Deep Learning and Mass Spectrum Based Analysis of Vocs Components
1. School of Environmental and Chemical Engineering, Shanghai University, Shanghai 200444, China
2. China Petroleum University (Beijing), Beijing 102200, China
3. Zhuhai Comleader Information Science & Technology Co. Ltd., Zhuhai 519060, China
| Abstract: | The composition and concentration of Volatile Organic Compounds (VOCs) in the atmosphere can reflect the quality of the air, and the environmental quality changes with the quantity of these compounds. When unknown VOCs are encountered, researchers usually use gas chromatography-mass spectrometry (GC-MS) to measure and analyze them. This discriminative mode requires data analysts with a certain theoretical and practical foundation, is demanding and labor-intensive, and may also introduce errors due to the numerous steps. In order to solve these problems, we propose a deep learning and mass spectrum based method for the analysis of Vocs components. Using the deep learning technique, first, a high-quality mass spectral library is constructed as a reference library using molecular fingerprint information, and then, the sample data obtained in the GC-MS gas chromatography-mass spectrometer is preprocessed with data to extract mass spectra that can represent the VOCs components; finally, the selected candidate mass spectra are library matched with the reference library to return high matching VOCs components results. The experimental results show that the method can accurately and quickly discriminate the components of VOCs. |
| Keywords: | Volatile Organic Compounds; Deep Learning; Mass Spectrum; Molecular Fingerprint; Library Matching |
| DOI: | 10.57237/j.wjese.2023.02.006 |
View:
Downloads:
Received: 11 July 2023
Accepted: 1 September 2023
Published Online: 8 September 2023
References
| [1] | Simayi M, Shi Y, Xi Z, et al. Emission trends of industrial VOCs in China since the clean air action and future reduction perspectives [J]. Science of The Total Environment, 2022, 826: 153994. |
| [2] | Gallego E, Roca F J, Perales J F, et al. Characterization and determination of the odorous charge in the indoor air of a waste treatment facility through the evaluation of volatile organic compounds (VOCs) using TD–GC/MS [J]. Waste management, 2012, 32 (12): 2469-2481. |
| [3] | Wu W, Xue W, Zheng Y, et al. Diurnal regulation of VOCs may not be effective in controlling ozone pollution in China [J]. Atmospheric Environment, 2021, 256: 118442. |
| [4] | Maung T Z, Bishop J E, Holt E, et al. Indoor air pollution and the health of vulnerable groups: a systematic review focused on particulate matter (PM), volatile organic compounds (VOCs) and their effects on children and people with pre-existing lung disease [J]. International Journal of Environmental Research and Public Health, 2022, 19 (14): 8752. |
| [5] | Dong S, Wang P, Abbas K. A survey on deep learning and its applications [J]. Computer Science Review, 2021, 40: 100379. |
| [6] | Li X, Peng L, Hu Y, et al. Deep learning architecture for air quality predictions [J]. Environmental Science and Pollution Research, 2016, 23 (22): 22408-22417. |
| [7] | Zhang Z, Zeng Y, Yan K. A hybrid deep learning technology for PM2.5 air quality forecasting [J]. Environmental Science and Pollution Research, 2021, 28 (29): 39409-39422. |
| [8] | Willett P. Similarity searching using 2D structural fingerprints [J]. Chemoinformatics and computational chemical biology, 2011: 133-158. |
| [9] | Murray M. Sampling bias in the molecular epidemiology of tuberculosis [J]. Emerging infectious diseases, 2002, 8 (4): 363. |
| [10] | Xue L, Bajorath J. Molecular descriptors in chemoinformatics, computational combinatorial chemistry, and virtual screening [J]. Combinatorial chemistry & high throughput screening, 2000, 3 (5): 363-372. |
| [11] | Duch W, Swaminathan K, Meller J. Artificial intelligence approaches for rational drug design and discovery [J]. Current pharmaceutical design, 2007, 13 (14): 1497-1508. |
| [12] | Yang J, Cai Y, Zhao K, et al. Concepts and applications of chemical fingerprint for hit and lead screening [J]. Drug Discovery Today, 2022: 103356. |
| [13] | Yang W, Hu J, Stojmenovic M. NDTC: A novel topology-based fingerprint matching algorithm using N-layer Delaunay triangulation net check [C] // 2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA). IEEE, 2012: 866-870. |
| [14] | Schietgat L, Cuissart B, Lepailleur A, et al. Comparing chemical fingerprints for ecotoxicology [J]. Proceedings of the 6ièmes Journées Nationales de Chémoinformatique, 2013: 20-21. |
| [15] | Glen R C, Bender A, Arnby C H, et al. Circular fingerprints: flexible molecular descriptors with applications from physical chemistry to ADME [J]. IDrugs, 2006, 9 (3): 199. |
