首页> 外文会议>Pattern Recognition in Bioinformatics >Identifying Conserved Discriminative Motifs
【24h】

Identifying Conserved Discriminative Motifs

机译:识别保守的区分母题

获取原文
获取原文并翻译 | 示例

摘要

The identification of regulatory motifs underlying gene expression is a challenging problem, particularly in eukaryotes. An algorithm to identify statistically significant discriminative motifs that distinguish between gene expression clusters is presented. The predictive power of the identified motifs is assessed with a supervised Naive Bayes classifier. An information-theoretic feature selection criterion helps find the most informative motifs. Results on benchmark and real data demonstrate that our algorithm accurately identifies discriminative motifs. We show that the integration of comparative genomics information into the motif finding process significantly improves the discovery of discriminative motifs and overall classification accuracy.
机译:基因表达调控基序的鉴定是一个挑战性的问题,特别是在真核生物中。提出了一种算法,该算法可识别具有统计学意义的区分基元,以区分基因表达簇。使用监督的朴素贝叶斯分类器评估识别出的图案的预测能力。信息理论的特征选择标准有助于找到最有用的图案。基准数据和真实数据的结果表明,我们的算法可以准确识别出有区别的图案。我们表明,将比较基因组学信息整合到模体发现过程中,显着提高了判别性模体的发现和整体分类的准确性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号