Abstract
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 underpolishing. Here, we present an encoder-only transformer model for assembly polishing called DeepPolisher, which predicts corrections to the underlying sequence using Pacific Biosciences (PacBio) HiFi read alignments to a diploid assembly. Our pipeline introduces a method, PHAsing Reads in Areas Of Homozygosity (PHARAOH), which uses ultralong Oxford Nanopore Technologies (ONT) data to ensure alignments are accurately phased and to correctly introduce heterozygous edits in falsely homozygous regions. We demonstrate that the DeepPolisher pipeline can reduce assembly errors by approximately half, mostly driven by reductions in indel errors. We have applied our DeepPolisher-based pipeline to 180 assemblies from the next Human Pangenome Reference Consortium (HPRC) data release, producing an average predicted quality value (QV) improvement of 3.4 (54% error reduction) for the majority of the genome.