Engineering biological systems to specification–for example, designing a microbe to produce a cancer-fighting agent–requires a detailed mechanistic understanding of how all the parts of a cell work. Typically, this knowledge is acquired through years of painstaking work and a fair amount of trial and error. But Berkeley Lab scientists have created an Automated Recommendation Tool (ART) that adapts machine learning algorithms to the needs of synthetic biology to guide development systematically. With a limited set of training data, the algorithms are able to predict how changes in a cell’s DNA or biochemistry will affect its behavior, then make recommendations for the next engineering cycle along with probabilistic predictions for attaining the desired goal. The work was led by Hector Garcia Martin, a researcher in Berkeley Lab’s Biological Systems and Engineering (BSE) Division and Tijana Radivojevic, a BSE data scientist. In a pair of papers recently published in the journal Nature Communications, they presented the algorithm and demonstrated its capabilities.
Read more in the Berkeley Lab News Center.