Support Vector Machine-Based Global Classification Model of the Toxicity of Organic Compounds to <i>Vibrio fischeri</i>
<i>Vibrio fischeri</i> is widely used as the model species in toxicity and risk assessment. For the first time, a global classification model was proposed in this paper for a two-class problem (Class − 1 with log1/IBC<sub>50</sub> ≤ 4.2 and Class + 1 with log1/IBC<sub>5...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Molecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1420-3049/28/6/2703 |
| _version_ | 1797609853310468096 |
|---|---|
| author | Feng Wu Xinhua Zhang Zhengjun Fang Xinliang Yu |
| author_facet | Feng Wu Xinhua Zhang Zhengjun Fang Xinliang Yu |
| author_sort | Feng Wu |
| collection | DOAJ |
| description | <i>Vibrio fischeri</i> is widely used as the model species in toxicity and risk assessment. For the first time, a global classification model was proposed in this paper for a two-class problem (Class − 1 with log1/IBC<sub>50</sub> ≤ 4.2 and Class + 1 with log1/IBC<sub>50</sub> > 4.2, the unit of IBC<sub>50</sub>: mol/L) by utilizing a large data set of 601 toxicity log1/IBC<sub>50</sub> of organic compounds to <i>Vibrio fischeri</i>. Dragon software was used to calculate 4885 molecular descriptors for each compound. Stepwise multiple linear regression (MLR) analysis was used to select the descriptor subset for the models. The ten molecular descriptors used in the classification model reflect the structural information on the Michael-type addition of nucleophiles, molecular branching, molecular size, polarizability, hydrophobic, and so on. Furthermore, these descriptors were interpreted from the point of view of toxicity mechanisms. The optimal support vector machine (SVM) model (<i>C</i> = 253.8 and <i>γ</i> = 0.009) was obtained with the genetic algorithm. The SVM classification model produced a prediction accuracy of 89.1% for the training set (451 log1/IBC<sub>50</sub>), of 80.0% for the test set (150 log1/IBC<sub>50</sub>), and of 86.9% for the total data set (601 log1/IBC<sub>50</sub>), which are higher than that (80.5%, 76%, and 79.4%, respectively) from the binary logistic regression (BLR) model. The global SVM classification model is successful, although it deals with a large data set in relation to the toxicity of organics to <i>Vibrio fischeri</i>. |
| first_indexed | 2024-03-11T06:07:20Z |
| format | Article |
| id | doaj.art-6882c1e1929940c28391aee43e56ea08 |
| institution | Directory Open Access Journal |
| issn | 1420-3049 |
| language | English |
| last_indexed | 2024-03-11T06:07:20Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Molecules |
| spelling | doaj.art-6882c1e1929940c28391aee43e56ea082023-11-17T12:54:01ZengMDPI AGMolecules1420-30492023-03-01286270310.3390/molecules28062703Support Vector Machine-Based Global Classification Model of the Toxicity of Organic Compounds to <i>Vibrio fischeri</i>Feng Wu0Xinhua Zhang1Zhengjun Fang2Xinliang Yu3Hunan Provincial Key Laboratory of Environmental Catalysis & Waste Regeneration, College of Materials and Chemical Engineering, Hunan Institute of Engineering, Xiangtan 411104, ChinaHunan Provincial Key Laboratory of Environmental Catalysis & Waste Regeneration, College of Materials and Chemical Engineering, Hunan Institute of Engineering, Xiangtan 411104, ChinaHunan Provincial Key Laboratory of Environmental Catalysis & Waste Regeneration, College of Materials and Chemical Engineering, Hunan Institute of Engineering, Xiangtan 411104, ChinaHunan Provincial Key Laboratory of Environmental Catalysis & Waste Regeneration, College of Materials and Chemical Engineering, Hunan Institute of Engineering, Xiangtan 411104, China<i>Vibrio fischeri</i> is widely used as the model species in toxicity and risk assessment. For the first time, a global classification model was proposed in this paper for a two-class problem (Class − 1 with log1/IBC<sub>50</sub> ≤ 4.2 and Class + 1 with log1/IBC<sub>50</sub> > 4.2, the unit of IBC<sub>50</sub>: mol/L) by utilizing a large data set of 601 toxicity log1/IBC<sub>50</sub> of organic compounds to <i>Vibrio fischeri</i>. Dragon software was used to calculate 4885 molecular descriptors for each compound. Stepwise multiple linear regression (MLR) analysis was used to select the descriptor subset for the models. The ten molecular descriptors used in the classification model reflect the structural information on the Michael-type addition of nucleophiles, molecular branching, molecular size, polarizability, hydrophobic, and so on. Furthermore, these descriptors were interpreted from the point of view of toxicity mechanisms. The optimal support vector machine (SVM) model (<i>C</i> = 253.8 and <i>γ</i> = 0.009) was obtained with the genetic algorithm. The SVM classification model produced a prediction accuracy of 89.1% for the training set (451 log1/IBC<sub>50</sub>), of 80.0% for the test set (150 log1/IBC<sub>50</sub>), and of 86.9% for the total data set (601 log1/IBC<sub>50</sub>), which are higher than that (80.5%, 76%, and 79.4%, respectively) from the binary logistic regression (BLR) model. The global SVM classification model is successful, although it deals with a large data set in relation to the toxicity of organics to <i>Vibrio fischeri</i>.https://www.mdpi.com/1420-3049/28/6/2703classification modelsupport vector machinetoxicity<i>Vibrio fischeri</i> |
| spellingShingle | Feng Wu Xinhua Zhang Zhengjun Fang Xinliang Yu Support Vector Machine-Based Global Classification Model of the Toxicity of Organic Compounds to <i>Vibrio fischeri</i> Molecules classification model support vector machine toxicity <i>Vibrio fischeri</i> |
| title | Support Vector Machine-Based Global Classification Model of the Toxicity of Organic Compounds to <i>Vibrio fischeri</i> |
| title_full | Support Vector Machine-Based Global Classification Model of the Toxicity of Organic Compounds to <i>Vibrio fischeri</i> |
| title_fullStr | Support Vector Machine-Based Global Classification Model of the Toxicity of Organic Compounds to <i>Vibrio fischeri</i> |
| title_full_unstemmed | Support Vector Machine-Based Global Classification Model of the Toxicity of Organic Compounds to <i>Vibrio fischeri</i> |
| title_short | Support Vector Machine-Based Global Classification Model of the Toxicity of Organic Compounds to <i>Vibrio fischeri</i> |
| title_sort | support vector machine based global classification model of the toxicity of organic compounds to i vibrio fischeri i |
| topic | classification model support vector machine toxicity <i>Vibrio fischeri</i> |
| url | https://www.mdpi.com/1420-3049/28/6/2703 |
| work_keys_str_mv | AT fengwu supportvectormachinebasedglobalclassificationmodelofthetoxicityoforganiccompoundstoivibriofischerii AT xinhuazhang supportvectormachinebasedglobalclassificationmodelofthetoxicityoforganiccompoundstoivibriofischerii AT zhengjunfang supportvectormachinebasedglobalclassificationmodelofthetoxicityoforganiccompoundstoivibriofischerii AT xinliangyu supportvectormachinebasedglobalclassificationmodelofthetoxicityoforganiccompoundstoivibriofischerii |