FragmentNet: Adaptive Graph Fragmentation for Graph-to-Sequence Molecular Representation Learning

TL;DR

FragmentNet introduces an adaptive, learned graph tokenizer for molecular graphs that improves property prediction by capturing meaningful fragments and structural information, outperforming existing methods with better scalability and interpretability.

Contribution

The paper presents FragmentNet, a novel graph-to-sequence model with an adaptive tokenizer that enhances molecular representation learning through chemically valid fragmentation and hierarchical embeddings.

Findings

Outperforms similar-sized models on MoleculeNet tasks

Achieves competitive results with larger state-of-the-art models

Enables interpretability and editing of molecular fragments

Abstract

Molecular property prediction uses molecular structure to infer chemical properties. Chemically interpretable representations that capture meaningful intramolecular interactions enhance the usability and effectiveness of these predictions. However, existing methods often rely on atom-based or rule-based fragment tokenization, which can be chemically suboptimal and lack scalability. We introduce FragmentNet, a graph-to-sequence foundation model with an adaptive, learned tokenizer that decomposes molecular graphs into chemically valid fragments while preserving structural connectivity. FragmentNet integrates VQVAE-GCN for hierarchical fragment embeddings, spatial positional encodings for graph serialization, global molecular descriptors, and a transformer. Pre-trained with Masked Fragment Modeling and fine-tuned on MoleculeNet tasks, FragmentNet outperforms models with similarly scaled architectures and datasets while rivaling larger state-of-the-art models requiring significantly more resources. This novel framework enables adaptive decomposition, serialization, and reconstruction of molecular graphs, facilitating fragment-based editing and visualization of property trends in learned embeddings - a powerful tool for molecular design and optimization.