About the Author

---

I’m a computational biologist developing expertise in graph-based machine learning, protein structure networks, and high-performance AI systems for scientific research. My work bridges structural biology, graph theory, and emerging agentic AI, with the goal of building tools and models that advance drug discovery and molecular design.

I am actively building and applying capabilities in:

• Graph neural networks for protein structure and conformation analysis
• Protein structure network (PSN) pipelines and PyMOL-integrated tools
• Agentic AI workflows and memory-aware reasoning systems
• High-performance computing environments for scientific ML
• Integrating NLP models with protein sequences and graph representations

My research interests revolve around how topology, interaction networks, and information flow shape protein behavior. I’m particularly motivated by the idea that AI models — from residue-level embeddings to GATs and GraphSAGE — can reveal allosteric communication and structural shifts that traditional methods overlook. My goal is to develop tools that make these structural patterns accessible and actionable for working biologists.

• PDB2Graph: A PyMOL plugin for constructing and analyzing protein structure networks
• GAT Classifier for LRH-1: A model for distinguishing high-energy and low-energy conformations
• ΔΔG Structural Network Analysis: Prior work mapping ligand-controlled conformation routes
• Pocket-Ordered Residue Embeddings: Blending NLP and structural biology 
• Agentic AI Workstation: A custom dual-Xeon, 256 GB ECC, RTX 3090 scientific compute environment

My path into computational biology hasn’t been linear. I came into the field through hands-on scientific work, deep curiosity about structure and function, and a desire to understand the systems that shape biological behavior. Over time, that led me toward graph theory, machine learning, and high-performance computing — areas where I’m now building both competence and long-term expertise.