Low rank adaptation of chemical foundation models generates effective odorant representations

Featurizing odorants to enable robust prediction of their properties is difficult due to the complex activation patterns that odorants evoke in the olfactory system. Structurally similar odorants can elicit distinct activation patterns in both the sensory periphery (i.e., at the receptor level) and downstream brain circuits (i.e., at a perceptual level). Despite efforts to design or discover features for odorants to better predict how they activate the olfactory system, we lack a universally accepted way to featurize odorants. In this work, we demonstrate that featurebased approaches that rely on pre-trained foundation models do not significantly outperform classical hand-designed features, but that targeted foundation model fine-turning can increase model performance beyond these limits. To show this, we introduce a new model that creates olfaction-specific representations: L oRA-based O dorant- R eceptor A ffinity prediction with CROSS -attention ( LORAX ). We compare existing chemical foundation model representations to hand-designed physicochemical descriptors using feature-based methods and identify large information overlap between these representations, highlighting the necessity of finetuning to generate novel and superior odorant representations. We show that LO-RAX produces a feature space more closely aligned with olfactory neural representation, enabling it to outperform existing models on predictive tasks.