Leap: molecular synthesisability scoring with intermediates
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929312395952128 |
|---|---|
| author | Calvi, Antonia Gaudin, Théophile Miketa, Dominik Sydow, Dominique Wilbraham, Liam |
| author_facet | Calvi, Antonia Gaudin, Théophile Miketa, Dominik Sydow, Dominique Wilbraham, Liam |
| contents | Assessing whether a molecule can be synthesised is a primary task in drug discovery. It enables computational chemists to filter for viable compounds or bias molecular generative models. The notion of synthesisability is dynamic as it evolves depending on the availability of key compounds. A common approach in drug discovery involves exploring the chemical space surrounding synthetically-accessible intermediates. This strategy improves the synthesisability of the derived molecules due to the availability of key intermediates. Existing synthesisability scoring methods such as SAScore, SCScore and RAScore, cannot condition on intermediates dynamically. Our approach, Leap, is a GPT-2 model trained on the depth, or longest linear path, of predicted synthesis routes that allows information on the availability of key intermediates to be included at inference time. We show that Leap surpasses all other scoring methods by at least 5% on AUC score when identifying synthesisable molecules, and can successfully adapt predicted scores when presented with a relevant intermediate compound. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13005 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leap: molecular synthesisability scoring with intermediates Calvi, Antonia Gaudin, Théophile Miketa, Dominik Sydow, Dominique Wilbraham, Liam Biomolecules Machine Learning Chemical Physics Assessing whether a molecule can be synthesised is a primary task in drug discovery. It enables computational chemists to filter for viable compounds or bias molecular generative models. The notion of synthesisability is dynamic as it evolves depending on the availability of key compounds. A common approach in drug discovery involves exploring the chemical space surrounding synthetically-accessible intermediates. This strategy improves the synthesisability of the derived molecules due to the availability of key intermediates. Existing synthesisability scoring methods such as SAScore, SCScore and RAScore, cannot condition on intermediates dynamically. Our approach, Leap, is a GPT-2 model trained on the depth, or longest linear path, of predicted synthesis routes that allows information on the availability of key intermediates to be included at inference time. We show that Leap surpasses all other scoring methods by at least 5% on AUC score when identifying synthesisable molecules, and can successfully adapt predicted scores when presented with a relevant intermediate compound. |
| title | Leap: molecular synthesisability scoring with intermediates |
| topic | Biomolecules Machine Learning Chemical Physics |
| url | https://arxiv.org/abs/2403.13005 |