Non-coding RNA Structure Analysis Based on Deep Neural Networks

此次合作的主要目标是基于深度神经网络的最新发展，开发新的机器学习算法来分析非编码核糖核酸（ncRNA）结构。ncrna在细胞过程中发挥重要作用，如影响高阶染色体动力学、端粒生物学、亚细胞结构组织和基因表达。分析ncRNA结构是了解其生物学功能的基本步骤。通过与堪萨斯大学的合作，该项目解决了一个非常重要的跨学科问题，涉及ncRNA，计算生物学和机器学习。它将为测序数据分析提供新的生物信息学基础设施，这将对生物医学、生物学、RNA治疗学和药物发现产生重大研究影响，同时促进加拿大在生物工程和人工智能方面的全球领导地位。

The main objective of this collaboration is to develop new machine learning algorithms to analyze non-coding ribonucleic acid (ncRNA) structures based on recent developments in deep neural networks. ncRNAs play important roles in cell processes such as to effect high-order chromosomal dynamics, telomere biology, subcellular structural organization, and gene expression. Analyzing ncRNA structure is a fundamental step towards understanding their biological functions. Through this collaboration with the University of Kansas, this project addresses a very important interdisciplinary problem that involves ncRNA, computational biology, and machine learning. It will provide a new bioinformatics infrastructure for sequencing data analysis which will have significant research impacts in biomedicine, biology, RNA therapeutics, and drug discovery, while promoting Canada's global leadership in bioengineering and artificial intelligence.