Doctoral Thesis: Learning the language of bimolecular interactions

Tuesday, April 23
10:30 am - 12:30 pm

32-G882, Hewlett

By: Samuel Sledzieski

Thesis Supervisor: Bonnie Berger


  • Date: Tuesday, April 23
  • Time: 10:30 am - 12:30 pm
  • Category:
  • Location: 32-G882, Hewlett
Additional Location Details:

Abstract: Proteins are the primary functional unit of the cell, and their interactions drive cellular function. Unsupervised language modeling on amino acid sequences learns patterns in sequence evolution that encode protein structure and function. Here, we present novel machine learning models to leverage protein language modeling for prediction of protein interactions at scale, enabling de novo interaction network inference and large-scale drug compound screening. In addition, we introduce methods for efficient training of these models and applications which take advantage of the scale enabled by lightweight models for discovery of new biological function.