Soumare H, Rezgui S, Gmati N, Benkahla A
The Laboratory of Mathematical Modelling and Numeric in Engineering Sciences, National Engineering School of Tunis, Rue Béchir Salem Belkhiria Campus universitaire, B.P. 37, 1002 Tunis Belvédère, University of Tunis El Manar, Tunis, Tunisia.
Laboratory of BioInformatics, bioMathematics, and bioStatistics, 13 place Pasteur, B.P. 74 1002 Tunis, Belvédère, Institut Pasteur de Tunis, University of Tunis El Manar, Tunis, Tunisia.
BioData Min. 2021 Jun 28;14(1):30. doi: 10.1186/s13040-021-00258-7.
Artificial Neural Network (ANN) algorithms have been widely used to analyse genomic data. Single Nucleotide Polymorphisms(SNPs) represent the genetic variations, the most common in the human genome, it has been shown that they are involved in many genetic diseases, and can be used to predict their development. Developing ANN to handle this type of data can be considered as a great success in the medical world. However, the high dimensionality of genomic data and the availability of a limited number of samples can make the learning task very complicated. In this work, we propose a New Neural Network classification method based on input perturbation. The idea is first to use SVD to reduce the dimensionality of the input data and to train a classification network, which prediction errors are then reduced by perturbing the SVD projection matrix. The proposed method has been evaluated on data from individuals with different ancestral origins, the experimental results have shown the effectiveness of the proposed method. Achieving up to 96.23% of classification accuracy, this approach surpasses previous Deep learning approaches evaluated on the same dataset.
人工神经网络（ANN）算法已被广泛用于分析基因组数据。单核苷酸多态性（SNP）代表了基因变异，这是人类基因组中最常见的变异，研究表明它们与许多遗传疾病有关，并且可用于预测这些疾病的发展。开发能够处理此类数据的人工神经网络可被视为医学领域的一项巨大成功。然而，基因组数据的高维度以及有限数量样本的可得性会使学习任务变得非常复杂。在这项工作中，我们提出了一种基于输入扰动的新型神经网络分类方法。其思路是首先使用奇异值分解（SVD）来降低输入数据的维度并训练一个分类网络，然后通过扰动奇异值分解投影矩阵来减少预测误差。所提出的方法已在来自不同祖先起源个体的数据上进行了评估，实验结果表明了该方法的有效性。这种方法实现了高达96.23%的分类准确率，超过了在同一数据集上评估的先前深度学习方法。
