Since finishing my PhD, I have been working with causal discovery to build causal machine learning models that illuminate the hidden biological mechanisms of disease. These models leverage huge genomic and transcriptomic datasets to reverse engineer causal graphs that are directly related to microbiological functions. The causal nature of these models allows us to ask counterfactual questions. For example, we can knockdown a gene for a particular genetic subpopulation and simulate the effect on disease progression.

While I am still working on causal discovery, I am also interested in other applications of machine learning in this space. I am particularly interested in the potential of deep learning to either supplement or enhance causal models.

During my PhD, I conducted microscopy experiments to study soft matter systems. Using various image analysis techniques such as particle tracking and particle image velocimetry (PIV), these systems were interrogated to understand the underlying physics.

After graduating I began work in AI-driven drug discovery. This work requires a deep understanding of machine learning and bayesian parametric modeling coupled with disease domain knowledge in the context of genetics. Additionally, expertise in NGS, WGS, and clinical data processing and analysis is required.

Programming Languages and Tools

• Python: TensorFlow, Pytorch, Hugging Face, Pandas, NumPy, Scikit-learn
• R: BioConductor, Seurat, Glmnet, Tidyverse, iGraph, Shiny
• SQL
• Git
• Linux and HPC: StarCluster, ParallelCluster, AWS, BASH
• Matlab
• ImageJ
• Microscopy and Microfluidics

Hard Skills

• Machine Learning: GLMs, Causal, Deep Learning
• Modeling: Statistical, Probabilistic, Bayesian
• Multi-omic data pipelines and modeling: RNAseq, WGS, single-cell, proteomics, metabolomics
• Clinical Data Processing and Analysis

Soft Skills

• Critical thinking
• Project Management
• Troubleshooting
• Detail Oriented
• Communication
• Collaboration