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<br/>efficiently exploit vast databases with experimental data on chemical reactions. However, this success story is intimately connected to the <br/>availability of existing experimental data. It may well occur in retrosynthetic and synthesis design tasks that predictions in individual<br/>steps of a reaction cascade are affected by large uncertainties. In such cases, it will, in general, not be easily possible to provide<br/>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<br/>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.