Deep Learning-Based Sensor Array: 3D Fluorescence Spectra of Gold Nanoclusters for Qualitative and Quantitative Analysis of Vitamin B6 Derivatives,Analytical Chemistry

当前位置： X-MOL 学术 › Anal. Chem. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Deep Learning-Based Sensor Array: 3D Fluorescence Spectra of Gold Nanoclusters for Qualitative and Quantitative Analysis of Vitamin B6 Derivatives
Analytical Chemistry ( IF 6.7 ) Pub Date : 2022-06-18 , DOI: 10.1021/acs.analchem.2c00655
Hamada A A Noreldeen _{1,

2} , Kai-Yuan Huang ₁ , Gang-Wei Wu ₃ , Hua-Ping Peng ₁ , Hao-Hua Deng ₁ , Wei Chen ₁

Affiliation

Vitamin B₆ derivatives (VB6Ds) are of great importance for all living organisms to complete their physiological processes. However, their excess in the body can cause serious problems. What is more, the qualitative and quantitative analysis of different VB6Ds may present significant challenges due to the high similarity of their chemical structures. Also, the transfer of deep learning model from one task to a similar task needs to be present more in the fluorescence-based biosensor. Therefore, to address these problems, two deep learning models based on the intrinsic fingerprint of 3D fluorescence spectra have been developed to identify five VB6Ds. The accuracy ranges of a deep neural network (DNN) and a convolutional neural network (CNN) were 94.44–97.77% and 97.77–100%, respectively. After that, the developed models were transferred for quantitative analysis of the selected VB6Ds at a broad concentration range (1–100 μM). The determination coefficient (R²) values of the test set for DNN and CNN were 93.28 and 97.01%, respectively, which also represents the outperformance of CNN over DNN. Therefore, our approach opens new avenues for qualitative and quantitative sensing of small molecules, which will enrich fields related to deep learning, analytical chemistry, and especially sensor array chemistry.

中文翻译：

基于深度学习的传感器阵列：用于维生素 B6 衍生物定性和定量分析的金纳米簇的 3D 荧光光谱

维生素 B ₆衍生物（VB6Ds）对于所有生物体完成其生理过程非常重要。然而，它们在体内的过量会导致严重的问题。更重要的是，由于其化学结构的高度相似性，不同 VB6D 的定性和定量分析可能会面临重大挑战。此外，深度学习模型从一项任务到类似任务的转移需要更多地出现在基于荧光的生物传感器中。因此，为了解决这些问题，已经开发了两个基于 3D 荧光光谱固有指纹的深度学习模型来识别五个 VB6D。深度神经网络 (DNN) 和卷积神经网络 (CNN) 的准确度范围分别为 94.44-97.77% 和 97.77-100%。在那之后，将开发的模型用于在宽浓度范围（1-100 μM）下对选定的 VB6D 进行定量分析。决定系数 (R ² ) DNN 和 CNN 测试集的值分别为 93.28 和 97.01%，这也代表了 CNN 优于 DNN。因此，我们的方法为小分子的定性和定量传感开辟了新途径，这将丰富与深度学习、分析化学，尤其是传感器阵列化学相关的领域。

更新日期：2022-06-18

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11