Improving variant calling using population data and deep learning
Chen, N.-C.; Kolesnikov, A.; Goel, S.; Yun, T.; Chang, P.-C.; Carroll, A.
Show abstract
Large-scale population variant data is often used to filter and aid interpretation of variant calls in a single sample. These approaches do not incorporate population information directly into the process of variant calling, and are often limited to filtering which trades recall for precision. In this study, we develop population-aware DeepVariant models with a new channel encoding allele frequencies from the 1000 Genomes Project. This model reduces variant calling errors, improving both precision and recall in single samples, and reduces rare homozygous and pathogenic clinvar calls cohort-wide. We assess the use of population-specific or diverse reference panels, finding the greatest accuracy with diverse panels, suggesting that large, diverse panels are preferable to individual populations, even when the population matches sample ancestry. Finally, we show that this benefit generalizes to samples with different ancestry from the training data even when the ancestry is also excluded from the reference panel.
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- An Algorithm for Sequence Location Approximation using Nuclear Families (ASLAN) Validates Regions of the Telomere-to-Telomere Assembly and Identifies New Hotspots for Genetic Diversity 96%
- Low-pass sequencing increases the power of GWAS and decreases measurement error of polygenic risk scores compared to genotyping arrays 96%
- A Complete Pedigree-Based Graph Workflow for Rare Candidate Variant Analysis 96%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.