SBIR Phase I: A novel platform for accelerated strain development for precision fermentation

About This Grant

The broader impact of this Small Business Innovation Research (SBIR) Phase I project is a food protein production platform aimed at reducing the environmental impact of livestock farming. Current livestock farming practices have a significant negative impact on the environment, human health, and sustainability, contributing 15% of human-driven greenhouse gas emissions and consuming one-third of all agricultural water and land for livestock feed crops. Additional negative consequences of animal agriculture include pesticide runoff, eutrophication, water resource contamination, and the propagation of antibiotic resistance. This project seeks to mitigate these effects by enhancing an alternative means of food production, precision fermentation, or the process of using microbial hosts as cellular factories for the production of specific proteins. The platform proposed in this project will enhance precision fermentation methods by accelerating the development of new strains, enabling the high-yield production of a range of food proteins. The proposed project leverages machine learning and experimental biology to accelerate the industrial-scale production of animal protein in yeast. The current discovery and development process for yeast production strains is expensive (>$50 million) and slow (6-8 years), constrained by the limitations of existing technology in predicting strain performance. The proposed platform overcomes this limitation using a high-throughput approach for screening millions of signal sequences and target protein combinations, and a novel application of machine learning for the rapid prediction and design of signal sequences with high secretion potential. The insights derived from these analyses may guide genetic engineering efforts for the development of custom, optimized, and efficient strains for specific applications in precision fermentation. This project is aimed at demonstrating the feasibility of this approach by 1) developing a high-throughput sequence screen for high-expression proteins and signal peptides, 2) training an artificial intelligence model to predict high-performing signal peptides and signal peptide-target protein pairs, and 3) constructing high-yield strains. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.