1
|
Yang Y, Sun S, Yang S, Yang Q, Lu X, Wang X, Yu Q, Huo X, Qian X. Structural annotation of unknown molecules in a miniaturized mass spectrometer based on a transformer enabled fragment tree method. Commun Chem 2024; 7:109. [PMID: 38740942 DOI: 10.1038/s42004-024-01189-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2023] [Accepted: 04/26/2024] [Indexed: 05/16/2024] Open
Abstract
Structural annotation of small molecules in tandem mass spectrometry has always been a central challenge in mass spectrometry analysis, especially using a miniaturized mass spectrometer for on-site testing. Here, we propose the Transformer enabled Fragment Tree (TeFT) method, which combines various types of fragmentation tree models and a deep learning Transformer module. It is aimed to generate the specific structure of molecules de novo solely from mass spectrometry spectra. The evaluation results on different open-source databases indicated that the proposed model achieved remarkable results in that the majority of molecular structures of compounds in the test can be successfully recognized. Also, the TeFT has been validated on a miniaturized mass spectrometer with low-resolution spectra for 16 flavonoid alcohols, achieving complete structure prediction for 8 substances. Finally, TeFT confirmed the structure of the compound contained in a Chinese medicine substance called the Anweiyang capsule. These results indicate that the TeFT method is suitable for annotating fragmentation peaks with clear fragmentation rules, particularly when applied to on-site mass spectrometry with lower mass resolution.
Collapse
Affiliation(s)
- Yiming Yang
- Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, China
| | - Shuang Sun
- Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, China
| | - Shuyuan Yang
- Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, China
| | - Qin Yang
- Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, China
| | - Xinqiong Lu
- CHIN Instrument (Hefei) Co., Ltd., Hefei, 231200, China
| | - Xiaohao Wang
- Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, China
| | - Quan Yu
- Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, China
| | - Xinming Huo
- Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province, School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, 518107, China.
| | - Xiang Qian
- Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, China.
| |
Collapse
|
2
|
Jiao Q, Cai B, Liu M, Dong L, Hei M, Kong L, Zhao Y. A three-stage deep learning-based training frame for spectra baseline correction. ANALYTICAL METHODS : ADVANCING METHODS AND APPLICATIONS 2024; 16:1496-1507. [PMID: 38372130 DOI: 10.1039/d3ay02062b] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/20/2024]
Abstract
For spectrometers, baseline drift seriously affects the measurement and quantitative analysis of spectral data. Deep learning has recently emerged as a powerful method for baseline correction. However, the dependence on vast amounts of paired data and the difficulty in obtaining spectral data limit the performance and development of deep learning-based methods. Therefore, we solve these problems from the network architecture and training framework. For the network architecture, a Learned Feature Fusion (LFF) module is designed to improve the performance of U-net, and a three-stage training frame is proposed to train this network. Specifically, the LFF module is designed to adaptively integrate features from different scales, greatly improving the performance of U-net. For the training frame, stage 1 uses airPLS to ameliorate the problem of vast amounts of paired data, stage 2 uses synthetic spectra to further ease reliance on real spectra, and stage 3 uses contrastive learning to reduce the gap between synthesized and real spectra. The experiments show that the proposed method is a powerful tool for baseline correction and possesses potential for application in spectral quantitative analysis.
Collapse
Affiliation(s)
- Qingliang Jiao
- Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China.
- Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, Zhejiang, 314019, China
| | - Boyong Cai
- Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China.
- Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, Zhejiang, 314019, China
| | - Ming Liu
- Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China.
- Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, Zhejiang, 314019, China
| | - Liquan Dong
- Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China.
- Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, Zhejiang, 314019, China
| | - Mei Hei
- Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China.
- Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, Zhejiang, 314019, China
| | - Lingqin Kong
- Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China.
- Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, Zhejiang, 314019, China
| | - Yuejin Zhao
- Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China.
- Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, Zhejiang, 314019, China
| |
Collapse
|
3
|
Zhang Y, Wang Y. Recent trends of machine learning applied to multi-source data of medicinal plants. J Pharm Anal 2023; 13:1388-1407. [PMID: 38223450 PMCID: PMC10785154 DOI: 10.1016/j.jpha.2023.07.012] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2023] [Revised: 07/17/2023] [Accepted: 07/19/2023] [Indexed: 01/16/2024] Open
Abstract
In traditional medicine and ethnomedicine, medicinal plants have long been recognized as the basis for materials in therapeutic applications worldwide. In particular, the remarkable curative effect of traditional Chinese medicine during corona virus disease 2019 (COVID-19) pandemic has attracted extensive attention globally. Medicinal plants have, therefore, become increasingly popular among the public. However, with increasing demand for and profit with medicinal plants, commercial fraudulent events such as adulteration or counterfeits sometimes occur, which poses a serious threat to the clinical outcomes and interests of consumers. With rapid advances in artificial intelligence, machine learning can be used to mine information on various medicinal plants to establish an ideal resource database. We herein present a review that mainly introduces common machine learning algorithms and discusses their application in multi-source data analysis of medicinal plants. The combination of machine learning algorithms and multi-source data analysis facilitates a comprehensive analysis and aids in the effective evaluation of the quality of medicinal plants. The findings of this review provide new possibilities for promoting the development and utilization of medicinal plants.
Collapse
Affiliation(s)
- Yanying Zhang
- Medicinal Plants Research Institute, Yunnan Academy of Agricultural Sciences, Kunming, 650200, China
- College of Traditional Chinese Medicine, Yunnan University of Chinese Medicine, Kunming, 650500, China
| | - Yuanzhong Wang
- Medicinal Plants Research Institute, Yunnan Academy of Agricultural Sciences, Kunming, 650200, China
| |
Collapse
|
4
|
Yang Z, Arakawa H. A double sliding-window method for baseline correction and noise estimation for Raman spectra of microplastics. MARINE POLLUTION BULLETIN 2023; 190:114887. [PMID: 37023548 DOI: 10.1016/j.marpolbul.2023.114887] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/10/2023] [Revised: 03/19/2023] [Accepted: 03/24/2023] [Indexed: 06/19/2023]
Abstract
When measuring microplastics of environmental samples, additives and attachment of biological materials may result in strong fluorescence in Raman spectra, which increases difficulty for imaging, identification, and quantification. Although there are several baseline correction methods available, user intervention is usually needed, which is not feasible for automated processes. In current study, a double sliding-window (DSW) method was proposed to estimate the baseline and standard deviation of noise. Simulated spectra and experimental spectra were used to evaluate the performance in comparison with two popular and widely used methods. Validation with simulated spectra and spectra of environmental samples showed that DSW method can accurately estimate the standard deviation of spectral noise. DSW method also showed better performance than compared methods when handling spectra of low signal-to-noise ratio (SNR) and elevated baselines. Therefore, DSW method is a useful approach for preprocessing Raman spectra of environmental samples and automated processes.
Collapse
Affiliation(s)
- Zijiang Yang
- Tokyo University of Marine Science and Technology, Konan 4-5-7, Minato-Ku, Tokyo 108-8477, Japan.
| | - Hisayuki Arakawa
- Tokyo University of Marine Science and Technology, Konan 4-5-7, Minato-Ku, Tokyo 108-8477, Japan.
