1
|
Chowdhury MAZ, Rice TE, Oehlschlaeger MA. TSMC-Net: Deep-Learning Multigas Classification Using THz Absorption Spectra. ACS Sens 2023; 8:1230-1240. [PMID: 36815833 DOI: 10.1021/acssensors.2c02615] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/24/2023]
Abstract
The identification of gas mixture speciation from a complex multicomponent absorption spectrum is a problem in gas sensing that can be addressed using machine-learning approaches. Here, we report on a deep convolutional neural network for multigas classification using terahertz (THz) absorption spectra, THz spectra mixture classifier network or TSMC-Net. TSMC-Net has been developed to identify eight volatile organic compounds in mixtures based on their fingerprint rotational absorption spectra in the 220-330 GHz frequency range. A data set consisting of simulated absorption spectra for randomly generated mixtures, with absorption greater than thresholds representing detectable limits and annotated with multiple labels, was prepared for model development. The supervised multilabel classification problem, i.e., the identification of individual gases in a mixture, is converted to a supervised multiclass classification problem via label powerset conversion. The trained model is validated and tested against simulated spectra for gas mixtures, with and without white Gaussian noise. The trained model exhibits high precision, recall, and accuracy for each pure compound. Class activation maps illustrate the complex decision-making process of the model and highlight relevant frequency regions that are needed to identify unique mixtures. Finally, the model was demonstrated against measured THz absorption spectra for pure species and mixtures, acquired using a microelectronics-based THz absorption spectrometer. The data set generation strategy and deep convolutional neural network approach are generalized and can be extrapolated to other spectroscopy types, frequency ranges, and sensors.
Collapse
Affiliation(s)
- M Arshad Zahangir Chowdhury
- Department of Mechanical, Aerospace and Nuclear Engineering, Rensselaer Polytechnic Institute, Troy, New York 12180-3522, United States
| | - Timothy E Rice
- Department of Mechanical, Aerospace and Nuclear Engineering, Rensselaer Polytechnic Institute, Troy, New York 12180-3522, United States
| | - Matthew A Oehlschlaeger
- Department of Mechanical, Aerospace and Nuclear Engineering, Rensselaer Polytechnic Institute, Troy, New York 12180-3522, United States
| |
Collapse
|
2
|
Kopriva I, Jerić I, Hadžija MP, Hadžija M, Lovrenčić MV, Brkljačić L. Library-assisted nonlinear blind separation and annotation of pure components from a single 1H nuclear magnetic resonance mixture spectra. Anal Chim Acta 2019; 1080:55-65. [PMID: 31409475 DOI: 10.1016/j.aca.2019.07.004] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2019] [Revised: 06/27/2019] [Accepted: 07/02/2019] [Indexed: 01/07/2023]
Abstract
Due to its capability for high-throughput screening 1H nuclear magnetic resonance (NMR) spectroscopy is commonly used for metabolite research. The key problem in 1H NMR spectroscopy of multicomponent mixtures is overlapping of component signals and that is increasing with the number of components, their complexity and structural similarity. It makes metabolic profiling, that is carried out through matching acquired spectra with metabolites from the library, a hard problem. Here, we propose a method for nonlinear blind separation of highly correlated components spectra from a single 1H NMR mixture spectra. The method transforms a single nonlinear mixture into multiple high-dimensional reproducible kernel Hilbert Spaces (mRKHSs). Therein, highly correlated components are separated by sparseness constrained nonnegative matrix factorization in each induced RKHS. Afterwards, metabolites are identified through comparison of separated components with the library comprised of 160 pure components. Thereby, a significant number of them are expected to be related with diabetes type 2. Conceptually similar methodology for nonlinear blind separation of correlated components from two or more mixtures is presented in the Supplementary material. Single-mixture blind source separation is exemplified on: (i) annotation of five components spectra separated from one 1H NMR model mixture spectra; (ii) annotation of fifty five metabolites separated from one 1H NMR mixture spectra of urine of subjects with and without diabetes type 2. Arguably, it is for the first time a method for blind separation of a large number of components from a single nonlinear mixture has been proposed. Moreover, the proposed method pinpoints urinary creatine, glutamic acid and 5-hydroxyindoleacetic acid as the most prominent metabolites in samples from subjects with diabetes type 2, when compared to healthy controls.
