An official website of the United States government
Conformer‐RL: A deep reinforcement learning library for conformer generation
More Like this
-
Abstract This study reports the development and application of a conformer‐dependent quantitative quadrant descriptor for generating models that relate catalyst performance to catalyst structure in enantioselective transformations. The generality of these descriptors is demonstrated by using them for three different reactions: (1) copper‐catalyzed, enantioselective cyclopropanation of alkenes, (2) rhodium‐catalyzed enantioselective hydrogenation ofα‐substitutedN‐acyl‐enamides, and (3) enantioselective addition of thiols toN‐acyl imines. This work will provide researchers an interpretable steric descriptor that merges the heuristic value of quadrant models with a quantitative tool that can be used to create statistically meaningful correlations between the steric occupancy of catalyst quadrants and stereoselectivity. The low dimensionality of this descriptor, its ability to capture conformational effects and stereostructure, and its direct relationship to intuitive structural properties make it particularly well‐suited for creating Quantitative Structure‐Selectivity Relationships (QSSR) with smaller datasets of asymmetric reactions.more » « less
-
Molecular Representation Learning (MRL) has proven impactful in numerous biochemical applications such as drug discovery and enzyme design. While Graph Neural Networks (GNNs) are effective at learning molecular representations from a 2D molecular graph or a single 3D structure, existing works often overlook the flexible nature of molecules, which continuously interconvert across conformations via chemical bond rotations and minor vibrational perturbations. To better account for molecular flexibility, some recent works formulate MRL as an ensemble learning problem, focusing on explicitly learning from a set of conformer structures. However, most of these studies have limited datasets, tasks, and models. In this work, we introduce the first MoleculAR Conformer Ensemble Learning (MARCEL) benchmark to thoroughly evaluate the potential of learning on con- former ensembles and suggest promising research directions. MARCEL includes four datasets covering diverse molecule- and reaction-level properties of chemically diverse molecules including organocatalysts and transition-metal catalysts, extending beyond the scope of common GNN benchmarks that are confined to drug-like molecules. In addition, we conduct a comprehensive empirical study, which benchmarks representative 1D, 2D, and 3D MRL models, along with two strategies that explicitly incorporate conformer ensembles into 3D models. Our findings reveal that direct learning from an accessible conformer space can improve performance on a variety of tasks and models.more » « less
