基于机器学习和分子对接,对BindingDB数据库连接体对EGFR,HER2,雌激素,孕激素和NF-κB受体进行查
Parham Rezaee1, Shahab Rezaee2, Malik Maaza3
1Department of Biophysics, School of Biological Sciences, Tarbiat Modares University, Tehran, Iran; UNESCO-UNISA-iTLABS Africa Chair in Nanoscience and Nanotechnology (U2ACN2), College of Graduate Studies, University of South Africa (UNISA), Pretoria, South Africa.
这项研究引入了GA-SVM-SVM:GA-SVM-SVM模型用于乳腺癌药物发现,识别了针对EGFR和ER等关键蛋白的有希望的配体,用于新疗法.
科学领域:
- 计算化学是一种计算化学.
- 生物信息学是一种生物信息学.
- 药物发现 药物发现
背景情况:
- 乳腺癌是全球女性的主要癌症,需要新的治疗方法.
- 针对特定的子组 (例如,激素受体阳性/阴性,HER2阳性/阴性) 需要抑制EGFR,HER2,ER,NF-κB和PR等关键蛋白质.
研究的目的:
- 评估乳腺癌候选药物的虚拟查分类方法.
- 识别具有高精度和针对特定乳腺癌标的活性的新型配体.
主要方法:
- 使用二进制和多类分类模型,选择GA-SVM-SVM:GA-SVM-SVM.
- 从BindingDB数据库中对联体进行虚拟选.
- 应用分子对接和药物化学规则用于连接物优先排序.
主要成果:
- 该GA-SVM-SVM:GA-SVM-SVM模型实现了0.74准确度,0.73 F1得分和0.92 AUC.
- 为EGFR+HER2,ER,NF-κB和PR目标确定了成千上万的高精度配体.
- 分子对接揭示了约束能量在-15到-5kcal/mol之间.
结论:
- 该研究成功地确定并优先考虑了乳腺癌治疗的新型候选药物.
- 开发的模型和树图有助于探索针对性治疗的化学空间.
- 选择的配体显示出进一步临床前研究的巨大潜力.
更多相关视频
06:26Nano-Differential Scanning Fluorimetry for Screening in Fragment-based Lead Discovery
Published on: May 16, 2021
13:18Network Pharmacology Prediction and Experimental Validation of Trichosanthes-Fritillaria thunbergii Action Mechanism Against Lung Adenocarcinoma
Published on: March 3, 2023
相关概念视频
Ligand Binding Sites
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
The Equilibrium Binding Constant and Binding Strength
