Molecular deep learning at the edge of chemical space

17 March 2025, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

Molecular machine learning models often fail to generalize beyond the chemical space of their training data, limiting their ability to reliably perform predictions on structurally novel bioactive molecules. To advance the ability of machine learning to go beyond the ‘edge’ of their training chemical space, we introduce a joint modeling approach that combines molecular property prediction with molecular reconstruction, enabling us to estimate model generalizability through a new reconstruction-based ‘unfamiliarity’ metric. Via a systematic analysis spanning more than 30 bioactivity datasets, we demonstrate that unfamiliarity not only effectively identifies out-of-distribution molecules but also serves as a reliable predictor of classifier performance. Even when faced with the presence of strong distribution shifts, unfamiliarity yields robust and meaningful molecular insights that go unnoticed by traditional methods. Our findings highlight that joint modelling can be a powerful strategy for extending the reach of machine learning models into uncharted regions of chemical space, advancing the discovery of diverse and novel molecules.

Keywords

out-of-distribution
joint modeling
molecular machine learning
drug discovery

Supplementary weblinks

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.