mRNA2vec: mRNA Embedding with Language Model in the 5'UTR-CDS for mRNA Design

TL;DR

mRNA2vec introduces a novel language model-based embedding method for mRNA sequences, improving prediction of translation efficiency, expression levels, and stability, aiding mRNA therapeutic design.

Contribution

The paper presents a new self-supervised embedding approach tailored for mRNA, integrating sequence location, energy prediction, and secondary structure tasks, outperforming existing methods.

Findings

Enhanced translation efficiency prediction in UTRs

Improved expression level prediction in mRNA sequences

Competitive performance in stability and protein production tasks

Abstract

Messenger RNA (mRNA)-based vaccines are accelerating the discovery of new drugs and revolutionizing the pharmaceutical industry. However, selecting particular mRNA sequences for vaccines and therapeutics from extensive mRNA libraries is costly. Effective mRNA therapeutics require carefully designed sequences with optimized expression levels and stability. This paper proposes a novel contextual language model (LM)-based embedding method: mRNA2vec. In contrast to existing mRNA embedding approaches, our method is based on the self-supervised teacher-student learning framework of data2vec. We jointly use the 5' untranslated region (UTR) and coding sequence (CDS) region as the input sequences. We adapt our LM-based approach specifically to mRNA by 1) considering the importance of location on the mRNA sequence with probabilistic masking, 2) using Minimum Free Energy (MFE) prediction and Secondary Structure (SS) classification as additional pretext tasks. mRNA2vec demonstrates significant improvements in translation efficiency (TE) and expression level (EL) prediction tasks in UTR compared to SOTA methods such as UTR-LM. It also gives a competitive performance in mRNA stability and protein production level tasks in CDS such as CodonBERT.