CNV-MEANN: A Neural Network and Mind Evolutionary Algorithm-Based Detection of Copy Number Variations From Next-Generation Sequencing Data.
CNV-MEANN: A Neural Network and Mind Evolutionary Algorithm-Based Detection of Copy Number Variations From Next-Generation Sequencing Data.
复制标题
DOI：
10.3389/fgene.2021.700874
复制
发表时间：
2021
影响因子：
3.7
通讯作者：
Sang H
中科院分区：
文献类型：
--
作者：
Huang T;Li J;Jia B;Sang H
拷贝数变异(CNV)是指1Kb到5Mb的基因组片段的重复或缺失，是人类疾病的主要诱因。下一代测序技术的高通量和低成本特性为检测全基因组中的CNV提供了可能，也极大地提高了下一代测序(NGS)测试的临床实用性。然而，目前检测CNV的方法容易受到测序和作图错误以及读数分布不均匀的影响。在本文中，我们提出了一种改进的CNV-Meann方法，该方法改变了MFCNV方法中使用的神经网络结构。与MFCNV方法相比，该方法有三个不同之处：(1)利用映射质量这一新的特征来代替MFCNV中的两个特征；(2)考虑了CNV的损失类别对疾病预测的影响，并对输出结构进行了优化；(3)使用思维进化算法来优化BP神经网络模型，并计算每个基因组片段的个体得分来预测CNV。使用模拟数据集和真实数据集对CNV-Meann的性能进行了测试，并将其性能与七种广泛使用的CNV检测方法进行了比较。实验结果表明，CNV-Meann方法在灵敏度、精确度和F1-Score方面都优于其他方法。该方法能够检测出许多其他方法无法检测到的CNV，并且减少了边界偏差。CNV-Meann有望成为分析基因组中CNV变化的一种有效方法。
Copy number variation (CNV), is defined as repetitions or deletions of genomic segments of 1 Kb to 5 Mb, and is a major trigger for human disease. The high-throughput and low-cost characteristics of next-generation sequencing technology provide the possibility of the detection of CNVs in the whole genome, and also greatly improve the clinical practicability of next-generation sequencing (NGS) testing. However, current methods for the detection of CNVs are easily affected by sequencing and mapping errors, and uneven distribution of reads. In this paper, we propose an improved approach, CNV-MEANN, for the detection of CNVs, involving changing the structure of the neural network used in the MFCNV method. This method has three differences relative to the MFCNV method: (1) it utilizes a new feature, mapping quality, to replace two features in MFCNV, (2) it considers the influence of the loss categories of CNV on disease prediction, and refines the output structure, and (3) it uses a mind evolutionary algorithm to optimize the backpropagation (neural network) neural network model, and calculates individual scores for each genome bin to predict CNVs. Using both simulated and real datasets, we tested the performance of CNV-MEANN and compared its performance with those of seven widely used CNV detection methods. Experimental results demonstrated that the CNV-MEANN approach outperformed other methods with respect to sensitivity, precision, and F1-score. The proposed method was able to detect many CNVs that other approaches could not, and it reduced the boundary bias. CNV-MEANN is expected to be an effective method for the analysis of changes in CNVs in the genome.
登录
查看更多内容
影响因子：
9.8
作者：
Fellermann, Klaus;Stange, Daniel E.;Stange, Eduard F.
通讯作者：
Stange, Eduard F.
DOI：
10.1093/bioinformatics/btr670
发表时间：
2012-02-01
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Boeva V;Popova T;Bleakley K;Chiche P;Cappo J;Schleiermacher G;Janoueix-Lerosey I;Delattre O;Barillot E
通讯作者：
Barillot E
影响因子：
3.7
作者：
Dharanipragada P;Vogeti S;Parekh N
通讯作者：
Parekh N
SM-RCNV：一种检测测序样本中反复出现的拷贝数变异的统计方法
影响因子：
2.1
作者：
Li, Yaoyao;Yuan, Xiguo;Jiang, Shan
通讯作者：
Jiang, Shan
影响因子：
3.9
作者：
Johansson, Lennart F.;van Dijk, Freerk;Sikkema-Raddatz, Birgit
通讯作者：
Sikkema-Raddatz, Birgit