深度学习在生物序列分析领域的应用进展

    Progress in the Applications of Deep Learning in Biological Sequences Analysis

    • 摘要: 随着生物技术的不断发展和生物学数据的大量产出,传统生物学数据分析方式不足以应对日益复杂庞大的生物序列数据. 面对这种情况,国内外学者逐步将深度学习应用到生物学分析中,利用其处理高维数据的优势,取得了一系列进展,并成为生物序列数据分析中的研究热门. 为了更好地了解深度学习在生物序列数据分析领域中的新进展,对该领域研究现状进行了综述. 首先,介绍深度学习应用到生物序列数据分析中的重要意义;其次,对目前应用领域中具有代表性的深度学习模型进行阐述;然后,分析深度学习在生物学领域的应用研究现状;最后,说明目前深度学习在生物学领域中的局限性,并进一步提出未来发展应考虑的因素.

       

      Abstract: With the continuous development of bioinformatics, traditionally biological sequence analysis methods are insufficient to deal with the increasingly complex and huge biological data. In the face of this situation, deep learning has been gradually applied in biological analysis and made a series of progresses, which has become a hot research topic in biological data analysis with its advantages in processing high-dimensional data. The current research status was reviewed to better understand the new development of deep learning in the field of bioinformatics data analysis. First, the importance of applying deep learning were introduced. Second, representative deep learning models in the current application fields was described. Then, the application research status of deep learning in this field was analyzed. Finally, current limitations of deep learning in the bioinformatics field and the factors that should be considered in future development were illustrated in this paper.

       

    /

    返回文章
    返回