一个深度学习模型,用于高效的新精神活性物质的非目标查,使用桌面核磁共振设备
Pengfei Liu1, Wei Jia2, Cuimei Liu2
1School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong 510006, China.
Analytical chemistry
|December 10, 2025
概括
一个新的深度学习模型,NMR4NPScreen,使用基准核磁共振 (NMR) 数据准确检测新的精神活性物质 (NPS). 这项技术增强了非法毒品贩运的实时选,即使在复杂的混合物中.
科学领域:
- 分析化学 分析化学
- 计算化学计算化学
- 法医科学 法医科学 法医科学
背景情况:
- 桌面核磁共振 (NMR) 设备提供快速的现场检测新精神活性物质 (NPS),对于打击非法毒品贩运至关重要.
- 基准NMR的低信号噪声比率和有限的数据集挑战了准确的识别,特别是在复杂的混合物中.
- 传统的机器学习模型在NPS检测的低信号对噪声条件下表现不佳.
研究的目的:
- 开发一种深度学习模型,用于使用基准NMR数据对NPS进行非有针对性的查.
- 提高NPS检测在具有挑战性的低信号对噪声环境中的准确性和稳定性.
- 加强执法和海关的实时选能力.
主要方法:
- 提出了NMR4NPScreen,这是一个具有道注意力增强架构的深度学习模型.
- 实施了基于化学的预处理和对比预训练,将NMR光谱与SMILES表示对齐.
- 利用基准NMR数据进行模型的训练和验证.
主要成果:
- 在分类九个不同的NPS类别中获得了94.8%的准确性,超过了传统的机器学习方法.
- 在复杂的混合物中检测NPS方面表现出高度的稳定性.
- 在低信号对噪声条件下成功增强了光谱特征提取.
结论:
- NMR4NPScreen有效地克服了用于NPS检测的基准NMR数据的局限性.
- 该模型的性能为基于NMR的药物查中先进的神经网络应用铺平了道路.
- 这一进步显著提高了移动检查站和海关的实时NPS检测能力.
相关概念视频
Applications Of NMR In Biology
4.4K
Nuclear magnetic resonance (NMR) spectroscopy is a very valuable analytical technique for researchers. It has been used for more than 50 years as an analytical tool. F. Bloch and E. Purcell formulated NMR in 1946 and won the 1952 Nobel Prize in Physics for their work. Biological macromolecules such as proteins, nucleic acids, lipids, and organic molecules including pharmaceutical compounds, can be studied using this versatile tool that exploits the magnetic properties of certain nuclei.
4.4K
Nuclear Magnetic Resonance (NMR): Overview
6.6K
Nuclear magnetic resonance (NMR) is a phenomenon exhibited by certain nuclei that can absorb characteristic radio frequency radiation under certain conditions. NMR has been extensively applied in molecular spectroscopy and medical diagnostic imaging. In both these applications, the molecule or subject under study is placed in a magnetic field and irradiated with radio frequency energy.
NMR spectroscopy generates a spectrum where the characteristic absorption frequencies of the sample are...
NMR spectroscopy generates a spectrum where the characteristic absorption frequencies of the sample are...
6.6K


