Chemistry and Chemical Biology ETDs

Publication Date

Spring 5-16-2026

Abstract

Advancements in machine learning have emerged as a pivotal tool in computational biochemistry, offering new advancements to address challenges in protein structure and function. However, current machine-learning approaches offer limited insight in understanding protein dynamics. The purpose of this work is to combine traditional physics-based computational tools, such as molecular dynamics and coarse-grained simulations, with recently developed AI-driven computational tools to bridge gaps and advance the understanding of proteins in both structural and dynamic aspects. I investigated several approaches such as (i) traditional physics-based methods to study protein conformation and ensembles; (ii) identifying a peptide inhibitor for the PICK1 PDZ domain to block its function tied to substance use and other neurological disorders; (iii) designing peptide/protein binders targeting intrinsically disordered proteins (IDPs) known to be a challenge due to their conformational flexibility. These contributions demonstrate the wide range of applications enabled by traditional computational methods combined with AI-driven models.

Project Sponsors

National Science Foundation Graduate Research Fellowship

Language

English

Keywords

PICK1, SSX1, Protein Engineering, Ligand Design, Machine Learning

Document Type

Dissertation

Degree Name

Chemistry and Chemical Biology

Level of Degree

Doctoral

Department Name

Department of Chemistry and Chemical Biology

First Committee Member (Chair)

Yi He

Second Committee Member

Mark Walker

Third Committee Member

Jing Pu

Fourth Committee Member

Jun-Yong Choe

Download

Share

COinS