About the Talk

Presenter

Yaron Orenstein

Yaron Orenstein is a Senior Lecturer and head of the Computational Biology Lab at the School of Electrical and Computer Engineering, Ben-Gurion University of the Negev. Yaron completed his B.Sc. summa cum laude in Electrical Engineering and Computer Science at Tel Aviv University and continued directly into graduate studies under the supervision of Prof. Dana Ron. He then completed his Ph.D. in Computer Science at Tel Aviv University under the supervision of Prof. Ron Shamir, receiving several awards and fellowships along the way, including the Deutsch Prize and the Dan David Scholarship. He completed his postdoctoral training with Prof. Bonnie Berger at the Massachusetts Institute of Technology and served for a period as a Research Fellow at the Simons Institute for the Theory of Computing. Over the past four and a half years, Yaron has led a productive lab with numerous publications, grants, and graduate students. He has authored more than 40 journal articles and conference papers, received grants from the ISF, BSF, NIH, ICA, and IIA, and has supervised more than 15 graduate students. His main research interests include sequence design problems and genomic applications of deep neural networks.

Abstract

Protein-RNA interactions play vital roles in many cellular processes and are therefore a central focus of much biological research. Biologists want to measure protein-RNA interactions at high throughput, and, based on these high-throughput experimental measurements, to train accurate machine learning models that predict interactions with new RNA sequences. In this talk, I will present solutions to both challenges: the design of efficient high-throughput experiments, and the training of highly accurate prediction models on high-throughput genomic data. First, I will introduce DeCoDe, a new method based on Integer Linear Programming for designing protein-coding templates that efficiently cover many proteins in a single high-throughput experiment. Second, I will introduce DeepUTR, a new deep-learning-based method for predicting mRNA decay dynamics from an mRNA’s 3′-UTR sequence.

Date: 14 June 2022 – 11:00 AM (GMT+3)

Language: English