Model Overview

MoFlow is a model for molecule generation that leverages Normalizing Flows. This implementation is an optimized version of the model in the original paper.

Model Architecture

Chengxi Zang and Fei Wang. 2020. MoFlow: An Invertible Flow Model for Generating Molecular Graphs. In Proceedings of the 26th ACM SIGKDD

The MoFlow model consists of two parts. The first part, Glow, processes edges to convert an adjacency matrix into a latent vector Z_B. The second part, Graph Conditional Flow, processes nodes in the context of edges to produce conditional latent vector Z_{A|B}. Each part is a normalizing flow—a chain of invertible transformations with learnable parameters, which provide the ability to learn the distribution of the data.

Training

This model was trained using script available on NGC and in GitHub repo.

Dataset

The following datasets were used to train this model:

• ZINC 250k - Dataset of ~250k molecules sampled from ZINC database together with logP, qed, and SAS values

Performance

Performance numbers for this model are available in NGC.

References

• Original paper
• NVIDIA model implementation in NGC
• NVIDIA model implementation on GitHub

License

This model was trained using open-source software available in Deep Learning Examples repository. For terms of use, please refer to the license of the script and the datasets the model was derived from.