Identifying opportunities for late-stage C-H alkylation with high-throughput experimentation and in silico reaction screening

Abstract

Enhancing the properties of advanced drug candidates is aided by the direct incorporation of specific chemical groups, avoiding the need to construct the entire compound from the ground up. Nevertheless, their chemical intricacy often poses challenges in predicting reactivity for C-H activation reactions and planning their synthesis. We adopted a reaction screening approach that combines high-throughput experimentation (HTE) at a nanomolar scale with computational graph neural networks (GNNs). This approach aims to identify suitable substrates for late-stage C-H alkylation using Minisci-type chemistry. GNNs were trained using experimentally generated reactions derived from in-house HTE and literature data. These trained models were then used to predict, in a forward-looking manner, the coupling of 3180 advanced heterocyclic building blocks with a diverse set of sp3-rich carboxylic acids. This predictive approach aimed to explore the substrate landscape for Minisci-type alkylations. Promising candidates were chosen, their production was scaled up, and they were subsequently isolated and characterized. This process led to the creation of 30 novel, functionally modified molecules that hold potential for further refinement. These results positively advocate the application of HTE-based machine learning to virtual reaction screening.

Prospective de novo drug design with deep interactome learning

“…Message passing : The atomic features were embedded and transformed using a multilayer Perceptron (MLP) to obtain atomic feature vectors . Message passing as suggested by Satorras et al 77 and used in other 3D-based prediction tasks 78 , 79 was applied to L = 3 layers, iteratively applied over all atomic representations . Edges were introduced differently in the 2D and 3D graph representations.…”

Simple User-Friendly Reaction Format

“…With SURF, reaction data is presented in a structured, both human and machine-readable format. Hence, SURF has shown to be a key enabler for several reaction prediction case studies at Roche [28,50]. The use of SURF necessitated minimal data cleaning, mainly focusing on structural information validation and the exclusion of non-relevant columns.…”

“…Three SURF files containing reaction data from literature covering Minisci-type alkylations [50], C-H borylation [28] and post-borylation modification reactions as well as program code for seamless interoperability with other data formats are available at http: //reaction-surf.com.…”

Exploring protein–ligand binding affinity prediction with electron density-based geometric deep learning

“…Third, the electron density and other derived properties at intermolecular BCPs were successfully employed in previous quantitative structureactivity relationship (QSAR) studies. 32,34,[41][42][43][44][45][46][47][48] While the idea of combining QM with machine learning (ML) is not new (e.g., ML to predict QM-calculated properties, [49][50][51][52][53][54] or QM-calculated features being used as ML inputs, [55][56][57][58][59] ) this work represents, to the best or our knowledge, the rst combination of BCPs with 3D-aware neural networks. Previous studies on BCP-based QSAR models mainly relied on aggregated information or scalar descriptors of structural information.…”