Inverse design of 3d molecular structures with conditional generative neural networks
This work addresses the challenge of rational molecule design in chemistry, offering a method for inverse design with potential applications in drug discovery and materials science, though it appears incremental as it builds on existing generative neural network approaches.
The authors tackled the problem of designing molecules with desired properties by proposing a conditional generative neural network for 3D molecular structures, enabling targeted sampling of novel molecules and demonstrating utility in generating molecules with specified motifs, discovering stable ones, and targeting multiple electronic properties.
The rational design of molecules with desired properties is a long-standing challenge in chemistry. Generative neural networks have emerged as a powerful approach to sample novel molecules from a learned distribution. Here, we propose a conditional generative neural network for 3d molecular structures with specified chemical and structural properties. This approach is agnostic to chemical bonding and enables targeted sampling of novel molecules from conditional distributions, even in domains where reference calculations are sparse. We demonstrate the utility of our method for inverse design by generating molecules with specified motifs or composition, discovering particularly stable molecules, and jointly targeting multiple electronic properties beyond the training regime.