Semi-Equivariant Continuous Normalizing Flows for Target-Aware Molecule Generation

TL;DR

This paper introduces a semi-equivariant continuous normalizing flow model for generating ligand molecules conditioned on a target receptor, ensuring invariance to rigid transformations and permutations, and demonstrates improved binding affinity predictions.

Contribution

It presents a novel semi-equivariant flow architecture for target-aware molecule generation, incorporating invariance properties and effective learning despite size disparities.

Findings

Achieved significant improvement in binding affinity over existing methods.

Developed a graph neural network architecture implementing the flow.

Ensured invariance to rigid body transformations and permutations.

Abstract

We propose an algorithm for learning a conditional generative model of a molecule given a target. Specifically, given a receptor molecule that one wishes to bind to, the conditional model generates candidate ligand molecules that may bind to it. The distribution should be invariant to rigid body transformations that act $\textit{jointly}$ on the ligand and the receptor; it should also be invariant to permutations of either the ligand or receptor atoms. Our learning algorithm is based on a continuous normalizing flow. We establish semi-equivariance conditions on the flow which guarantee the aforementioned invariance conditions on the conditional distribution. We propose a graph neural network architecture which implements this flow, and which is designed to learn effectively despite the vast differences in size between the ligand and receptor. We evaluate our method on the CrossDocked2020 dataset, attaining a significant improvement in binding affinity over competing methods.