Using the Maximum Entropy Model to Enhance CSLA Enzyme β-Mannan Polysaccharide Synthesis

August 2024 – Present

Principal Investigator: Dr. Cătălin Voiniciuc
Institution: University of Florida
Department: Horticultural Sciences

Research Focus

Currently, I am a part of the AI Scholars program at the University of Florida, where I am working under Dr. Cătălin Voiniciuc at the Designer Glycans Lab, as well as Dr. Wenjun Xie’s Xie Lab.
My project, “Using the Maximum Entropy Model to Enhance CSLA Enzyme β-Mannan Polysaccharide Synthesis”, explores how to computationally generate CSLA enzymes that produce plant β-mannan polysaccharides with programmable activities, using our lab’s data on enzyme structures and functions.

Mannans are a type of polysaccharide found in hemicellulose, which is critical to food, material, energy, and biomedical industries.
They are present in plant cell walls and represent a major source of biomass. Structural variations—from β-mannans in palm seeds to galactomannans in legumes—enable their roles as thickeners, stabilizers, and dietary fibers in food, as well as renewable resources for biofuels and bioplastics.

Responsibilities

I have used Dr. Wenjun Xie’s Maximum Entropy (MaxEnt) model, which takes .a3m multiple sequence aligned (MSA) files as input for training.
The trained model calculates mutational energies for mutations in CSLA enzyme sequences.
These energies, once ranked, reveal how favorable each mutation is for enzyme activity.

Additionally, I developed Python automation scripts to streamline steps in the experimental assay, demonstrating that the predicted mutations increased β-mannan production compared to the wild-type enzymes.