Combining Decision Trees and Neural Networks for Drug Discovery
Combining Decision Trees and Neural Networks for Drug Discovery
复制标题
结合决策树和神经网络进行药物发现
DOI：
--
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
B. Buxton
中科院分区：
文献类型：
--
作者：
J. Foster;E. Lutton;Julian F. Miller;C. Ryan;Andrea G B;W. Langdon;S. Barrett;B. Buxton
遗传程序设计（GP）提供了一种通用的方法，自动融合在一起的分类器使用其接收器工作特性（ROC），以产生上级合奏。我们结合联合收割机决策树（C4.5）和人工神经网络（ANN）的一个困难的药物数据挖掘（KDD）的药物发现应用。特别是预测P450酶的抑制。训练数据来自高通量筛选（HTS）运行。演化模型可用于预测虚拟（即，尚待制造的）化学品的行为。还描述了减少过拟合的措施。
Genetic programming (GP) offers a generic method of automatically fusing together classifiers using their receiver operating characteristics (ROC) to yield superior ensembles. We combine decision trees (C4.5) and artificial neural networks (ANN) on a difficult pharmaceutical data mining (KDD) drug discovery application. Specifically predicting inhibition of a P450 enzyme. Training data came from high throughput screening (HTS) runs. The evolved model may be used to predict behaviour of virtual (i.e. yet to be manufactured) chemicals. Measures to reduce over fitting are also described.