Mira Mastoras

Accurate genome assemblies are essential for biological research, but even the highest quality assemblies retain errors caused by the technologies used to construct them. Here we present an encoder-only transformer model for assembly polishing called DeepPolisher, and show it produces a 54% reduction in errors for the majority of the genome.

Accurate genome assemblies are essential for biological research, but even the highest quality assemblies retain errors caused by the technologies used to construct them. Base-level errors are typically fixed with an additional polishing step that uses reads aligned to the draft assembly to identify necessary edits. However, current methods struggle to find a balance between over- and under polishing. Here, we present an encoder-only transformer model for assembly polishing called DeepPolisher, which predicts corrections to the underlying sequence using PacBio HiFi read alignments to a diploid assembly. Our pipeline introduces a method, PHARAOH (Phasing Reads in Areas Of Homozygosity), which uses ultra-long ONT data to ensure alignments are accurately phased and to correctly introduce heterozygous edits in falsely homozygous regions. We demonstrate that the DeepPolisher pipeline reduces assembly errors by approximately half, mostly driven by reductions in indel errors. We applied our DeepPolisher-based pipeline to 230 assemblies from the next Human Pangenome Reference Consortium (HPRC) release, producing an average Quality Value (QV) improvement of 3.4 (54% error reduction) for the majority of the genome.