Computational Modeling of β-Secretase 1 (BACE-1) Inhibitors Using Ligand Based Approaches
Computational Modeling of β-Secretase 1 (BACE-1) Inhibitors Using Ligand Based Approaches
复制标题
DOI：
10.1021/acs.jcim.6b00290
复制
发表时间：
2016-10-01
影响因子：
5.6
通讯作者：
Denny, Rajiah Aldrin
中科院分区：
文献类型：
--
作者：
Subramanian, Govindan;Ramsundar, Bharath;Denny, Rajiah Aldrin
使用基于多种计算机模拟配体的建模方法和统计技术，对文献中报告的不同结构和化学类别的人β-分泌酶1（BACE-1）抑制剂的结合亲和力（IC 50）进行建模。描述符空间包括简单的二进制分子指纹，一维和二维的宪法，物理化学和拓扑描述符，和复杂的三维分子领域，需要适当的结构对齐不同的化学支架在一个通用的化学空间。使用定性分类或定量回归方案对亲和力进行建模，该方案涉及科学文献中用于定量-结构活性关系（QSAR）的线性、非线性和深度神经网络（DNN）机器学习方法。与传统不同的是，类似于20%的化学多样性数据集（205种化合物）用于训练模型，剩余的类似于80%的结构和化学类似物分别用作外部验证（1273种化合物）和前瞻性测试（69种化合物）集的一部分，以确定模型性能。本文研究的机器学习方法在定性分类（类似于70%准确度）和定量IC 50预测（RMSE类似于1 log）两者中表现良好。当与针对hBACE-1抑制剂所追求的基于3D场的技术相比时，基于2D描述符的机器学习方法的成功为在针对其他蛋白质家族的先导鉴定和优化工作期间系统地应用这些方法提供了强大的动力。
The binding affinities (IC50) reported for diverse structural and chemical classes of human beta-secretase 1 (BACE-1) inhibitors in literature were modeled using multiple in silico ligand based modeling approaches and statistical techniques. The descriptor space encompasses simple binary molecular fingerprint, one- and two-dimensional constitutional, physicochemical, and topological descriptors, and sophisticated three-dimensional molecular fields that require appropriate structural alignments of varied chemical scaffolds in one universal chemical space. The affinities were modeled using qualitative classification or quantitative regression schemes involving linear, nonlinear, and deep neural network (DNN) machine-learning methods used in the scientific literature for quantitative-structure activity relationships (QSAR). In a departure from tradition, similar to 20% of the chemically diverse data set (205 compounds) was used to train the model with the remaining similar to 80% of the structural and chemical analogs used as part of an external validation (1273 compounds) and prospective test (69 compounds) sets respectively to ascertain the model performance. The machine -learning methods investigated herein performed well in both the qualitative classification (similar to 70% accuracy) and quantitative IC50 predictions (RMSE similar to 1 log). The success of the 2D descriptor based machine learning approach when compared against the 3D field based technique pursued for hBACE-1 inhibitors provides a strong impetus for systematically applying such methods during the lead identification and optimization efforts for other protein families as well.