《BioRxiv,1月30日,从基因组测序数据中检测新型人类病毒》

  • 来源专题:COVID-19科研动态监测
  • 编译者: zhangzx
  • 发布时间:2020-01-31
  • Viruses evolve extremely quickly, so reliable methods for viral host prediction are necessary to safeguard biosecurity and biosafety alike. Novel human-infecting viruses are difficult to detect with standard bioinformatics workflows. Here, we predict whether a virus can infect humans directly from next-generation sequencing reads. We show that deep neural architectures significantly outperform both shallow machine learning and standard, homology-based algorithms, cutting the error rates in half and generalizing to taxonomic units distant from those presented during training. We propose a new approach for convolutional filter visualization to disentangle the information content of each nucleotide from its contribution to the final classification decision. Nucleotide-resolution maps of the learned associations between pathogen genomes and the infectious phenotype can be used to detect virulence-related genes in novel agents, as we show here for the 2019-nCoV coronavirus, unknown before it caused a pneumonia outbreak in December 2019.

  • 原文来源:https://www.biorxiv.org/content/10.1101/2020.01.29.925354v1
相关报告
  • 《BioRxiv,2月1日,(第2版更新)从基因组测序数据中检测新型人类病毒》

    • 来源专题:COVID-19科研动态监测
    • 编译者:zhangmin
    • 发布时间:2020-02-03
    • Viruses evolve extremely quickly, so reliable methods for viral host prediction are necessary to safeguard biosecurity and biosafety alike. Novel human-infecting viruses are difficult to detect with standard bioinformatics workflows. Here, we predict whether a virus can infect humans directly from next-generation sequencing reads. We show that deep neural architectures significantly outperform both shallow machine learning and standard, homology-based algorithms, cutting the error rates in half and generalizing to taxonomic units distant from those presented during training. We propose a new approach for convolutional filter visualization to disentangle the information content of each nucleotide from its contribution to the final classification decision. Nucleotide-resolution maps of the learned associations between pathogen genomes and the infectious phenotype can be used to detect virulence-related genes in novel agents, as we show here for the 2019-nCoV coronavirus, unknown before it caused a pneumonia outbreak in December 2019. *注,本文为预印本论文手稿,是未经同行评审的初步报告,其观点仅供科研同行交流,并不是结论性内容,请使用者谨慎使用.
  • 《1月30日_德国团队开发新的生物信息法方法,利用基因组数据研究新型冠状病毒》

    • 来源专题:COVID-19科研动态监测
    • 编译者:zhangmin
    • 发布时间:2020-02-06
    • 1.时间:2020年1月30日 2.机构或团队:德国罗伯特•科赫研究所、哈索•普拉特纳研究所、Central Research Institute of Ambulatory Health Care 3.事件概要: 1月30日,bipRxiv在线发表了德国团队的一项最新研究,设计了一种新的生物信息学方法,通过解析基因组测序数据检测新型人类病毒。 病毒的进化速度非常快,因此需要可靠的病毒宿主预测方法来保障生物安全,而新的人类感染病毒很难用标准的生物信息学工作流程来检测。在研究中,研究者通过下一代测序结果预测病毒是否能够直接感染人类。结果表明,他们的新方法可以基于单DNA read或一个read pair,预测一种新型病毒的宿主。这种深度神经结构学习方法明显优于传统的浅层机器学习和标准的、基于同源性的算法,将错误率降低了一半。文中提出了一种新的卷积滤波器可视化方法,可以将每个核苷酸的信息内容和最终分类决策贡献值分别提取并展示出来。采用IGV可视化了病原体基因组和感染表型之间的已知关联的核苷酸解析图(Nucleotide-resolution maps),可用于检测新制剂中的毒力相关基因,文中还构建使用全基因组表型分析(genome-wide phenotype analysis ,GWPA)分析病毒的哪些基因组部分具有传染性表型。文中列举了其算法在中国2019年12月暴发的2019-nCoV病毒中的应用和分析。代码可在https://gitlab.com/rki_bioinformatics/deepac获取。 *注,本文为预印本论文手稿,是未经同行评审的初步报告,其观点仅供科研同行交流,并不是结论性内容,请使用者谨慎使用。 4.附件:原文链接 https://www.biorxiv.org/content/10.1101/2020.01.29.925354v1