|
"Recent algal blooms of Sargassum are causing an environmental disaster since 2011 in the waters and coasts of Puerto Rico and the Caribbean, more recently in Florida, and likely for the same to occur in other Gulf states in the near future. This has caused a severe crisis in the tourism industry of the region, the local economies, and their infrastructure to manage waste, overwhelming landfills and incinerators. Therefore, there is a pressing need to find solutions to utilize this unused feedstock for biomanufacturing, while addressing an urgent environmental crisis.
In an ongoing project with multiple institutions around the country, we're developing enzymes for degrading Sargassum. As Sargassum is a complex biomass, we need to optimize many enzymes for activity under complex environmental conditions. We're developing AI Agentic workflows that can help design and run end-to-end pipelines for enzyme identification, enzyme engineering using liquid handling robotics and active learning from data, and multi-enzyme formulation to most efficiently degrade Sargassum polysaccharides. A key component of our agent (Ai-PEAT) is running inference from complex protein design neural network models and biophysical simulations using NSF High Performance Computing (HPC) resources, along with interfacing with liquid handling robotics. Combining a range of modalities and learning from both our experimental data as well as foundational structural biology models, we hope to enable streamlined and highly effective enzyme design in general, and Sargassum degradation in particular.
The ideal candidate would be passionate about and grounded in AI development, with some awareness of the domain of protein design and engineering and biochemical sciences."
|
Sign in
to view more information about this project.
