This talk will present the roadmap to the first machine learning models for Buchwald-Hartwig <i>N</i>-Arylation using structurally diverse pharmaceutically relevant data sets. The use of nano-scale High-Throughput Experimentation (HTE) together with in-house software platforms to effectively navigate the vast possibilities (&gt;15 billion) of reaction conditions and products will be detailed. The discovery of the state-of-the-art nanoscale compatible C–N coupling was critical for the generation of the large data sets (~ 5000 unique products).  The de novo software platforms enabled the end-to-end design, building block ordering, reaction execution, analytical data integration and UPLC data capture of large reaction arrays which is unattainable using other commercial software. The application of the machine learning models toward accelerating medicinal chemistry campaigns will be showcased.

Roadmap to predictive reactivity models  for pharmaceutically relevant transformations

Where thousands of chemistry professionals meet to share ideas and advance scientific and technical knowledge. Spring 2023 abstracts, posters, and presentations will launch at the end of March.

ACS Spring 2023

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.