Analysis of heterogeneous genomic samples using image normalization and machine learning.
Analysis of heterogeneous genomic samples using image normalization and machine learning.
复制标题
DOI：
10.1186/s12864-020-6661-6
复制
发表时间：
2020-12-21
期刊：
影响因子：
4.4
通讯作者：
Pan Y
中科院分区：
文献类型：
--
作者：
Basodi S;Baykal PI;Zelikovsky A;Skums P;Pan Y
病毒准种等异质群体的分析是生物信息学中最具挑战性的问题之一。尽管机器学习模型正被广泛用于分析来自这些群体的序列数据，但它们的直接应用受到与技术限制和偏见相关的多重挑战的阻碍，相关特征的选择困难以及需要比较不同大小和结构的基因组数据集。我们提出了一种新的预处理方法，将不规则的基因组数据转化为规范化的图像数据。这样的表示允许重述的问题的分类和比较的异质群体的图像分类问题，可以使用各种可用的机器学习工具来解决。然后，我们将所提出的方法应用于分子流行病学中的两个重要问题：推断病毒感染阶段和使用下一代测序数据检测病毒传播簇。感染分期方法已被应用于从108个最近和257个慢性感染者收集的HCV HVR1样本。基于SVM的图像分类方法对最近和慢性HCV感染者的准确率均达到95%以上。对从33起流行病学策划的疫情中收集的数据进行了聚类，准确率超过97%。序列图像标准化方法允许基因组数据到数值数据的鲁棒转换，并克服了与将机器学习方法用于病毒群体相关的若干问题。图像数据也有助于基因组数据的可视化。实验结果表明，所提出的方法可以成功地应用于不同的问题，在分子流行病学和病毒性疾病的监测。应用于图像数据的简单二进制分类器和聚类技术与其他模型一样准确或更准确。
Analysis of heterogeneous populations such as viral quasispecies is one of the most challenging bioinformatics problems. Although machine learning models are becoming to be widely employed for analysis of sequence data from such populations, their straightforward application is impeded by multiple challenges associated with technological limitations and biases, difficulty of selection of relevant features and need to compare genomic datasets of different sizes and structures. We propose a novel preprocessing approach to transform irregular genomic data into normalized image data. Such representation allows to restate the problems of classification and comparison of heterogeneous populations as image classification problems which can be solved using variety of available machine learning tools. We then apply the proposed approach to two important problems in molecular epidemiology: inference of viral infection stage and detection of viral transmission clusters using next-generation sequencing data. The infection staging method has been applied to HCV HVR1 samples collected from 108 recently and 257 chronically infected individuals. The SVM-based image classification approach achieved more than 95% accuracy for both recently and chronically HCV-infected individuals. Clustering has been performed on the data collected from 33 epidemiologically curated outbreaks, yielding more than 97% accuracy. Sequence image normalization method allows for a robust conversion of genomic data into numerical data and overcomes several issues associated with employing machine learning methods to viral populations. Image data also help in the visualization of genomic data. Experimental results demonstrate that the proposed method can be successfully applied to different problems in molecular epidemiology and surveillance of viral diseases. Simple binary classifiers and clustering techniques applied to the image data are equally or more accurate than other models.
登录
查看更多内容
影响因子：
4.4
作者：
Campo DS;Dimitrova Z;Yamasaki L;Skums P;Lau DT;Vaughan G;Forbi JC;Teo CG;Khudyakov Y
通讯作者：
Khudyakov Y
影响因子：
56.3
作者：
Collier, Melissa G.;Khudyakov, Yury E.;Xu, Fujie
通讯作者：
Xu, Fujie
影响因子：
11.8
作者：
Fischer, Gayle E.;Schaefer, Melissa K.;Holmberg, Scott D.
通讯作者：
Holmberg, Scott D.
影响因子：
39.2
作者：
Hellinger, Walter C.;Bacalis, Laura P.;Perz, Joseph F.
通讯作者：
Perz, Joseph F.
DOI：
10.1093/infdis/jiv542
发表时间：
2016-03-15
期刊：
The Journal of infectious diseases
影响因子：
--
作者：
Campo DS;Xia GL;Dimitrova Z;Lin Y;Forbi JC;Ganova-Raeva L;Punkova L;Ramachandran S;Thai H;Skums P;Sims S;Rytsareva I;Vaughan G;Roh HJ;Purdy MA;Sue A;Khudyakov Y
通讯作者：
Khudyakov Y