MS2MetGAN: Latent-space adversarial training for metabolite-spectrum matching in MS/MS database search
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_ | 1866911514558988288 |
|---|---|
| author | Tsai, Meng Dwyer, Alexzander Nuckels, Estelle Wang, Yingfeng |
| author_facet | Tsai, Meng Dwyer, Alexzander Nuckels, Estelle Wang, Yingfeng |
| contents | Database search is a widely used approach for identifying metabolites from tandem mass spectra (MS/MS). In this strategy, an experimental spectrum is matched against a user-specified database of candidate metabolites, and candidates are ranked such that true metabolite-spectrum matches receive the highest scores. Machine-learning methods have been widely incorporated into database-search-based identification tools and have substantially improved performance. To further improve identification accuracy, we propose a new framework for generating negative training samples. The framework first uses autoencoders to learn latent representations of metabolite structures and MS/MS spectra, thereby recasting metabolite-spectrum matching as matching between latent vectors. It then uses a GAN to generate latent vectors of decoy metabolites and constructs decoy metabolite-spectrum matches as negative samples for training. Experimental results show that our tool, MS2MetGAN, achieves better overall performance than existing metabolite identification methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13342 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MS2MetGAN: Latent-space adversarial training for metabolite-spectrum matching in MS/MS database search Tsai, Meng Dwyer, Alexzander Nuckels, Estelle Wang, Yingfeng Machine Learning Information Retrieval Quantitative Methods Database search is a widely used approach for identifying metabolites from tandem mass spectra (MS/MS). In this strategy, an experimental spectrum is matched against a user-specified database of candidate metabolites, and candidates are ranked such that true metabolite-spectrum matches receive the highest scores. Machine-learning methods have been widely incorporated into database-search-based identification tools and have substantially improved performance. To further improve identification accuracy, we propose a new framework for generating negative training samples. The framework first uses autoencoders to learn latent representations of metabolite structures and MS/MS spectra, thereby recasting metabolite-spectrum matching as matching between latent vectors. It then uses a GAN to generate latent vectors of decoy metabolites and constructs decoy metabolite-spectrum matches as negative samples for training. Experimental results show that our tool, MS2MetGAN, achieves better overall performance than existing metabolite identification methods. |
| title | MS2MetGAN: Latent-space adversarial training for metabolite-spectrum matching in MS/MS database search |
| topic | Machine Learning Information Retrieval Quantitative Methods |
| url | https://arxiv.org/abs/2603.13342 |