In Silico Prediction of Intestinal Permeability by Hierarchical Support Vector Regression
The vast majority of marketed drugs are orally administrated. As such, drug absorption is one of the important drug metabolism and pharmacokinetics parameters that should be assessed in the process of drug discovery and development. A nonlinear quantitative structure–activity relationship (QSAR) mod...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-05-01
|
Series: | International Journal of Molecular Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/1422-0067/21/10/3582 |
_version_ | 1797567598832910336 |
---|---|
author | Ming-Han Lee Giang Huong Ta Ching-Feng Weng Max K. Leong |
author_facet | Ming-Han Lee Giang Huong Ta Ching-Feng Weng Max K. Leong |
author_sort | Ming-Han Lee |
collection | DOAJ |
description | The vast majority of marketed drugs are orally administrated. As such, drug absorption is one of the important drug metabolism and pharmacokinetics parameters that should be assessed in the process of drug discovery and development. A nonlinear quantitative structure–activity relationship (QSAR) model was constructed in this investigation using the novel machine learning-based hierarchical support vector regression (HSVR) scheme to render the extremely complicated relationships between descriptors and intestinal permeability that can take place through various passive diffusion and carrier-mediated active transport routes. The predictions by HSVR were found to be in good agreement with the observed values for the molecules in the training set (<i>n</i> = 53, <i>r</i><sup>2</sup> = 0.93, <inline-formula> <math display="inline"> <semantics> <mrow> <msubsup> <mi>q</mi> <mi>CV</mi> <mn>2</mn> </msubsup> </mrow> </semantics> </math> </inline-formula> = 0.84, RMSE = 0.17, <i>s</i> = 0.08), test set (<i>n</i> = 13, <i>q</i><sup>2</sup> = 0.75–0.89, RMSE = 0.26, <i>s</i> = 0.14), and even outlier set (<i>n</i> = 8, <i>q</i><sup>2</sup> = 0.78–0.92, RMSE = 0.19, <i>s</i> = 0.09). The built HSVR model consistently met the most stringent criteria when subjected to various statistical assessments. A mock test also assured the predictivity of HSVR. Consequently, this HSVR model can be adopted to facilitate drug discovery and development. |
first_indexed | 2024-03-10T19:45:11Z |
format | Article |
id | doaj.art-e12dbfe366ad41a0bebd40cc9c6e10e4 |
institution | Directory Open Access Journal |
issn | 1661-6596 1422-0067 |
language | English |
last_indexed | 2024-03-10T19:45:11Z |
publishDate | 2020-05-01 |
publisher | MDPI AG |
record_format | Article |
series | International Journal of Molecular Sciences |
spelling | doaj.art-e12dbfe366ad41a0bebd40cc9c6e10e42023-11-20T00:57:22ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672020-05-012110358210.3390/ijms21103582In Silico Prediction of Intestinal Permeability by Hierarchical Support Vector RegressionMing-Han Lee0Giang Huong Ta1Ching-Feng Weng2Max K. Leong3Department of Chemistry, National Dong Hwa University, Shoufeng, Hualien 974301, TaiwanDepartment of Chemistry, National Dong Hwa University, Shoufeng, Hualien 974301, TaiwanDepartment of Basic Medical Science, Center for Transitional Medicine, Xiamen Medical College, Xiamen 361023, ChinaDepartment of Chemistry, National Dong Hwa University, Shoufeng, Hualien 974301, TaiwanThe vast majority of marketed drugs are orally administrated. As such, drug absorption is one of the important drug metabolism and pharmacokinetics parameters that should be assessed in the process of drug discovery and development. A nonlinear quantitative structure–activity relationship (QSAR) model was constructed in this investigation using the novel machine learning-based hierarchical support vector regression (HSVR) scheme to render the extremely complicated relationships between descriptors and intestinal permeability that can take place through various passive diffusion and carrier-mediated active transport routes. The predictions by HSVR were found to be in good agreement with the observed values for the molecules in the training set (<i>n</i> = 53, <i>r</i><sup>2</sup> = 0.93, <inline-formula> <math display="inline"> <semantics> <mrow> <msubsup> <mi>q</mi> <mi>CV</mi> <mn>2</mn> </msubsup> </mrow> </semantics> </math> </inline-formula> = 0.84, RMSE = 0.17, <i>s</i> = 0.08), test set (<i>n</i> = 13, <i>q</i><sup>2</sup> = 0.75–0.89, RMSE = 0.26, <i>s</i> = 0.14), and even outlier set (<i>n</i> = 8, <i>q</i><sup>2</sup> = 0.78–0.92, RMSE = 0.19, <i>s</i> = 0.09). The built HSVR model consistently met the most stringent criteria when subjected to various statistical assessments. A mock test also assured the predictivity of HSVR. Consequently, this HSVR model can be adopted to facilitate drug discovery and development.https://www.mdpi.com/1422-0067/21/10/3582intestinal permeabilitypassive diffusionactive transportin silicoquantitative structure–activity relationshiphierarchical support vector regression |
spellingShingle | Ming-Han Lee Giang Huong Ta Ching-Feng Weng Max K. Leong In Silico Prediction of Intestinal Permeability by Hierarchical Support Vector Regression International Journal of Molecular Sciences intestinal permeability passive diffusion active transport in silico quantitative structure–activity relationship hierarchical support vector regression |
title | In Silico Prediction of Intestinal Permeability by Hierarchical Support Vector Regression |
title_full | In Silico Prediction of Intestinal Permeability by Hierarchical Support Vector Regression |
title_fullStr | In Silico Prediction of Intestinal Permeability by Hierarchical Support Vector Regression |
title_full_unstemmed | In Silico Prediction of Intestinal Permeability by Hierarchical Support Vector Regression |
title_short | In Silico Prediction of Intestinal Permeability by Hierarchical Support Vector Regression |
title_sort | in silico prediction of intestinal permeability by hierarchical support vector regression |
topic | intestinal permeability passive diffusion active transport in silico quantitative structure–activity relationship hierarchical support vector regression |
url | https://www.mdpi.com/1422-0067/21/10/3582 |
work_keys_str_mv | AT minghanlee insilicopredictionofintestinalpermeabilitybyhierarchicalsupportvectorregression AT gianghuongta insilicopredictionofintestinalpermeabilitybyhierarchicalsupportvectorregression AT chingfengweng insilicopredictionofintestinalpermeabilitybyhierarchicalsupportvectorregression AT maxkleong insilicopredictionofintestinalpermeabilitybyhierarchicalsupportvectorregression |