{"doi":"10.1101/2024.08.16.608331","title":"DeepSomatic: Accurate somatic small variant discovery for multiple sequencing technologies","abstract":"Somatic variant detection is an integral part of cancer genomics analysis. While most methods have focused on short-read sequencing, long-read technologies now offer potential advantages in terms of repeat mapping and variant phasing. We present DeepSomatic, a deep learning method for detecting somatic SNVs and insertions and deletions (indels) from both short-read and long-read data, with modes for whole-genome and exome sequencing, and able to run on tumor-normal, tumor-only, and with FFPE-prepared samples. To help address the dearth of publicly available training and benchmarking data for somatic variant detection, we generated and make openly available a dataset of five matched tumor-normal cell line pairs sequenced with Illumina, PacBio HiFi, and Oxford Nanopore Technologies, along with benchmark variant sets. Across samples and technologies (short-read and long-read), DeepSomatic consistently outperforms existing callers, particularly for indels.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2024,"id":484057,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":19,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9505,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":30872,"name":"Daniel E. Cook","orcid":"0000-0003-3347-562X","position":1,"is_corresponding":false},{"id":24447,"name":"Pi-Chuan Chang","orcid":"0000-0003-3021-6446","position":2,"is_corresponding":false},{"id":550821,"name":"Alexey Kolesnikov","orcid":"0000-0002-4761-4072","position":3,"is_corresponding":false},{"id":1223268,"name":"Lucas Brambrink","orcid":null,"position":4,"is_corresponding":false},{"id":1326248,"name":"Juan Carlos Mier","orcid":null,"position":5,"is_corresponding":false},{"id":1325605,"name":"Joshua Gardner","orcid":"0000-0003-4386-0628","position":6,"is_corresponding":false},{"id":1161928,"name":"Brandy McNulty","orcid":null,"position":7,"is_corresponding":false},{"id":24537,"name":"Samuel Sacco","orcid":"0000-0003-1227-8934","position":8,"is_corresponding":false},{"id":1173072,"name":"Ayse Keskus","orcid":null,"position":9,"is_corresponding":false},{"id":1172724,"name":"Asher Bryant","orcid":"0009-0005-9132-782X","position":10,"is_corresponding":false},{"id":1241530,"name":"Tanveer Ahmad","orcid":"0009-0006-2440-6381","position":11,"is_corresponding":false},{"id":369484,"name":"Jyoti Shetty","orcid":"0000-0003-1496-4057","position":12,"is_corresponding":false},{"id":228426,"name":"Yongmei Zhao","orcid":"0000-0003-0800-4658","position":13,"is_corresponding":false},{"id":271310,"name":"Bao Tran","orcid":"0000-0002-0261-4458","position":14,"is_corresponding":false},{"id":391321,"name":"Giuseppe Narzisi","orcid":"0000-0003-1118-8849","position":15,"is_corresponding":false},{"id":985717,"name":"Adrienne Helland","orcid":"0009-0006-2552-7791","position":16,"is_corresponding":false},{"id":280979,"name":"Byunggil Yoo","orcid":"0000-0002-7912-1862","position":17,"is_corresponding":false},{"id":765514,"name":"Irina Pushel","orcid":"0000-0002-0862-1923","position":18,"is_corresponding":false},{"id":417576,"name":"Lisa A. Lansdon","orcid":"0000-0002-8214-6083","position":19,"is_corresponding":false},{"id":433472,"name":"Chengpeng Bi","orcid":null,"position":20,"is_corresponding":false},{"id":1246197,"name":"Adam Walter","orcid":"0000-0001-5819-5160","position":21,"is_corresponding":false},{"id":1326249,"name":"Margaret Gibson","orcid":null,"position":22,"is_corresponding":false},{"id":51475,"name":"Tomi Pastinen","orcid":"0000-0003-4016-5021","position":23,"is_corresponding":false},{"id":577536,"name":"Midhat S. Farooqi","orcid":"0000-0002-5238-1349","position":24,"is_corresponding":false},{"id":11495,"name":"Nicolas Robine","orcid":"0000-0001-5698-8183","position":25,"is_corresponding":false},{"id":108047,"name":"Karen H. Miga","orcid":"0000-0002-3670-4507","position":26,"is_corresponding":false},{"id":227319,"name":"Andrew Carroll","orcid":"0000-0002-4824-6689","position":27,"is_corresponding":false},{"id":49028,"name":"Mikhail Kolmogorov","orcid":"0000-0002-5489-9045","position":28,"is_corresponding":false},{"id":108063,"name":"Benedict Paten","orcid":"0000-0001-8863-3539","position":29,"is_corresponding":false},{"id":24544,"name":"Kishwar Shafin","orcid":"0000-0001-5252-3434","position":30,"is_corresponding":false},{"id":1325604,"name":"Jimin Park","orcid":"0000-0002-4702-382X","position":0,"is_corresponding":true}],"reference_count":37,"raw_metadata":null,"created_at":"2026-07-19T02:07:38.055693Z","pmid":"39229187","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}