Open-Source Molecular Processing Pipeline for Generating Molecules
This provides accessible tools for computational chemistry, but it is incremental as it builds on existing methods.
The authors tackled the difficulty non-experts face in using generative models for molecules by introducing an open-source pipeline integrated into the DeepChem library, adding PyTorch implementations of MolGAN and Normalizing Flows that show strong performance comparable to past work.
Generative models for molecules have shown considerable promise for use in computational chemistry, but remain difficult to use for non-experts. For this reason, we introduce open-source infrastructure for easily building generative molecular models into the widely used DeepChem [Ramsundar et al., 2019] library with the aim of creating a robust and reusable molecular generation pipeline. In particular, we add high quality PyTorch [Paszke et al., 2019] implementations of the Molecular Generative Adversarial Networks (MolGAN) [Cao and Kipf, 2022] and Normalizing Flows [Papamakarios et al., 2021]. Our implementations show strong performance comparable with past work [Kuznetsov and Polykovskiy, 2021, Cao and Kipf, 2022].