Hierarchical Generation of Molecular Graphs using Structural Motifs

TL;DR

This paper introduces a hierarchical graph generation model using large structural motifs, significantly improving the generation of larger molecules like polymers over previous atom-based methods.

Contribution

A novel hierarchical encoder-decoder framework employing large motifs for molecular graph generation, enabling better handling of complex, larger molecules.

Findings

Outperforms previous models on multiple molecule generation tasks

Effective in generating larger molecules such as polymers

Significantly improves performance for complex molecular structures

Abstract

Graph generation techniques are increasingly being adopted for drug discovery. Previous graph generation approaches have utilized relatively small molecular building blocks such as atoms or simple cycles, limiting their effectiveness to smaller molecules. Indeed, as we demonstrate, their performance degrades significantly for larger molecules. In this paper, we propose a new hierarchical graph encoder-decoder that employs significantly larger and more flexible graph motifs as basic building blocks. Our encoder produces a multi-resolution representation for each molecule in a fine-to-coarse fashion, from atoms to connected motifs. Each level integrates the encoding of constituents below with the graph at that level. Our autoregressive coarse-to-fine decoder adds one motif at a time, interleaving the decision of selecting a new motif with the process of resolving its attachments to the emerging molecule. We evaluate our model on multiple molecule generation tasks, including polymers, and show that our model significantly outperforms previous state-of-the-art baselines.