Scholarlink

<p>Glycogen Synthase Kinase-3 Beta is a multifunctional serine/threonine kinase, involved in regulating multiple cellular processes. Its dysregulation plays a key role in progression of Alzheimer’s disease and no FDA-approved GSK3β inhibitors for AD therapy are available, due to challenges in isoform selectivity, safety and pharmacokinetic limitations. Here, an OECD guideline-compliant, two-stage machine learning-based virtual screening framework is developed for GSK3β inhibitors. A chemically diverse dataset from different databases were pre-processed and used for model development and validation. A comparative study confirmed the superiority of this two-stage approach over standard multiclass models, by yielding significantly higher balanced accuracy on the internal test set (0.86 against 0.74) and specificity. The best predictive models were deployed as an open-access web tool and were used for screening ASINEX Synergy Library. In the structure-based approach, molecular docking with a validated docking protocol was performed and the best molecules were subjected to molecular dynamics simulation, binding free energy and per-residue decomposition analysis. Principal component analysis of trajectories confirmed global stability and consistent binding modes. Cross-screening against the homologous GSK3α isoform and the structurally distinct Cyclin-dependent kinase 2 (CDK2) by molecular docking revealed distinct mechanistic interaction profiles. Rather than exhibiting strict single-target exclusivity, the top hits showed binding affinity profiles consistent with potential CMGC family Multi-Target Directed Ligands (MTDLs), warranting experimental kinome validation. This presumed polypharmacological profile is advantageous for Alzheimer’s therapeutics, positioning these compounds as robust candidates for simultaneously mitigating multiple kinase pathways that drive Tau hyperphosphorylation. Overall, this integrated ML model development, validation, screening, protein selection, molecular docking and molecular dynamics workflow provides a reproducible, interpretable, and high-confidence method for identification of GSK3β inhibitors for Alzheimer’s disease.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrated machine learning, molecular docking, and molecular dynamics simulations for in silico identification of GSK3β inhibitors for Alzheimer’s disease

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月27日

查看全文
  • Dileep Kumar,
  • Ajwin Joseph Martin

摘要

Glycogen Synthase Kinase-3 Beta is a multifunctional serine/threonine kinase, involved in regulating multiple cellular processes. Its dysregulation plays a key role in progression of Alzheimer’s disease and no FDA-approved GSK3β inhibitors for AD therapy are available, due to challenges in isoform selectivity, safety and pharmacokinetic limitations. Here, an OECD guideline-compliant, two-stage machine learning-based virtual screening framework is developed for GSK3β inhibitors. A chemically diverse dataset from different databases were pre-processed and used for model development and validation. A comparative study confirmed the superiority of this two-stage approach over standard multiclass models, by yielding significantly higher balanced accuracy on the internal test set (0.86 against 0.74) and specificity. The best predictive models were deployed as an open-access web tool and were used for screening ASINEX Synergy Library. In the structure-based approach, molecular docking with a validated docking protocol was performed and the best molecules were subjected to molecular dynamics simulation, binding free energy and per-residue decomposition analysis. Principal component analysis of trajectories confirmed global stability and consistent binding modes. Cross-screening against the homologous GSK3α isoform and the structurally distinct Cyclin-dependent kinase 2 (CDK2) by molecular docking revealed distinct mechanistic interaction profiles. Rather than exhibiting strict single-target exclusivity, the top hits showed binding affinity profiles consistent with potential CMGC family Multi-Target Directed Ligands (MTDLs), warranting experimental kinome validation. This presumed polypharmacological profile is advantageous for Alzheimer’s therapeutics, positioning these compounds as robust candidates for simultaneously mitigating multiple kinase pathways that drive Tau hyperphosphorylation. Overall, this integrated ML model development, validation, screening, protein selection, molecular docking and molecular dynamics workflow provides a reproducible, interpretable, and high-confidence method for identification of GSK3β inhibitors for Alzheimer’s disease.