| |
Collapse
|
5
|
Shi W, Huo X, Ding X, Zhu P, Wan Y, Lu X, Feng R, Yu Q, Wang X. Rapid screening of illegally added drugs in functional food using a miniature ion trap mass spectrometer. Food Chem 2022; 386:132808. [PMID: 35364493 DOI: 10.1016/j.foodchem.2022.132808] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2021] [Revised: 03/22/2022] [Accepted: 03/23/2022] [Indexed: 11/04/2022]
Abstract
With the expansion of the functional food market, the qualification assessment of these products has become a major challenge, and efficient analytical tools are urgently needed. Here, a miniature mass spectrometer (MS) with self-aspiration capillary electrospray ionization (SACESI) source and ion trap analyzer was developed for rapid screening of various illegally added drugs in functional foods. No chromatographic separation was required, but a simplified two-step pretreatment method was developed to reduce the operational procedures and time consumption of the entire analysis. SACESI source uses capillary action to drive solution injection, which utilizes a simple structure and convenient operation to constitute a kind of disposable MS detection solution. To achieve accurate and automatic identification, an intelligent recognition algorithm with steps of spectrum preprocessing, characteristic peak matching, and support vector machine learning was constructed. The relative accuracy of rapid screening of 31 suspicious drugs in various samples is up to 99.78%. It achieves 100% correct identification for the 55 batches of actual samples captured by on-site inspection, which demonstrates the feasibility of the proposed analytical system and strategy in food safety applications.
Collapse
Affiliation(s)
- Wenyan Shi
- Division of Advanced Manufacturing, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China; State Key Laboratory of Precision Measurement Technology and Instruments, Department of Precision Instrument, Tsinghua University, Beijing 100084, China
| | - Xinming Huo
- School of Biomedical Engineering, Sun Yat-sen University, Shenzhen 518107, China.
| | - Xinyue Ding
- Division of Advanced Manufacturing, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China
| | - Peiyuan Zhu
- Shenzhen Han Industrial Technologies Co.Ltd., Shenzhen 518055, China
| | - Yutong Wan
- Shenzhen Chin Instrument Co., Ltd., Shenzhen 518055, China
| | - Xinqiong Lu
- Shenzhen Chin Instrument Co., Ltd., Shenzhen 518055, China
| | - Rui Feng
- Research Institute for Frontier Science, Beihang University, Beijing 100191, China
| | - Quan Yu
- Division of Advanced Manufacturing, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China.
| | - Xiaohao Wang
- Division of Advanced Manufacturing, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China; State Key Laboratory of Precision Measurement Technology and Instruments, Department of Precision Instrument, Tsinghua University, Beijing 100084, China
| |
Collapse
|
6
|
Li F, Wang C, Zhang Y, He X, Zhang C, Sha F. Accurate Concentration Measurement Model of Multicomponent Mixed Gases during a Mine Disaster Period. ACS OMEGA 2022; 7:25443-25457. [PMID: 35910180 PMCID: PMC9330090 DOI: 10.1021/acsomega.2c02391] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/17/2022] [Accepted: 07/04/2022] [Indexed: 06/15/2023]
Abstract
A variety of gaseous products are formed when mine fires and coal and gas outbursts occur in mines. On the one hand, these gas products affect the normal production of mines and the occupational health of miners; on the other hand, the gaseous products can also provide much important information to prevent mine disasters. Thus, the rapid and accurate determination of the component content of multicomponent mixed gases is of great significance. However, the distortion of gas chromatography measurement results, which deviate from the true values, has a serious impact on gas composition determination in mines. To reduce the influence of distortion, an Agilent 490 portable gas chromatograph is used to measure the component content of 11 groups of standard multicomponent mixed gases. It is found that the error rate of the measured result is highly related to the concentration of the selected reference component and the component to be measured. Besides, the key point of each gas concentration is determined according to the scatter diagram of the error rate. Each gas is divided into a high and a low concentration group by the key points, and each gas is selected as the reference component to measure the corresponding component concentration in other gases with multiple-point external standards. Researchers have used the least-squares method to fit univariate linear regression analysis between the measured values and true values of mixed gases. Then, the optimal analysis function and the optimal reference component concentration of each gas can be determined by comparing the regression analysis parameters. Finally, it is found that the error rate of measured values corrected by the optimal analysis function is significantly reduced. It is proved that this method can effectively alleviate the measurement results' distortion, which solves the problem of gas composition determination in underground areas.
