Date/Time
Date(s) - 11/09/2025
1:30 pm - 2:20 pm

Title: Predicting the translation efficiency of messenger RNA in mammalian cells

Date: Thursday September 11, 2025

Time: 1:30pm-2:20pm

Room: ABB 165

Host: Dr. Ryan Wylie

Abstract:
One of the core principles of post-transcriptional gene regulation occurs at the step of translation, during which the cell tunes the number of proteins produced per mRNA molecule. The degree to which translational control is specified by mRNA sequence is poorly understood. Here, we collected a compendium of 2,894 mammalian ribosomal profiling datasets, distilling them into a transcriptome-wide atlas of translation efficiency measurements representing 78 human and 68 mouse cell types. We developed RiboNN, a multi-task deep convolutional neural network, and classic machine learning models to demonstrate that sequence-encoded mRNA features were sufficient to strongly predict translation efficiency. We further interpreted RiboNN to give mechanistic insight into how mRNA sequence features influence translation rates.

Biography:
Vikram Agarwal completed his Ph.D. in Dr. David Bartel’s lab at MIT, and his post-doc in Dr. Jay Shendure’s lab at the University of Washington. There, he applied deep learning methods and massively parallel reporter assays to investigate the mechanisms of transcriptional gene regulation, further building upon these approaches at Calico Life Sciences. He is currently the Head of mRNA Platform Design Data Science at the mRNA Center of Excellence at Sanofi, where he is applying machine learning and deep learning methods towards the design of enhanced mRNA therapeutics.