Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universität Bonn, Dahlmannstrasse 2, Bonn, Germany.
Chem Biol Drug Des. 2011 Jan;77(1):30-8. doi: 10.1111/j.1747-0285.2010.01059.x. Epub 2010 Nov 29.
Support vector machine modeling has become increasingly popular in chemoinformatics. Recently, several advanced support vector machine applications have been reported including, among others, multitask learning for ligand-target prediction. Here, we introduce another support vector machine approach to add compound potency information to similarity searching and enrich database selection sets with potent hits. For this purpose, we introduce a structure-activity kernel function and a potency-oriented support vector machine linear combination approach. Using fingerprint descriptors, potency-directed support vector machine searching has been successfully applied to four high-throughput screening data sets, and different support vector machine strategies have been compared. For potency-balanced compound reference sets, potency-directed support vector machine searching meets or exceeds recall rates of standard support vector machine calculations but detects many more potent hits.
支持向量机建模在化学生物信息学中变得越来越流行。最近，已经有几项先进的支持向量机应用被报道，包括配体-靶标预测的多任务学习等。在这里，我们引入了另一种支持向量机方法，将化合物效力信息添加到相似性搜索中，并使用有效命中物来丰富数据库选择集。为此，我们引入了一种结构-活性核函数和一种基于效力的支持向量机线性组合方法。使用指纹描述符，基于效力的支持向量机搜索已成功应用于四个高通量筛选数据集，并对不同的支持向量机策略进行了比较。对于效力平衡的化合物参考集，基于效力的支持向量机搜索达到或超过了标准支持向量机计算的召回率，但检测到了更多的有效命中物。
