Contrastive Learning of Molecular Representation with Fragmented Views

Molecular representation learning is a fundamental task for AI-based drug design and discovery. Contrastive learning is an attractive framework for this task, as also evidenced in various domains of representation learning, e.g., image, language, and speech. However, molecule-specific ways of constructing good positive or negative views in contrastive training under consideration of their chemical semantics have been relatively under-explored. In this paper, we consider a molecule as a bag of meaningful fragments, e.g., functional groups, by disconnecting a non-ring single bond as the semantic-preserving transformation. Then, we suggest to construct a complete (or incomplete) bag of fragments as the positive (or negative) views of a molecule: each fragment loses chemical substructures from the original molecule, while the union of the fragments does not. Namely, this provides easy positive and hard negative views simultaneously for contrastive representation learning so that it can selectively learn useful features and ignore nuisance features. Furthermore, we additionally suggest to optimize the torsional angle reconstruction loss around the fragmented bond to incorporate with 3D geometric structure in the pre-training dataset. Our experiments demonstrate that our scheme outperforms prior state-of-the-art molecular representation learning methods across various downstream molecule property prediction tasks.