Improving Molecular Pretraining with Complementary Featurizations
This work addresses the need for improved molecular representations in computational chemistry and drug discovery, offering an incremental enhancement over existing methods.
The paper tackles the problem of molecular pretraining by showing that different molecular featurizations convey chemical information differently, and proposes MOCO, a framework that leverages complementary featurizations to outperform state-of-the-art models on molecular property prediction tasks.
Molecular pretraining, which learns molecular representations over massive unlabeled data, has become a prominent paradigm to solve a variety of tasks in computational chemistry and drug discovery. Recently, prosperous progress has been made in molecular pretraining with different molecular featurizations, including 1D SMILES strings, 2D graphs, and 3D geometries. However, the role of molecular featurizations with their corresponding neural architectures in molecular pretraining remains largely unexamined. In this paper, through two case studies -- chirality classification and aromatic ring counting -- we first demonstrate that different featurization techniques convey chemical information differently. In light of this observation, we propose a simple and effective MOlecular pretraining framework with COmplementary featurizations (MOCO). MOCO comprehensively leverages multiple featurizations that complement each other and outperforms existing state-of-the-art models that solely relies on one or two featurizations on a wide range of molecular property prediction tasks.