Active Deep Kernel Learning of Molecular Properties: Realizing Dynamic Structural Embeddings

Year: 2024

Type: preprint

Abstract: As vast databases of chemical identities become increasingly available, the challenge shifts to how we effectively explore and leverage these resources to study molecular properties. This paper presents an active learning approach for molecular discovery using Deep Kernel Learning (DKL), demonstrated on the QM9 dataset. DKL links structural embeddings directly to properties, creating organized latent spaces that prioritize relevant property information. By iteratively recalculating embedding vectors in alignment with target properties, DKL uncovers concentrated maxima representing key molecular properties and reveals unexplored regions with potential for innovation. This approach underscores DKL's potential in advancing molecular research and discovery.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2403.01234

Authors: Ghosh, Ayana, Ziatdinov, Maxim, Kalinin, Sergei V.

Institutions: Oak Ridge National Laboratory, Pacific Northwest National Laboratory, University of Tennessee at Knoxville

Language: English

Topic: Computational Drug Discovery Methods

Subfield: Computational Theory and Mathematics

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: U.S. Department of Energy, Battelle, University of Washington, UT-Battelle, Office of Science, Basic Energy Sciences, Oak Ridge National Laboratory, Energy Frontier Research Centers

OpenAlex ID: W4392490796