A Robust Regression-Based Modeling to Predict Antiplasmodial Activity of Thiazolyl–Pyrimidine Hybrid Derivatives against <i>Plasmodium falciparum</i>
Thiazolyl–pyrimidine hybrid plays significant roles in the biological activities and SAR of thiazolylpyrimidines (Tzpd), thiazolopyrimidines, and thienopyrimidines due to the combination of the thiazole and pyrimidine pharmacophores. The study developed regression-based models for the prediction of...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Chemistry Proceedings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4583/14/1/52 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850241267982663680 |
|---|---|
| author | Kevin S. Umoette Charles O. Nnadi Wilfred O. Obonga |
| author_facet | Kevin S. Umoette Charles O. Nnadi Wilfred O. Obonga |
| author_sort | Kevin S. Umoette |
| collection | DOAJ |
| description | Thiazolyl–pyrimidine hybrid plays significant roles in the biological activities and SAR of thiazolylpyrimidines (Tzpd), thiazolopyrimidines, and thienopyrimidines due to the combination of the thiazole and pyrimidine pharmacophores. The study developed regression-based models for the prediction of antiplasmodial activity of 43 Tzpd hybrid obtained from the ChEMBL database. The molecular descriptors (145 features) were scaled down to 6 using the recursive feature elimination. The X- and Y-matrix were split into 34 train and 9 test sets using a split ratio of 0.20. Regression models were built using scikit-learn algorithms: multiple linear regression (MLR), k-Nearest Neighbors (kNN), Support Vector Regressor (SVR), and Random Forest Regressor (RFR) to predict the pIC<sub>50</sub> of the test set. The models were evaluated using R<sup>2</sup>, mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), <i>p</i>-values, <i>F</i>-statistic, and variance inflation factor (VIF). Of the 145 features calculated for the 43 Tzpd, 6 molecular features, FCASA-, MNDO_LUMO, E_str, vsurf_HB1, vsurf_G, and vsurf_DD12 (<i>p</i> < 0.05; VIF < 5), were found to significantly influence the antiplasmodial activity. Fivefold cross-validation performance scores of MLR, kNN, SVR, and RFR showed that the performance metrics of MLR (MSE = 0.1453; R<sup>2</sup> = 0.680; MAE = 0.290; RMSE = 0.381; pIC<sub>50</sub>(predicted) = 8.06 − 0.45vsurf_G + 0.37FCASA- − 0.42MNDO_LUMO − 0.20E_str + 0.30vsurf_HB1 − 0.38vsurf_DD12) outperformed other models. The study developed predictive models and provided insights into the chemical features necessary for the optimization of thiazolyl–pyrimidine to enhance antiplasmodial activity. |
| format | Article |
| id | doaj-art-71d664f2e4bf4420ad1e5bdd03debd6c |
| institution | OA Journals |
| issn | 2673-4583 |
| language | English |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Chemistry Proceedings |
| spelling | doaj-art-71d664f2e4bf4420ad1e5bdd03debd6c2025-08-20T02:00:39ZengMDPI AGChemistry Proceedings2673-45832023-11-011415210.3390/ecsoc-27-16167A Robust Regression-Based Modeling to Predict Antiplasmodial Activity of Thiazolyl–Pyrimidine Hybrid Derivatives against <i>Plasmodium falciparum</i>Kevin S. Umoette0Charles O. Nnadi1Wilfred O. Obonga2Department of Pharmaceutical and Medicinal Chemistry, Faculty of Pharmaceutical Sciences, University of Nigeria Nsukka, Enugu 410001, NigeriaDepartment of Pharmaceutical and Medicinal Chemistry, Faculty of Pharmaceutical Sciences, University of Nigeria Nsukka, Enugu 410001, NigeriaDepartment of Pharmaceutical and Medicinal Chemistry, Faculty of Pharmaceutical Sciences, University of Nigeria Nsukka, Enugu 410001, NigeriaThiazolyl–pyrimidine hybrid plays significant roles in the biological activities and SAR of thiazolylpyrimidines (Tzpd), thiazolopyrimidines, and thienopyrimidines due to the combination of the thiazole and pyrimidine pharmacophores. The study developed regression-based models for the prediction of