AROMMA: Unifying Olfactory Embeddings for Single Molecules and Mixtures
This addresses the challenge of generalizable odor representations for researchers in computational olfaction, though it is incremental as it builds on existing methods for mixtures.
The paper tackles the problem of fragmented olfactory datasets for single molecules and mixtures by proposing AROMMA, a framework that learns a unified embedding space, achieving state-of-the-art performance with up to 19.1% AUROC improvement.
Public olfaction datasets are small and fragmented across single molecules and mixtures, limiting learning of generalizable odor representations. Recent works either learn single-molecule embeddings or address mixtures via similarity or pairwise label prediction, leaving representations separate and unaligned. In this work, we propose AROMMA, a framework that learns a unified embedding space for single molecules and two-molecule mixtures. Each molecule is encoded by a chemical foundation model and the mixtures are composed by an attention-based aggregator, ensuring both permutation invariance and asymmetric molecular interactions. We further align odor descriptor sets using knowledge distillation and class-aware pseudo-labeling to enrich missing mixture annotations. AROMMA achieves state-of-the-art performance in both single-molecule and molecule-pair datasets, with up to 19.1% AUROC improvement, demonstrating a robust generalization in two domains.