Accelerating Black-Box Molecular Property Optimization by Adaptively Learning Sparse Subspaces

TL;DR

This paper introduces a novel Bayesian optimization approach for molecular property optimization that adaptively learns sparse subspaces using numerical descriptors and Gaussian processes, significantly improving efficiency and accuracy.

Contribution

The work proposes combining numerical molecular descriptors with a sparse Gaussian process to better identify relevant subspaces, overcoming limitations of previous encoding-based methods.

Findings

Outperforms existing MPO methods on benchmarks and real-world problems.

Finds near-optimal molecules within 100 queries from over 100,000 candidates.

Demonstrates rapid identification of relevant subspaces for property modeling.

Abstract

Molecular property optimization (MPO) problems are inherently challenging since they are formulated over discrete, unstructured spaces and the labeling process involves expensive simulations or experiments, which fundamentally limits the amount of available data. Bayesian optimization (BO) is a powerful and popular framework for efficient optimization of noisy, black-box objective functions (e.g., measured property values), thus is a potentially attractive framework for MPO. To apply BO to MPO problems, one must select a structured molecular representation that enables construction of a probabilistic surrogate model. Many molecular representations have been developed, however, they are all high-dimensional, which introduces important challenges in the BO process -- mainly because the curse of dimensionality makes it difficult to define and perform inference over a suitable class of surrogate models. This challenge has been recently addressed by learning a lower-dimensional encoding of a SMILE or graph representation of a molecule in an unsupervised manner and then performing BO in the encoded space. In this work, we show that such methods have a tendency to "get stuck," which we hypothesize occurs since the mapping from the encoded space to property values is not necessarily well-modeled by a Gaussian process. We argue for an alternative approach that combines numerical molecular descriptors with a sparse axis-aligned Gaussian process model, which is capable of rapidly identifying sparse subspaces that are most relevant to modeling the unknown property function. We demonstrate that our proposed method substantially outperforms existing MPO methods on a variety of benchmark and real-world problems. Specifically, we show that our method can routinely find near-optimal molecules out of a set of more than $>100$k alternatives within 100 or fewer expensive queries.