Lumen Bioscience, a clinical-stage biopharma company, announced results from a research collaboration with Google that applied machine learning (ML) to significantly advance the scalability of spirulina-based biologic drugs. The research, led by Caitlin Gamble, Lumen and Drew Bryant at Google Accelerated Science, was funded in part by the Bill & Melinda Gates Foundation.

Lumen Bioscience received $2 million of additional grant funding from the Department of Energy to support further development of these research findings. This project will expand the number of variables evaluated to also include improvements from alternative, genetically diverse production strains and other key variables, and significant increase in complexity and scale.
 
The research details the application of ML to increase spirulina productivity using Bayesian black box optimization to rapidly explore a 17-dimensional space containing numerous environmental variables including pH, temperature, and light spectrum and light intensity. Modifications over multiple experimental rounds resulted in outcomes that doubled spirulina-based protein production capabilities.
 
Even in an ultra-simple biomanufacturing system like Lumen’s—where the growth media includes only water and a handful of simple mineral salts—the number of potentially interacting variables is too vast to efficiently explore with traditional one-factor-at-a-time experimentation. Further productivity gains like this will enable broader distribution of these products in the developing world. This ML application provides a way to short-cut the productivity improvement process that took decades for older biomanufacturing platforms such as yeast, E. coli, and CHO.
 
“The combination of two pioneering innovations—the machine-learning of Google and our spirulina-based therapeutics production—brings us even closer to a fully optimized approach that could have a major impact on devastating diseases globally,” said Jim Roberts, M.D., Ph.D., co-founder and Chief Scientific Officer of Lumen Bioscience. “We believe this paper is the first to describe the application of AI techniques to biologics manufacturing. We look forward to the future implementation of these practices, as supported with funding from the Department of Energy, to provide mucosally and topically delivered biologics for highly prevalent diseases that, until now, have been infeasible due to the cost and scaling challenges of traditional biomanufacturing platforms.”
 
“Lumen Bioscience’s spirulina-based biopharmaceutical manufacturing platform represented a unique and meaningful challenge for our ML team,” said Drew Bryant. “Applying ML techniques to the challenge, we were able to significantly improve outcomes at a speed and cost that would not be possible using traditional methods. Further enhancements to this platform hold promise to revolutionize ideas about feasible disease targets and global access to spirulina-based biologic drugs.”