Transparent Machine Learning Model to Understand Drug Permeability through the Blood–Brain Barrier DOI Creative Commons

Hengjian Jia,

Gabriele C. Sosso

Journal of Chemical Information and Modeling, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 18, 2024

The blood–brain barrier (BBB) selectively regulates the passage of chemical compounds into and out central nervous system (CNS). As such, understanding permeability drug molecules through BBB is key to treating neurological diseases evaluating response CNS medical treatments. Within last two decades, a diverse portfolio machine learning (ML) models have been regularly utilized as tool predict, and, much lesser extent, understand, several functional properties medicinal drugs, including their propensity pass BBB. However, most numerically accurate date lack in transparency, they typically rely on complex blends different descriptors (or features or fingerprints), many which are not necessarily interpretable straightforward fashion. In fact, "black-box" nature these has prevented us from pinpointing any specific design rule craft next generation pharmaceuticals that need not) this work, we developed ML model leverages an uncomplicated, transparent set predict addition its simplicity, our achieves comparable results terms accuracy compared state-of-the-art models. Moreover, use naive Bayes analytical provide further insights structure–function relation underpins capacity given molecule Although computational rather than experimental, identified molecular fragments groups may significantly impact drug's likelihood permeating This work provides unique angle problem lays foundations for future aimed at leveraging additional descriptors, potentially obtained via bespoke dynamics simulations.

Language: Английский

ARKA: a framework of dimensionality reduction for machine-learning classification modeling, risk assessment, and data gap-filling of sparse environmental toxicity data DOI
Arkaprava Banerjee, Kunal Roy

Environmental Science Processes & Impacts, Journal Year: 2024, Volume and Issue: 26(6), P. 991 - 1007

Published: Jan. 1, 2024

A scatter plot of the data points using values two ARKA descriptors can potentially identify activity cliffs, less confident points, and modelable points.

Language: Английский

Citations

28
Molecular similarity in chemical informatics and predictive toxicity modeling: from quantitative read-across (q-RA) to quantitative read-across structure–activity relationship (q-RASAR) with the application of machine learning DOI
Arkaprava Banerjee, Supratik Kar, Kunal Roy

et al.

Critical Reviews in Toxicology, Journal Year: 2024, Volume and Issue: 54(9), P. 659 - 684

Published: Sept. 3, 2024

This article aims to provide a comprehensive critical, yet readable, review of general interest the chemistry community on molecular similarity as applied chemical informatics and predictive modeling with special focus read-across (RA) structure-activity relationships (RASAR). Molecular similarity-based computational tools, such quantitative (QSARs) RA, are routinely used fill data gaps for wide range properties including toxicity endpoints regulatory purposes. will explore background RA starting from how structural information has been through other contexts physicochemical, absorption, distribution, metabolism, elimination (ADME) properties, biological aspects being characterized. More recent developments RA's integration QSAR have resulted in emergence novel models ToxRead, generalized (GenRA), RASAR (q-RASAR). Conventional techniques excluded this except where necessary context.

Language: Английский

Citations

12
How to correctly develop q-RASAR models for predictive cheminformatics DOI
Arkaprava Banerjee, Kunal Roy

Expert Opinion on Drug Discovery, Journal Year: 2024, Volume and Issue: 19(9), P. 1017 - 1022

Published: July 5, 2024

Language: Английский

Citations

11
Computational Modeling of Pharmaceuticals with an Emphasis on Crossing the Blood–Brain Barrier DOI Creative Commons

Patrícia Alencar Alves,

Luana Cristina Camargo, Gabriel Souza

et al.

Pharmaceuticals, Journal Year: 2025, Volume and Issue: 18(2), P. 217 - 217

Published: Feb. 6, 2025

The discovery and development of new pharmaceutical drugs is a costly, time-consuming, highly manual process, with significant challenges in ensuring drug bioavailability at target sites. Computational techniques are employed design, particularly to predict the pharmacokinetic properties molecules. One major kinetic challenge central nervous system permeation through blood–brain barrier (BBB). Several different computational used evaluate both BBB permeability delivery. Methods such as quantitative structure–activity relationships, machine learning models, molecular dynamics simulations, end-point free energy calculations, or transporter models have pros cons for development, all contributing better understanding specific characteristic. Additionally, design (assisted not by computers) prodrug nanoparticle-based delivery systems can enhance leveraging enzymatic activation transporter-mediated uptake. Neuroactive peptide also relevant field since biopharmaceuticals on edge discovery. By integrating these formulation-based strategies, researchers rational BBB-permeable while minimizing off-target effects. This review valuable selectivity principles latest silico nanotechnological approaches improving CNS

Language: Английский

Citations

1
Quantitative read-across structure-activity relationship (q-RASAR): A novel approach to estimate the subchronic oral safety (NOAEL) of diverse organic chemicals in rats DOI

Shilpayan Ghosh,

Kunal Roy

Toxicology, Journal Year: 2024, Volume and Issue: 505, P. 153824 - 153824

Published: May 4, 2024

Language: Английский

Citations

7
The application of chemical similarity measures in an unconventional modeling framework c-RASAR along with dimensionality reduction techniques to a representative hepatotoxicity dataset DOI Creative Commons
Arkaprava Banerjee, Kunal Roy

