Modeling of Neural Network Based Gene Transcriptional and Post-Transcriptional Regulation and their Applications

• Main Authors: Shih-Yi Chao, 趙士儀
• Other Authors: Jung-Hsien Chiang
• Format: Others
• Language: en_US
• Published: 2008
• Online Access: http://ndltd.ncl.edu.tw/handle/56682581318694732694

博士 === 國立成功大學 === 資訊工程學系碩博士班 === 96 === Modeling cancer-related regulatory modules from gene expression profiling of cancer tissues is expected to contribute to our understanding of cancer biology. In this study, we introduce a GA-RNN hybrid method to construct cancer-related regulatory modules in human cancer microarray data. As for the post-transcriptional regulation level, most of microRNAs are thought to control post-transcriptional mechanism by base pairing with microRNA recognition elements found in their mRNA targets. A computational method we provide is to predict mRNA targets for microRNAs by combining structure-based features and conserved data across species. Finally, a graph-based approach for comparing RNA secondary structures is introduced to imply or predict the functions of non-coding RNAs. We have proved the performance of the proposed algorithm by providing the experimental results. While the proposed algorithm has been designed for use in detection of common RNA secondary structures, it may be applicable to other graph-based similarity applications, such as protein structure problems.