Search for: All records

Electrochemical research often requires stringent combinations of experimental parameters that are demanding to manually locate. Recent advances in automated instrumentation and machine-learning algorithms unlock the possibility for accelerated studies of electrochemical fundamentals via high-throughput, online decision-making. Here we report an autonomous electrochemical platform that implements an adaptive, closed-loop workflow for mechanistic investigation of molecular electrochemistry. As a proof-of-concept, this platform autonomously identifies and investigates anECmechanism, an interfacial electron transfer (Estep) followed by a solution reaction (Cstep), for cobalt tetraphenylporphyrin exposed to a library of organohalide electrophiles. The generally applicable workflow accurately discerns theECmechanism’s presence amid negative controls and outliers, adaptively designs desired experimental conditions, and quantitatively extracts kinetic information of theCstep spanning over 7 orders of magnitude, from which mechanistic insights into oxidative addition pathways are gained. This work opens opportunities for autonomous mechanistic discoveries in self-driving electrochemistry laboratories without manual intervention.

 

The lack of publicly available, large, and unbiased datasets is a key bottleneck for the application of machine learning (ML) methods in synthetic chemistry. Data from electronic laboratory notebooks (ELNs) could provide less biased, large datasets, but no such datasets have been made publicly available. The first real-world dataset from the ELNs of a large pharmaceutical company is disclosed and its relationship to high-throughput experimentation (HTE) datasets is described. For chemical yield predictions, a key task in chemical synthesis, an attributed graph neural network (AGNN) performs as well as or better than the best previous models on two HTE datasets for the Suzuki–Miyaura and Buchwald–Hartwig reactions. However, training the AGNN on an ELN dataset does not lead to a predictive model. The implications of using ELN data for training ML-based models are discussed in the context of yield predictions. 

This perspective describes Auto-QChem, an automatic, high-throughput and end-to-end DFT calculation workflow that computes chemical descriptors for organic molecules. Tailored toward users without extensive programming experience, Auto-QChem has facilitated more than 38 000 DFT calculations for 17 000 molecules as of January 2022. Starting from string representations of molecules, Auto-QChem automatically (a) generates conformational ensembles, (b) submits and manages DFT calculations on a high-performance computing (HPC) cluster, (c) extracts production-ready features that are suitable for statistical analysis and machine learning model development, and (d) stores resulting calculations in a cloud-hosted and web-accessible database. We describe in detail the design and implementation of Auto-QChem, as well as its current functionalities. We also review three case studies where Auto-QChem was applied to our recent efforts in combining data science approaches in organic chemistry methodology development: (a) the design of a diverse and unbiased aryl bromide substrate scope for a Ni/photoredox catalyzed alkylation reaction, (b) mechanistic studies on the effect of bioxazoline (BiOx) and biimidazoline (BiIm) ligands on enantioselectivity in a Ni/photoredox catalyzed cross-electrophile coupling of epoxides and aryl iodides, (c) the development of a reaction condition optimization framework using Bayesian optimization. In addition, we discuss limitations and future directions of Auto-QChem and similar automated DFT calculation systems.