.org/W6732528198","https://openalex.org/W6773441297"],"related_works":["https://openalex.org/W2060908277","https://openalex.org/W2438531772","https://openalex.org/W1992103432","https://openalex.org/W4251027247","https://openalex.org/W81105053","https://openalex.org/W1881137434","https://openalex.org/W3021321537","https://openalex.org/W2081894066","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"MOTIVATION:":[0],"Somatic":[1],"mutations":[2],"are":[3,135],"usually":[4],"called":[5,68],"by":[6,93],"analyzing":[7],"the":[8,63],"DNA":[9],"sequence":[10],"of":[11],"a":[12,18,22,87,126],"tumor":[13,83],"sample":[14],"in":[15,31,82],"conjunction":[16],"with":[17],"matched":[19,23,88],"normal.":[20,89],"However,":[21],"normal":[24],"is":[25,123],"not":[26],"always":[27],"available,":[28],"for":[29,70,114],"instance,":[30],"retrospective":[32],"analysis":[33],"or":[34],"diagnostic":[35],"settings.":[36],"For":[37],"such":[38],"cases,":[39],"tumor-only":[40,115],"somatic":[41,72,116],"variant":[42,117],"calling":[43],"tools":[44],"need":[45],"to":[46],"be":[47],"designed.":[48],"Previously":[49],"proposed":[50,112],"approaches":[51],"demonstrate":[52,104],"inferior":[53],"performance":[54,96],"on":[55,97,106],"whole-genome":[56],"sequencing":[57],"(WGS)":[58],"samples.":[59],"RESULTS:":[60],"We":[61,90,102],"present":[62],"convolutional":[64],"neural":[65],"network-based":[66],"approach":[67],"DeepSom":[69,92,109,122],"detecting":[71],"single":[73],"nucleotide":[74],"polymorphism":[75],"and":[76,79],"short":[77],"insertion":[78],"deletion":[80],"variants":[81],"WGS":[84,107],"samples":[85,108],"without":[86],"validate":[91],"reporting":[94],"its":[95],"five":[98],"different":[99],"cancer":[100],"datasets.":[101],"also":[103],"that":[105],"outperforms":[110],"previously":[111],"methods":[113],"calling.":[118],"AVAILABILITY":[119],"AND":[120],"IMPLEMENTATION:":[121],"available":[124,136],"as":[125],"GitHub":[127],"repository":[128],"at":[129,137],"https://github.com/heiniglab/DeepSom.":[130],"SUPPLEMENTARY":[131],"INFORMATION:":[132],"Supplementary":[133],"data":[134],"Bioinformatics":[138],"online.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}
