Hierarchical Graph-to-Graph Translation for Molecules

TL;DR

This paper introduces a hierarchical, autoregressive graph-to-graph translation model for molecular optimization, significantly advancing the ability to generate molecules with improved biochemical properties.

Contribution

The work presents a novel multi-resolution, autoregressive graph decoder that enhances molecular optimization by integrating substructure and atom-level encoding.

Findings

Outperforms previous state-of-the-art models on multiple tasks

Achieves more coherent and chemically valid molecule generation

Demonstrates significant improvements in optimization metrics

Abstract

The problem of accelerating drug discovery relies heavily on automatic tools to optimize precursor molecules to afford them with better biochemical properties. Our work in this paper substantially extends prior state-of-the-art on graph-to-graph translation methods for molecular optimization. In particular, we realize coherent multi-resolution representations by interweaving the encoding of substructure components with the atom-level encoding of the original molecular graph. Moreover, our graph decoder is fully autoregressive, and interleaves each step of adding a new substructure with the process of resolving its attachment to the emerging molecule. We evaluate our model on multiple molecular optimization tasks and show that our model significantly outperforms previous state-of-the-art baselines.