arXiv:2605.27009v1 Announce Type: new 
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.

تم تطوير إطار جديد يسمى SCENT لتحسين توقع الإدراك الشمي البشري من خلال محاذاة بيانات مطيافية الكتلة مع الهياكل الجزيئية، مما يعالج التحدي المتمثل في عدم توفر الهياكل الكيميائية الصريحة في التطبيقات العملية.

Se ha desarrollado un nuevo marco llamado SCENT para mejorar la predicción de la percepción olfativa humana alineando los datos de espectrometría de masas con estructuras moleculares, abordando el desafío de la falta de estructuras químicas explícitas en aplicaciones prácticas.

Un nouveau cadre nommé SCENT a été développé pour améliorer la prédiction de la perception olfactive humaine en alignant les données de spectrométrie de masse avec des structures moléculaires, abordant le défi du manque de structures chimiques explicites dans les applications pratiques.

A new framework named SCENT has been developed to enhance the prediction of human olfactory perception by aligning mass spectrometry data with molecular structures, addressing the challenge of lacking explicit chemical structures in practical applications.