Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2508.04180 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918181319213056 |
|---|---|
| author | Neo, Neng Kai Nigel Jing, Lim Preston, Ngoui Yong Zhau Serene, Koh Xue Ting Shen, Bingquan |
| author_facet | Neo, Neng Kai Nigel Jing, Lim Preston, Ngoui Yong Zhau Serene, Koh Xue Ting Shen, Bingquan |
| contents | A common approach to the de novo molecular generation problem from mass spectra involves a two-stage pipeline: (1) encoding mass spectra into molecular fingerprints, followed by (2) decoding these fingerprints into molecular structures. In our work, we adopt MIST (Goldman et. al., 2023) as the encoder and MolForge (Ucak et. al., 2023) as the decoder, leveraging additional training data to enhance performance. We also threshold the probabilities of each fingerprint bit to focus on the presence of substructures. This results in a tenfold improvement over previous state-of-the-art methods, generating top-1 31% / top-10 40% of molecular structures correctly from mass spectra in MassSpecGym (Bushuiev et. al., 2024). We position this as a strong baseline for future research in de novo molecule elucidation from mass spectra. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04180 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | One Small Step with Fingerprints, One Giant Leap for De Novo Molecule Generation from Mass Spectra Neo, Neng Kai Nigel Jing, Lim Preston, Ngoui Yong Zhau Serene, Koh Xue Ting Shen, Bingquan Machine Learning A common approach to the de novo molecular generation problem from mass spectra involves a two-stage pipeline: (1) encoding mass spectra into molecular fingerprints, followed by (2) decoding these fingerprints into molecular structures. In our work, we adopt MIST (Goldman et. al., 2023) as the encoder and MolForge (Ucak et. al., 2023) as the decoder, leveraging additional training data to enhance performance. We also threshold the probabilities of each fingerprint bit to focus on the presence of substructures. This results in a tenfold improvement over previous state-of-the-art methods, generating top-1 31% / top-10 40% of molecular structures correctly from mass spectra in MassSpecGym (Bushuiev et. al., 2024). We position this as a strong baseline for future research in de novo molecule elucidation from mass spectra. |
| title | One Small Step with Fingerprints, One Giant Leap for De Novo Molecule Generation from Mass Spectra |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.04180 |