Python and Machine Learning Projects

Elucidating Protein Conformational Differences with the Random Forest Classifier

Viewing and analzying molecular dynamics trajectories can be a daunting task, but by using the Random Forest algorithm to classify between protein states, such as with or without an inhibitor, one can use the Random Forest classifier’s feature importances to simplify the task.

Continuous Constant-pH Molecular Dynamics Lambda and Log File Parser

Continuous Constant-pH Molecular Dynamics (CpHMD) simulations produce lambda and log files containing information about the protonation states of acidic and basic residues and the progress of sampling over a range of pH environments. These files can be processed using the CpHMD-Analysis python library to produce important CpHMD metrics and statistics as well as produce plots of the data.

Predicting the Survival of Passengers on the Titanic using Machine Learning

In this short project, I used machine learning to predict the survival of Titanic passengers with a success rate of 87%. The dataset was obtained from Kaggle.

Background

I will earn my Ph. D. in Pharmaceutical Sciences on Oct. 22nd from the University of Maryland Baltimore performing Molecular Dynamics (MD) simulations to aid the development and discovery of novel drugs. My research uses a specialized type of MD simulation that allows for the titration of acidic and basic residues during the progression of the MD process and is known as Continuous-Constant pH Molecular Dynamics (CpHMD). My graduate work has exposed me to many computational skills relevant to Data Science such as machine learning, statistical analysis, and managing large quantities of data.

First Author Publications

2021

Continuous constant pH molecular dynamics simulations of transmembrane proteins

A tutorial on how to simulate transmembrane proteins to allow for the titration of acidic and basic residues.

2020

Proton-Coupled Conformational Activation of SARS Coronavirus Main Proteases and Opportunity for Designing Small-Molecule Broad-Spectrum Targeted Covalent Inhibitors

A study on the main protease of COVID19 and other coronaviruses to investigate the effects of pH on the substrate-binding site.

Alternative proton-binding site and long-distance coupling in Escherichia coli sodium–proton antiporter NhaA

A study answering a hotly debated question about proton binding in a protein named NhaA that exchanges protons for sodium ions.

Assessment of proton-coupled conformational dynamics of SARS and MERS coronavirus papain-like proteases: Implication for designing broad-spectrum antiviral inhibitors

A study investigating protonation state changes and their effects on protein dynamics of the Papain-Like Protease used for viral replication in COVID19 and other coronaviruses. This work received a special press release.

2018

How Ligand Protonation State Controls Water in Protein–Ligand Binding

A study showing how changes in the protonation state of a drug can affect water interactions resulting in implications on inhibitor selectivity.

For a full list of publications please see my Google Scholar page.