OpenMM: Scalable biomolecular modeling, simulation, and machine learning

OpenMM：可扩展的生物分子建模、模拟和机器学习

• 批准号: 10441130
• 负责人: Thomas Edward Markland
• 金额: $ 47.19万
• 依托单位: STANFORD UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-01 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10441130
• 关键词: Academia; Architecture; Automobile Driving; Binding; Biological; Biological Process; Biological Response Modifier Therapy; Biology; Chemical Models; Chemicals; Chemistry; Code; Communities; Computer Vision Systems; Custom; Data; Data Set; Development; Disease; Ecosystem; Ensure; Event; Free Energy; Funding; Future; Goals; Home; Hybrids; Industry; Investigation; Investments; Laboratories; Learning; Libraries; Ligands; Machine Learning; Methods; Modeling; Modernization; Molecular; Molecular Conformation; Performance; Plug-in; Productivity; Proteins; Pythons; Research; Research Personnel; Running; Sampling; Science; Speed; Standardization; Structure; Study models; Sustainable Development; System; Technology; TensorFlow; Training; United States National Institutes of Health; Update; Work; cluster computing; deep learning; deep neural network; drug development; enzyme mechanism; flexibility; insight; interoperability; machine learning framework; machine learning model; model development; models and simulation; molecular mechanics; next generation; novel therapeutics; open source; operation; physical model; predictive modeling; protein data bank; quantum; repository; simulation; small molecule; small molecule therapeutics; software infrastructure; tool

PROJECT SUMMARY / ABSTRACT OpenMM [http://openmm.org] is the most widely-used open source GPU-accelerated framework for biomolecular modeling and simulation (>1300 citations, >270,000 downloads, >1M deployed instances). Its Python API makes it widely popular as both an application (for modelers) and a library (for developers), while its C/C++/Fortran bindings enable major legacy simulation packages to use OpenMM to provide high performance on modern hardware. OpenMM has been used for probing biological questions that leverage the $14B global investment in structural data from the PDB at multiple scales, from detailed studies of single disease proteins to superfamily-wide modeling studies and large-scale drug development efforts in industry and academia. Originally developed with NIH funding by the Pande lab at Stanford, we aim to fully transition toward a community governance and sustainable development model and extend its capabilities to ensure OpenMM can power the next decade of biomolecular research. To fully exploit the revolution in QM-level accuracy with machine-learning (ML) potentials, we will add plug-in support for ML models augmented by GPU-accelerated kernels, enabling transformative science with QM-level accuracy. To enable high-productivity development of new ML models with training dataset sizes approaching 100 million molecules, we will develop a Python framework to enable OpenMM to be easily used within modern ML frameworks such as TensorFlow and PyTorch. Together with continued optimizations to exploit inexpensive GPUs, these advances will power a transformation within biomolecular modeling and simulation, much as deep learning has transformed computer vision.

项目总结/摘要 OpenMM [http://openmm.org]是最广泛使用的开源GPU加速框架，用于生物分子 建模和仿真（>1300次引用，> 270，000次下载，> 1 M部署实例）。它的Python API使 它作为一个应用程序（对于建模者）和一个库（对于开发者）广泛流行，而它的C/C++/Fortran 绑定使主要的遗留仿真包能够使用OpenMM， 硬件. OpenMM已被用于探索生物学问题，这些问题利用了全球140亿美元的投资， PDB在多个尺度上的结构数据，从单个疾病蛋白的详细研究到整个超家族 在工业界和学术界开展建模研究和大规模药物开发工作。 最初由斯坦福大学的Pande实验室在NIH的资助下开发，我们的目标是完全过渡到一个社区 管理和可持续发展模式，并扩展其能力，以确保OpenMM能够为 生物分子研究的未来十年通过机器学习充分利用QM级精度的革命 (ML)潜力，我们将添加插件支持由GPU加速内核增强的ML模型， 具有QM级精度的变革性科学。为了实现新ML模型的高生产力开发， 训练数据集大小接近1亿个分子，我们将开发一个Python框架来支持OpenMM 可以在现代ML框架（如TensorFlow和PyTorch）中轻松使用。加上持续 优化利用廉价的GPU，这些进步将推动生物分子内的转变 建模和仿真，就像深度学习改变了计算机视觉一样。