In Silico Prediction of Blood Brain Barrier Permeability:  An Artificial Neural Network Model

Garg, Prabha; Verma, Jaya

doi:10.1021/ci050303i

Cited by 123 publications

(86 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When results obtained using the AS measurement were compared with those summarized in previous QSAR models, 24,25 the AS predictive ability achieved compares reasonably well with that of approaches based on 3D methods and on the use of both physical-chemical descriptors and neural networks (the latter approach showed r 2 parameter values between 0.80 and 0.90 in training and test, and errors around 0.30). Simplicity of our method is ensured by both the topological similarity calculation and the use of linear regression techniques.…”

Section: External Validationsmentioning

confidence: 55%

“…But the development of new models has also the aim of both helping and reducing in-vivo and in-vitro experimentation by screening of large data sets. With this purpose, new approaches have been recently carried out, 24,25 thus enabling the comparison of the method proposed here with them. This work has been divided as follows: after this introductory section, the methodology proposed (new isomorphism detection and data fusion formulas) and the chemical and chemometric information (structures, properties, data preparation and data set statistical information) are summarized in Methodology and Chemical Structures section.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

QSAR models based on isomorphic and nonisomorphic data fusion for predicting the blood brain barrier permeability

2007

View full text Add to dashboard Cite

A QSAR model for predicting the blood brain barrier permeability (BBBP) in a large and heterogeneous variety of compounds (136 compounds) has been developed using approximate similarity (AS) matrices as predictors and PLS as multivariate regression technique. AS values fuse information of both the isomorphic similarity and nonisomorphic dissimilarity with the purpose of achieving an accurate predictive space. In addition to the fact of applying AS values to heterogeneous data sets, a new concept on graph isomorphism based on the extended maximum common subgraph (EMCS) is defined for the building of AS spaces considering the atoms and bonds, which are bridges between the isomorphic and nonisomorphic substructures. This new isomorphism detection has as objective to take into account the position and nature of the nucleus substituents, thus allowing the development of accurate models for large and diverse sets of compounds. After an outliers study, the training and test stages were made and the results obtained using several AS approaches were compared. Several validation processes were carried out by means of employing several test sets, and high predictive ability was obtained for all the cases (Q(2) = 0.81 and standard error in prediction, SEP = 0.29).

show abstract

Section: External Validationsmentioning

confidence: 55%

Section: Introductionmentioning

confidence: 99%

QSAR models based on isomorphic and nonisomorphic data fusion for predicting the blood brain barrier permeability

2007

View full text Add to dashboard Cite

show abstract

“…Four models consider, besides passive passage, also active transport such as by the efflux pump P-glycoprotein (P-gp) (Chen et al, 2009;Garg & Verma, 2006;Iyer et al, 2002 andSuenderhauf et al, 2012) Whether a substance is actively transported through the BBB depends on the properties of that substance, but may also be influenced by the presence of another substance that acts as transport inhibitors. One model, trained with alcohols, estimates the impact on Na+/K+-ATPase and AchE activity (indicators of CNS membrane fluidity).…”

