Data Science

最近的基因组测序技术正在产生前所未有的数据量。基因组数据的无环境计算分析对于精准医学至关重要。在这里，我们提出了新的算法和数据科学方法，可以以快速和具有成本效益的方式在测序数据的模糊部分中推断出重要的临床信息。我们还提出了一个全面的特定领域的框架，开发高性能的计算工具，可以产生快速和可扩展的数据处理软件，为不同的计算机体系结构。通过与当地和国际研究中心的合作，我们设想所提出的方法将提高加拿大的医疗保健和研究能力。

Recent genome sequencing technologies are generating unprecedented amounts of data. Unambiguous computational analysis of genomic data is of key importance for precision medicine. Here we propose novel algorithmic and data science methods that can infer important clinical information within the ambiguous parts of sequencing data in fast and cost-efficient manner. We also propose a comprehensive domain-specific framework for developing high-performance computational tools that can produce fast and scalable data processing software for different computer architectures. In collaboration with local and international research centers, we envision that the proposed methods will boost Canadian health care and research capabilities.