印象第二代 - 准确,快速和通用的神经网络模型,用于预测NMR参数,而不是DFT
Calvin Yiu1, Ben Honoré1, Will Gerrard1
1School of Chemistry, University of Bristol UK Craig.Butts@Bristol.ac.uk.
Chemical science
|April 14, 2025
概括
IMPRESSION-G2是一种新型的神经网络,从3D结构中快速预测多个核磁共振 (NMR) 参数,比密度函数理论 (DFT) 等传统方法提供了显著的加速. 这种进步加速了对广泛的有机分子的分子结构和动态分析.
科学领域:
- 计算化学的计算化学
- 分子建模分子建模
- 频谱学是一种光谱学.
背景情况:
- 准确预测3D感知核磁共振 (NMR) 特性对于确定溶液中的分子结构和动态至关重要.
- 目前的预测工具是有限的,量子化学方法 (例如密度函数理论/DFT) 是缓慢的,而经验或机器学习方法通常只能在有限的化学空间中预测单个参数.
研究的目的:
- 推出IMPRESSION-Generation 2 (G2),一个基于变压器的神经网络,旨在快速,同时预测多个NMR参数.
- 为涉及NMR参数预测的计算工作流提供一个明显更快的替代高级DFT计算.
主要方法:
- 开发一个基于变压器的神经网络IMPRESSION-G2.
- 从3D分子结构同时预测所有NMR化学转移和标量合 (1H,13C,15N,19F最多4个键) 的情况.
- 与快速的GFN2-xTB几何优化集成,用于生成输入的3D结构.
主要成果:
- 对于成千上万个NMR参数,IMPRESSION-G2的预测时间为每分子<50毫秒,比DFT的速度增加了约10^6倍.
- 完整的工作流 (GFN2-xTB + IMPRESSION-G2) 的速度是基于DFT的工作流的10^3-10^4倍.
- 实现了与DFT相似的高精度,对1H化学转移 (~0.07 ppm),13C化学转移 (~0.8 ppm) 和3JHH标量合 (<0.15 Hz) 在广的化学空间 (高达~1000 g mol-1) 实现了特定误差.
- 在独立的测试数据和DFT几乎无法区分的结果上证明了概括性,与对5000个化合物的实验性NMR数据相比.
结论:
- IMPRESSION-G2为预测3D感知NMR参数提供了一个高度准确和数量级更快的DFT替代方案.
- 与GFN-xTB相结合的IMPRESSION-G2的速度和准确性,使其能够在训练化学空间内的许多NMR预测应用中作为DFT的直接替代品.
相关概念视频
¹H NMR: Interpreting Distorted and Overlapping Signals
937
Spin systems where the difference in chemical shifts of the coupled nuclei is greater than ten times J are called first-order spin systems. These nuclei are weakly coupled, and their chemical shifts and coupling constant can generally be estimated from the well-separated signals in the spectrum.
As Δν decreases and the signals move closer, the doublets appear increasingly distorted. The intensities of the inner lines increase at the cost of those of the outer lines as the signals are...
As Δν decreases and the signals move closer, the doublets appear increasingly distorted. The intensities of the inner lines increase at the cost of those of the outer lines as the signals are...
937
Two-Dimensional (2D) NMR: Overview
573
The 1D NMR spectrum of large and complex molecules like natural products has complicated splitting patterns and overlapping signals, which can be easily interpreted using 2-dimensional (2D) NMR. Unlike 1D NMR, 2D NMR has two frequency axes that provide the coupling information between the nucleus A and nucleus B in a molecule. The process from which 2D spectra are obtained has four steps.
The first step is the preparation period, during which nucleus A is excited with a radiofrequency pulse....
The first step is the preparation period, during which nucleus A is excited with a radiofrequency pulse....
573
Interpreting ¹H NMR Signal Splitting: The (n + 1) Rule
1.1K
In the AX proton spin system, proton A can sense the two spin states of a coupled proton X, resulting in a doublet NMR signal with two peaks of equal (1:1) intensity. When proton A is coupled to two equivalent protons (AX2 spin system), the spin states of each X can be aligned with or against the external field, creating three possible scenarios. This results in a 1:2:1 triplet signal, where the central peak corresponds to the chemical shift of A and is twice as large or intense as the...
1.1K
¹H NMR of Labile Protons: Deuterium (²H) Substitution
826
This lesson illustrates the role of deuterium substitution in simplifying the NMR spectrum of compounds comprising labile protons. One method employed is the use of deuterium. Amongst the three isotopes of hydrogen, deuterium (2H) has a nucleus composed of one proton and one neutron. When the D2O solvent is added to a pure dry ethanol solution, its labile proton is substituted with deuterium.
826
NMR Spectrometers: Resolution and Error Correction
603
When magnetic nuclei in a sample achieve resonance and undergo relaxation, the signal detected in NMR is an approximately exponential free induction decay. Fourier transform of an exponential decay yields a Lorentzian peak in the frequency domain. Lorentzian peaks in an NMR spectrum are defined by their amplitude, full width at half maximum, and position, where the peak width is governed by the spin-spin relaxation time alone. In real experiments, however, the applied magnetic field is rendered...
603
¹³C NMR: ¹H–¹³C Decoupling
961
The probability of having two carbon-13 atoms next to each other is negligible because of the low natural abundance of carbon-13. Consequently, peak splitting due to carbon-carbon spin-spin coupling is not observed in spectra. However, protons up to three sigma bonds away split the carbon signal according to the n+1 rule, resulting in complicated spectra.
A broadband decoupling technique is used to simplify these complex, sometimes overlapping, signals. Broadband decoupling relies on a...
A broadband decoupling technique is used to simplify these complex, sometimes overlapping, signals. Broadband decoupling relies on a...
961