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Sept. 6, 2024

With the exponential progress in field of cheminformatics, conventional modeling approaches have so far been to employ supervised and unsupervised machine learning (ML) deep models, utilizing standard molecular descriptors, which represent structural, physicochemical, electronic properties a particular compound. Deviating from approach, this investigation, we employed classification Read-Across Structure-Activity Relationship (c-RASAR), involves amalgamation concepts classification-based quantitative structure-activity relationship (QSAR) incorporate Read-Across-derived similarity error-based descriptors into statistical framework. ML models developed these RASAR use similarity-based information close source neighbors query We different algorithms on selected QSAR develop predictive for efficient prediction compounds' hepatotoxicity. The predictivity each was evaluated large number test set compounds. best-performing model also used screen true external data set. explainable AI (XAI) coupled with were interpret contributions best c-RASAR explain chemical diversity dataset. application various dimensionality reduction techniques like t-SNE UMAP ARKA framework showed usefulness over their ability group similar compounds, enhancing modelability dataset efficiently identifying activity cliffs. Furthermore, cliffs identified by observing nature compounds constituting nearest On comparing our simple linear previously reported using same derived US FDA Orange Book ( https://www.accessdata.fda.gov/scripts/cder/ob/index.cfm ), it observed that is simple, reproducible, transferable, highly predictive. performance LDA supersedes work. Therefore, present can be predict hepatotoxicity chemicals.

Language: Английский

Citations

4
Machine learning assisted classification RASAR modeling for the nephrotoxicity potential of a curated set of orally active drugs DOI Creative Commons
Arkaprava Banerjee, Kunal Roy

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 4, 2025

We have adopted the classification Read-Across Structure–Activity Relationship (c-RASAR) approach in present study for machine-learning (ML)-based model development from a recently reported curated dataset of nephrotoxicity potential orally active drugs. initially developed ML models using nine different algorithms separately on topological descriptors (referred to as simply "descriptors" subsequent sections manuscript) and MACCS fingerprints "fingerprints" manuscript), thus generating 18 QSAR models. Using chemical spaces defined by modeling fingerprints, similarity error-based RASAR were computed, most discriminating used develop another set c-RASAR All 36 cross-validated 20 times with fivefold cross-validation strategy, their predictivity was checked test data. A multi-criteria decision-making strategy – Sum Ranking Differences (SRD) approach—was identify best-performing based robustness external validation parameters. This statistical analysis suggested that had an overall good performance, while also (LDA derived descriptors, MCC values 0.229 0.431 training sets, respectively). screen true data prepared known nephrotoxic compounds DrugBankDB, demonstrating predictivity.

Language: Английский

Citations

0
Motor Neuron Disorder DOI
Poonam Maurya, Preeti Gupta,

K. A. Shaima

et al.

Advances in medical education, research, and ethics (AMERE) book series, Journal Year: 2025, Volume and Issue: unknown, P. 541 - 584

Published: Jan. 10, 2025

Motor neuron disorder (MND) affects brain and spinal cord motor neurons that drive muscle movement. disease-induced degeneration limits limb movements, breathing, eating, speaking. Riluzole, edaravone, levodopa, baclofen, phenytoin, quinine, amitriptyline, fluvoxamine are FDA-approved MND drugs. They have several side effects barely extend the patient's life by two to three months. These treatments threaten long-term drug use. Thus, treatment must be low-cost, natural, relatively side-effect-free. Ayurveda, Unani, Siddha, Chinese, homoeopathy all researched a variety of plants for their ability treat MND. Ayurvedic, Siddha traditional medical systems among those worldwide authorised use herbal in This chapter discusses aetiology, conventional treatments, neuroprotective phytochemical research, national regulations, nano-formulation breakthroughs treatment.

Language: Английский

Citations

0
Retro-forward synthesis design and experimental validation of potent structural analogs of known drugs DOI Creative Commons

Ahmad Makkawi,

Wiktor Beker, Agnieszka Wołos

et al.

Chemical Science, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Generation of structural analogs to "parent" molecule(s) interest remains one the important elements drug development. Ideally, such should be synthesizable by concise and robust synthetic routes. The current work illustrates how this process can facilitated a computational pipeline spanning (i) diversification parent via substructure replacements aimed at enhancing biological activity, (ii) retrosynthesis thus generated "replicas" identify substrates, (iii) forward syntheses originating from these substrates (and synthetically versatile "auxiliaries") guided "towards" parent, (iv) evaluation candidates for target binding other medicinal-chemical properties. This proposes thousands readily makeable in matter minutes, is deployed here validate experiment seven Ketoprofen six Donepezil. concise, computer-designed are confirmed 12 out 13 cases, offering access several potent inhibitors. While synthesis-design component robust, affinities predicted less accurately although still order-of-magnitude, which may valuable discerning promising inadequate binders.

Language: Английский

Citations

0
Recent progress on nanotechnologies for enhancing blood‐brain barrier permeability DOI Creative Commons
Qibin Liu,

Z.P. Chen,

Anthony Guiseppi‐Elie

et al.

Smart Molecules, Journal Year: 2025, Volume and Issue: unknown

Published: March 20, 2025

Abstract The blood‐brain barrier (BBB) is a substantial impediment to effectively delivering central nervous system (CNS) therapies. In this review, we provide comprehensive dissection of the BBB's elaborate structure and function discuss inherent limitations conventional drug delivery mechanisms due its impermeability. We summarized creative deployment nanocarriers, astute modification small molecules bolster their CNS penetration capabilities as well burgeoning potential magnetic nanoparticles optical techniques that are positioned enable more precise targeted across BBB current clinical application some nanomedicines. addition, emphasize indispensable role artificial intelligence in designing novel materials paramount significance interdisciplinary research surmounting challenges associated with penetration. Our review meticulously integrates these insights accentuate impact nanotechnological innovations disease management. It presents promising trajectory for evolution patient care neurological disorders suggests scientific strides could lead efficacious treatments improved outcomes those afflicted such conditions.

Language: Английский

Citations

0