Abstract
Mass spectrometry (MS) is a powerful tool for analyzing small molecules in complex samples, yet accurate structure elucidation from spectral data remains challenging. We present a Transformer-based model for de novo molecular generation, named MoleNovo, which directly predicts SMILES strings from MS spectra. MoleNovo employs a tailored embedding strategy for both mass-to-charge ratio (m/z) and intensity values within a sequence-to-sequence architecture. Evaluated on the NIST20 dataset, MoleNovo outperforms existing models such as Spec2Mol and MS2Mol across multiple metrics, including BLEU score, Levenshtein distance, fingerprint similarity, and chemical validity. These results underscore the potential of Transformer architectures for scalable, automated compound identification in metabolomics and drug discovery.
| Original language | English |
|---|---|
| Title of host publication | Advanced Data Mining and Applications - 21st International Conference, ADMA 2025, Proceedings |
| Editors | Masatoshi Yoshikawa, Xiaofeng Meng, Yang Cao, Chuan Xiao, Weitong Chen, Yanda Wang |
| Place of Publication | Singapore Singapore |
| Publisher | Springer |
| Pages | 97-111 |
| Number of pages | 15 |
| ISBN (Electronic) | 9789819534593 |
| ISBN (Print) | 9789819534586 |
| DOIs | |
| Publication status | Published - 2026 |
| Event | International Conference on Advanced Data Mining and Applications 2025 - Kyoto, Japan Duration: 22 Oct 2025 → 24 Oct 2025 Conference number: 21st https://link.springer.com/book/10.1007/978-981-95-3456-2 (Proceedings) https://adma2025.github.io/ (Website) |
Publication series
| Name | Lecture Notes in Computer Science |
|---|---|
| Publisher | Springer |
| Volume | 16199 |
| ISSN (Print) | 0302-9743 |
| ISSN (Electronic) | 1611-3349 |
Conference
| Conference | International Conference on Advanced Data Mining and Applications 2025 |
|---|---|
| Abbreviated title | ADMA 2025 |
| Country/Territory | Japan |
| City | Kyoto |
| Period | 22/10/25 → 24/10/25 |
| Internet address |
|
Keywords
- De Novo Molecular Generation
- Mass Spectrometry
- SMILES
- Transformer
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver