Introduction

Protein function prediction plays a vital role in deciphering disease mechanisms, biological processes, and drug discovery. This project aims to utilize machine learning techniques, including Large Language Models (Transformers), Graph Neural Networks (GNNs), and Convolutional Neural Networks (CNNs), to predict protein functions and their Gene Ontologies (GOs) based on protein sequences. Our team seeks to gain insights into why certain models outperform others and identify key features for improved protein function prediction. The project’s success will enhance our understanding of protein functions, enabling more efficient drug target identification and exploration of disease mechanisms.

We are currently not looking for more developers. However, if you have any ideas and suggestions, please reach out to “Adibvafa.fallahpour@mail.utoronto.ca”.

Proposal

The Team