Salvato in:
Dettagli Bibliografici
Autori principali: Tom, Gary, Ser, Cher Tian, Rajaonson, Ella M., Lo, Stanley, Park, Hyun Suk, Lee, Brian K., Sanchez-Lengeling, Benjamin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2501.16271
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910801722343424
author Tom, Gary
Ser, Cher Tian
Rajaonson, Ella M.
Lo, Stanley
Park, Hyun Suk
Lee, Brian K.
Sanchez-Lengeling, Benjamin
author_facet Tom, Gary
Ser, Cher Tian
Rajaonson, Ella M.
Lo, Stanley
Park, Hyun Suk
Lee, Brian K.
Sanchez-Lengeling, Benjamin
contents Olfaction -- how molecules are perceived as odors to humans -- remains poorly understood. Recently, the principal odor map (POM) was introduced to digitize the olfactory properties of single compounds. However, smells in real life are not pure single molecules, but complex mixtures of molecules, whose representations remain relatively under-explored. In this work, we introduce POMMix, an extension of 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_16271
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Molecules to Mixtures: Learning Representations of Olfactory Mixture Similarity using Inductive Biases
Tom, Gary
Ser, Cher Tian
Rajaonson, Ella M.
Lo, Stanley
Park, Hyun Suk
Lee, Brian K.
Sanchez-Lengeling, Benjamin
Machine Learning
Artificial Intelligence
Olfaction -- how molecules are perceived as odors to humans -- remains poorly understood. Recently, the principal odor map (POM) was introduced to digitize the olfactory properties of single compounds. However, smells in real life are not pure single molecules, but complex mixtures of molecules, whose representations remain relatively under-explored. In this work, we introduce POMMix, an extension of 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.
title From Molecules to Mixtures: Learning Representations of Olfactory Mixture Similarity using Inductive Biases
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2501.16271