SCENT: Aligning Mass Spectra with Molecular Structure for Olfactory Perception

2026-05-26

AI Summary

Existing approaches to olfactory perception prediction rely on molecular structural information, which is typically unavailable in real-world sensing scenarios. To address this limitation, this work proposes SCENT, a novel framework that leverages multimodal contrastive learning to align electron ionization mass spectrometry (EI-MS) data with pretrained molecular structure embeddings. By doing so, SCENT enables high-accuracy odor prediction using only mass spectra, without requiring molecular structures during inference. The method significantly outperforms spectrum-only baselines on multi-label odor descriptor prediction and achieves performance comparable to structure-based approaches. Furthermore, SCENT demonstrates strong generalization on real-world laboratory-collected mass spectra, effectively bridging the gap between analytical mass spectrometry and chemical semantic understanding.

Abstract

Predicting human olfactory perception from molecular structure has seen remarkable progress, yet these approaches require explicit chemical structure at inference, which is not available in practical sensing settings. We address this gap by exploring direct electron ionization mass spectrometry (EI-MS), a sensing technique that acquires chemically informative fragmentation fingerprints in seconds, as an alternative input modality for olfactory prediction. We contribute Spectrum-to-Chemical Embedding alignmeNT (SCENT), a multi-modal contrastive learning framework that aligns EI-MS representations with pretrained chemical structure embeddings, while requiring only mass spectra at inference. On the multi-label odor descriptor prediction task, SCENT significantly outperforms MS-only baselines and achieves performance comparable to structure-based models, despite requiring no explicit molecular structure at test time. The learned representations also better approximate continuous human perceptual ratings and generalize to real-world lab-measured spectra, suggesting that cross-modal alignment is an effective strategy for grounding analytical spectra in chemical semantics.

Problem

• olfactory perception
• mass spectrometry
• molecular structure
• sensory prediction
• chemical semantics

Innovation

• mass spectrometry
• olfactory perception
• contrastive learning
• cross-modal alignment
• molecular representation