Physics-informed generative model for drug-like molecule conformers
This work addresses the need for physically relevant conformer generation in drug discovery, representing an incremental improvement over existing methods.
The paper tackles the problem of generating accurate drug-like molecule conformers by developing a diffusion-based generative model that uses physics-informed terms from classical force fields, achieving high accuracy for bonded parameters and exceeding conventional knowledge-based methods.
We present a diffusion-based, generative model for conformer generation. Our model is focused on the reproduction of bonded structure and is constructed from the associated terms traditionally found in classical force fields to ensure a physically relevant representation. Techniques in deep learning are used to infer atom typing and geometric parameters from a training set. Conformer sampling is achieved by taking advantage of recent advancements in diffusion-based generation. By training on large, synthetic data sets of diverse, drug-like molecules optimized with the semiempirical GFN2-xTB method, high accuracy is achieved for bonded parameters, exceeding that of conventional, knowledge-based methods. Results are also compared to experimental structures from the Protein Databank (PDB) and Cambridge Structural Database (CSD).