| [16] | Li S, Zhang L, Feng H, et al. MutagenPred-GCNNs: a graph convolutional neural network-based classification model for mutagenicity prediction with data-driven molecular fingerprints [J]. Interdisciplinary Sciences: Computational Life Sciences, 2021, 13: 25-33. |
| [17] | Butina D. Unsupervised data base clustering based on daylight's fingerprint and Tanimoto similarity: A fast and automated way to cluster small and large data sets [J]. Journal of Chemical Information and Computer Sciences, 1999, 39 (4): 747-750. |
| [18] | Muegge I, Mukherjee P. An overview of molecular fingerprint similarity search in virtual screening [J]. Expert opinion on drug discovery, 2016, 11 (2): 137-148. |
| [19] | Weininger D. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules [J]. Journal of chemical information and computer sciences, 1988, 28 (1): 31-36. |
| [20] | Heller S, McNaught A, Stein S, et al. InChI-the worldwide chemical structure identifier standard [J]. Journal of cheminformatics, 2013, 5 (1): 1-9. |
| [21] | Rogers D, Hahn M. Extended-connectivity fingerprints [J]. Journal of chemical information and modeling, 2010, 50 (5): 742-754. |
| [22] | Kuzminykh D, Polykovskiy D, Kadurin A, et al. 3D molecular representations based on the wave transform for convolutional neural networks [J]. Molecular pharmaceutics, 2018, 15 (10): 4378-4385. |
| [23] | Bento A P, Hersey A, Félix E, et al. An open source chemical structure curation pipeline using RDKit [J]. Journal of Cheminformatics, 2020, 12: 1-16. |
| [24] | De Hoffmann E, Stroobant V. Mass spectrometry: principles and applications [M]. John Wiley & Sons, 2007. |
| [25] | Wei JN, Belanger D, Adams RP, Sculley D. Rapid Prediction of Electron-Ionization Mass Spectrometry Using Neural Networks. ACS Cent Sci. 2019 Apr 24; 5 (4): 700-708. doi: 10.1021/acscentsci.9b00085. Epub 2019 Mar 19. PMID: 31041390; PMCID: PMC6487538. |
| [26] | Liu Z, Shen Z, Li S, et al. How do adam and training strategies help bnns optimization [C]//International Conference on Machine Learning. PMLR, 2021: 6936-6946. |
| [27] | Huber F, van der Burg S, van der Hooft J J J, et al. MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra [J]. Journal of cheminformatics, 2021, 13 (1): 1-14. |
| [28] | Smolinska A, Hauschild A C, Fijten R R R, et al. Current breathomics—a review on data pre-processing techniques and machine learning in metabolomics breath analysis [J]. Journal of breath research, 2014, 8 (2): 027105. |
| [29] | Bader S. Identification and quantification of peaks in spectrometric data [J]. Technical University of Dortmund: Dortmund, Germany, 2008. |
| [30] | Bunkowski A. MCC-IMS data analysis using automated spectra processing and explorative visualisation methods [D]. Universitätsbibliothek Bielefeld, Hochschulschriften, 2012. |
| [31] | Gemperline P J, Cash E. Advantages of soft versus hard constraints in self-modeling curve resolution problems. Alternating least squares with penalty functions [J]. Analytical Chemistry, 2003, 75 (16): 4236-4243. |
| [32] | Morháč M. An algorithm for determination of peak regions and baseline elimination in spectroscopic data [J]. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2009, 600 (2): 478-487. |
| [33] | Statham P J. Deconvolution and background subtraction by least-squares fitting with prefiltering of spectra [J]. Analytical Chemistry, 1977, 49 (14): 2149-2154. |
| [34] | Melnikov A D, Tsentalovich Y P, Yanshole V V. Deep learning for the precise peak detection in high-resolution LC–MS data [J]. Analytical chemistry, 2019, 92 (1): 588-592. |
| [35] | Lemmon E W, Huber M L, McLinden M O. NIST standard reference database 23 [J]. Reference fluid thermodynamic and transport properties (REFPROP), version, 2010, 9. |
| [36] | Wang M, Carver J J, Phelan V V, et al. Sharing and community curation of mass spectrometry data with Global Natural Products Social Molecular Networking [J]. Nature biotechnology, 2016, 34 (8): 828-837. |
| [37] | Montgomery D C, Peck E A, Vining G G. Introduction to linear regression analysis [M]. John Wiley & Sons, 2021. |
| [38] | Timofeev R. Classification and regression trees (CART) theory and applications [J]. Humboldt University, Berlin, 2004, 54. |
| [39] | Zhu Y, Lesch A, Li X, et al. Rapid Noninvasive Skin Monitoring by Surface Mass Recording and Data Learning [J]. Jacs Au, 2021, 1 (5): 598-611. |
| [40] | Huber F, Ridder L, Verhoeven S, et al. Spec2Vec: Improved mass spectral similarity scoring through learning of structural relationships [J]. PLoS computational biology, 2021, 17 (2): e1008724. |
Join the Editorial Board
We invite active, qualified and high profile scientists and researchers to join as Editorial Board Members.
Join UsBecome a Reviewer
Scholars with a strong interest in reviewing are invited to join the reviewer panel to ensure the quality of the research to be published.
Join Us