MolBind：语言、分子与蛋白质的多模态对齐
MolBind: Multimodal Alignment of Language, Molecules, and Proteins
AI总结：
本文提出MolBind框架，通过对比学习将语言、2D分子图、3D分子构象和3D蛋白质对齐到共享特征空间，并构建四模态数据集MolBind-M4，在多种任务上实现优越的零样本学习性能。
摘要：
近年来，生物学和化学领域的进展利用多模态学习，将分子及其自然语言描述相结合以加速药物发现。然而，当前的预训练框架仅限于两种模态，设计一个统一网络来处理不同模态（如自然语言、2D分子图、3D分子构象和3D蛋白质）仍因它们之间的固有差异而面临挑战。本文提出MolBind框架，通过对比学习训练多种模态的编码器，将所有模态映射到共享特征空间以实现多模态语义对齐。为促进MolBind在多种模态上的有效预训练，我们还构建并收集了包含四种模态的高质量数据集MolBind-M4，其中包括图-语言、构象-语言、图-构象和构象-蛋白质配对数据。MolBind在广泛任务中展现出优越的零样本学习性能，表明其具有捕捉多种模态底层语义的强大能力。
英文摘要：
Recent advancements in biology and chemistry have leveraged multi-modal learning, integrating molecules and their natural language descriptions to enhance drug discovery. However, current pre-training frameworks are limited to two modalities, and designing a unified network to process different modalities (e.g., natural language, 2D molecular graphs, 3D molecular conformations, and 3D proteins) remains challenging due to inherent gaps among them. In this work, we propose MolBind, a framework that trains encoders for multiple modalities through contrastive learning, mapping all modalities to a shared feature space for multi-modal semantic alignment. To facilitate effective pre-training of MolBind on multiple modalities, we also build and collect a high-quality dataset with four modalities, MolBind-M4, including graph-language, conformation-language, graph-conformation, and conformation-protein paired data. MolBind shows superior zero-shot learning performance across a wide range of tasks, demonstrating its strong capability of capturing the underlying semantics of multiple modalities.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
