融合分子结构与化学语义，提升分子属性预测精度
Local-Global Multimodal Contrastive Learning for Molecular Property Prediction
- 用图神经网络捕捉局部官能团和全局拓扑特征
- 通过对比学习对齐分子文本与结构表示，提升表征质量
- 适合需要高精度分子性质预测的研究者使用
准确的分子属性预测需整合分子结构与化学语义的互补信息。本文提出LGM-CL框架，联合建模分子图与来自SMILES及化学增强文本的文本表示。利用AttentiveFP捕捉局部官能团信息，通过Graph Transformer建模全局分子拓扑，并采用自监督对比学习进行对齐。同时，将化学富集的文本描述与原始SMILES进行对比，以任务无关方式融入理化语义。微调阶段，通过双交叉注意力实现分子指纹与多模态表示的融合。在MoleculeNet基准上的大量实验表明，LGM-CL在分类与回归任务中均表现一致且领先，验证了统一的局部-全局与多模态表征学习的有效性。
原文摘要 · Abstract (English)
Accurate molecular property prediction requires integrating complementary information from molecular structure and chemical semantics. In this work, we propose LGM-CL, a local-global multimodal contrastive learning framework that jointly models molecular graphs and textual representations derived from SMILES and chemistry-aware augmented texts. Local functional group information and global molecular topology are captured using AttentiveFP and Graph Transformer encoders, respectively, and aligned through self-supervised contrastive learning. In addition, chemically enriched textual descriptions are contrasted with original SMILES to incorporate physicochemical semantics in a task-agnostic manner. During fine-tuning, molecular fingerprints are further integrated via Dual Cross-attention multimodal fusion. Extensive experiments on MoleculeNet benchmarks demonstrate that LGM-CL achieves consistent and competitive performance across both classification and regression tasks, validating the effectiveness of unified local-global and multimodal representation learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。