Abstract
We present a robotic chemical discovery system capable of navigating a chemical space based on a learned general association between molecular structures and reactivity, while incorporating a neural network model that can process data from online analytics and assess reactivity without knowing the identity of the reagents. Working in conjunction with this learned knowledge, our robotic platform is able to autonomously explore a large number of potential reactions and assess the reactivity of mixtures, including unknown chemical spaces, regardless of the identity of the starting materials. Through the system, we identified a range of chemical reactions and products, some of which were well-known, some new but predictable from known pathways, and some unpredictable reactions that yielded new molecules. The validation of the system was done within a budget of 15 inputs combined in 1018 reactions, further analysis of which allowed us to discover not only a new photochemical reaction but also a new reactivity mode for a well-known reagent (p-toluenesulfonylmethyl isocyanide, TosMIC). This involved the reaction of 6 equiv of TosMIC in a “multistep, single-substrate” cascade reaction yielding a trimeric product in high yield (47% unoptimized) with the formation of five new C–C bonds involving sp–sp2 and sp–sp3 carbon centers. An analysis reveals that this transformation is intrinsically unpredictable, demonstrating the possibility of a reactivity-first robotic discovery of unknown reaction methodologies without requiring human input.
Highlights
Many discoveries in the chemistry laboratory are the result of chance observations, and it is hard to know ahead of time where a new reaction or molecule will be found.[1]
The chemical space was expanded with the addition of either a Lewis acid (24) or a base (23) in order to change the chemical environment
We showed that closed-loop approaches combining automatic reaction execution and reactivity assessment using machine learning can play a crucial role in the discovery of novel reactions in unexplored parts of chemical space
Summary
Many discoveries in the chemistry laboratory are the result of chance observations, and it is hard to know ahead of time where a new reaction or molecule will be found.[1]. The search for unexpected results can be accelerated with automated systems, and in the past decade high-throughput experimentation[20] has shown its potential in speeding up reaction preparation and analysis (typically applied in reaction optimization and combinatorial chemistry).[21−23] an increase of reaction throughput does not automatically lead to the serendipitous discovery of entirely new transformations while, on the other hand, the discovery of new reaction pathways from first principles (i.e., in silico, based on quantum mechanics) is hard due to both the combinatorial explosion of possible reaction pathways and the computational cost of accurate modeling of the energy hypersurface. The system requires three main parts: a chemical robot to perform and analyze the reactions, a program for interpretation of analytical data, and an algorithm that correlates the outcome of the reaction with the input and process
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
