• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>12th European Conference on Machine Learning, 12th, Sep 5-7, 2001, Freiburg, Germany >Symbolic Discriminant Analysis for Mining Gene Expression Patterns
【24h】

Symbolic Discriminant Analysis for Mining Gene Expression Patterns

机译：挖掘基因表达模式的符号判别分析

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

New laboratory technologies have made it possible to measure the expression levels of thousands of genes simultaneously in a particular cell or tissue. The challenge for computational biologists will be to develop methods that are able to identify subsets of gene expression variables that classify cells and tissues into meaningful clinical groups. Linear discriminant analysis is a popular multivariate statistical approach for classification of observations into groups. This is because the theory is well described and the method is easy to implement and interpret. However, an important limitation is that linear discriminant functions need to be pre-specified. To address this limitation and the limitation of linearity, we developed symbolic discriminant analysis (SDA) for the automatic selection of gene expression variables and discriminant functions that can take any form. We have implemented the genetic programming machine learning methodology for optimizing SDA in parallel on a Beowulf-style computer cluster.
机译：新的实验室技术使在特定细胞或组织中同时测量数千种基因的表达水平成为可能。计算生物学家面临的挑战将是开发能够识别将细胞和组织分类为有意义的临床组的基因表达变量子集的方法。线性判别分析是一种流行的多元统计方法，用于将观察结果分类。这是因为该理论已被很好地描述，并且该方法易于实现和解释。但是，一个重要的限制是线性判别函数需要预先指定。为了解决此限制和线性限制，我们开发了符号判别分析（SDA），用于自动选择可以采用任何形式的基因表达变量和判别函数。我们已经实现了遗传编程机器学习方法，以在Beowulf风格的计算机集群上并行优化SDA。

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