Abstract
mRNA therapeutics are revolutionizing the pharmaceutical industry, but methods to optimize the primary sequence for increased expression are still lacking. Here, we design 5’UTRs for efficient mRNA translation using deep learning. We perform polysome profiling of fully or partially randomized 5’UTR libraries in three cell types and find that UTR performance is highly correlated across cell types. We train models on all our datasets and use them to guide the design of high-performing 5’UTRs using gradient descent and generative neural networks. We experimentally test designed 5’UTRs with mRNA encoding megaTALTM gene editing enzymes for two different gene targets and in two different cell lines. We find that the designed 5’UTRs support strong gene editing activity. Editing efficiency is correlated between cell types and gene targets, although the best performing UTR was specific to one cargo and cell type. Our results highlight the potential of model-based sequence design for mRNA therapeutics.
Competing Interest Statement
SF and MC are employees of 2seventy bio. KH is an employee of Tornado Bio but did all work reported here as an employee of 2seventy bio. J.L. is an employee of Calico Life Sciences LLC but did work reported here while being affiliated with the University of Washington. GS is an advisor of Modulus Therapeutics and co-founder of Parse Biosciences.