分子结构与振动光谱之间的双向翻译深度学习
Tianqing Hu1,2, Zihan Zou1, Bo Li2
1State Key Laboratory of Precision and Intelligent Chemistry, University of Science and Technology of China, Hefei, Anhui 230026, China.
深度学习模型TranSpec和SpecGNN将分子光谱转化为结构. 增强了从光谱数据中解释功能组和异构体的准确性.
科学领域:
- 计算化学
- 光谱学
- 人工智能
背景情况:
- 分子振动谱和简化分子输入线输入系统 (SMILES) 对于化学识别至关重要.
- 建立这两个代表之间的直接,双向联系仍然是一个挑战.
- 现有的方法往往缺乏光谱解释的准确性或效率.
研究的目的:
- 开发深度学习模型用于分子光谱和SMILES表示之间的翻译.
- 通过人工智能提高光谱解释的准确性和效率.
- 从光谱数据中识别功能组和区分异构体和同类物.
主要方法:
- 开发两个深度学习模型:TranSpec和SpecGNN.
- 实施包括模型融合,转移学习和多源学习在内的技术.
- 数据集的增加和分子质量过的应用.
- 使用SpecGNN进行光谱模拟和候选物重新排序.
主要成果:
- 对于计算的光谱,TranSpec的初始精度达到55-63%,但对于实验性IR数据,精度下降到11%.
- 改进的方法提高了实验IR数据的TranSpec准确度,达到53.6%.
- 与传统量子化学方法相比,SpecGNN显示出更高的光谱精度和计算效率.
- 成功识别功能组并区分异构体/同类物.
结论:
- TranSpec和SpecGNN为分子结构和光谱解释提供了一个高效准确的AI驱动框架.
- 这些模型可用于光谱学和化学信息学.
- 开发的模型为从光谱数据中阐明化学结构提供了强大的工具.
更多相关视频
08:54Vibrational Spectra of a N719-Chromophore/Titania Interface from Empirical-Potential Molecular-Dynamics Simulation, Solvated by a Room Temperature Ionic Liquid
Published on: January 25, 2020
09:43Interfacial Molecular-level Structures of Polymers and Biomacromolecules Revealed via Sum Frequency Generation Vibrational Spectroscopy
Published on: August 13, 2019
相关概念视频
UV–Vis Spectroscopy: Molecular Electronic Transitions
Molecular Spectroscopy: Absorption and Emission
IR Spectroscopy: Molecular Vibration Overview
Stretching vibrations are vibrational motions that occur along the bond line, changing the bond length or distance between two bonded atoms. They are further distinguished as symmetric or asymmetric. In symmetric stretching, the...
IR Spectroscopy: Hooke's Law Approximation of Molecular Vibration
According to Hooke's law, the vibrational frequency is directly proportional to...
UV–Vis Spectroscopy of Conjugated Systems
One of the factors influencing λmax is the extent...
Predicting Molecular Geometry
