QSAR study of heparanase inhibitors activity using artificial neural networks and Levenberg-Marquardt algorithm
QSAR study of heparanase inhibitors activity using artificial neural networks and Levenberg-Marquardt algorithm
复制标题
DOI：
10.1016/j.ejmech.2007.04.014
复制
发表时间：
2008-03-01
影响因子：
6.7
通讯作者：
Shahbazikhah, P.
中科院分区：
文献类型：
--
作者：
Jalali-Heravi, M.;Asadollahi-Baboh, A.;Shahbazikhah, P.
采用线性和非线性定量构效关系（QSAR）方法对乙酰肝素酶抑制剂的活性进行建模和预测。本研究使用了由92个2，3-二氢-1，3-二氧代-1H-异吲哚-5-羧酸、呋喃基-1，3-噻唑-2-基和苯并恶唑-5-基乙酸衍生物组成的数据集。在大量的描述符，四个参数分类为物理化学，拓扑和电子指数，采用逐步多元回归技术。人工神经网络（ANN）模型的优势，在多元线性回归（MLR）的解释87.9%的变异的乙酰肝素酶抑制剂的抗病毒效力。本文重点研究权重更新函数在开发ANN中的作用。Levenberg-Marquardt（L-M）算法与基本反向传播（BBP）算法和共轭梯度（CG）算法相比具有更好的性能。采用留一法、留多法交叉验证和Y-随机化方法验证了4-3-1 L-M神经网络模型的准确性。描述子的平均效应和敏感性分析表明，log P是影响分子抑制行为的最重要参数。(c)2007年，Elsevier Masson SAS。All rights reserved.
A linear and non-linear quantitative structure-activity relationship (QSAR) study is presented for modeling and predicting heparanase inhibitors' activity. A data set that consisted of 92 derivatives of 2,3-dihydro-1,3-dioxo-1H-isoindole-5-carboxylic acid, furanyl-1,3-thiazol-2yl and benzoxazol-5-yl acetic acids is used in this study. Among a large number of descriptors, four parameters classified as physico-chemical, topological and electronic indices are chosen using stepwise multiple regression technique. The artificial neural networks (ANNs) model shows superiority over the multiple linear regressions (MLR) by accounting 87.9% of the variances of antiviral potency of the heparanase inhibitors. This paper focuses on investigating the role of weight update functions in developing ANNs. Levenberg-Marquardt (L-M) algorithm shows a better performance compared with basic back propagation (BBP) and conjugate gradient (CG) algorithms. The accuracy of 4-3-1 L-M ANN model was illustrated using leave-one-out (LOO), leave-multiple-out (LMO) cross-validations and Y-randomization. The mean effect of descriptors and sensitivity analysis show that log P is the most important parameter affecting the inhibitory behavior of the molecules. (c) 2007 Elsevier Masson SAS. All rights reserved.