Learning to Generate 5' UTR Sequences for Optimized Ribosome Load and Gene Expression
01:40 Share

Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2023.01.30.526198v1?rss=1

Authors: Barazandeh, S., Ozden, F., Hincer, A., Seker, U. O. S., Cicek, A. E.

Abstract: The 5 untranslated region (5 UTR) of the messenger RNA plays a crucial role in the translatability and stability of a molecule. Thus, it is an important component in the design of synthetic biological circuits for high and stable expression of intermediate proteins. Several UTR sequences are patented and used frequently in laboratories. We present a novel model UTRGAN, a Generative Adversarial Network (GAN)-based model designed to generate 5 UTR sequences coupled with an optimization procedure to ensure a target property such as high expression for a target gene sequence or high ribosome load. We rigorously analyze and show that the model can generate sequences that mimic various properties of natural UTR sequences. Then, we show that the optimization procedure yields sequences that are expected to yield 32% higher expression (up to 7-fold) on a set of target genes and 12% higher ribosome load on average on a set of generated 5 UTRs (up to 90% for the best 5 UTR), compared to the initially generated UTR sequences. We also demonstrate that when there is a single target gene of interest, the expected expression increases by 55% on average and up to 100% for certain genes (up to 15-fold for the best 5 UTR).

Copy rights belong to original authors. Visit the link for more info

Podcast created by Paper Player, LLC