Collapse
Affiliation(s)
- Feng Li
- School
of Emergency Management and Safety Engineering, China University of Mining and Technology (Beijing), No. 11, Xueyuan Road, Haidian District, Beijing 100083, China
| | - Chenchen Wang
- School
of Emergency Management and Safety Engineering, China University of Mining and Technology (Beijing), No. 11, Xueyuan Road, Haidian District, Beijing 100083, China
| | - Yue Zhang
- CNOOC
Energy Development Co., Ltd., Beijing 100028, China
| | - Xiaoxuan He
- School
of Emergency Management and Safety Engineering, China University of Mining and Technology (Beijing), No. 11, Xueyuan Road, Haidian District, Beijing 100083, China
| | - Chenyu Zhang
- School
of Emergency Management and Safety Engineering, China University of Mining and Technology (Beijing), No. 11, Xueyuan Road, Haidian District, Beijing 100083, China
| | - Fangfei Sha
- Xuchang
Cigarette Factory of China Tobacco Tenants Industrial Co., Ltd., Xuchang 461001, Henan, China
| |
Collapse
|
7
|
Wang HP, Chen P, Dai JW, Liu D, Li JY, Xu YP, Chu XL. Recent advances of chemometric calibration methods in modern spectroscopy: Algorithms, strategy, and related issues. Trends Analyt Chem 2022. [DOI: 10.1016/j.trac.2022.116648] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
|
8
|
Chen Z, Fu J, Peng Y, Chen T, Zhang L, Yuan C. Baseline Correction of Acceleration Data Based on a Hybrid EMD-DNN Method. SENSORS 2021; 21:s21186283. [PMID: 34577490 PMCID: PMC8473153 DOI: 10.3390/s21186283] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/10/2021] [Revised: 09/15/2021] [Accepted: 09/15/2021] [Indexed: 11/16/2022]
Abstract
Measuring displacement response is essential in the field of structural health monitoring and seismic engineering. Numerical integration of the acceleration signal is a common measurement method of displacement data. However, due to the circumstances of ground tilt, low-frequency noise caused by instruments, hysteresis of the transducer, etc., it would generate a baseline drift phenomenon in acceleration integration, failing to obtain an actual displacement response. The improved traditional baseline correction methods still have some problems, such as high baseline correction error, poor adaptability, and narrow application scope. This paper proposes a deep neural network model based on empirical mode decomposition (EMD–DNN) to solve baseline correction by removing the drifting trend. The feature of multiple time sequences that EMD obtains is extracted via DNN, achieving the real displacement time history of prediction. In order to verify the effectiveness of the proposed method, two natural waves (EL centro wave, Taft wave) and one Artificial wave are selected to test in a shaking table test. Comparing the traditional methods such as the least squares method, EMD, and DNN method, EMD–DNN has the best baseline correction effect in terms of the evaluation indexes: Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and degree of fit (R-Square).
Collapse
Affiliation(s)
- Zengshun Chen
- Institute of Engineering Mechanics, China Earthquake Administration, Harbin 061019, China;
- School of Civil Engineering, Chongqing University, Chongqing 400045, China; (J.F.); (C.Y.)
| | - Jun Fu
- School of Civil Engineering, Chongqing University, Chongqing 400045, China; (J.F.); (C.Y.)
| | - Yanjian Peng
- Research and Development Center, Gas & Power Group, CNOOC, Beijing 100028, China; (Y.P.); (T.C.)
| | - Tuanhai Chen
- Research and Development Center, Gas & Power Group, CNOOC, Beijing 100028, China; (Y.P.); (T.C.)
| | - LiKai Zhang
- School of Civil Engineering, Chongqing University, Chongqing 400045, China; (J.F.); (C.Y.)
- Correspondence:
| | - Chenfeng Yuan
- School of Civil Engineering, Chongqing University, Chongqing 400045, China; (J.F.); (C.Y.)
| |
Collapse
|