BiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning

TL;DR

BiScale-GTR is a novel multi-scale graph transformer framework that enhances molecular property prediction by integrating fragment-aware tokenization with adaptive reasoning across multiple molecular scales.

Contribution

It introduces a chemically grounded fragment tokenization method and a multi-scale architecture that jointly captures local, substructure, and long-range molecular features.

Findings

Achieves state-of-the-art results on MoleculeNet, PharmaBench, and LRGB datasets.

Effectively captures chemically meaningful motifs for interpretability.

Outperforms existing methods in both classification and regression tasks.

Abstract

Graph Transformers have recently attracted attention for molecular property prediction by combining the inductive biases of graph neural networks (GNNs) with the global receptive field of Transformers. However, many existing hybrid architectures remain GNN-dominated, causing the resulting representations to remain heavily shaped by local message passing. Moreover, most existing methods operate at only a single structural granularity, limiting their ability to capture molecular patterns that span multiple molecular scales. We introduce BiScale-GTR, a unified framework for self-supervised molecular representation learning that combines chemically grounded fragment tokenization with adaptive multi-scale reasoning. Our method improves graph Byte Pair Encoding (BPE) tokenization to produce consistent, chemically valid, and high-coverage fragment tokens, which are used as fragment-level inputs to a parallel GNN-Transformer architecture. Architecturally, atom-level representations learned by a GNN are pooled into fragment-level embeddings and fused with fragment token embeddings before Transformer reasoning, enabling the model to jointly capture local chemical environments, substructure-level motifs, and long-range molecular dependencies. Experiments on MoleculeNet, PharmaBench, and the Long Range Graph Benchmark (LRGB) demonstrate state-of-the-art performance across both classification and regression tasks. Attribution analysis further shows that BiScale-GTR highlights chemically meaningful functional motifs, providing interpretable links between molecular structure and predicted properties. Code will be released upon acceptance.