MICROARRAY GENE EXPRESSION BICLUSTERING USING ASSOCIATIVE PATTERN MINING

使用关联模式挖掘的微阵列基因表达双聚类

• 批准号: 8168135
• 负责人: PRERNA SETHI
• 金额: $ 5.55万
• 依托单位: LOUISIANA STATE UNIV A&M COL BATON ROUGE
• 依托单位国家: 美国
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-07-15 至 2011-04-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8168135
• 关键词: Algorithms; Computer Retrieval of Information on Scientific Projects Database; Data; Data Set; Dependency; Early Diagnosis; Effectiveness; Funding; Gene Expression; Genes; Grant; Histocompatibility Testing; Institution; Knowledge; Measures; Mining; Pattern; Reporting; Research; Research Personnel; Resources; Sampling; Source; Techniques; Time; United States National Institutes of Health; Weight; base; cancer classification; cancer gene expression; design; heuristics; text searching; usability; vector

This subproject is one of many research subprojects utilizing the resources provided by a Center grant funded by NIH/NCRR. The subproject and investigator (PI) may have received primary funding from another NIH source, and thus could be represented in other CRISP entries. The institution listed is for the Center, which is not necessarily the institution for the investigator. Analysis of gene expression data for cancer classification can provide valuable information for early diagnosis and treatment. The computational extraction of derived patterns from microarray gene expression is a non-trivial task that involves sophisticated algorithm design and analysis for specific domain discovery. Moreover, the extraction of biologically significant knowledge from the gene expression data is a growing computational challenge, as the large number of genes, which can correspond to different time sequences or tissue types, has a dimensionality that is several orders of magnitude more than the evaluated samples. During this reporting period, we have developed a formal approach for feature extraction of genes by first applying feature selection heuristics based on the statistical impurity measures and analyzing the associative dependencies between the genes and then computing weights to the genes based on their degree of participation in the rules. Consequently, we developed a weighted Jaccard and vector cosine similarity measure to compute the similarity between the discovered rules. To demonstrate the usability and efficiency of the concept of our technique, we applied it to three publicly available, multiclass cancer gene expression datasets and performed a biomedical literature search to support the effectiveness of our results.

这个子项目是许多研究子项目中的一个 由NIH/NCRR资助的中心赠款提供的资源。子项目和 研究者（PI）可能从另一个NIH来源获得了主要资金， 因此可以在其他CRISP条目中表示。所列机构为 研究中心，而研究中心不一定是研究者所在的机构。 分析基因表达数据用于癌症分类可以为早期诊断和治疗提供有价值的信息。从微阵列基因表达中计算提取衍生模式是一项重要的任务，涉及复杂的算法设计和特定领域发现的分析。此外，从基因表达数据中提取生物学上重要的知识是一个日益增长的计算挑战，因为大量的基因，其可以对应于不同的时间序列或组织类型，具有比评估的样本多几个数量级的维度。在本报告所述期间，我们已经开发了一种正式的基因特征提取方法，首先应用基于统计杂质度量的特征选择算法，分析基因之间的关联依赖关系，然后根据基因在规则中的参与程度计算基因的权重。因此，我们开发了一个加权Jaccard和向量余弦相似性度量来计算发现的规则之间的相似性。为了证明我们的技术概念的可用性和效率，我们将其应用于三个公开的多类癌症基因表达数据集，并进行了生物医学文献检索，以支持我们的结果的有效性。