In Silico Prediction of Intestinal Permeability by Hierarchical Support Vector Regression

Lee, Ming-Han; Ta, Giang Huong; Weng, Ching‐Feng; Leong, Max K.

doi:10.3390/ijms21103582

Cited by 12 publications

(8 citation statements)

References 109 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the hierarchical support vector regression (HSVR) scheme, which is an innovative machine learning-based scheme initially developed by Leong et al [ 54 ], can properly address the complicated and varied dependencies of descriptors that, in turn, can be greatly contributed to its advantageous features of both a local model and a global model, namely wider coverage of applicability domain (AD) and a higher capability of prediction, respectively. When comparing with most theoretical models, which are vulnerable to the outliers that represent mathematic extrapolations, HSVR can still show consistent performance, as demonstrated elsewhere [ 1 , 54 , 55 , 56 , 57 ]. Herein, the objective of this study was to develop an in silico model based on the HSVR scheme to predict Caco-2 permeability in conjunction with previously published PAMPA permeability, intestinal absorption, and MDCK efflux in silico models [ 1 , 55 , 57 ] to facilitate drug discovery and development, since medicinal chemists can employ these models to predict the drug absorption of (virtual) hit compounds as well as drug metabolism and pharmacokinetics (DM/PK) scientists can adopt these models to prioritize the lead compounds.…”

Section: Introductionsupporting

confidence: 62%

See 1 more Smart Citation

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

Jhang

Weng³

et al. 2021

Pharmaceutics

Self Cite

View full text Add to dashboard Cite

Drug absorption is one of the critical factors that should be taken into account in the process of drug discovery and development. The human colon carcinoma cell layer (Caco-2) model has been frequently used as a surrogate to preliminarily investigate the intestinal absorption. In this study, a quantitative structure–activity relationship (QSAR) model was generated using the innovative machine learning-based hierarchical support vector regression (HSVR) scheme to depict the exceedingly confounding passive diffusion and transporter-mediated active transport. The HSVR model displayed good agreement with the experimental values of the training samples, test samples, and outlier samples. The predictivity of HSVR was further validated by a mock test and verified by various stringent statistical criteria. Consequently, this HSVR model can be employed to forecast the Caco-2 permeability to assist drug discovery and development.

show abstract

Section: Introductionsupporting

confidence: 62%

“…HSVR has a higher level of predictivity and broader applicability domain (AD) as compared with SVR, since it can seamlessly combine the advantages of the local model and global model [ 56 ]. More significantly, the superiority of HSVR has been revealed by some studies [ 1 , 54 , 55 , 56 , 57 ].…”

Section: Methodsmentioning

confidence: 99%

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

Jhang

Weng³

et al. 2021

Pharmaceutics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The related analyses implemented by ML mainly include the partial least square (PLS), random forest (RF), K-nearest neighbors (KNN), error back propagation training (EBPT), discrimination analysis (DA), PLS-DA, support vector machine (SVM), and other single classifier algorithms ( Jiang et al, 2020 ; Maharao et al, 2020 ; Spiegel and Senderowitz, 2020 ). Some impediments in using the reported QSAR models have long existed, including variable selection, data redundancy, and a lack of consistent and homogenous data in the public domain ( Lee et al, 2020 ). The accelerated pace of drug discovery has heightened the need for efficient prediction methods.…”

Section: Introductionmentioning

confidence: 99%

Gaultheria leucocarpa var. yunnanensis for Treating Rheumatoid Arthritis—An Assessment Combining Machine Learning–Guided ADME Properties Prediction, Network Pharmacology, and Pharmacological Assessment

