Development of a Hierarchical Support Vector Regression-Based In Silico Model for Caco-2 Permeability

Ta, Giang Huong; Jhang, Cin-Syong; Weng, Ching‐Feng; Leong, Max K.

doi:10.3390/pharmaceutics13020174

Cited by 14 publications

(9 citation statements)

References 147 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The opposite effect occurred with the slogP lipophilicity descriptor. Although the correlations of all these properties with the log P app values in our data were not very strong (Pearson correlation coefficient <0.4), their impact on the permeation rate has been widely described [ 10 , 25 , 33 ].…”

Section: Resultsmentioning

confidence: 61%

“…However, the difficulties in developing a robust in silico tool to predict intestinal permeability remain, yet without satisfactory solutions. Indeed, Caco-2 permeability is a dramatically puzzling process that can take place through numerous nonlinear pathways (influx and efflux transporters) [ 10 ]. The paucity of high-quality Caco-2 permeability data has limited the development of accurate models with a comprehensive applicability domain.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reliable Prediction of Caco-2 Permeability by Supervised Recursive Machine Learning Approaches

Falcón-Cano

Molina²,

Cabrera‐Pérez

2022

Pharmaceutics

View full text Add to dashboard Cite

The heterogeneity of the Caco-2 cell line and differences in experimental protocols for permeability assessment using this cell-based method have resulted in the high variability of Caco-2 permeability measurements. These problems have limited the generation of large datasets to develop accurate and applicable regression models. This study presents a QSPR approach developed on the KNIME analytical platform and based on a structurally diverse dataset of over 4900 molecules. Interpretable models were obtained using random forest supervised recursive algorithms for data cleaning and feature selection. The development of a conditional consensus model based on regional and global regression random forest produced models with RMSE values between 0.43–0.51 for all validation sets. The potential applicability of the model as a surrogate for the in vitro Caco-2 assay was demonstrated through blind prediction of 32 drugs recommended by the International Council for the Harmonization of Technical Requirements for Pharmaceuticals (ICH) for validation of in vitro permeability methods. The model was validated for the preliminary estimation of the BCS/BDDCS class. The KNIME workflow developed to automate new drug prediction is freely available. The results suggest that this automated prediction platform is a reliable tool for identifying the most promising compounds with high intestinal permeability during the early stages of drug discovery.

show abstract

Section: Resultsmentioning

confidence: 61%

Section: Introductionmentioning

confidence: 99%

Reliable Prediction of Caco-2 Permeability by Supervised Recursive Machine Learning Approaches

Falcón-Cano

Molina²,

Cabrera‐Pérez

2022

Pharmaceutics

View full text Add to dashboard Cite

show abstract

“…It has been observed the neutral compounds are more permeable in the human colon carcinoma cell layer (Caco-2) and parallel artificial membrane permeability assay (PAMPA) system [ 7 , 89 ]. It is of interest to investigate that if neutral compounds have higher permeability values in the ex vivo skin permeability model as compared with the other ion classes.…”

Section: Discussionmentioning

confidence: 99%

“…the coverage of applicability domain (AD) vs. the level of predictivity [ 85 ]. More notably, the excellent performance of HSVR can be illustrated by a number of studies [ 7 , 43 , 44 , 86 , 87 , 88 , 89 ].…”

Section: Methodsmentioning

confidence: 99%

In Silico Prediction of Skin Permeability Using a Two-QSAR Approach

Yu-Wen

Yi-Chieh

et al. 2022

Pharmaceutics

Self Cite

View full text Add to dashboard Cite

Topical and transdermal drug delivery is an effective, safe, and preferred route of drug administration. As such, skin permeability is one of the critical parameters that should be taken into consideration in the process of drug discovery and development. The ex vivo human skin model is considered as the best surrogate to evaluate in vivo skin permeability. This investigation adopted a novel two-QSAR scheme by collectively incorporating machine learning-based hierarchical support vector regression (HSVR) and classical partial least square (PLS) to predict the skin permeability coefficient and to uncover the intrinsic permeation mechanism, respectively, based on ex vivo excised human skin permeability data compiled from the literature. The derived HSVR model functioned better than PLS as represented by the predictive performance in the training set, test set, and outlier set in addition to various statistical estimations. HSVR also delivered consistent performance upon the application of a mock test, which purposely mimicked the real challenges. PLS, contrarily, uncovered the interpretable relevance between selected descriptors and skin permeability. Thus, the synergy between interpretable PLS and predictive HSVR models can be of great use for facilitating drug discovery and development by predicting skin permeability.

show abstract

“…Human intestinal absorption and human intestinal colon carcinoma cell (caco-2) permeation values can give idea about intestinal absorption of a compound. 54 Human intestinal absorption was found to be high for all compounds except paashaanolactone which also had low caco-2 permeability. Caco-2 permeability was low for afzelechin although its human intestinal absorption value was high.…”

Section: In Silico Adme/t Predictionmentioning

confidence: 95%

In silico Evaluation of Selected Compounds from Bergenia ciliata (Haw.) Sternb against Molecular Targets of Breast Cancer

Spriha¹,

Rahman²

2022

IJPER

View full text Add to dashboard Cite

Background: A daunting public health issue that mainly affects women is breast cancer. Resistance to drugs applied in the treatment of this cancer as well as their side effects have made it necessary to look for new therapeutic agents. Objectives: The study is aimed at identification of multi-targeted inhibitors of molecular targets associated with breast cancer. Methods: We investigated fifteen compounds from Bergenia ciliata (haw.) Sternb against four major molecular targets of breast cancer viz; estrogen receptor-α (ER-α), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2/ ERBB2) and epidermal growth factor receptor (EGFR) by docking simulation. Properties describing ADME/T aspects of the potential compounds were also investigated by in silico approach. Results: Among the fifteen compounds investigated, stigmasterol, β-sitosterol, paashaanolactone and afzelechin exhibited more or comparable binding affinity values with the different targets compared to that of native ligands and therefore may be developed as leads for multi-targeted therapy against breast cancer. Conclusion: Considering the molecular docking results and ADME/T analysis, it can be suggested that these compounds can be subjected to further structural modification and in vivo analysis for evaluating the potential of their candidacy as new drugs in the field of treatment and management of breast cancer.

show abstract

Development of a Hierarchical Support Vector Regression-Based In Silico Model for Caco-2 Permeability

Cited by 14 publications

References 147 publications

Reliable Prediction of Caco-2 Permeability by Supervised Recursive Machine Learning Approaches

Reliable Prediction of Caco-2 Permeability by Supervised Recursive Machine Learning Approaches

In Silico Prediction of Skin Permeability Using a Two-QSAR Approach

In silico Evaluation of Selected Compounds from Bergenia ciliata (Haw.) Sternb against Molecular Targets of Breast Cancer

Contact Info

Product

Resources

About