Gradual Optimization Learning for Conformational Energy Minimization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914710320840704 |
|---|---|
| author | Tsypin, Artem Ugadiarov, Leonid Khrabrov, Kuzma Telepov, Alexander Rumiantsev, Egor Skrynnik, Alexey Panov, Aleksandr I. Vetrov, Dmitry Tutubalina, Elena Kadurin, Artur |
| author_facet | Tsypin, Artem Ugadiarov, Leonid Khrabrov, Kuzma Telepov, Alexander Rumiantsev, Egor Skrynnik, Alexey Panov, Aleksandr I. Vetrov, Dmitry Tutubalina, Elena Kadurin, Artur |
| contents | Molecular conformation optimization is crucial to computer-aided drug discovery and materials design. Traditional energy minimization techniques rely on iterative optimization methods that use molecular forces calculated by a physical simulator (oracle) as anti-gradients. However, this is a computationally expensive approach that requires many interactions with a physical simulator. One way to accelerate this procedure is to replace the physical simulator with a neural network. Despite recent progress in neural networks for molecular conformation energy prediction, such models are prone to distribution shift, leading to inaccurate energy minimization. We find that the quality of energy minimization with neural networks can be improved by providing optimization trajectories as additional training data. Still, it takes around $5 \times 10^5$ additional conformations to match the physical simulator's optimization quality. In this work, we present the Gradual Optimization Learning Framework (GOLF) for energy minimization with neural networks that significantly reduces the required additional data. The framework consists of an efficient data-collecting scheme and an external optimizer. The external optimizer utilizes gradients from the energy prediction model to generate optimization trajectories, and the data-collecting scheme selects additional training data to be processed by the physical simulator. Our results demonstrate that the neural network trained with GOLF performs on par with the oracle on a benchmark of diverse drug-like molecules using $50$x less additional data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_06295 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Gradual Optimization Learning for Conformational Energy Minimization Tsypin, Artem Ugadiarov, Leonid Khrabrov, Kuzma Telepov, Alexander Rumiantsev, Egor Skrynnik, Alexey Panov, Aleksandr I. Vetrov, Dmitry Tutubalina, Elena Kadurin, Artur Chemical Physics Machine Learning Molecular conformation optimization is crucial to computer-aided drug discovery and materials design. Traditional energy minimization techniques rely on iterative optimization methods that use molecular forces calculated by a physical simulator (oracle) as anti-gradients. However, this is a computationally expensive approach that requires many interactions with a physical simulator. One way to accelerate this procedure is to replace the physical simulator with a neural network. Despite recent progress in neural networks for molecular conformation energy prediction, such models are prone to distribution shift, leading to inaccurate energy minimization. We find that the quality of energy minimization with neural networks can be improved by providing optimization trajectories as additional training data. Still, it takes around $5 \times 10^5$ additional conformations to match the physical simulator's optimization quality. In this work, we present the Gradual Optimization Learning Framework (GOLF) for energy minimization with neural networks that significantly reduces the required additional data. The framework consists of an efficient data-collecting scheme and an external optimizer. The external optimizer utilizes gradients from the energy prediction model to generate optimization trajectories, and the data-collecting scheme selects additional training data to be processed by the physical simulator. Our results demonstrate that the neural network trained with GOLF performs on par with the oracle on a benchmark of diverse drug-like molecules using $50$x less additional data. |
| title | Gradual Optimization Learning for Conformational Energy Minimization |
| topic | Chemical Physics Machine Learning |
| url | https://arxiv.org/abs/2311.06295 |