A decoupled Bayesian optimization method that samples candidate molecules from a VAE prior weighted by a structure-space Gaussian process's probability of improvement outperforms latent-space BO on low-budget molecular design tasks.
Gaussian Process Molecule Property Prediction with FlowMO
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present FlowMO: an open-source Python library for molecular property prediction with Gaussian Processes. Built upon GPflow and RDKit, FlowMO enables the user to make predictions with well-calibrated uncertainty estimates, an output central to active learning and molecular design applications. Gaussian Processes are particularly attractive for modelling small molecular datasets, a characteristic of many real-world virtual screening campaigns where high-quality experimental data is scarce. Computational experiments across three small datasets demonstrate comparable predictive performance to deep learning methods but with superior uncertainty calibration.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces
A decoupled Bayesian optimization method that samples candidate molecules from a VAE prior weighted by a structure-space Gaussian process's probability of improvement outperforms latent-space BO on low-budget molecular design tasks.