Gaussian Process Molecule Property Prediction with FlowMO

TL;DR

FlowMO is an open-source Python library that uses Gaussian Processes for molecular property prediction, providing well-calibrated uncertainty estimates suitable for small datasets and active learning.

Contribution

The paper introduces FlowMO, a new tool that combines Gaussian Processes with molecular data, emphasizing uncertainty calibration and applicability to small datasets.

Findings

Comparable predictive performance to deep learning methods

Superior uncertainty calibration in predictions

Effective for small molecular datasets

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.