Advances in Machine Learning for Directed Evolution: A Five-Year Retrospective

Machine Learning (ML) allows computers to learn from data and identify patterns to make predictions without predetermined human instructions, improving over time with high-quality data. While ML has transformed various protein engineering disciplines, its impact on directed evolution remains limited. This is attributed to a disconnect between MLDE researchers seeking optimal proteins and broader directed evolution goals of finding sufficient proteins. Current MLDE methods often fail to account for practical constraints, such as the cost of DNA synthesis.