Section: Models On Blood-brain-barrier (Bbb) Permeation and Neurotoximentioning

confidence: 99%

Literature review and appraisal on alternative neurotoxicity testing methods

Masjosthusmann

Barenys

El‐Gamal

et al. 2018

EFSA Supporting Publications

View full text Add to dashboard Cite

The goal of this review was the evaluation of information on assessment methods in the field of alternative neurotoxicity (NT) testing. We therefore performed a systematic and comprehensive collection of scientific literature (in English) from the past 27 years until mid of 2017 on state of the art alternative testing methods including in vitro test methods, in silico methods and alternative non-mammalian models. This review identified a variety of test methods that have the ability to predict NT of chemicals based on predefined key NT endpoint categories (27). Those endpoint categories were derived from the Mode of Action (MoA) of known human neurotoxicants. Pre-evaluated MoAs of human neurotoxicants allowed the identification of performance characteristics with regard to the ability of a test system to correctly predict a chemical effect on an endpoint category. The most predictive in vitro model that covers a large variety of endpoint categories are primary rodent cells or tissues. Human based systems derived from induced pluripotent stem cells (iPSC) are promising and warrant human relevance. There is however not yet sufficient data on these models to demonstrate their suitability to reliably substitute primary rodent cells for NT testing purposes. Test methods for glia toxicity are rare and glia endpoint categories are clearly underrepresented. Therefore, a focus for future method development should be placed on glia, astrocytes, oligodendrocytes and microglia based models, preferably in a co-culture se up. The review on in silico methods, resulted into 54 QSARs publications, relevant for NT, of which 39 on blood brain barrier (BBB) permeation. The QSARs available in the publications were developed from data on drugs and chemicals, but there appears a limited set of experimental data for chemicals and pesticides on blood-brain barrier passage. The evaluation of NT methods using alternative whole organism approaches demonstrated a majority of data for C. elegans (nematode species), represented with high true prediction (96%). The main endpoint category was inhibition of cholinergic transmission, with specific endpoints for AChE activity and motor activity, the latter confirming the added value of a whole organism approach among alternative models. Though D. rerio, the zebrafish model appeared a www.efsa.europa.eu/publications 2 EFSA Supporting publication 2018:EN-1410The present document has been produced and adopted by the bodies identified above as authors. This task has been carried out exclusively by the authors in the context of a contract between the European Food Safety Authority and the authors, awarded following a tender procedure. The present document is published complying with the transparency principle to which the Authority is subject. It may not be considered as an output adopted by the Authority. The European Food Safety Authority reserves its rights, view and position as regards the issues addressed and the conclusions reached in the present document, without prejudice to the rights ...

show abstract

“…High-throughput in silico models have been investigated as predictors of in vivo BBB permeability (Garg and Verma, 2006;Goodwin and Clark, 2005;Liu et al, 2004). Based on physical parameter properties such as octanol-water partition coefficient (logPoct), hydrogen-bonding potential (Δlog P), molecular polar surface area (PSA), and surface tension (Liu et al, 2004), they essentially predict passive transcellular diffusion.…”

Section: In Vitro Bbb Modelsmentioning

confidence: 99%

In vitro blood brain barrier models as a screening tool for colloidal drug delivery systems and other nanosystems

Garcel

Martel

Carrupt

et al. 2010

IJBNN

View full text Add to dashboard Cite

The brain is one of the least accessible organs of the body due to the presence of the blood-brain barrier (BBB), thus making drug delivery to the brain quite a challenge. Various strategies have been explored to circumvent this physiological barrier, including the use of colloidal carriers. These carriers hold great promise as they may increase the delivery of drugs into the brain by protecting them from degradation and prolonging their circulation in the blood, as well as promoting their transport through the BBB. Moreover, functionalisation of these carriers with various ligands allows specific targeting of the central nervous system compartment. Additionally, various in vitro BBB models have been developed and are increasingly useful for screening of drug delivery systems, especially cell-based models that provide mechanistic information. In fact, this paper specifically reviews selected in vitro BBB models as a screening tool for drug delivery colloidal systems.Keywords: drug delivery; colloidal systems; nanocarriers; nanoparticles; liposomes; micelles; blood-brain barrier; BBB; in vitro model.Reference to this paper should be made as follows: Garcel, A., Martel, S., Carrupt, P.A., Doelker, E. and Delie, F. (2010) 'In vitro blood brain barrier models as a screening tool for colloidal drug delivery systems and other nanosystems', Int.

show abstract

In Silico Prediction of Blood Brain Barrier Permeability: An Artificial Neural Network Model

Cited by 123 publications

References 52 publications

QSAR models based on isomorphic and nonisomorphic data fusion for predicting the blood brain barrier permeability

QSAR models based on isomorphic and nonisomorphic data fusion for predicting the blood brain barrier permeability

Literature review and appraisal on alternative neurotoxicity testing methods

In vitro blood brain barrier models as a screening tool for colloidal drug delivery systems and other nanosystems

Contact Info

Product

Resources

About