DemQSAR: predicting human volume of distribution and clearance of drugs
DemQSAR: predicting human volume of distribution and clearance of drugs
复制标题
DOI：
10.1007/s10822-011-9496-z
复制
发表时间：
2011-12-01
影响因子：
3.5
通讯作者：
Knapp, Ernst-Walter
中科院分区：
文献类型：
--
作者：
Demir-Kavuk, Ozgur;Bentzien, Joerg;Knapp, Ernst-Walter
通过计算机方法表征分子化合物的药理学相关特性可以加速新药的鉴定并降低其开发成本。定量结构-活性/性质关系（QSAR/QSPR）将分子化合物的结构和物理化学性质与所研究的特定功能活性/性质相关联。通常会为化合物生成大量分子特征。在许多情况下，生成的特征数量超过了可用于学习的具有已知属性值的分子化合物的数量。在这种情况下，机器学习方法往往会过度拟合训练数据，即该方法会根据训练数据的非常具体的特征进行调整，而这些特征并不适合所考虑的属性。这个问题可以通过减少不重要、冗余甚至误导性特征的影响来缓解。更好的策略是完全消除这些功能。理想情况下，分子特性可以通过少量化学上可解释的特征来描述。本贡献的目的是提供一种预测建模方法，它将特征生成、特征选择、模型构建和过度训练控制结合到一个名为 DemQSAR 的单个应用程序中。 DemQSAR 用于预测人体分布容积 (VDss) 和人体清除率 (CL)。为了控制过度训练，采用了二次和线性正则化项。使用递归特征选择方法来减少描述符的数量。预测性能与最近文献中报道的最佳预测一样好。此处提供的示例表明 DemQSAR 可以生成使用很少特征的模型，同时保持高预测能力。 DemPRED 网页上提供了用于任何用户定义属性的模型构建的独立 DemQSAR Java 应用程序以及用于预测人类 VDss 和 CL 的 Web 界面：http://agknapp.chemie.fu-berlin.de/dempred/。
In silico methods characterizing molecular compounds with respect to pharmacologically relevant properties can accelerate the identification of new drugs and reduce their development costs. Quantitative structure-activity/-property relationship (QSAR/QSPR) correlate structure and physico-chemical properties of molecular compounds with a specific functional activity/property under study. Typically a large number of molecular features are generated for the compounds. In many cases the number of generated features exceeds the number of molecular compounds with known property values that are available for learning. Machine learning methods tend to overfit the training data in such situations, i.e. the method adjusts to very specific features of the training data, which are not characteristic for the considered property. This problem can be alleviated by diminishing the influence of unimportant, redundant or even misleading features. A better strategy is to eliminate such features completely. Ideally, a molecular property can be described by a small number of features that are chemically interpretable. The purpose of the present contribution is to provide a predictive modeling approach, which combines feature generation, feature selection, model building and control of overtraining into a single application called DemQSAR. DemQSAR is used to predict human volume of distribution (VDss) and human clearance (CL). To control overtraining, quadratic and linear regularization terms were employed. A recursive feature selection approach is used to reduce the number of descriptors. The prediction performance is as good as the best predictions reported in the recent literature. The example presented here demonstrates that DemQSAR can generate a model that uses very few features while maintaining high predictive power. A standalone DemQSAR Java application for model building of any user defined property as well as a web interface for the prediction of human VDss and CL is available on the webpage of DemPRED: http://agknapp.chemie.fu-berlin.de/dempred/.