(468g) Invited Talk: AI/ML for Synthetic Biology

Synthetic biology has been rapidly growing in the past two decades. However, due to the complexity of biological systems, performing synthetic biology in a quantitative and predictive manner still remains a challenge. In recent years, thanks to the increasing availability of big data and recent advances in data science, artificial intelligence (AI) and machine learning (ML) that allow computers to learn from experience has emerged as a potentially powerful tool to address this challenge. In my talk, I will highlight our recent efforts in developing and applying AI/ML tools for synthetic biology, including but are not limited to: (a) development of an AI/ML enabled fully closed design-build-test-learn loop named BioAutomata for pathway optimization (1); (b) development of a deep learning model named ECNet for protein engineering (2); (c) development of an AI/ML algorithm named CLEAN (contrastive learning enabled enzyme annotation) to assign enzyme classification numbers to enzymes with better accuracy, reliability, and sensitivity than the state-of-the-art tool BLASTp (3), and (d) development of AI/ML tools for synthesis planning that combines enzymatic and chemical synthesis to achieve the most efficient synthetic routes for target molecules. These AI/ML tools should greatly accelerate the development and application of synthetic biology for a wide variety of biomedical and biotechnological applications.

1. HamediRad, R. Chao, S. Weisberg, J. Lian, S. Sinha, and H. Zhao. “Towards a Fully-Automated Algorithm-Driven Platform for Biosystems Design.” Nature Communications, 10:5150 (2019).
2. Z Luo, G. Jiang, T. Yu, Y. Liu, L. Vo, H. Ding, Y. Su, W. W. Qian, H. Zhao, and J. Peng. “ECNet is an Evolutionary Context-integrated Deep Learning Framework for Protein Engineering.” Nature Communications, 12:5743 (2021).
3. Yu, H. Cui, J. Li, Y. Luo, G. Jiang, and H. Zhao. “Enzyme Function Prediction using Contrastive Learning.” Science, 379, 1358–1363 (2023).