{"doi":"10.26508/lsa.202403039","title":"Efficient identification of de novo mutations in family trios: a consensus-based informatic approach","abstract":"Accurate identification of de novo variants (DNVs) remains challenging despite advances in sequencing technologies, often requiring ad hoc filters and manual inspection. Here, we explored a purely informatic, consensus-based approach for identifying DNVs in proband-parent trios using short-read genome sequencing data. We evaluated variant calls generated by three sequence analysis pipelines-GATK HaplotypeCaller, DeepTrio, and Velsera GRAF-and examined the assumption that a requirement of consensus can serve as an effective filter for high-quality DNVs. Comparison with a highly accurate DNV set, validated previously by manual inspection and Sanger sequencing, demonstrated that consensus filtering, followed by a force-calling procedure, effectively removed false-positive calls, achieving 98.0-99.4% precision. At the same time, sensitivity of the workflow based on the previously established DNVs reached 99.4%. Validation in the HG002-3-4 Genome-in-a-Bottle trio confirmed its robustness, with precision reaching 99.2% and sensitivity up to 96.6%. We believe that this consensus approach can be widely implemented as an automated bioinformatics workflow suitable for large-scale analyses without the need for manual intervention, especially when very high precision is valued over sensitivity.","journal":"Life Science Alliance","year":2025,"id":563520,"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":0.9582,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":551500,"name":"Özem Kalay","orcid":null,"position":1,"is_corresponding":false},{"id":550825,"name":"Sinem Demirkaya-Budak","orcid":"0000-0003-3500-2682","position":2,"is_corresponding":false},{"id":324204,"name":"Charles A. LeDuc","orcid":"0000-0002-2073-5050","position":3,"is_corresponding":false},{"id":23578,"name":"Wendy K. Chung","orcid":"0000-0003-3438-5685","position":4,"is_corresponding":false},{"id":550826,"name":"Deniz Turgut","orcid":"0000-0003-0543-3561","position":5,"is_corresponding":false},{"id":550827,"name":"Güngör Budak","orcid":"0000-0003-1641-3304","position":6,"is_corresponding":false},{"id":1466199,"name":"Elif Arslan","orcid":"0000-0003-4198-9196","position":7,"is_corresponding":false},{"id":550830,"name":"Vladimir Semenyuk","orcid":"0000-0002-7461-6153","position":8,"is_corresponding":false},{"id":14348,"name":"Brandi N. Davis‐Dusenbery","orcid":"0000-0001-7811-8613","position":9,"is_corresponding":false},{"id":5583,"name":"Christine E. Seidman","orcid":"0000-0001-6380-1209","position":10,"is_corresponding":false},{"id":493771,"name":"H. Joseph Yost","orcid":"0000-0003-2961-5669","position":11,"is_corresponding":false},{"id":550831,"name":"Amit Jain","orcid":"0000-0002-7184-9322","position":12,"is_corresponding":false},{"id":24961,"name":"Bruce D. Gelb","orcid":"0000-0001-8527-5027","position":13,"is_corresponding":false},{"id":711536,"name":"Mariya Shadrina","orcid":"0000-0001-5962-0771","position":0,"is_corresponding":true}],"reference_count":39,"raw_metadata":null,"created_at":"2026-07-19T02:56:13.374766Z","pmid":"40155050","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":[]}