Deep Learning for Molecular Graphs with Tiered Graph Autoencoders and Graph Prediction

TL;DR

This paper introduces tiered graph autoencoders combined with graph prediction to learn and utilize hierarchical latent representations of molecular graphs, capturing functional groups and rings for improved interpretability and efficiency.

Contribution

The work presents a novel tiered autoencoder architecture that explicitly models hierarchical molecular structures and integrates it with graph prediction for enhanced molecular analysis.

Findings

Functional groups and ring groups effectively represent molecular structures.

Tiered autoencoders enable transferable unsupervised learning.

Combined approach improves interpretability and efficiency in molecular graph analysis.

Abstract

Tiered graph autoencoders provide the architecture and mechanisms for learning tiered latent representations and latent spaces for molecular graphs that explicitly represent and utilize groups (e.g., functional groups). This enables the utilization and exploration of tiered molecular latent spaces, either individually - the node (atom) tier, the group tier, or the graph (molecule) tier - or jointly, as well as navigation across the tiers. In this paper, we discuss the use of tiered graph autoencoders together with graph prediction for molecular graphs. We show features of molecular graphs used, and groups in molecular graphs identified for some sample molecules. We briefly review graph prediction and the QM9 dataset for background information, and discuss the use of tiered graph embeddings for graph prediction, particularly weighted group pooling. We find that functional groups and ring groups effectively capture and represent the chemical essence of molecular graphs (structures). Further, tiered graph autoencoders and graph prediction together provide effective, efficient and interpretable deep learning for molecular graphs, with the former providing unsupervised, transferable learning and the latter providing supervised, task-optimized learning.