The companies announce the results of a research collaboration that applied machine learning to significantly advance the scalability of spirulina-based biologic drugs.
Lumen Bioscience, a clinical-stage biopharmaceutical company, announced in an August 11, 2021 press release the results of a research collaboration with Google that applied machine learning (ML) to significantly advance the scalability of spirulina-based biologic drugs. Lumen’s platform builds on discoveries of engineering spirulina and subsequent development of a low-cost system to manufacture them at large-scale under biopharmaceutical-grade current good manufacturing practice controls.
In a biomanufacturing system like Lumen’s—where the growth media includes water and mineral salts—the number of potentially interacting variables is too vast to explore with one-factor-at-a-time experimentation, according to Lumen’s press release. The ML application helps to improve the productivity process that took decades for older biomanufacturing platforms like yeast, E. coli, and CHO.
In the paper, the application of ML to increase spirulina productivity using Bayesian black box optimization to rapidly explore a 17-dimensional space containing several environmental variables, including pH, temperature, and light spectrum and light intensity is detailed. The research is titled “Machine Learning Optimization of Photosynthetic Microbe Cultivation and Recombinant Protein Production” and is pending peer review.