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

TL;DR

This paper introduces an active learning method using Deep Kernel Learning to efficiently explore and identify key molecular properties in large chemical databases, enhancing molecular discovery.

Contribution

It presents a novel active learning framework that dynamically updates structural embeddings in Deep Kernel Learning for improved molecular property prediction.

Findings

DKL creates organized latent spaces emphasizing relevant properties

Iterative recalculations uncover key molecular maxima

The approach reveals unexplored regions with potential for discovery

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.