Use of probabilistic graphical models for bioinformatics

概率图形模型在生物信息学中的应用

• 批准号: 517576-2017
• 负责人: Domaratzki, Michael
• 金额: $ 1.82万
• 依托单位: University of Manitoba
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2017
• 资助国家: 加拿大
• 起止时间: 2017-01-01 至 2018-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=640697
• 关键词: Use; probabilistic; graphical; models; bioinformatics

This project will help Sightline Innovation develop new techniques to employ machine learning for biology.Sightline Innovation provides artificial intelligent products and solutions for businesses around the world.Sightline Innovation is working to adapt its artificial intelligence tools for biological data. This data may beDNA, RNA or protein data, and is typically part of large, complex datasets. Machine learning will helpdetermine patterns in this biological data that allow researchers to characterize observable, physical traits inindividuals from the biological data. These traits may include susceptibility to disease or prognosis forrecovery.In this project, Dr. Domaratzki (U.Manitoba) and Dr. Mark Alexiuk (CTO, Sightline Innovation) will worktogether with a research associate to develop new, high-performance tools for bioinformatics datasets. Thesetools will provide critical understanding of causality and correlationship between experimental data and clinicalor observed states in patient data. The research project will also help in developing new and more accuratealgorithms and computational tools to predict future trends. With improved computational tools, SightlineInnovation will be able to improve predictions for a variety of application areas. This represents a contributionto the fundamental machine learning tools developed and employed by Sightline Innovation.

该项目将帮助Sightline Innovation开发新技术，将机器学习应用于生物学。Sightline Innovation为世界各地的企业提供人工智能产品和解决方案。Sightline Innovation正在努力使其人工智能工具适应生物数据。这些数据可能是DNA、RNA或蛋白质数据，通常是大型复杂数据集的一部分。机器学习将有助于确定这些生物数据中的模式，使研究人员能够从生物数据中描述个体的可观察的物理特征。在这个项目中，Domaratzki博士（U.马尼托巴）和Mark Alexiuk博士（Sightline Innovation首席技术官）将与一名研究助理合作，为生物信息学数据集开发新的高性能工具。这些工具将提供关键的因果关系和相关性之间的理解实验数据和临床或观察状态的病人数据。该研究项目还将有助于开发新的、更准确的算法和计算工具，以预测未来的趋势。通过改进计算工具，SightlineInnovation将能够改进各种应用领域的预测。这代表了对Sightline Innovation开发和使用的基本机器学习工具的贡献。