<aside> 🍁 This page is a work in progress, contact me with any questions.
</aside>
My PhD research united under the theme of Characterizing Variability in Biological Systems through Approximate Density Estimation. A brief overview of one of my research projects follows.
GENERALIST: An efficient generative model for protein sequence families
Proteins are made of amino acids, and the amino acid sequence determines the structure and function of the protein. Surprisingly, evolutionarily related proteins vary tremendously in their amino acid sequence. This variation could reach up to 80% of their total length!.
In our lab, we are building a probabilistic model that infers the probability distribution from which this variation arises. This model allows us to generate sequences that preserve the properties of the natural proteins, such as statistics and extent of variability within the sequences.
Our model aids in intelligent protein design which an ongoing goal in aiding efforts of biomedical engineering.