Machine learning techniques to discover genes with potential prognosis role in Alzheimer’s disease using different biological sources

详细信息    查看全文

• 作者：Mar&iacute ; a Mart&iacute ; nez-Ballesteros ; ^a ; ^{mariamartinez@us.es} ; José ; M. Garc&iacute ; a-Heredia^b ; ^{jmgheredia@us.es} ; Isabel A. Nepomuceno-Chamorro^a ; ^{inepomuceno@us.es} ; José ; C. Riquelme-Santos^a ; ^{riquelme@us.es}
• 关键词：Association rules ; Gene expression profiles ; Alzheimer&rsquo ; s disease ; Statistical significant genes ; Ensemble learning ; Biological knowledge integration
• 刊名：Information Fusion
• 出版年：2017
• 出版时间：July 2017
• 年：2017
• 卷：36
• 期：Complete
• 页码：114-129
• 全文大小：2882 K
• 卷排序：36

文摘

Analyze Alzheimer disease gene expression profiles by changes in expression levels. Integration of machine learning methods: decision tree, associations and clustering. Fusion of external information sources: microarray, PubMed, GO and PPI network. Significant set of down/up regulated genes highly related with Alzheimer disease. Gene expression patterns and deep knowledge into relevant biological functions.