1
|
Deep Learning-Based Method for Compound Identification in NMR Spectra of Mixtures. MOLECULES (BASEL, SWITZERLAND) 2022; 27:molecules27123653. [PMID: 35744782 PMCID: PMC9227391 DOI: 10.3390/molecules27123653] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/18/2022] [Revised: 06/03/2022] [Accepted: 06/05/2022] [Indexed: 11/16/2022]
Abstract
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.
Collapse
|
2
|
Nardelli F, Martini F, Lee J, Lluvears-Tenorio A, La Nasa J, Duce C, Ormsby B, Geppi M, Bonaduce I. The stability of paintings and the molecular structure of the oil paint polymeric network. Sci Rep 2021; 11:14202. [PMID: 34244532 PMCID: PMC8270892 DOI: 10.1038/s41598-021-93268-8] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2021] [Accepted: 06/11/2021] [Indexed: 02/06/2023] Open
Abstract
A molecular-level understanding of the structure of the polymeric network formed upon the curing of air-drying artists' oil paints still represents a challenge. In this study we used a set of analytical methodologies classically employed for the characterisation of a paint film-based on infrared spectroscopy and mass spectrometry-in combination with solid state NMR (SSNMR), to characterise model paint layers which present different behaviours towards surface cleaning with water, a commonly applied procedure in art conservation. The study demonstrates, with the fundamental contribution of SSNMR, a relationship between the painting stability and the chemical structure of the polymeric network. In particular, it is demonstrated for the first time that a low degree of cross-linking in combination with a high degree of oxidation of the polymeric network render the oil paint layer sensitive to water.
Collapse
Affiliation(s)
- Francesca Nardelli
- Department of Chemistry and Industrial Chemistry, University of Pisa, Via Giuseppe Moruzzi 13, 56124, Pisa, Italy
| | - Francesca Martini
- Department of Chemistry and Industrial Chemistry, University of Pisa, Via Giuseppe Moruzzi 13, 56124, Pisa, Italy
- Centro Per L'Integrazione Della Strumentazione Scientifica Dell'Università Di Pisa (CISUP), Lungarno Pacinotti 43, 56126, Pisa, Italy
| | - Judith Lee
- Conservation Department, Tate, Millbank, London, SW1P 4RG, UK
| | - Anna Lluvears-Tenorio
- Department of Chemistry and Industrial Chemistry, University of Pisa, Via Giuseppe Moruzzi 13, 56124, Pisa, Italy
| | - Jacopo La Nasa
- Department of Chemistry and Industrial Chemistry, University of Pisa, Via Giuseppe Moruzzi 13, 56124, Pisa, Italy
| | - Celia Duce
- Department of Chemistry and Industrial Chemistry, University of Pisa, Via Giuseppe Moruzzi 13, 56124, Pisa, Italy
| | - Bronwyn Ormsby
- Conservation Department, Tate, Millbank, London, SW1P 4RG, UK
| | - Marco Geppi
- Department of Chemistry and Industrial Chemistry, University of Pisa, Via Giuseppe Moruzzi 13, 56124, Pisa, Italy
- Centro Per L'Integrazione Della Strumentazione Scientifica Dell'Università Di Pisa (CISUP), Lungarno Pacinotti 43, 56126, Pisa, Italy
| | - Ilaria Bonaduce
- Department of Chemistry and Industrial Chemistry, University of Pisa, Via Giuseppe Moruzzi 13, 56124, Pisa, Italy.
| |
Collapse
|
3
|
Rudszuck T, Nirschl H, Guthausen G. Perspectives in process analytics using low field NMR. JOURNAL OF MAGNETIC RESONANCE (SAN DIEGO, CALIF. : 1997) 2021; 323:106897. [PMID: 33518174 DOI: 10.1016/j.jmr.2020.106897] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/29/2020] [Revised: 12/15/2020] [Accepted: 12/18/2020] [Indexed: 06/12/2023]
Abstract
Low field NMR is a powerful analytical tool which creates an enormous added value in process analytics. Based on specific applications in process analytics and perspectives for low field NMR in form of spectroscopy, relaxation, diffusion, and imaging in quality control, diverse applications and technical realizations like spectrometers, time domain NMR, mobile NMR sensors and MRI will be discussed.
