Quantum Chemical Data Generation as Fill-In for Reliability Enhancement of Machine-Learning Reaction and Retrosynthesis Planning
Data-driven synthesis planning has seen remarkable successes in recent years by virtue of modern approaches of artificial intelligence that efficiently exploit vast databases with experimental data on chemical reactions. However, this success story is intimately connected to the availability of existing experimental data. It may well occur in retrosynthetic and synthesis design tasks that predictions in individual steps of a reaction cascade are affected by large uncertainties. In such cases, it will, in general, not be easily possible to provide missing data from autonomously conducted experiments on demand. However, first-principles calculations can, in principle, provide missing data to enhance the confidence of an individual prediction or for model retraining. Here, we demonstrate the feasibility of such an ansatz and analyze resource requirements for conducting autonomous first-principles calculations on demand. We introduce our integrated AI-QC framework and discuss the challenges for the implementation and for the interface of the two technologies at play (IBM RXN platform for AI-based retrosynthesis and SCINE Chemoton for double-ended reaction network exploration). We present proof-of-concept results on two organic reactions (a Williamson ether synthesis and a more complex Friedel-Crafts reaction) and we discuss resource estimates and the scalability of our framework to a production environment.