Matthew Andres

The paper shows that odor mixtures can be predicted linearly from component odorant profiles, challenging the assumption of nonlinear interactions.

The paper introduces an odor sampling bag system that improves odorant concentration control and reliability compared to traditional methods.

This study develops a deep learning framework to predict odor intensity from physical properties of molecules and mixtures, overcoming limitations of traditional methods.

The paper develops a Principal Odor Map using graph neural networks that matches human-level odor description performance and generalizes to diverse odor prediction tasks.