Scholarlink

<p>Human acetylcholinesterase (AChE) plays a pivotal role in the central nervous system and responsible for Alzheimers disease. This is a significant target for therapeutic drugs. Employing a machine learning XGBoost model trained on 3000 known AChE inhibitors yielded a commendable accuracy value of 0.875. This model was then employed to screen a vast database, leading to the identification of the top 10 molecules through docking-based virtual screening. Subsequently, these top 10 molecules underwent assessment for ADME properties, with a particular focus on the blood–brain barrier as a crucial factor for AChE inhibition. Following 100&#xa0;ns molecular dynamics simulations and the output of molecular docking, the two best compounds, Z26394837 and Z95618476, were identified based on their stability in the AChE proteins active site.</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

Identifying acetylcholinesterase inhibitors using machine learning, docking, and molecular dynamics simulations

  • 期刊论文

  • 发表日期：

    2025年11月4日

查看全文
  • Uppula Purushotham,
  • Karunakar Tanneeru,
  • Stephen Abhishek Raju

摘要

Human acetylcholinesterase (AChE) plays a pivotal role in the central nervous system and responsible for Alzheimers disease. This is a significant target for therapeutic drugs. Employing a machine learning XGBoost model trained on 3000 known AChE inhibitors yielded a commendable accuracy value of 0.875. This model was then employed to screen a vast database, leading to the identification of the top 10 molecules through docking-based virtual screening. Subsequently, these top 10 molecules underwent assessment for ADME properties, with a particular focus on the blood–brain barrier as a crucial factor for AChE inhibition. Following 100 ns molecular dynamics simulations and the output of molecular docking, the two best compounds, Z26394837 and Z95618476, were identified based on their stability in the AChE proteins active site.