Contrastive Domain Generalization for Cross-Instrument Molecular Identification in Mass Spectrometry
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911413009645568 |
|---|---|
| author | Yoo, Seunghyun Kim, Sanghong Yoon, Namkyung Kim, Hwangnam |
| author_facet | Yoo, Seunghyun Kim, Sanghong Yoon, Namkyung Kim, Hwangnam |
| contents | Identifying molecules from mass spectrometry (MS) data remains a fundamental challenge due to the semantic gap between physical spectral peaks and underlying chemical structures. Existing deep learning approaches often treat spectral matching as a closed-set recognition task, limiting their ability to generalize to unseen molecular scaffolds. To overcome this limitation, we propose a cross-modal alignment framework that directly maps mass spectra into the chemically meaningful molecular structure embedding space of a pretrained chemical language model. On a strict scaffold-disjoint benchmark, our model achieves a Top-1 accuracy of 42.2% in fixed 256-way zero-shot retrieval and demonstrates strong generalization under a global retrieval setting. Moreover, the learned embedding space demonstrates strong chemical coherence, reaching 95.4% accuracy in 5-way 5-shot molecular re-identification. These results suggest that explicitly integrating physical spectral resolution with molecular structure embedding is key to solving the generalization bottleneck in molecular identification from MS data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00547 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Contrastive Domain Generalization for Cross-Instrument Molecular Identification in Mass Spectrometry Yoo, Seunghyun Kim, Sanghong Yoon, Namkyung Kim, Hwangnam Machine Learning Artificial Intelligence I.2.1 Identifying molecules from mass spectrometry (MS) data remains a fundamental challenge due to the semantic gap between physical spectral peaks and underlying chemical structures. Existing deep learning approaches often treat spectral matching as a closed-set recognition task, limiting their ability to generalize to unseen molecular scaffolds. To overcome this limitation, we propose a cross-modal alignment framework that directly maps mass spectra into the chemically meaningful molecular structure embedding space of a pretrained chemical language model. On a strict scaffold-disjoint benchmark, our model achieves a Top-1 accuracy of 42.2% in fixed 256-way zero-shot retrieval and demonstrates strong generalization under a global retrieval setting. Moreover, the learned embedding space demonstrates strong chemical coherence, reaching 95.4% accuracy in 5-way 5-shot molecular re-identification. These results suggest that explicitly integrating physical spectral resolution with molecular structure embedding is key to solving the generalization bottleneck in molecular identification from MS data. |
| title | Contrastive Domain Generalization for Cross-Instrument Molecular Identification in Mass Spectrometry |
| topic | Machine Learning Artificial Intelligence I.2.1 |
| url | https://arxiv.org/abs/2602.00547 |