Collapse
Affiliation(s)
- T Rudszuck
- Institute for Mechanical Engineering and Mechanics, KIT, 76131 Karlsruhe, Germany
| | - H Nirschl
- Institute for Mechanical Engineering and Mechanics, KIT, 76131 Karlsruhe, Germany
| | - G Guthausen
- Institute for Mechanical Engineering and Mechanics, KIT, 76131 Karlsruhe, Germany; Engler-Bunte Institut, Water Science and Technology, KIT, 76131 Karlsruhe, Germany
| |
Collapse
|
4
|
Catalano J, Di Tullio V, Wagner M, Zumbulyadis N, Centeno SA, Dybowski C. Review of the use of NMR spectroscopy to investigate structure, reactivity, and dynamics of lead soap formation in paintings. MAGNETIC RESONANCE IN CHEMISTRY : MRC 2020; 58:798-811. [PMID: 32247290 DOI: 10.1002/mrc.5025] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/14/2020] [Revised: 03/24/2020] [Accepted: 03/27/2020] [Indexed: 06/11/2023]
Abstract
Heavy metal carboxylate or soap formation is a widespread deterioration problem affecting oil paintings and other works of art bearing oil-based media. Lead soaps are prevalent in traditional oil paintings because lead white was the white pigment most frequently chosen by old masters for the paints and in some cases for the ground preparations, until the development of other white pigments from approximately the middle of the 18th century on, and because of the wide use of lead-tin yellow. In the latter part of the 19th century, lead white began to be replaced by zinc white. The factors that influence soap formation have been the focus of intense study starting in the late 1990s. Since 2014, nuclear magnetic resonance (NMR) studies have contributed a unique perspective on the issue by providing chemical, structural, and dynamic information about the species involved in the process, as well as the effects of environmental conditions such as relative humidity and temperature on the kinetics of the reaction(s). In this review, we explore recent insights into soap formation gained through solid-state NMR and single-sided NMR techniques.
Collapse
Affiliation(s)
- Jaclyn Catalano
- Department of Chemistry and Biochemistry, Montclair State University, Montclair, NJ, USA
| | - Valeria Di Tullio
- Magnetic Resonance Laboratory "Annalaura Segre", ISB-CNR, Rome, Italy
| | - Molly Wagner
- Department of Chemistry and Biochemistry, University of Delaware, Newark, DE, USA
| | - Nicholas Zumbulyadis
- Department of Chemistry and Biochemistry, University of Delaware, Newark, DE, USA
| | - Silvia A Centeno
- Department of Scientific Research, The Metropolitan Museum of Art, New York, NY, USA
| | - Cecil Dybowski
- Department of Chemistry and Biochemistry, University of Delaware, Newark, DE, USA
| |
Collapse
|
5
|
Awad WM, Baias M. How mobile NMR can help with the conservation of paintings. MAGNETIC RESONANCE IN CHEMISTRY : MRC 2020; 58:792-797. [PMID: 32602967 DOI: 10.1002/mrc.5071] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/13/2020] [Revised: 05/25/2020] [Accepted: 06/28/2020] [Indexed: 06/11/2023]
Abstract
The conservation of paintings is fundamental to ensure that future generations will have access to the ideas of the grand masters who created these art pieces. Many factors, such as humidity, temperature, light, and pollutants, pose a risk to the conservation of paintings. To help with painting conservation, it is essential to be able to noninvasively study how these factors affect paintings and to develop methods to investigate their effects on painting degradation. Hence, the use of mobile nuclear magnetic resonance (NMR) as a method of investigation of paintings is gaining increased attention in the world of Heritage Science. In this mini-review, we discuss how this method was used to better understand the stratigraphy of paintings and the effect different factors have on the painting integrity, to analyze the different cleaning techniques suitable for painting conservation, and to show how mobile NMR can be used to identify forgeries. It is also important to keep in mind its limitations and build upon this information to optimize it to extend its applicability to the study of paintings and other precious objects of cultural heritage.
Collapse
Affiliation(s)
- Wegood M Awad
- Science Division, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates
| | - Maria Baias
- Science Division, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates
| |
Collapse
|
6
|
New Insights to Characterize Paint Varnishes and to Study Water in Paintings by Nuclear Magnetic Resonance Spectroscopy (NMR). MAGNETOCHEMISTRY 2020. [DOI: 10.3390/magnetochemistry6020021] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Paintings are complex multi-layered systems made of organic and inorganic materials. Several factors can affect the degradation of paintings, such as environmental conditions, past restoration works and, finally, the type of painting technique and the art materials used over the centuries. The chemical–physical characterization of paintings is a constant challenge that requires research into and the development of novel analytical methodologies and processes. In recent years, solvents and water-related issues in paintings are attracting more attention, and several studies have been focused on analyzing the interaction between water molecules and the constitutive materials. In this study, recent applications applying different NMR methodologies were shown, highlighting the weakness and the strength of the techniques in analyzing paintings. In particular, the study of water and its diffusive interactions within wall and oil paintings was performed to prove how the portable NMR can be used directly in museums for planning restoration work and to monitor the degradation processes. Furthermore, some preliminary results on the analysis of varnishes and binders, such us linseed oil, shellac, sandarac and colophony resins, were obtained by 1H HR-MAS NMR spectroscopy, highlighting the weakness and strengths of this technique in the field of conservation science.
Collapse
|
7
|
Nuclear Magnetic Resonance Spectroscopy. MAGNETOCHEMISTRY 2018. [DOI: 10.3390/magnetochemistry4020020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|