{"doi":"10.64898/2025.12.09.693327","title":"The Impact of Variant Calling on Substitution Mutational Signature Inference","abstract":"<jats:title>ABSTRACT</jats:title>\n                <jats:p>\n                  Identifying mutational signatures is a key component of cancer genomics studies, yet the influence of variant calling strategies on signature extraction has not been systematically evaluated. Here, we analyzed over 8,900 whole exomes from The Cancer Genome Atlas (TCGA) and over 1,800 whole genomes from the Pan-Cancer Analysis of Whole Genomes (PCAWG) consortium to assess how mutation callers shape\n                  <jats:italic>de novo</jats:italic>\n                  single-base substitution (SBS) signatures. We found that consensus calling yielded stable\n                  <jats:italic>de novo</jats:italic>\n                  signatures across reference genomes and pipeline versions, whereas individual callers introduced false-positive SBSs that manifested as artifactual signatures that were reproducibly detected by three independent signatures extraction tools. A minimal consensus approach requiring agreement between only two variant calling algorithms effectively removed these artifacts while preserving true biological signal. Together, these results establish consensus variant calling as essential for robust inference of\n                  <jats:italic>de novo</jats:italic>\n                  SBS mutational signatures and provide practical guidelines for distinguishing genuine mutational processes from technical artifacts.\n                </jats:p>","journal":null,"year":null,"id":652398,"datarank":0.10397207708399181,"base_score":0.6931471805599453,"endowment":0.6931471805599453,"self_citation_contribution":0.10397207708399181,"citation_network_contribution":0.0,"self_endowment_contribution":0.10397207708399181,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1701806,"name":"Jessica N. Au","orcid":null,"position":1,"is_corresponding":false},{"id":618973,"name":"Mariya Kazachkova","orcid":"0000-0003-4453-4357","position":2,"is_corresponding":false},{"id":1328971,"name":"Marcos Díaz-Gay","orcid":null,"position":3,"is_corresponding":false},{"id":839791,"name":"Raviteja Vangara","orcid":"0000-0001-5272-6207","position":4,"is_corresponding":false},{"id":13201,"name":"Ludmil B. Alexandrov","orcid":"0000-0003-3596-4515","position":5,"is_corresponding":false},{"id":1427185,"name":"Zichen Jiang","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"The Impact of Variant Calling on Substitution Mutational Signature Inference","abstract":"<jats:title>ABSTRACT</jats:title>\n                <jats:p>\n                  Identifying mutational signatures is a key component of cancer genomics studies, yet the influence of variant calling strategies on signature extraction has not been systematically evaluated. Here, we analyzed over 8,900 whole exomes from The Cancer Genome Atlas (TCGA) and over 1,800 whole genomes from the Pan-Cancer Analysis of Whole Genomes (PCAWG) consortium to assess how mutation callers shape\n                  <jats:italic>de novo</jats:italic>\n                  single-base substitution (SBS) signatures. We found that consensus calling yielded stable\n                  <jats:italic>de novo</jats:italic>\n                  signatures across reference genomes and pipeline versions, whereas individual callers introduced false-positive SBSs that manifested as artifactual signatures that were reproducibly detected by three independent signatures extraction tools. A minimal consensus approach requiring agreement between only two variant calling algorithms effectively removed these artifacts while preserving true biological signal. Together, these results establish consensus variant calling as essential for robust inference of\n                  <jats:italic>de novo</jats:italic>\n                  SBS mutational signatures and provide practical guidelines for distinguishing genuine mutational processes from technical artifacts.\n                </jats:p>","is_dataset_classified":null,"base_score":0.6931471805599453,"endowment":0.6931471805599453,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"41427300","pmcid":null,"openalex_id":"https://openalex.org/W7114897091","authors":[],"funders":[{"funder_name":"NCI NIH HHS","grant_id":"R01 CA296974","title":null},{"funder_name":"NIEHS NIH HHS","grant_id":"R01 ES032547","title":null},{"funder_name":"NCI NIH HHS","grant_id":"U01 CA290479","title":null},{"funder_name":"NIEHS NIH HHS","grant_id":"R01 ES036931","title":null},{"funder_name":"NCI NIH HHS","grant_id":"P01 CA281819","title":null},{"funder_name":"NCI NIH HHS","grant_id":"R01 CA269919","title":null},{"funder_name":"NCI NIH HHS","grant_id":"T32 CA067754","title":null}],"total_grants":7,"fwci":null,"citation_percentile":null,"influential_citations":0,"citation_trend":[{"year":2026,"count":1}],"oa_status":"green","license":"cc-by-nc","oa_locations":[{"url":"https://doi.org/10.64898/2025.12.09.693327","host_type":"repository"},{"url":"https://doi.org/10.64898/2025.12.09.693327","host_type":"repository"},{"url":"https://syndication.highwire.org/content/doi/10.64898/2025.12.09.693327","host_type":"publisher"},{"url":"https://pubmed.ncbi.nlm.nih.gov/41427300","host_type":"repository"},{"url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12713130/","host_type":"repository"}],"fields_of_study":["Cancer Genomics and Diagnostics","Genomics and Rare Diseases","Genomics and Phylogenetic Studies"],"mesh_terms":[],"keywords":["Genome","Genomics","Inference","Pipeline (software)","1000 Genomes Project","Signature (topology)","Exome"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-10T13:32:51.966120Z","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":[]}