当前位置: X-MOL 学术Curr. Comput.-Aided Drug Des. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
The Quantitative Structure-Activity Relationships between GABAA Receptor and Ligands based on Binding Interface Characteristic.
Current Computer-Aided Drug Design ( IF 1.7 ) Pub Date : 2021-01-01 , DOI: 10.2174/1573409916666200724153240
Shu Cheng 1 , Yanrui Ding 1
Affiliation  

BACKGROUND Quantitative Structure Activity Relationship (QSAR) methods based on machine learning play a vital role in predicting biological effect. OBJECTIVE Considering the characteristics of the binding interface between ligands and the inhibitory neurotransmitter Gamma-Aminobutyric Acid A(GABAA) receptor, we built a QSAR model of ligands that bind to the human GABAA receptor. METHODS After feature selection with Mean Decrease Impurity, we selected 53 from 1,286 docked ligand molecular descriptors. Three QSAR models are built using a gradient boosting regression tree algorithm based on the different combinations of docked ligand molecular descriptors and ligand receptor interaction characteristics. RESULTS The features of the optimal QSAR model contain both the docked ligand molecular descriptors and ligand-receptor interaction characteristics. The Leave-One-Out-Cross-Validation (Q2 LOO) of the optimal QSAR model is 0.8974, the Coefficient of Determination (R2) for the testing set is 0.9261, the Mean Square Error (MSE) is 0.1862. We also used this model to predict the pIC50 of two new ligands, the differences between the predicted and experimental pIC50 are -0.02 and 0.03, respectively. CONCLUSION We found the BELm2, BELe2, MATS1m, X5v, Mor08v, and Mor29m are crucial features, which can help to build the QSAR model more accurately.

中文翻译:

基于结合界面特征的 GABAA 受体与配体之间的定量构效关系。

背景技术基于机器学习的定量结构活性关系(QSAR)方法在预测生物效应方面发挥着至关重要的作用。目的考虑配体与抑制性神经递质γ-氨基丁酸A(GABAA)受体结合界面的特点,建立与人GABAA受体结合的配体QSAR模型。方法 在使用平均减少杂质进行特征选择后,我们从 1,286 个对接配体分子描述符中选择了 53 个。基于对接配体分子描述符和配体受体相互作用特征的不同组合,使用梯度提升回归树算法构建了三个 QSAR 模型。结果最优QSAR模型的特征包括对接配体分子描述符和配体-受体相互作用特征。最优 QSAR 模型的 Leave-One-Out-Cross-Validation (Q2 LOO) 为 0.8974,测试集的确定系数 (R2) 为 0.9261,均方误差 (MSE) 为 0.1862。我们还使用该模型来预测两个新配体的 pIC50,预测和实验 pIC50 之间的差异分别为 -0.02 和 0.03。结论 我们发现 BELm2、BELe2、MATS1m、X5v、Mor08v 和 Mor29m 是关键特征,有助于更准确地构建 QSAR 模型。我们还使用该模型来预测两个新配体的 pIC50,预测和实验 pIC50 之间的差异分别为 -0.02 和 0.03。结论 我们发现 BELm2、BELe2、MATS1m、X5v、Mor08v 和 Mor29m 是关键特征,有助于更准确地构建 QSAR 模型。我们还使用该模型来预测两个新配体的 pIC50,预测和实验 pIC50 之间的差异分别为 -0.02 和 0.03。结论 我们发现 BELm2、BELe2、MATS1m、X5v、Mor08v 和 Mor29m 是关键特征,有助于更准确地构建 QSAR 模型。
更新日期:2020-07-24
down
wechat
bug