et al. 2021

View full text Add to dashboard Cite

Background: Dianbaizhu (Gaultheria leucocarpa var. yunnanensis), a traditional Chinese/ethnic medicine (TC/EM), has been used to treat rheumatoid arthritis (RA) for a long time. The anti–rheumatic arthritis fraction (ARF) of G. yunnanensis has significant anti-inflammatory and analgesic activities and is mainly composed of methyl salicylate glycosides, flavonoids, organic acids, and others. The effective ingredients and rudimentary mechanism of ARF remedying RA have not been elucidated to date.Purpose: The aim of the present study is to give an insight into the effective components and mechanisms of Dianbaizhu in ameliorating RA, based on the estimation of the absorption, distribution, metabolism, and excretion (ADME) properties, analysis of network pharmacology, and in vivo and in vitro validations.Study design and methods: The IL-1β–induced human fibroblast-like synoviocytes of RA (HFLS-RA) model and adjuvant-induced arthritis in the rat model were adopted to assess the anti-RA effect of ARF. The components in ARF were identified by using UHPLC-LTQ-Orbitrap-MSn. The quantitative structure–activity relationship (QSAR) models were developed by using five machine learning algorithms, alone or in combination with genetic algorithms for predicting the ADME properties of ARF. The molecular networks and pathways presumably referring to the therapy of ARF on RA were yielded by using common databases and visible software, and the experimental validations of the key targets conducted in vitro.Results: ARF effectively relieved RA in vivo and in vitro. The five optimized QSAR models that were developed showed robustness and predictive ability. The characterized 48 components in ARF had good biological potency. Four key signaling pathways were obtained, which were related to both cytokine signaling and cell immune response. ARF suppressed IL-1β–induced expression of EGFR, MMP 9, IL2, MAPK14, and KDR in the HFLS-RA .Conclusions: ARF has good druggability and high exploitation potential. Methyl salicylate glycosides and flavonoids play essential roles in attuning RA. ARF may partially attenuate RA by regulating the expression of multi-targets in the inflammation–immune system. These provide valuable information to rationalize ARF and other TC/EMs in the treatment of RA.

show abstract

“…Beyond efficacy, potential drug candidates should have good absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties at a therapeutic dose (Guan et al, 2019). Absorption of drugs relies mainly on intestinal permeability and a drug molecule with human intestinal absorption (absorbance) value of less than 30% is considered to be poorly absorbed (Balimane et al, 2000;Pires et al, 2015;Lee et al, 2020). Carnosol and luteolin compounds from M. tomentosa exhibited good intestinal absorption similar to standard and co-crystallized ligands.…”

Section: Discussionmentioning

confidence: 99%

Phytoconstituents from Markhamia tomentosa Bind To HPV Oncoprotein with Apoptogenic Potential: A Molecular Modeling Approach

Ibrahim

Kola-Mustapha

Adelakun

et al. 2021

Annals of Science and Technology

View full text Add to dashboard Cite

Markhamia tomentosa crude extract and fractions exhibited potent growth inhibitory effects capable to induce apoptosis in cervical (HeLa) cancer cell line via in vitro model. Presently, interaction of M. tomentosa phytoconstituents with molecular drug targets to exert its anticancer property is evaluated via in silico study. Identified phytoconstituents from M. tomentosa were retrieved from PubChem database and docked in active sites of HPV 16 E6, caspase -3 and caspase -8 targets using AutoDockVina from PyRx software. Screening for druglikeness; and absorption, distribution, metabolism, excretion, and toxicity (ADMET) predictions was carried out with the use of SwissADME and pkCSM web servers. Standard melphalan and co-crystallized ligands of caspases -3 and -8 enzymes were used to validate protein-ligand interactions. Molecular dynamic simulation was used to validate the stability of the hit molecules complexed with caspases -3 and -8. All identified phytoconstituents from M. tomentosa showed binding affinity for HPV with docking scores range of - 5.4 to -2.6 kcal/mol. Ajugol, carnosol, luteolin and phytol showed good docking energy range of -6.8 to -3.6 kcal/mol; and -4.8 to -1.9 kcal/mol for the active sites of caspases -3 and -8 targets respectively. Based on docking scores; drug-likeliness; and ADMET predictions; luteolin and carnosol were selected as hit compounds. These molecules were found to be stable within the binding site of caspase -3 target throughout the 40ns simulation time. These findings identified hit ligands from M. tomentosa phytoconstituents that inhibit HPV 16 E6 oncogene expression with stimulation of caspases -3 and -8 targets.

show abstract

In Silico Prediction of Intestinal Permeability by Hierarchical Support Vector Regression

Cited by 12 publications

References 109 publications

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

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

Gaultheria leucocarpa var. yunnanensis for Treating Rheumatoid Arthritis—An Assessment Combining Machine Learning–Guided ADME Properties Prediction, Network Pharmacology, and Pharmacological Assessment

Phytoconstituents from Markhamia tomentosa Bind To HPV Oncoprotein with Apoptogenic Potential: A Molecular Modeling Approach

Contact Info

Product

Resources

About