A Recurrent Neural Network model to predict blood–brain barrier permeability

Alsenan, Shrooq; Al-Turaiki, Isra; Hafez, Alaaeldin M.

doi:10.1016/j.compbiolchem.2020.107377

Cited by 51 publications

(31 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…External estimates of probability that a compound will undergo active efflux mediated by P-glycoprotein (P-gp) can also be included [21,24,37]. In other approaches, large pools of various 1D, 2D (including molecular fingerprints), and 3D molecular descriptors calculated by different methods [26,[38][39][40][41][42][43][44][45][46][47][48][49][50][51][52] are analyzed by various statistical learning techniques, e.g., multiple linear regression, linear discriminant analysis, partial least squares regression, support vector machines, artificial neural networks, random forests, etc., often in combination with some descriptor selection protocols [23,24,26,[43][44][45][46][47][48][49][50][51][52]. However, the limited size of the training sets, use of unverified data, and too-small modeling errors for such an inherently noisy endpoint often give rise to the concerns of possible model overfitting [16].…”

Section: Introductionmentioning

confidence: 99%

Towards Deep Neural Network Models for the Prediction of the Blood–Brain Barrier Permeability for Diverse Organic Compounds

2020

View full text Add to dashboard Cite

Permeation through the blood–brain barrier (BBB) is among the most important processes controlling the pharmacokinetic properties of drugs and other bioactive compounds. Using the fragmental (substructural) descriptors representing the occurrence number of various substructures, as well as the artificial neural network approach and the double cross-validation procedure, we have developed a predictive in silico LogBB model based on an extensive and verified dataset (529 compounds), which is applicable to diverse drugs and drug-like compounds. The model has good predictivity parameters (Q2=0.815, RMSEcv=0.318) that are similar to or better than those of the most reliable models available in the literature. Larger datasets, and perhaps more sophisticated network architectures, are required to realize the full potential of deep neural networks. The analysis of fragment contributions reveals patterns of influence consistent with the known concepts of structural characteristics that affect the BBB permeability of organic compounds. The external validation of the model confirms good agreement between the predicted and experimental LogBB values for most of the compounds. The model enables the evaluation and optimization of the BBB permeability of potential neuroactive agents and other drug compounds.

show abstract

Section: Introductionmentioning

confidence: 99%

Towards Deep Neural Network Models for the Prediction of the Blood–Brain Barrier Permeability for Diverse Organic Compounds

2020

View full text Add to dashboard Cite

show abstract

“…The proposed solution is to apply oversampling techniques to balance the ratio between the two classes. Alsenan et al (2020) have employed Synthetic Minority Oversampling Technique (SMOTE) as the re-sampling method to balance the class imbalance. This work will test the SMOTE and Adaptive Synthetic (ADASYN) sampling algorithms to balance classes.…”

Section: Methodsmentioning

confidence: 99%

Optimizing blood–brain barrier permeation through deep reinforcement learning for de novo drug design

et al. 2021

View full text Add to dashboard Cite

Motivation The process of placing new drugs into the market is time-consuming, expensive and complex. The application of computational methods for designing molecules with bespoke properties can contribute to saving resources throughout this process. However, the fundamental properties to be optimized are often not considered or conflicting with each other. In this work, we propose a novel approach to consider both the biological property and the bioavailability of compounds through a deep reinforcement learning framework for the targeted generation of compounds. We aim to obtain a promising set of selective compounds for the adenosine A2A receptor and, simultaneously, that have the necessary properties in terms of solubility and permeability across the blood–brain barrier to reach the site of action. The cornerstone of the framework is based on a recurrent neural network architecture, the Generator. It seeks to learn the building rules of valid molecules to sample new compounds further. Also, two Predictors are trained to estimate the properties of interest of the new molecules. Finally, the fine-tuning of the Generator was performed with reinforcement learning, integrated with multi-objective optimization and exploratory techniques to ensure that the Generator is adequately biased. Results The biased Generator can generate an interesting set of molecules, with approximately 85% having the two fundamental properties biased as desired. Thus, this approach has transformed a general molecule generator into a model focused on optimizing specific objectives. Furthermore, the molecules’ synthesizability and drug-likeness demonstrate the potential applicability of the de novo drug design in medicinal chemistry. Availability and implementation All code is publicly available in the https://github.com/larngroup/De-Novo-Drug-Design. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

“…This is generally accounted for by the use of resampling and molecular docking simulations, which are simpler and faster than MDS. QSAR studies have thus benefitted from non-linear models, which have machine learning and resampling in-built, which has facilitated the advent of computational neural networks for high throughput nanoparticle permeability studies [215]. These models are more deterministic in nature for examining binding kinetics of nanoparticle-cell interactions, transport across the BBB and biodistribution/biofate.…”

Section: In Silico Simulated Ntp Transport Studiesmentioning

confidence: 99%

Advances in Non-Animal Testing Approaches towards Accelerated Clinical Translation of Novel Nanotheranostic Therapeutics for Central Nervous System Disorders

Lynch

Gobbo

2021

Nanomaterials

View full text Add to dashboard Cite

Nanotheranostics constitute a novel drug delivery system approach to improving systemic, brain-targeted delivery of diagnostic imaging agents and pharmacological moieties in one rational carrier platform. While there have been notable successes in this field, currently, the clinical translation of such delivery systems for the treatment of neurological disorders has been limited by the inadequacy of correlating in vitro and in vivo data on blood–brain barrier (BBB) permeation and biocompatibility of nanomaterials. This review aims to identify the most contemporary non-invasive approaches for BBB crossing using nanotheranostics as a novel drug delivery strategy and current non-animal-based models for assessing the safety and efficiency of such formulations. This review will also address current and future directions of select in vitro models for reducing the cumbersome and laborious mandate for testing exclusively in animals. It is hoped these non-animal-based modelling approaches will facilitate researchers in optimising promising multifunctional nanocarriers with a view to accelerating clinical testing and authorisation applications. By rational design and appropriate selection of characterised and validated models, ranging from monolayer cell cultures to organ-on-chip microfluidics, promising nanotheranostic particles with modular and rational design can be screened in high-throughput models with robust predictive power. Thus, this article serves to highlight abbreviated research and development possibilities with clinical translational relevance for developing novel nanomaterial-based neuropharmaceuticals for therapy in CNS disorders. By generating predictive data for prospective nanomedicines using validated in vitro models for supporting clinical applications in lieu of requiring extensive use of in vivo animal models that have notable limitations, it is hoped that there will be a burgeoning in the nanotherapy of CNS disorders by virtue of accelerated lead identification through screening, optimisation through rational design for brain-targeted delivery across the BBB and clinical testing and approval using fewer animals. Additionally, by using models with tissue of human origin, reproducible therapeutically relevant nanomedicine delivery and individualised therapy can be realised.

show abstract

A Recurrent Neural Network model to predict blood–brain barrier permeability

Cited by 51 publications

References 45 publications

Towards Deep Neural Network Models for the Prediction of the Blood–Brain Barrier Permeability for Diverse Organic Compounds

Towards Deep Neural Network Models for the Prediction of the Blood–Brain Barrier Permeability for Diverse Organic Compounds

Optimizing blood–brain barrier permeation through deep reinforcement learning for de novo drug design

Advances in Non-Animal Testing Approaches towards Accelerated Clinical Translation of Novel Nanotheranostic Therapeutics for Central Nervous System Disorders

Contact Info

Product

Resources

About