Computational Origins of Biological Energy
How It
Started
I met Dr. Brian Stockman during a talk in the spring 2026 semester. After learning he was an expert in biology, I approached him once the session was over to ask some questions about AlphaFold — something I'm deeply interested in.
After talking for a while, he encouraged me to apply to a research project he was leading. I did, he accepted me, and I am now actively working on this investigation.
The Core Question
Could small peptides — built from only the 10 amino acids available before the genetic code existed — fold into functional structures capable of transferring electrons?
My Focus
My focus sits at the intersection of AI, machine learning, and computational biology. I investigate how primordial electron transfer proteins emerged at the origin of life, testing whether prebiotic peptides could fold into structures capable of sustaining biological energy transfer.
Why This Excites Me
This project bridges AI, computer science, and prebiotic biophysics. We're using computational modeling not merely as a modern utility, but as a time machine to simulate the molecular emergence of life's earliest energy systems.
Computational
Methodology & Tools
To investigate prebiotic sequence space and analyze whether ancient peptide candidates can support functional electron transfer, I leverage modern structural biology suites, AI models, and custom software:
AlphaFold
Predicting tertiary conformations of candidate prebiotic peptides to assess whether sequences composed solely of early prebiotic amino acids can fold into stable, structured motifs without modern evolutionary homologs.
Rosetta (Baker Lab)
Evaluating thermodynamic stability, energy landscape minimization, and conformational scoring to test whether primordial folds are physically stable and capable of coordinating electron-carrying prosthetic groups.
MadraX
Analyzing molecular dynamics, conformational stability, and residue-level energetic contributions to understand structural resilience in primitive peptide environments.
Custom Python & ML Code
Writing bespoke Python pipelines to automate high-throughput sequence sampling, extract structural and geometric descriptors, parse simulation outputs, and apply machine learning models to the resulting molecular datasets.
Why
Biology
The intersection of AI and biology is where some of the most exciting breakthroughs will happen. Protein folding, drug discovery, genomics, personalized medicine — these aren't distant dreams, they're happening right now, and they all need people who understand both sides.
I chose biology as a field to do research in because I believe the next frontier of AI is about understanding life itself, and using computation to accelerate discoveries that can save lives and expand human potential. If there's a chance, no matter how small, to improve human lives, then I believe it's worth exploring.
Plus, biology challenges me to think differently. In computer science, everything is deterministic and precise. In biology, systems are messy, adaptive, and beautifully complex. Studying both disciplines gives me a broader perspective and makes me a more creative problem solver.
Interested in
This Research?
If you're working on something similar or want to collaborate, I'd love to hear from you.