Combination of Machine Learning and Analytical Correlations for Establishing Quantitative Compliance between the Trolox Equivalent Antioxidant Capacity Values Obtained via Electron Paramagnetic Resonance and Ultraviolet–Visible Spectroscopies
Recent interest in the antioxidant capacity of foods and beverages is based on the established medical knowledge that antioxidants play an essential role in counteracting the damaging effects of free radicals, preventing human neurodegenerative diseases, cardiovascular disorders, and even cancer. At...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/23/19/11743 |
| _version_ | 1797478924438994944 |
|---|---|
| author | Eugene B. Postnikov Mariola Bartoszek Justyna Polak Mirosław Chorążewski |
| author_facet | Eugene B. Postnikov Mariola Bartoszek Justyna Polak Mirosław Chorążewski |
| author_sort | Eugene B. Postnikov |
| collection | DOAJ |
| description | Recent interest in the antioxidant capacity of foods and beverages is based on the established medical knowledge that antioxidants play an essential role in counteracting the damaging effects of free radicals, preventing human neurodegenerative diseases, cardiovascular disorders, and even cancer. At the same time, there is no “the method" that uniquely defines the antioxidant capacity of substances; moreover, the question of interrelation between results obtained by different experimental techniques is still open. In this work, we consider the trolox equivalent antioxidant capacity (TEAC) values obtained by electron paramagnetic resonance (EPR) spectroscopy and ultraviolet–visible (UV–vis) spectroscopy using the classic objects for such studies as an example: red, rosé, and white wine samples. Based on entirely different physical principles, these two methods give values that are not so simply interrelated; this creates a demand for machine learning as a suitable tool for revealing quantitative correspondence between them. The consideration consists of an approximate correlation-based analytical model for the key argument (i.e., <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>T</mi><mi>E</mi><mi>A</mi><msub><mi>C</mi><mrow><mi>E</mi><mi>P</mi><mi>R</mi></mrow></msub></mrow></semantics></math></inline-formula>) with subsequent adjustment by machine learning-based processing utilizing the CatBoost algorithm with the usage of auxiliary chemical data, such as the total phenolic content and color index, which cannot be accurately described by analytical expressions. |
| first_indexed | 2024-03-09T21:38:32Z |
| format | Article |
| id | doaj.art-beb88a72ffb6436b940ba7d9d7654bf5 |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-09T21:38:32Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-beb88a72ffb6436b940ba7d9d7654bf52023-11-23T20:38:32ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672022-10-0123191174310.3390/ijms231911743Combination of Machine Learning and Analytical Correlations for Establishing Quantitative Compliance between the Trolox Equivalent Antioxidant Capacity Values Obtained via Electron Paramagnetic Resonance and Ultraviolet–Visible SpectroscopiesEugene B. Postnikov0Mariola Bartoszek1Justyna Polak2Mirosław Chorążewski3Theoretical Physics Department, Kursk State University, Radishcheva Str., 33, 305000 Kursk, RussiaInstitute of Chemistry, University of Silesia in Katowice, Ul. 9 Szkolna, 40-006 Katowice, PolandInstitute of Chemistry, University of Silesia in Katowice, Ul. 9 Szkolna, 40-006 Katowice, PolandInstitute of Chemistry, University of Silesia in Katowice, Ul. 9 Szkolna, 40-006 Katowice, PolandRecent interest in the antioxidant capacity of foods and beverages is based on the established medical knowledge that antioxidants play an essential role in counteracting the damaging effects of free radicals, preventing human neurodegenerative diseases, cardiovascular disorders, and even cancer. At the same time, there is no “the method" that uniquely defines the antioxidant capacity of substances; moreover, the question of interrelation between results obtained by different experimental techniques is still open. In this work, we consider the trolox equivalent antioxidant capacity (TEAC) values obtained by electron paramagnetic resonance (EPR) spectroscopy and ultraviolet–visible (UV–vis) spectroscopy using the classic objects for such studies as an example: red, rosé, and white wine samples. Based on entirely different physical principles, these two methods give values that are not so simply interrelated; this creates a demand for machine learning as a suitable tool for revealing quantitative correspondence between them. The consideration consists of an approximate correlation-based analytical model for the key argument (i.e., <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>T</mi><mi>E</mi><mi>A</mi><msub><mi>C</mi><mrow><mi>E</mi><mi>P</mi><mi>R</mi></mrow></msub></mrow></semantics></math></inline-formula>) with subsequent adjustment by machine learning-based processing utilizing the CatBoost algorithm with the usage of auxiliary chemical data, such as the total phenolic content and color index, which cannot be accurately described by analytical expressions.https://www.mdpi.com/1422-0067/23/19/11743antioxidant capacitywineCatBoost machine learningEPR spectroscopyUV–vis spectrophotometry |
| spellingShingle | Eugene B. Postnikov Mariola Bartoszek Justyna Polak Mirosław Chorążewski Combination of Machine Learning and Analytical Correlations for Establishing Quantitative Compliance between the Trolox Equivalent Antioxidant Capacity Values Obtained via Electron Paramagnetic Resonance and Ultraviolet–Visible Spectroscopies International Journal of Molecular Sciences antioxidant capacity wine CatBoost machine learning EPR spectroscopy UV–vis spectrophotometry |
| title | Combination of Machine Learning and Analytical Correlations for Establishing Quantitative Compliance between the Trolox Equivalent Antioxidant Capacity Values Obtained via Electron Paramagnetic Resonance and Ultraviolet–Visible Spectroscopies |
| title_full | Combination of Machine Learning and Analytical Correlations for Establishing Quantitative Compliance between the Trolox Equivalent Antioxidant Capacity Values Obtained via Electron Paramagnetic Resonance and Ultraviolet–Visible Spectroscopies |
| title_fullStr | Combination of Machine Learning and Analytical Correlations for Establishing Quantitative Compliance between the Trolox Equivalent Antioxidant Capacity Values Obtained via Electron Paramagnetic Resonance and Ultraviolet–Visible Spectroscopies |
| title_full_unstemmed | Combination of Machine Learning and Analytical Correlations for Establishing Quantitative Compliance between the Trolox Equivalent Antioxidant Capacity Values Obtained via Electron Paramagnetic Resonance and Ultraviolet–Visible Spectroscopies |
| title_short | Combination of Machine Learning and Analytical Correlations for Establishing Quantitative Compliance between the Trolox Equivalent Antioxidant Capacity Values Obtained via Electron Paramagnetic Resonance and Ultraviolet–Visible Spectroscopies |
| title_sort | combination of machine learning and analytical correlations for establishing quantitative compliance between the trolox equivalent antioxidant capacity values obtained via electron paramagnetic resonance and ultraviolet visible spectroscopies |
| topic | antioxidant capacity wine CatBoost machine learning EPR spectroscopy UV–vis spectrophotometry |
| url | https://www.mdpi.com/1422-0067/23/19/11743 |
| work_keys_str_mv | AT eugenebpostnikov combinationofmachinelearningandanalyticalcorrelationsforestablishingquantitativecompliancebetweenthetroloxequivalentantioxidantcapacityvaluesobtainedviaelectronparamagneticresonanceandultravioletvisiblespectroscopies AT mariolabartoszek combinationofmachinelearningandanalyticalcorrelationsforestablishingquantitativecompliancebetweenthetroloxequivalentantioxidantcapacityvaluesobtainedviaelectronparamagneticresonanceandultravioletvisiblespectroscopies AT justynapolak combinationofmachinelearningandanalyticalcorrelationsforestablishingquantitativecompliancebetweenthetroloxequivalentantioxidantcapacityvaluesobtainedviaelectronparamagneticresonanceandultravioletvisiblespectroscopies AT mirosławchorazewski combinationofmachinelearningandanalyticalcorrelationsforestablishingquantitativecompliancebetweenthetroloxequivalentantioxidantcapacityvaluesobtainedviaelectronparamagneticresonanceandultravioletvisiblespectroscopies |