Pangenome-aware DeepVariant
Preprint
Abstract
Population-scale genomics information provides valuable prior knowledge for various genomic analyses, especially variant calling. A notable example of such application is the human pangenome reference released by the Human Pangenome Reference Consortium, which has been shown to improve read mapping and structural variant genotyping. In this work, we introduce pangenome-aware DeepVariant, a variant caller that uses a pangenome reference alongside sample-specific read alignments. It generates pileup images of both reads and pangenome haplotypes near potential variants and uses a Convolutional Neural Network to infer genotypes. This approach allows directly using a pangenome for distinguishing true variant signals from sequencing or alignment noise. We assessed its performance on various short-read sequencing platforms and read mappers. Across all settings, pangenome-aware DeepVariant outperformed the linear-reference-based DeepVariant, reducing errors by up to 25.5%. We also show that Element reads with pangenome-aware DeepVariant can achieve 23.6% more accurate variant calling performance compared to existing methods.Keywords
Funding Information
- National Human Genome Research Institute (NHGRI) [HHS - NIH] (R01HG010485)
- National Human Genome Research Institute (NHGRI) [HHS - NIH] (U01HG010961)
- National Human Genome Research Institute (NHGRI) [HHS - NIH] (U24HG010262)
- National Human Genome Research Institute (NHGRI) [HHS - NIH] (U24HG011853)
This publication has 31 references indexed in Scilit:
- Comprehensive genome analysis and variant detection at scale using DRAGENNature Biotechnology, 2024
- Personalized pangenome referencesNature Methods, 2024
- A draft human pangenome referenceNature, 2023
- GBZ file format for pangenome graphsBioinformatics, 2022
- The Human Pangenome Project: a global resource to map genomic diversityNature, 2022
- Pangenome-based genome inference allows efficient and accurate genotyping across a wide spectrum of variant classesNature Genetics, 2022
- An open resource for accurately benchmarking small variant and reference callsNature Biotechnology, 2019
- A universal SNP and small-indel variant caller using deep neural networksNature Biotechnology, 2018
- Accurate genotyping across variant classes and lengths using variant graphsNature Genetics, 2018
- A framework for variation discovery and genotyping using next-generation DNA sequencing dataNature Genetics, 2011