Extended Data Fig. 1: BacterAI learns the amino acid requirements of S. gordonii.
From: BacterAI maps microbial metabolism without prior knowledge
BacterAI learns to predict the growth of S. gordonii in media containing combinations of amino acids. Over 13 days, the agent trains a neural network to guide the search for new experiments along the growth front. Each day, the neural network is retrained using the data from all previous data (train set). The accuracy of the model is measured using the 336 experiments selected each day (test set).