Collapse
Affiliation(s)
- Ivica Kopriva
- Division of Electronics, Ruđer Bošković Institute, Bijenička cesta 54, HR-10000, Zagreb, Croatia.
| | - Ivanka Jerić
- Division of Organic Chemistry and Biochemistry, Ruđer Bošković Institute, Bijenička cesta 54, HR-10000, Zagreb, Croatia
| | - Marijana Popović Hadžija
- Division of Molecular Medicine, Ruđer Bošković Institute, Bijenička cesta 54, HR-10000, Zagreb, Croatia
| | - Mirko Hadžija
- Division of Molecular Medicine, Ruđer Bošković Institute, Bijenička cesta 54, HR-10000, Zagreb, Croatia
| | - Marijana Vučić Lovrenčić
- Department of Medical Biochemistry and Laboratory Medicine, University Hospital Merkur, Zajčeva 19, HR-10000, Zagreb, Croatia
| | - Lidija Brkljačić
- Division of Organic Chemistry and Biochemistry, Ruđer Bošković Institute, Bijenička cesta 54, HR-10000, Zagreb, Croatia
| |
Collapse
|
3
|
Baikadi A, Bhatt N, Narasimhan S. Extraction of Pure Species Spectra from Labeled Mixture Spectral Data. Ind Eng Chem Res 2019. [DOI: 10.1021/acs.iecr.9b00437] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
4
|
Yang R, Zhao N, Xiao X, Zhu W, Chen Y, Yin G, Liu J, Liu W. Underdetermined blind separation of three-way fluorescence spectra of PAHs in water. SPECTROCHIMICA ACTA. PART A, MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 2018; 199:80-85. [PMID: 29573698 DOI: 10.1016/j.saa.2018.03.046] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/08/2017] [Revised: 02/27/2018] [Accepted: 03/12/2018] [Indexed: 06/08/2023]
Abstract
In this work, underdetermined blind decomposition method is developed to recognize individual components from the three-way fluorescent spectra of their mixtures by using sparse component analysis (SCA). The mixing matrix is estimated from the mixtures using fuzzy data clustering algorithm together with the scatters corresponding to local energy maximum value in the time-frequency domain, and the spectra of object components are recovered by pseudo inverse technique. As an example, using this method three and four pure components spectra can be blindly extracted from two samples of their mixture, with similarities between resolved and reference spectra all above 0.80. This work opens a new and effective path to realize monitoring PAHs in water by three-way fluorescence spectroscopy technique.
Collapse
Affiliation(s)
- Ruifang Yang
- Key Laboratory of Environment Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China.
| | - Nanjing Zhao
- Key Laboratory of Environment Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
| | - Xue Xiao
- Key Laboratory of Environment Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
| | - Wei Zhu
- Key Laboratory of Environment Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
| | - Yunan Chen
- Key Laboratory of Environment Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
| | - Gaofang Yin
- Key Laboratory of Environment Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
| | - Jianguo Liu
- Key Laboratory of Environment Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
| | - Wenqing Liu
- Key Laboratory of Environment Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
| |
Collapse
|
5
|
Ievlev AV, Belianinov A, Jesse S, Allison DP, Doktycz MJ, Retterer ST, Kalinin SV, Ovchinnikova OS. Automated Interpretation and Extraction of Topographic Information from Time of Flight Secondary Ion Mass Spectrometry Data. Sci Rep 2017; 7:17099. [PMID: 29213083 PMCID: PMC5719033 DOI: 10.1038/s41598-017-17049-y] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2017] [Accepted: 11/07/2017] [Indexed: 11/26/2022] Open
Abstract
Time of flight secondary ion mass spectrometry (ToF-SIMS) is a powerful surface-sensitive characterization tool allowing the imaging of chemical properties over a wide range of organic and inorganic material systems. This technique allows precise studies of chemical composition with sub-100-nm lateral and nanometer depth spatial resolution. However, comprehensive interpretation of ToF-SIMS results is challenging because of the very large data volume and high dimensionality. Furthermore, investigation of samples with pronounced topographical features is complicated by systematic and measureable shifts in the mass spectrum. In this work we developed an approach for the interpretation of the ToF-SIMS data, based on the advanced data analytics. Along with characterization of the chemical composition, our approach allows extraction of the sample surface morphology from a time of flight registration technique. This approach allows one to perform correlated investigations of surface morphology, biological function, and chemical composition of Arabidopsis roots.
