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. Here, to advance the ability of machine learning to go beyond the 'edge' of their training chemical space, we introduce a joint modelling approach that combines molecular property prediction with molecular reconstruction. This approach allows the introduction of unfamiliarity, a reconstruction-based metric that enables the estimation of model generalizability. 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 on large-scale molecular libraries, unfamiliarity yields robust and meaningful molecular insights that go unnoticed by traditional methods. Finally, we experimentally validate unfamiliarity-based molecule screening in the wet lab for two clinically relevant kinases, discovering seven compounds with low micromolar potency and limited similarity to training molecules. This demonstrates that unfamiliarity can extend the reach of machine learning beyond the edge of the charted chemical space, advancing the discovery of diverse and structurally novel molecules.