Studying bacterial quorum sensing from the signal's perspective: harnessing the predictive and explanatory power of machine learning

This project is focused on the synergistic combination of two emerging and exciting areas of chemistry: state-of the art computational methods based on machine learning with a chemical signaling pathway in bacteria that significantly impacts human health, agriculture, and industry. We seek to develop unnatural signaling molecules that can intercept bacterial cell-cell communication and provide new insights into this process. Here, we will apply machine learning to smartly design, at an unprecedented pace, new chemicals that block this signaling system and surpass the activity of known molecules. Blocking bacterial communication networks could represents a new therapeutic approach and is clinically timely. Moreover, the proposed computational methods could be readily exportable to other important biological signaling pathways for future discovery.