MolCL-SP: a multimodal contrastive learning framework with non-overlapping substructure perturbations for molecular property prediction.

Abstract

Accurate molecular property prediction remains a central challenge in molecular machine learning, critically dependent on comprehensive molecular representation. Existing methods, however, encounter two major limitations: (i) single-modal learning approaches frequently experience representation bottlenecks, whereas multimodal methods often struggle to effectively leverage complementary information without redundancy across modalities; and (ii) conventional data augmentation techniques typically treat atoms as isolated units, neglecting intrinsic dependencies among atoms within molecular substructures. Here, we propose MolCL-SP, a substructure-aware multimodal contrastive learning framework specifically designed for molecular property prediction. Our approach integrates molecular representations derived from three complementary modalities using a Transformer-based encoder, followed by modality-specific reconstruction to organically align and fuse cross-modal information. We also introduce a novel substructure-based non-overlapping perturbation strategy for data augmentation, preserving interpretability and effectively enhancing inter-modal interactions. Extensive experimental evaluations demonstrate that MolCL-SP achieves state-of-the-art performance on benchmark datasets for both 2D and 3D molecular property predictions. Additionally, evaluations on drug-drug interaction prediction tasks highlight the model's strong generalization capabilities. Visualization analyses further indicate that MolCL-SP effectively captures discriminative molecular embeddings even in task-agnostic contexts. Importantly, the model implicitly emphasizes chemically meaningful substructures associated with functional relevance, significantly enhancing interpretability. Codes and materials are available at https://github.com/lylikeeMoon/MolCL-SP.