Blind Biological Sequence Denoising with Self-Supervised Set Learning

TL;DR

This paper introduces Self-Supervised Set Learning (SSSL), a novel method for denoising biological sequences from noisy subreads without needing clean labels, improving accuracy especially on small and difficult reads.

Contribution

The paper presents a new self-supervised approach that effectively denoises sets of biological sequences by embedding and averaging subreads, outperforming existing alignment-based methods.

Findings

Reduces errors by 17% on small reads with ≤6 subreads

Reduces errors by 8% on larger reads with >6 subreads

Significantly improves denoising on challenging small reads in real datasets

Abstract

Biological sequence analysis relies on the ability to denoise the imprecise output of sequencing platforms. We consider a common setting where a short sequence is read out repeatedly using a high-throughput long-read platform to generate multiple subreads, or noisy observations of the same sequence. Denoising these subreads with alignment-based approaches often fails when too few subreads are available or error rates are too high. In this paper, we propose a novel method for blindly denoising sets of sequences without directly observing clean source sequence labels. Our method, Self-Supervised Set Learning (SSSL), gathers subreads together in an embedding space and estimates a single set embedding as the midpoint of the subreads in both the latent and sequence spaces. This set embedding represents the "average" of the subreads and can be decoded into a prediction of the clean sequence. In experiments on simulated long-read DNA data, SSSL methods denoise small reads of $\leq 6$ subreads with 17% fewer errors and large reads of $>6$ subreads with 8% fewer errors compared to the best baseline. On a real dataset of antibody sequences, SSSL improves over baselines on two self-supervised metrics, with a significant improvement on difficult small reads that comprise over 60% of the test set. By accurately denoising these reads, SSSL promises to better realize the potential of high-throughput DNA sequencing data for downstream scientific applications.