{"doi":"10.1371/journal.pcbi.1009119","title":"De novo mutational signature discovery in tumor genomes using SparseSignatures","abstract":"Cancer is the result of mutagenic processes that can be inferred from tumor genomes by analyzing rate spectra of point mutations, or \"mutational signatures\". Here we present SparseSignatures, a novel framework to extract signatures from somatic point mutation data. Our approach incorporates a user-specified background signature, employs regularization to reduce noise in non-background signatures, uses cross-validation to identify the number of signatures, and is scalable to large datasets. We show that SparseSignatures outperforms current state-of-the-art methods on simulated data using a variety of standard metrics. We then apply SparseSignatures to whole genome sequences of pancreatic and breast tumors, discovering well-differentiated signatures that are linked to known mutagenic mechanisms and are strongly associated with patient clinical features.","journal":"PLoS Computational Biology","year":2021,"id":163924,"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":40,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9578,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":684514,"name":"Keli Liu","orcid":"0000-0003-0815-7224","position":1,"is_corresponding":false},{"id":4649,"name":"Robert Tibshirani","orcid":"0000-0003-0553-5090","position":2,"is_corresponding":false},{"id":4981,"name":"Arend Sidow","orcid":"0000-0002-8287-331X","position":3,"is_corresponding":false},{"id":44793,"name":"Daniele Ramazzotti","orcid":"0000-0002-6087-2666","position":4,"is_corresponding":false},{"id":657182,"name":"Avantika Lal","orcid":"0000-0002-5827-0826","position":0,"is_corresponding":true}],"reference_count":45,"raw_metadata":null,"created_at":"2026-07-18T23:45:27.031465Z","pmid":"34181655","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":[]}