antiplasmodial activity of 43 Tzpd hybrid obtained from the ChEMBL database. The molecular descriptors (145 features) were scaled down to 6 using the recursive feature elimination. The X- and Y-matrix were split into 34 train and 9 test sets using a split ratio of 0.20. Regression models were built using scikit-learn algorithms: multiple linear regression (MLR), k-Nearest Neighbors (kNN), Support Vector Regressor (SVR), and Random Forest Regressor (RFR) to predict the pIC<sub>50</sub> of the test set. The models were evaluated using R<sup>2</sup>, mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), <i>p</i>-values, <i>F</i>-statistic, and variance inflation factor (VIF). Of the 145 features calculated for the 43 Tzpd, 6 molecular features, FCASA-, MNDO_LUMO, E_str, vsurf_HB1, vsurf_G, and vsurf_DD12 (<i>p</i> < 0.05; VIF < 5), were found to significantly influence the antiplasmodial activity. Fivefold cross-validation performance scores of MLR, kNN, SVR, and RFR showed that the performance metrics of MLR (MSE = 0.1453; R<sup>2</sup> = 0.680; MAE = 0.290; RMSE = 0.381; pIC<sub>50</sub>(predicted) = 8.06 − 0.45vsurf_G + 0.37FCASA- − 0.42MNDO_LUMO − 0.20E_str + 0.30vsurf_HB1 − 0.38vsurf_DD12) outperformed other models. The study developed predictive models and provided insights into the chemical features necessary for the optimization of thiazolyl–pyrimidine to enhance antiplasmodial activity.https://www.mdpi.com/2673-4583/14/1/52machine learning<i>Plasmodium falciparum</i>QSARregressionthiazolylpyrimidines |
| spellingShingle | Kevin S. Umoette Charles O. Nnadi Wilfred O. Obonga A Robust Regression-Based Modeling to Predict Antiplasmodial Activity of Thiazolyl–Pyrimidine Hybrid Derivatives against <i>Plasmodium falciparum</i> Chemistry Proceedings machine learning <i>Plasmodium falciparum</i> QSAR regression thiazolylpyrimidines |
| title | A Robust Regression-Based Modeling to Predict Antiplasmodial Activity of Thiazolyl–Pyrimidine Hybrid Derivatives against <i>Plasmodium falciparum</i> |
| title_full | A Robust Regression-Based Modeling to Predict Antiplasmodial Activity of Thiazolyl–Pyrimidine Hybrid Derivatives against <i>Plasmodium falciparum</i> |
| title_fullStr | A Robust Regression-Based Modeling to Predict Antiplasmodial Activity of Thiazolyl–Pyrimidine Hybrid Derivatives against <i>Plasmodium falciparum</i> |
| title_full_unstemmed | A Robust Regression-Based Modeling to Predict Antiplasmodial Activity of Thiazolyl–Pyrimidine Hybrid Derivatives against <i>Plasmodium falciparum</i> |
| title_short | A Robust Regression-Based Modeling to Predict Antiplasmodial Activity of Thiazolyl–Pyrimidine Hybrid Derivatives against <i>Plasmodium falciparum</i> |
| title_sort | robust regression based modeling to predict antiplasmodial activity of thiazolyl pyrimidine hybrid derivatives against i plasmodium falciparum i |
| topic | machine learning <i>Plasmodium falciparum</i> QSAR regression thiazolylpyrimidines |
| url | https://www.mdpi.com/2673-4583/14/1/52 |
| work_keys_str_mv | AT kevinsumoette arobustregressionbasedmodelingtopredictantiplasmodialactivityofthiazolylpyrimidinehybridderivativesagainstiplasmodiumfalciparumi AT charlesonnadi arobustregressionbasedmodelingtopredictantiplasmodialactivityofthiazolylpyrimidinehybridderivativesagainstiplasmodiumfalciparumi AT wilfredoobonga arobustregressionbasedmodelingtopredictantiplasmodialactivityofthiazolylpyrimidinehybridderivativesagainstiplasmodiumfalciparumi AT kevinsumoette robustregressionbasedmodelingtopredictantiplasmodialactivityofthiazolylpyrimidinehybridderivativesagainstiplasmodiumfalciparumi AT charlesonnadi robustregressionbasedmodelingtopredictantiplasmodialactivityofthiazolylpyrimidinehybridderivativesagainstiplasmodiumfalciparumi AT wilfredoobonga robustregressionbasedmodelingtopredictantiplasmodialactivityofthiazolylpyrimidinehybridderivativesagainstiplasmodiumfalciparumi |