FURI | Spring 2023

Developing Meaningful Protein Embeddings Using Structural Information For Use in TCR-Epitope Binding Affinity Prediction Tasks

Health icon, disabled. A red heart with a cardiac rhythm running through it.

This project aims to develop an end-to-end machine learning pipeline that utilizes predicted protein structure from AlphaFold to estimate T Cell Receptor (TCR)-Epitope binding affinity. It has been long known that the exact structural composition of proteins is a major factor in the outcome of protein-to-protein interactions. Recent work at Google resulted in the creation of AlphaFold, a machine learning model capable of accurately predicting protein structure. Prior attempts at predicting TCR-Epitope binding rely only on the underlying amino acid sequences. The researcher aims to incorporate this new information to improve upon existing methods.

Student researcher

Saajan Maslanka

Computer science

Hometown: Gilbert, Arizona, United States

Graduation date: Fall 2023