SAR study on inhibitors of GIIA secreted phospholipase A2 using machine learning methods
SAR study on inhibitors of GIIA secreted phospholipase A2 using machine learning methods
复制标题
使用机器学习方法对 GIIA 分泌型磷脂酶 A2 抑制剂进行 SAR 研究
DOI：
10.1111/cbdd.13470
复制
发表时间：
2019-02
影响因子：
3
通讯作者：
Yan Aixia
中科院分区：
文献类型：
--
作者：
Zhang Shengde;Tu Guiping;Qin Zijian;Li Yang;Chen Guang;Yan Aixia
GIIA 分泌型磷脂酶 A2 (GIIA sPLA2) 是药物发现的有效靶点。为了区分GIIA sPLA2抑制剂的活性水平，我们基于452种化合物，通过支持向量机（SVM）、决策树（DT）和随机森林（RF）三种机器学习算法建立了24个分类模型。这些分子分别由 CORINA 描述符、MACCS 指纹和 ECFP4 指纹表示。通过 Kohonen 的自组织映射 (SOM) 策略和随机策略，将数据集分为包含 312 种化合物的训练集和包含 140 种化合物的测试集。在分子描述符的选择中使用了递归特征消除（RFE）方法和信息增益（IG）方法。获得了三个性能良好的模型。它们是通过 SVM 算法与 CORINA 描述符（模型 1A 和 2A）和 ECFP4 指纹（模型 10A）构建的。在模型10A测试集的预测中，准确率达到90.71%，马修斯相关系数（MCC）值达到0.82。此外，通过K-Means算法将452个抑制剂聚类成8个子集，以分析其结构特征。发现高活性抑制剂主要含有吲哚支架或中氮茚支架和四个侧链。
GIIA secreted phospholipase A2 (GIIA sPLA2) is a potent target for drug discovery. To distinguish the activity level of the inhibitors of GIIA sPLA2, we built 24 classification models by three machine learning algorithms including support vector machine (SVM), decision tree (DT), and random forest (RF) based on 452 compounds. The molecules were represented by CORINA descriptors, MACCS fingerprints, and ECFP4 fingerprints, respectively. The dataset was split into a training set containing 312 compounds and a test set containing 140 compounds by Kohonen's self‐organizing map (SOM) strategy and a random strategy. A recursive feature elimination (RFE) method and an information gain (IG) method were used in the selection of molecular descriptors. Three favorable performing models were obtained. They were built by SVM algorithm with CORINA descriptors (Models 1A and 2A) and ECFP4 fingerprints (Model 10A). In the prediction of test set of Model 10A, the accuracy reached 90.71%, and the Matthews correlation coefficient (MCC) values reached 0.82. In addition, the 452 inhibitors were clustered into eight subsets by K‐Means algorithm for analyzing their structural features. It was found that highly active inhibitors mainly contained indole scaffold or indolizine scaffold and four side chains.
登录
查看更多内容
影响因子：
39.3
作者：
R. Rosenson;M. Elliott;Y. Stasiv;C. Hislop
通讯作者：
R. Rosenson;M. Elliott;Y. Stasiv;C. Hislop
影响因子：
8.8
作者：
Yamashita, S.-I.;Yamashita, J.-I.;Ogawa, M.
通讯作者：
Ogawa, M.
影响因子：
2.7
作者：
Oslund, Rob C.;Cermak, Nathan;Verlinde, Christophe L. M. J.;Gelb, Michael H.
通讯作者：
Gelb, Michael H.
使用指纹描述符对 mPGES-1 抑制剂进行分类的计算模型
影响因子：
3.8
作者：
Xia Zhonghua;Yan Aixia
通讯作者：
Yan Aixia
DOI：
10.1016/s0021-9258(18)83549-9
发表时间：
1989-04
期刊：
The Journal of biological chemistry
影响因子：
--
作者：
J. Seilhamer;Waldemar Pruzanski;P. Vadas;S. Plant;J. Miller;J. Kloss;Lorin K. Johnson
通讯作者：
J. Seilhamer;Waldemar Pruzanski;P. Vadas;S. Plant;J. Miller;J. Kloss;Lorin K. Johnson