Huawu Yang
Huawu Yang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Bo Kong
Technology Center, China Tobacco Hunan Industrial Co., Ltd., Changsha 410014, China
1 shared publication - Hongmei Lu
Central South University
1 shared publication Jianfu Liu
1 shared publicationJinyun Liu
1 shared publicationKejun Zhong
Hunan Tobacco Ind Co Ltd, Changsha 410014, Hunan, Peoples R China
1 shared publication- Shaoqi Wang
College of Chemistry and Chemical Engineering, Central South University, Changsha 410083, China
1 shared publication
Latest Publications
- Open Access
Deep Learning-Based Method for Compound Identification in NMR Spectra of Mixtures
Nuclear magnetic resonance (NMR) spectroscopy is highly unbiased and reproducible, which provides us a powerful tool to analyze mixtures consisting of small molecules. However, the compound identification in NMR spectra of mixtures is highly challenging because of chemical shift variations of the same compound in different mixtures and peak overlapping among molecules. Here, we present a pseudo-Siamese convolutional neural network method (pSCNN) to identify compounds in mixtures for NMR spectroscopy. A data augmentation method was implemented for the superposition of several NMR spectra sampled from a spectral database with random noises. The augmented dataset was split and used to train, validate and test the pSCNN model. Two experimental NMR datasets (flavor mixtures and additional flavor mixture) were acquired to benchmark its performance in real applications. The results show that the proposed method can achieve good performances in the augmented test set (ACC = 99.80%, TPR = 99.70% and FPR = 0.10%), the flavor mixtures dataset (ACC = 97.62%, TPR = 96.44% and FPR = 2.29%) and the additional flavor mixture dataset (ACC = 91.67%, TPR = 100.00% and FPR = 10.53%). We have demonstrated that the translational invariance of convolutional neural networks can solve the chemical shift variation problem in NMR spectra. In summary, pSCNN is an off-the-shelf method to identify compounds in mixtures for NMR spectroscopy because of its accuracy in compound identification and robustness to chemical shift variation.
Open AccessDeep Learning-Based Method for Compound Identification in NMR Spectra of Mixtures
Nuclear magnetic resonance (NMR) spectroscopy is highly unbiased and reproducible, which provides us a powerful tool to analyze mixtures consisting of small molecules. However, the compound identification in NMR spectra of mixtures is highly challenging because of chemical shift variations of the same compound in different mixtures and peak overlapping among molecules. Here, we present a pseudo-Siamese convolutional neural network method (pSCNN) to identify compounds in mixtures for NMR spectroscopy. A data augmentation method was implemented for the superposition of several NMR spectra sampled from a spectral database with random noises. The augmented dataset was split and used to train, validate and test the pSCNN model. Two experimental NMR datasets (flavor mixtures and additional flavor mixture) were acquired to benchmark its performance in real applications. The results show that the proposed method can achieve good performances in the augmented test set (ACC = 99.80%, TPR = 99.70% and FPR = 0.10%), the flavor mixtures dataset (ACC = 97.62%, TPR = 96.44% and FPR = 2.29%) and the additional flavor mixture dataset (ACC = 91.67%, TPR = 100.00% and FPR = 10.53%). We have demonstrated that the translational invariance of convolutional neural networks can solve the chemical shift variation problem in NMR spectra. In summary, pSCNN is an off-the-shelf method to identify compounds in mixtures for NMR spectroscopy because of its accuracy in compound identification and robustness to chemical shift variation.
- 8 August 2018
- Published by China Science Publishing & Media Ltd. in Chinese Journal of Chromatography
- Vol. 36 (8) , 772-779
Gas chromatography-mass spectrometry data analysis algorithm based on sparse model and its application in resolving severely overlapped peaks
A Gas chromatography-mass spectrometry (GC-MS) data analysis algorithm is proposed. The mass spectrum at the top of the chromatographic peak is the spectrum to be solved. A certain amount of related reference spectra is retrieved from the spectral library, then, the equation of the chromatographic response value of each pure component is solved. A step by step strategy is used for the mass spectra retrieval. Firstly, an efficient indexing technology is used for rough selection, then, the "strong peak out with high probability" and the "extrusion" rules are used to exclude more unrelated mass spectra. A regression algorithm based on a sparse model is proposed to solve the equation of the chromatographic response value. Compared with the traditional algorithm, this algorithm can extract the main structure of the spectrum to be solved, and avoid over-fitting. The experimental results show that the proposed algorithm has a higher accuracy and smaller residual reference spectrum set, and the sparse model achieves satisfactory experimental results in the analysis of severely overlapped peaks. The proposed method provides an effective solution for resolving overlapped peaks, especially severely overlapped peaks, in GC-MS data.
- 8 August 2018
- Published by China Science Publishing & Media Ltd. in Chinese Journal of Chromatography
- Vol. 36 (8) , 772-779
Gas chromatography-mass spectrometry data analysis algorithm based on sparse model and its application in resolving severely overlapped peaks
A Gas chromatography-mass spectrometry (GC-MS) data analysis algorithm is proposed. The mass spectrum at the top of the chromatographic peak is the spectrum to be solved. A certain amount of related reference spectra is retrieved from the spectral library, then, the equation of the chromatographic response value of each pure component is solved. A step by step strategy is used for the mass spectra retrieval. Firstly, an efficient indexing technology is used for rough selection, then, the "strong peak out with high probability" and the "extrusion" rules are used to exclude more unrelated mass spectra. A regression algorithm based on a sparse model is proposed to solve the equation of the chromatographic response value. Compared with the traditional algorithm, this algorithm can extract the main structure of the spectrum to be solved, and avoid over-fitting. The experimental results show that the proposed algorithm has a higher accuracy and smaller residual reference spectrum set, and the sparse model achieves satisfactory experimental results in the analysis of severely overlapped peaks. The proposed method provides an effective solution for resolving overlapped peaks, especially severely overlapped peaks, in GC-MS data.