From Molecules to Mixtures: Learning Representations of Olfactory Mixture Similarity using Inductive Biases

Gary Tom, Cher Tian Ser, Ella Miray Rajaonson, Stanley Lo, Hyun Suk Park, Brian Lee, Benjamin Manuel Sanchez

Keywords: representation learning, graph attention, graph neural networks, inductive bias, olfaction perception, molecular mixtures

TL;DR: We design the first representation that incorporates domain expertise for predicting mixture olfactory similarity and achieves state-of-the-art predictive performance.

Abstract: Olfaction---how molecules are perceived as odors to humans---remains poorly understood. Recently, the primary odor map (POM) was introduced to digitize the olfactory properties of single compounds. However, smells in real life are not pure single molecules, but are complex mixtures of molecules, whose representations remain relatively underexplored. In this work, we introduce POMMix, extending the POM to represent mixtures. Our representation builds upon the symmetries of the problem space in a hierarchical manner: (1) graph neural networks for building molecular embeddings, (2) attention mechanisms for aggregating molecular representations into mixture representations, and (3) cosine prediction heads to encode olfactory perceptual distance in the mixture embedding space. POMMix achieves state-of-the-art predictive performance across multiple datasets. We also evaluate the generalizability of the representation on multiple splits when applied to unseen molecules and mixture sizes. Our work advances the effort to digitize olfaction, and highlights the synergy of domain expertise and deep learning in crafting expressive representations in low-data regimes.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 8247