Algorithms for Protein Conformational Sampling

I have developed algorithms, inspired from the field of robot motion planning, to successfully model low-energy conformations of protein and protein-ligand systems in a scalable manner.

Adaptive Sampling for Simulation of Proteins

Sampling rare events with Molecular Dynamics can be accelerated with adaptive sampling methods, which use machine learning to automatically determine a bias that can speed up the exploration of the simulation. I have experience with the analysis of these methods, and I have applied them to study peptide binding with MHCs.

Machine Learning on Structural Data

I have developed a random forests model with the ability to perform large-scale structure-Based prediction of stable peptide binding to Class I HLAs.

Previous Next

Teaching

Teaching Assistant for Data Science Courses

Rice University Jul 2019
NLM-GCC Summer Undergraduate Program in Biomedical Informatics (Summer 2019)
K2I Data Science Bootcamp (Summer 2017, Summer 2018)
COMP 440 Artificial Intelligence (Fall 2015, Fall 2016, Fall 2017)
COMP 540 Statistical Machine Learning (Spring 2016, Spring 2017)

Certificate in Teaching and Learning

Rice University Dec 2018
Formal pedagogical training, practical experience, and mentoring to be an effective college teacher

Engineering Tutor

UT Austin Aug 2012 – May 2013
Tutored for core engineering classes such as biology, chemistry, physics, calculus, and programming

Software

Structure-based pHLA binding prediction

Large-Scale Structure-Based Prediction of Stable Peptide Binding to Class I HLAs Using Random Forests.

HLA-Arena

A customizable environment for the structural modeling and analysis of peptide-HLA complexes.

APE-Gen

Anchored Peptide-MHC Ensemble Generator.

MSMs for pMHCs

Markov state modeling and adaptive sampling for pMHCs.