Naïve Bayes Classification Using 2D Pharmacophore Feature Triplet Vectors

详细信息    查看全文

• 作者：Paul Watson
• 刊名：Journal of Chemical Information and Modeling
• 出版年：2008
• 出版时间：January 2008
• 年：2008
• 卷：48
• 期：1
• 页码：166 - 178
• 全文大小：2734K
• 年卷期：v.48,no.1(January 2008)
• ISSN：1549-960X

文摘

A naïve Bayes classifier, employed in conjunction with 2D pharmacophore feature triplet vectors describingthe molecules, is presented and validated. Molecules are described using a vector where each element in thevector contains the number of times a particular triplet of atom-based features separated by a set of topologicaldistances occurs. Using the feature triplet vectors it is possible to generate naïve Bayes classifiers thatpredict whether molecules are likely to be active against a given target (or family of targets). Two retrospectivevalidation experiments were performed using a range of actives from WOMBAT, the Prous Integrity database,and the Arena screening library. The performance of the classifiers was evaluated using enrichment curves,enrichment factors, and the BEDROC metric. The classifiers were found to give significant enrichments forthe various test sets.