DeepNMR: Unleashing the full potential of NMR spectroscopy with artificial intelligence and deep learning

核磁共振波谱在材料科学、化学、结构生物学和临床诊断中普遍存在。在化学合成中，化合物的鉴定和表征依赖于核磁共振和生物科学中的核磁共振，它提供了对功能运动和具有原子分辨率的非共价相互作用的前所未有的洞察。然而，核磁共振谱的分析，特别是生物分子核磁共振谱，仍然在很大程度上依赖于经过多年培训的专家的解释。更重要的是，开发核磁共振方法以实现新的应用依赖于经过数十年培训和卓越直觉的专家。这些限制意味着核磁共振作为化学、生物化学和医学工具的全部潜力还远远没有达到。拟议的研究将通过将人工智能(AI)与核磁共振数据分析和新核磁共振方法的开发完全结合起来，解决生物分子核磁共振的这一抑制约束。利用有监督的深度学习，将发展深度神经网络(DNN)来分析复杂的生物分子核磁共振谱。DNN的分析是稳健的，一旦DNN被训练，它不需要优化处理参数。因此，DNN可以很容易地集成到自动化数据处理管道中。强化深度学习将被用于设计智能机器，为下一代核磁共振方法提供支持。有了这些工具，科学家可以简单地要求智能机器得出一种方法和分析工具，以表征所讨论的大分子的一组特定参数或功能。能够将人工智能与核磁共振完全集成，并同时开发核磁共振和人工智能作为一个工具，这是一个高风险，但一旦成功，将释放当前和未来核磁共振硬件的巨大潜力，为材料科学、生物化学和医学等领域的广泛分子提供前所未有的见解。

Nuclear Magnetic Resonance (NMR) spectroscopy is ubiquitous in material science, chemistry, structural biology, and clinicaldiagnosis. In chemical synthesis, the identification and characterisation of compounds hinge on NMR and in bioscience NMR providesunprecedented insight into functional motions and on non-covalent interactions with atomic resolution. However, the analysis ofNMR spectra, in particular biomolecular NMR spectra, still largely depend on interpretations by specialists with years of training. Evenmore so, the development of NMR methods to allow for new applications relies on specialists with decades of training and excellentintuition. These constraints have meant that the full potential of NMR as a tool in chemistry, biochemistry, and medicine, is far frombeing reached. The proposed research will address this inhibitory constrain of biomolecular NMR by fully integrating artificialintelligence (AI) with the analysis of NMR data and with the development of new NMR methods. Using supervised deep learning,deep neural networks (DNNs) will be developed to analyse complex biomolecular NMR spectra. Analysis with DNNs is robust andonce the DNN is trained, it does not require an optimisation of processing parameters. The DNNs can therefore easily be integratedinto automated data-processing pipelines. Reinforcement deep learning will be employed to design intelligent machines that providethe next generations of NMR methods. With these tools, the scientist can simply request the intelligent machine to derive a methodand an analysis tool to characterise a specific set of parameters or functions of the macromolecule in question. Being able to fullyintegrate AI with NMR, and concomitantly develop NMR and AI as one tool, is high-risk, but once successful will unleash the immensepotential of current and future NMR hardware to provide unprecedented insights into a broad range of molecules, in material science,in biochemistry, and in medicine.