Prediction and Chemical Interpretation of Singlet-Oxygen-Scavenging Activity of Small Molecule Compounds by Using Machine Learning
A chemically explainable machine learning model was constructed with a small dataset to quantitatively predict the singlet-oxygen-scavenging ability. In this model, ensemble learning based on decision trees resulted in high accuracy. For explanatory variables, molecular descriptors by computational...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Antioxidants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3921/10/11/1751 |
| _version_ | 1827677562464108544 |
|---|---|
| author | Taiki Fujimoto Hiroaki Gotoh |
| author_facet | Taiki Fujimoto Hiroaki Gotoh |
| author_sort | Taiki Fujimoto |
| collection | DOAJ |
| description | A chemically explainable machine learning model was constructed with a small dataset to quantitatively predict the singlet-oxygen-scavenging ability. In this model, ensemble learning based on decision trees resulted in high accuracy. For explanatory variables, molecular descriptors by computational chemistry and Morgan fingerprints were used for achieving high accuracy and simple prediction. The singlet-oxygen-scavenging mechanism was explained by the feature importance obtained from machine learning outputs. The results are consistent with conventional chemical knowledge. The use of machine learning and reduction in the number of measurements for screening high-antioxidant-capacity compounds can considerably improve prediction accuracy and efficiency. |
| first_indexed | 2024-03-10T05:45:43Z |
| format | Article |
| id | doaj.art-f85ee57e14b544cbac95630c0dc2d789 |
| institution | Directory Open Access Journal |
| issn | 2076-3921 |
| language | English |
| last_indexed | 2024-03-10T05:45:43Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Antioxidants |
| spelling | doaj.art-f85ee57e14b544cbac95630c0dc2d7892023-11-22T22:13:10ZengMDPI AGAntioxidants2076-39212021-11-011011175110.3390/antiox10111751Prediction and Chemical Interpretation of Singlet-Oxygen-Scavenging Activity of Small Molecule Compounds by Using Machine LearningTaiki Fujimoto0Hiroaki Gotoh1Department of Chemistry and Life Science, Yokohama National University, 79-5 Tokiwadai, Hodogaya-ku, Yokohama 240-8501, JapanDepartment of Chemistry and Life Science, Yokohama National University, 79-5 Tokiwadai, Hodogaya-ku, Yokohama 240-8501, JapanA chemically explainable machine learning model was constructed with a small dataset to quantitatively predict the singlet-oxygen-scavenging ability. In this model, ensemble learning based on decision trees resulted in high accuracy. For explanatory variables, molecular descriptors by computational chemistry and Morgan fingerprints were used for achieving high accuracy and simple prediction. The singlet-oxygen-scavenging mechanism was explained by the feature importance obtained from machine learning outputs. The results are consistent with conventional chemical knowledge. The use of machine learning and reduction in the number of measurements for screening high-antioxidant-capacity compounds can considerably improve prediction accuracy and efficiency.https://www.mdpi.com/2076-3921/10/11/1751machine learningantioxidantsinglet oxygenfeature importanceinterpretabilitycarotenoid |
| spellingShingle | Taiki Fujimoto Hiroaki Gotoh Prediction and Chemical Interpretation of Singlet-Oxygen-Scavenging Activity of Small Molecule Compounds by Using Machine Learning Antioxidants machine learning antioxidant singlet oxygen feature importance interpretability carotenoid |
| title | Prediction and Chemical Interpretation of Singlet-Oxygen-Scavenging Activity of Small Molecule Compounds by Using Machine Learning |
| title_full | Prediction and Chemical Interpretation of Singlet-Oxygen-Scavenging Activity of Small Molecule Compounds by Using Machine Learning |
| title_fullStr | Prediction and Chemical Interpretation of Singlet-Oxygen-Scavenging Activity of Small Molecule Compounds by Using Machine Learning |
| title_full_unstemmed | Prediction and Chemical Interpretation of Singlet-Oxygen-Scavenging Activity of Small Molecule Compounds by Using Machine Learning |
| title_short | Prediction and Chemical Interpretation of Singlet-Oxygen-Scavenging Activity of Small Molecule Compounds by Using Machine Learning |
| title_sort | prediction and chemical interpretation of singlet oxygen scavenging activity of small molecule compounds by using machine learning |
| topic | machine learning antioxidant singlet oxygen feature importance interpretability carotenoid |
| url | https://www.mdpi.com/2076-3921/10/11/1751 |
| work_keys_str_mv | AT taikifujimoto predictionandchemicalinterpretationofsingletoxygenscavengingactivityofsmallmoleculecompoundsbyusingmachinelearning AT hiroakigotoh predictionandchemicalinterpretationofsingletoxygenscavengingactivityofsmallmoleculecompoundsbyusingmachinelearning |