MoFlow: An Invertible Flow Model for Generating Molecular Graphs

Abstract

Generating molecular graphs with desired chemical properties driven by deep graph generative models provides a very promising way to accelerate drug discovery process. Such graph generative models usually consist of two steps: learning latent representations and generation of molecular graphs. However, to generate novel and chemically-valid molecular graphs from latent representations is very challenging because of the chemical constraints and combinatorial complexity of molecular graphs. In this paper, we propose MoFlow, a flow-based graph generative model to learn invertible mappings between molecular graphs and their latent representations. To generate molecular graphs, our MoFlow first generates bonds (edges) through a Glow based model, then generates atoms (nodes) given bonds by a novel graph conditional flow, and finally assembles them into a chemically valid molecular graph with a posthoc validity correction. Our MoFlow has merits including exact and tractable likelihood training, efficient one-pass embedding and generation, chemical validity guarantees, 100\% reconstruction of training data, and good generalization ability. We validate our model by four tasks: molecular graph generation and reconstruction, visualization of the continuous latent space, property optimization, and constrained property optimization. Our MoFlow achieves state-of-the-art performance, which implies its potential efficiency and effectiveness to explore large chemical space for drug discovery.

Cited by in corpus (18)

• A Comprehensive Survey on Deep Graph Representation Learning
• Regression Transformer: Concurrent sequence regression and generation for molecular language modeling
• A Deep Generative Model for Molecule Optimization via One Fragment Modification
• Graph Neural Networks for Molecules
• Fast Graph Generation via Spectral Diffusion
• On the design space between molecular mechanics and machine learning force fields
• Controllable Data Generation by Deep Learning: A Review
• Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptides
• GraphXForm: Graph transformer for computer-aided molecular design
• Hybrid Quantum Generative Adversarial Networks for Molecular Simulation and Drug Discovery
• Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization
• HelixMO: Sample-Efficient Molecular Optimization in Scene-Sensitive Latent Space
• How Evaluation Choices Distort the Outcome of Generative Drug Discovery
• Improving Molecule Generation and Drug Discovery with a Knowledge-enhanced Generative Model
• Molecular Dynamics and Machine Learning Unlock Possibilities in Beauty Design -- A Perspective
• Zero Shot Molecular Generation via Similarity Kernels
• Fine-Grained Traffic Inference from Road to Lane via Spatio-Temporal Graph Node Generation
• PlantPose: Universal Plant Skeleton Estimation via Tree-constrained Graph Generation