{"doi":"10.6339/21-jds1016","title":"Mutstats: An Ultra-fast Computational Method to Determine Clonal Status of Somatic Mutations","abstract":"Tumor cell population is a mixture of heterogeneous cell subpopulations, known as subclones. Identification of clonal status of mutations, i.e., whether a mutation occurs in all tumor cells or in a subset of tumor cells, is crucial for understanding tumor progression and developing personalized treatment strategies. We make three major contributions in this paper: (1) we summarize terminologies in the literature based on a unified mathematical representation of subclones; (2) we develop a simulation algorithm to generate hypothetical sequencing data that are akin to real data; and (3) we present an ultra-fast computational method, Mutstats, to infer clonal status of somatic mutations from sequencing data of tumors. The inference is based on a Gaussian mixture model for mutation multiplicities. To validate Mutstats, we evaluate its performance on simulated datasets as well as two breast carcinoma samples from The Cancer Genome Atlas project.","journal":"Journal of Data Science","year":2021,"id":224720,"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":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9579,"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":14032,"name":"Subhajit Sengupta","orcid":"0000-0001-9476-528X","position":1,"is_corresponding":false},{"id":827005,"name":"Tianjian Zhou","orcid":"0000-0002-7196-4232","position":2,"is_corresponding":false},{"id":13612,"name":"Yuan Ji","orcid":"0000-0003-4712-5567","position":3,"is_corresponding":false},{"id":827004,"name":"Dehua Bi","orcid":"0000-0002-7883-5599","position":0,"is_corresponding":true}],"reference_count":37,"raw_metadata":null,"created_at":"2026-07-18T23:54:22.889584Z","pmid":null,"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":[]}