Collapse
Affiliation(s)
- Anton V Ievlev
- The Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA.
- Institute for Functional Imaging of Materials, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA.
| | - Alexei Belianinov
- The Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
- Institute for Functional Imaging of Materials, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
| | - Stephen Jesse
- The Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
- Institute for Functional Imaging of Materials, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
| | - David P Allison
- Biosciences Division, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
- Department Biochemistry & Cellular & Molecular Biology, University of Tennessee, Knoxville, Tennessee, USA
| | - Mitchel J Doktycz
- The Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
- Biosciences Division, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
| | - Scott T Retterer
- The Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
- Biosciences Division, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
| | - Sergei V Kalinin
- The Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
- Institute for Functional Imaging of Materials, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
| | - Olga S Ovchinnikova
- The Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
- Institute for Functional Imaging of Materials, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37831, USA
| |
Collapse
|
6
|
Kopriva I, Filipović M. A mixture model with a reference-based automatic selection of components for disease classification from protein and/or gene expression levels. BMC Bioinformatics 2011; 12:496. [PMID: 22208882 PMCID: PMC3292585 DOI: 10.1186/1471-2105-12-496] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2011] [Accepted: 12/30/2011] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Bioinformatics data analysis is often using linear mixture model representing samples as additive mixture of components. Properly constrained blind matrix factorization methods extract those components using mixture samples only. However, automatic selection of extracted components to be retained for classification analysis remains an open issue. RESULTS The method proposed here is applied to well-studied protein and genomic datasets of ovarian, prostate and colon cancers to extract components for disease prediction. It achieves average sensitivities of: 96.2 (sd = 2.7%), 97.6% (sd = 2.8%) and 90.8% (sd = 5.5%) and average specificities of: 93.6% (sd = 4.1%), 99% (sd = 2.2%) and 79.4% (sd = 9.8%) in 100 independent two-fold cross-validations. CONCLUSIONS We propose an additive mixture model of a sample for feature extraction using, in principle, sparseness constrained factorization on a sample-by-sample basis. As opposed to that, existing methods factorize complete dataset simultaneously. The sample model is composed of a reference sample representing control and/or case (disease) groups and a test sample. Each sample is decomposed into two or more components that are selected automatically (without using label information) as control specific, case specific and not differentially expressed (neutral). The number of components is determined by cross-validation. Automatic assignment of features (m/z ratios or genes) to particular component is based on thresholds estimated from each sample directly. Due to the locality of decomposition, the strength of the expression of each feature across the samples can vary. Yet, they will still be allocated to the related disease and/or control specific component. Since label information is not used in the selection process, case and control specific components can be used for classification. That is not the case with standard factorization methods. Moreover, the component selected by proposed method as disease specific can be interpreted as a sub-mode and retained for further analysis to identify potential biomarkers. As opposed to standard matrix factorization methods this can be achieved on a sample (experiment)-by-sample basis. Postulating one or more components with indifferent features enables their removal from disease and control specific components on a sample-by-sample basis. This yields selected components with reduced complexity and generally, it increases prediction accuracy.
Collapse
Affiliation(s)
- Ivica Kopriva
- Division of Laser and Atomic R&D, Ruđer Bošković Institute, Bijenička cesta 54, 10000 Zagreb, Croatia.
| | | |
Collapse
|
7
|
Affiliation(s)
- Barry Lavine
- Department of Chemistry, Oklahoma State University, Stillwater, Oklahoma 74078, USA
| | | |
Collapse
|
8
|
Kopriva I, Jerić I. Blind Separation of Analytes in Nuclear Magnetic Resonance Spectroscopy and Mass Spectrometry: Sparseness-Based Robust Multicomponent Analysis. Anal Chem 2010; 82:1911-20. [DOI: 10.1021/ac902640y] [Citation(s) in RCA: 12] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Ivica Kopriva
- Division of Laser and Atomic Research and Development and Division of Organic Chemistry and Biochemistry, Ruđer Bošković Institute, Bijenička cesta 54, HR-10000, Zagreb, Croatia
| | - Ivanka Jerić
- Division of Laser and Atomic Research and Development and Division of Organic Chemistry and Biochemistry, Ruđer Bošković Institute, Bijenička cesta 54, HR-10000, Zagreb, Croatia
| |
Collapse
|