Quantitative structure–activity relationship prediction of blood-to-brain partitioning behavior using support vector machine

Golmohammadi, Hassan; Dashtbozorgi, Zahra; Acree, William E.

doi:10.1016/j.ejps.2012.06.021

Cited by 80 publications

(21 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In such cases, data-driven approaches can be useful, because strong mechanistic understanding is not required for these approaches. The relevance of such empirical, data-driven modeling for predicting partitioning into the blood-brain barrier has already been widely demonstrated (13,(16)(17)(18)(19).…”

Section: Introductionmentioning

confidence: 99%

Structure-Based Prediction of Anti-infective Drug Concentrations in the Human Lung Epithelial Lining Fluid

et al. 2015

View full text Add to dashboard Cite

Purpose Obtaining pharmacologically relevant exposure levels of antibiotics in the epithelial lining fluid (ELF) is of critical importance to ensure optimal treatment of lung infections. Our objectives were to develop a model for the prediction of the ELF-plasma concentration ratio (EPR) of antibiotics based on their chemical structure descriptors (CSDs). Methods EPR data was obtained by aggregating ELF and plasma concentrations from historical clinical studies investigating antibiotics and associated agents. An elastic net regularized regression model was used to predict EPRs based on a large number of CSDs. The model was tuned using leave-one-drug-out cross validation, and the predictions were further evaluated using a test dataset. Results EPR data of 56 unique compounds was included. A high degree of variability in EPRs both between-and within drugs was apparent. No trends related to study design or pharmacokinetic factors could be identified. The model predicted 80% of the within-drug variability (R 2 WDV ) and 78.6% of drugs were within 3-fold difference from the observations. Key CSDs were related to molecular size and lipophilicity. When predicting EPRs for a test dataset the R 2 WDV was 75%. Conclusions This model is of relevance to inform dose selection and optimization during antibiotic drug development of agents targeting lung infections.

show abstract

Section: Introductionmentioning

confidence: 99%

Structure-Based Prediction of Anti-infective Drug Concentrations in the Human Lung Epithelial Lining Fluid

et al. 2015

View full text Add to dashboard Cite

show abstract

“…To check for actual predictive capability of the developed models, the dataset for each endpoint was divided prior to model development into a training set (∼70 % of compounds) used for model development and a test set (∼30 % of compounds) used for external validation. Sorted response [Dataset Division GUI 1.2, Version‐1.2, Kolkata, India, 2017; Software available at http://dtclab.webs.com/software‐tools], Euclidean distance and Kennard‐Stone techniques (available at http://dtclab.webs.com/software‐tools) were used for splitting the respective datasets into training and test sets. In the Kennard‐Stone algorithm, at first, two compounds with the highest distance (we have utilized Euclidean distance as a measure of distance) between them are placed in the training set, and the remaining training set compounds are then selected by finding maximum of the minimum distances between the selected training set compounds and the remaining compounds of the dataset.…”

Section: Methodsmentioning

confidence: 99%

Ecotoxicological Modeling, Ranking and Prioritization of Pharmaceuticals Using QSTR and i‐QSTTR Approaches: Application of 2D and Fragment Based Descriptors

Khan

Kar

Sanderson

et al. 2018

Molecular Informatics

View full text Add to dashboard Cite

This paper is dedicated to Prof. Paola Gramatica on the occasion of her retirement.Abstract: There is a huge lack of experimental data on ecotoxicity of pharmaceuticals, while existing resources are insufficient to gather these data against all possible environmental endpoints. Computational tools such as quantitative structure-toxicity relationship (QSTR) can help us to a great extent to overcome this problem through filling of data gaps. In the current study, QSTR models have been developed for toxicity of 260 diverse pharmaceuticals on three different trophic level species namely algae, daphnia and fish, using partial least squares (PLS) regression approach with 2D descriptors selected through a genetic algorithm approach in order to study underlying chemical features responsible for the observed acute toxicity. The final obtained statistically reliable QSTR models were extensively validated following the OECD guidelines. Interspecies quantitative structure-toxicity-toxicity (QSTTR) models were also developed using genetic algorithm followed by multiple linear regression (GA-MLR) approach to check for the pattern of responses observed as we move across the hierarchy of genetics in different taxonomical class. The obtained interspecies models were finally utilized to fill the data gaps for 260 pharmaceuticals, where experimental data were missing for at least one of the endpoints. Finally, a prioritized list for 7106 existing drug like substances was prepared by predicting their acute toxicity using developed QSTR models.

show abstract

“…Three techniques namely SVM, BPNN and MLR are used in the present study. [88][89][90] For the present study n-support vector regression and 3-support vector regression based on LIBSVM are considered, and in each case linear, polynomial, sigmoid, and radial basis functions are used. Support vector machine (SVM).…”

Section: Molecular Structural Data Setmentioning

confidence: 99%

In silico de novo design of novel NNRTIs: a bio-molecular modelling approach

Jain¹,

Gupta

Sapre³

et al. 2015

RSC Adv.

View full text Add to dashboard Cite

Six novel non-nucleoside reverse transcriptase inhibitors exhibiting high efficacy are designed using in silico mathematical modelling techniques and the results are validated using a docking technique. An in silico assessment of interaction potential and structural requirements of 5-alkyl-2-alkylamino-6-(2,6difluorophenylalkyl)-3,4-dihydropyrimidin-4(3H)-one (DABO) analogues in the non-nucleoside inhibitor binding pocket is also performed. Efficient use of 3D-pharamacophoric (S ALL , HD ALL , HA ALL and R ALL ) and 3D-averaged alignment (C log P and dipole moment) descriptors is made in this study. The chemometric analyses, using support vector machine, back propagation neural network and multiple linear regression, are performed. The relative potentials of these chemometric methods is also assessed and the results,indicates that SVM describes the relationship between the descriptors and inhibitory activity in a better manner. The results also suggest that there is a non-linear relationship between the descriptors and inhibitory activity. The study further suggests that isopropyl/propenyl groups as R and R 0 , oxobutyl group as X and di or tri-substitution as R 00 are the best suited substituents for exhibiting better inhibitory activity.View Article Online a pEC 50 ¼ Àlog EC 50 (where EC 50 is the effective concentration of a compound required to activate 50% protection of MT-4 cell against the cytopathic effect of HIV-1). The data points a represent the test set and b as Outliers.This journal is

show abstract

Quantitative structure–activity relationship prediction of blood-to-brain partitioning behavior using support vector machine

Cited by 80 publications

References 50 publications

Structure-Based Prediction of Anti-infective Drug Concentrations in the Human Lung Epithelial Lining Fluid

Structure-Based Prediction of Anti-infective Drug Concentrations in the Human Lung Epithelial Lining Fluid

Ecotoxicological Modeling, Ranking and Prioritization of Pharmaceuticals Using QSTR and i‐QSTTR Approaches: Application of 2D and Fragment Based Descriptors

In silico de novo design of novel NNRTIs: a bio-molecular modelling approach

Contact Info

Product

Resources

About