I led a team of 10 interdisciplinary researchers in the Cronin group, a world-leading AI+Chemistry lab headed by Prof. Lee Cronin, whose spin-out Chemify raised a $43M Series A to speed up the development of new drugs and medicines by automating the process of designing new molecules.
My main project was to design a new robotic platform capable of performing and analysing 300 physicochemical experiments per day. I implemented a curiosity algorithm to explore the states our chemical system could exhibit in search of novelty. This differs from optimisation where a global target is defined beforehand.
We applied this to the study of self-propelling multicomponent oil-in-water droplets. Our robot, named DropFactory, was able to perform, record, and clean eight droplet experiments in parallel. Equipped with the curiosity algorithm, the robot enabled the discovery of a sudden and highly specific response of droplets to slight temperature changes. Once the temperature dependence was discovered, six modes of self-propelled droplets motion were identified and classified using a time-temperature phase diagram and probed using a variety of techniques including NMR, which allowed the design of a payload release system triggered by temperature.
We published our work in Science Advances (Impact Factor: 11.7) in a paper titled ‘A curious formulation robot enables the discovery of a novel protocell behaviour’.
This work illustrates the breath and depth of my technical skills. I developed the robot and the algorithm, ran the experiments, and analysed the results. It also illustrates how target free search algorithms can significantly increase the rate of unpredictable observations leading to new discoveries.
