Leverage Natural Language Processing for Drug Discovery

Accelerate the learning of protein language representations by designing and deploying an NLP system to expedite drug discovery.

Proteins are integral biomolecules responsible for “executing” the instructions contained in DNA. As DNA is a sequence of nucleotides, the proteins created by DNA are also sequences. In humans, an alphabet of 20 amino acids form the characters of protein strings, which vary in length from a few dozen to a few thousand. Deciphering the “language” of proteins is far from an easy task, and even large-scale molecular simulations fail to accurately portray the structure that protein sequences form.

This project aims to develop and deploy an end-to-end hardware-accelerated NLP system to expedite drug discovery using unsupervised learning.