Improving molecular property prediction through a task similarity enhanced transfer learning strategy.

ABSTRACT: Deeply understanding the properties (e.g., chemical or biological characteristics) of small molecules plays an essential role in drug development. A large number of molecular property datasets have been rapidly accumulated in recent years. However, most of these datasets contain only a limited amount of data, which hinders deep learning methods from making accurate predictions of the corresponding molecular properties. In this work, we propose a transfer learning strategy to alleviate such a data scarcity problem by exploiting the similarity between molecular property prediction tasks. We introduce an effective and interpretable computational framework, named MoTSE (Molecular Tasks Similarity Estimator), to provide an accurate estimation of task similarity. Comprehensive tests demonstrated

SUBMITTER: Li H 

PROVIDER: S-EPMC9579493 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature