FREED++: Improving RL Agents for Fragment-Based Molecule Generation by Thorough Reproduction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910300863725568 |
|---|---|
| author | Telepov, Alexander Tsypin, Artem Khrabrov, Kuzma Yakukhnov, Sergey Strashnov, Pavel Zhilyaev, Petr Rumiantsev, Egor Ezhov, Daniel Avetisian, Manvel Popova, Olga Kadurin, Artur |
| author_facet | Telepov, Alexander Tsypin, Artem Khrabrov, Kuzma Yakukhnov, Sergey Strashnov, Pavel Zhilyaev, Petr Rumiantsev, Egor Ezhov, Daniel Avetisian, Manvel Popova, Olga Kadurin, Artur |
| contents | A rational design of new therapeutic drugs aims to find a molecular structure with desired biological functionality, e.g., an ability to activate or suppress a specific protein via binding to it. Molecular docking is a common technique for evaluating protein-molecule interactions. Recently, Reinforcement Learning (RL) has emerged as a promising approach to generating molecules with the docking score (DS) as a reward. In this work, we reproduce, scrutinize and improve the recent RL model for molecule generation called FREED (arXiv:2110.01219). Extensive evaluation of the proposed method reveals several limitations and challenges despite the outstanding results reported for three target proteins. Our contributions include fixing numerous implementation bugs and simplifying the model while increasing its quality, significantly extending experiments, and conducting an accurate comparison with current state-of-the-art methods for protein-conditioned molecule generation. We show that the resulting fixed model is capable of producing molecules with superior docking scores compared to alternative approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_09840 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FREED++: Improving RL Agents for Fragment-Based Molecule Generation by Thorough Reproduction Telepov, Alexander Tsypin, Artem Khrabrov, Kuzma Yakukhnov, Sergey Strashnov, Pavel Zhilyaev, Petr Rumiantsev, Egor Ezhov, Daniel Avetisian, Manvel Popova, Olga Kadurin, Artur Biomolecules Machine Learning A rational design of new therapeutic drugs aims to find a molecular structure with desired biological functionality, e.g., an ability to activate or suppress a specific protein via binding to it. Molecular docking is a common technique for evaluating protein-molecule interactions. Recently, Reinforcement Learning (RL) has emerged as a promising approach to generating molecules with the docking score (DS) as a reward. In this work, we reproduce, scrutinize and improve the recent RL model for molecule generation called FREED (arXiv:2110.01219). Extensive evaluation of the proposed method reveals several limitations and challenges despite the outstanding results reported for three target proteins. Our contributions include fixing numerous implementation bugs and simplifying the model while increasing its quality, significantly extending experiments, and conducting an accurate comparison with current state-of-the-art methods for protein-conditioned molecule generation. We show that the resulting fixed model is capable of producing molecules with superior docking scores compared to alternative approaches. |
| title | FREED++: Improving RL Agents for Fragment-Based Molecule Generation by Thorough Reproduction |
| topic | Biomolecules Machine Learning |
| url | https://arxiv.org/abs/2401.09840 |