Despite the impressive successes of deep learning approaches for various chemical problems such as property prediction, virtual screening, and de novo molecule design, separately designed models for specific tasks are usually required, and it is often difficult to synergistically combine these models for novel tasks. To address this, here we present a bidirectional molecular foundation model that can be used for both molecular structure and property inferences through a single model, inspired by recent multimodal learning methods such as VLP. Furthermore, thanks to the outstanding structure/property alignment in a common embedding space, experimental results confirm that our method leads to state-of-the-art performance and interpretable attention maps in both multimodal and unimodal tasks, including conditional molecule generation, property prediction, molecule classification, and reaction prediction.

翻译：尽管深度学习方法在化学领域的各种任务（如性质预测、虚拟筛选和新分子设计）中取得了令人瞩目的成功，但通常需要针对特定任务分别设计模型，且这些模型往往难以协同组合以应对新颖任务。为解决这一问题，受最新多模态学习方法（如VLP）的启发，我们在此提出一种双向分子基础模型，可通过单一模型同时用于分子结构与性质的推断。此外，得益于在共享嵌入空间中出色的结构/性质对齐效果，实验结果证实，我们的方法在多模态和单模态任务（包括条件分子生成、性质预测、分子分类及反应预测）中均达到了最先进的性能，并产生了可解释的注意力图。