Through advanced mechanistic modeling and the generation of large high-quality datasets, machine learning is becoming an integral part of understanding and engineering living systems.

Mechanistic and machine learning models can be combined to enable accurate genotype-to-phenotype predictions. We used a genome-scale model to pinpoint engineering targets, efficient library construction using synthetic biology, and high-throughput biosensor-enabled screening for training machine learning algorithms to enable successful forward engineering of yeast metabolism1.
Now, we have enabled these techniques via a robust implementation platform to allow efficient closed-loop optimization of biological molecules.