Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized Fingerprints

2026-09-14

AI Summary

该研究提出HiFi-Mol框架，通过结合层次图编码器和上下文化指纹编码器来解决分子属性预测中的泛化问题。

Abstract

Molecular property prediction requires representations that generalize from limited labeled data to structurally novel compounds. Existing molecular pretraining methods often rely on a single view: graph-based approaches model atom-bond topology but provide limited fragment-level supervision, whereas fingerprint descriptors encode chemical patterns but are typically used as fixed auxiliary features. We propose HiFi-Mol, a multi-view framework that separately pretrains a hierarchical graph encoder and a contextualized fingerprint encoder before downstream integration. The graph branch uses fragment-aware masking with multi-resolution supervision to capture substructure-aware representations, while the fingerprint branch tokenizes active entries from seven fingerprint families and applies masked language modeling to learn contextualized embeddings. During fine-tuning, HiFi-Mol combines projected multi-resolution graph features with fingerprint embeddings for downstream prediction. Evaluated on MoleculeNet benchmarks under the scaffold split, HiFi-Mol achieves a 2.77% improvement in average ROC-AUC over the best baseline across eight classification tasks while maintaining competitive performance on three regression tasks. Further analyses reveal that fragment-aware masking improves graph representation quality, and classification results demonstrate dataset-dependent strengths of the individual graph and fingerprint variants, confirming that the two views provide complementary predictive signals.

Problem

• molecular property prediction
• limited labeled data
• structurally novel compounds
• single view
• fragment-level supervision

Innovation

• multi-view framework
• hierarchical graph encoder
• contextualized fingerprint encoder
• fragment-aware masking
• masked language modeling