Biological features between miRNAs and their targets are unveiled from deep learning models.
Biological features between miRNAs and their targets are unveiled from deep learning models.
复制标题
DOI：
10.1038/s41598-021-03215-w
复制
发表时间：
2021-12-10
影响因子：
4.6
通讯作者：
Lee JH
中科院分区：
文献类型：
--
作者：
Gu T;Xie M;Barbazuk WB;Lee JH
MicroRNAs(MiRNAs)是一类普遍存在的22个核苷酸的基因调控因子( )。它们调节与人类健康和疾病有关的广泛的基本细胞过程。因此，识别miRNA靶点并了解它们的功能对于治疗miRNA相关疾病至关重要。在我们早期的工作中，开发了一种基于混合深度学习的方法(MITAR)来预测miRNA目标。它的性能大大好于现有的方法。该方法集成了两种主要的深度学习算法：卷积神经网络(CNN)和递归神经网络(RNN)。然而，Mitar了解到的miRNA：靶相互作用中的特征还没有被研究。在目前的研究中，我们证明了Mitar在miRNA：靶相互作用中捕获了已知的特征，包括种子区域和自由能的参与，以及许多新的特征。有趣的是，模型的CNN层和RNN层在捕获自由能特征方面的表现不同：RNN层中的单元在捕获特征方面更独特，但总的来说，CNN层在捕获特征方面更有效。虽然深度学习模型通常被认为是黑匣子，但我们的发现支持从深度学习模型中揭示miRNA：Target的生物学特性，这将有助于理解miRNA：Target相互作用的机制。
MicroRNAs (miRNAs) are ~ 22 nucleotide ubiquitous gene regulators. They modulate a broad range of essential cellular processes linked to human health and diseases. Consequently, identifying miRNA targets and understanding how they function are critical for treating miRNA associated diseases. In our earlier work, a hybrid deep learning-based approach (miTAR) was developed for predicting miRNA targets. It performs substantially better than the existing methods. The approach integrates two major types of deep learning algorithms: convolutional neural networks (CNNs) and recurrent neural networks (RNNs). However, the features in miRNA:target interactions learned by miTAR have not been investigated. In the current study, we demonstrated that miTAR captures known features, including the involvement of seed region and the free energy, as well as multiple novel features, in the miRNA:target interactions. Interestingly, the CNN and RNN layers of the model perform differently at capturing the free energy feature: the units in RNN layer is more unique at capturing the feature but collectively the CNN layer is more efficient at capturing the feature. Although deep learning models are commonly thought “black-boxes”, our discoveries support that the biological features in miRNA:target can be unveiled from deep learning models, which will be beneficial to the understanding of the mechanisms in miRNA:target interactions.
登录
查看更多内容
用于 miRNA 疾病关联预测的 MDHGI 矩阵分解和异质图推理
影响因子：
4.3
作者：
Chen X;Yin J;Qu J;Huang L
通讯作者：
Huang L
影响因子：
64.5
作者：
Lewis, BP;Shih, IH;Burge, CB
通讯作者：
Burge, CB
影响因子：
9.5
作者：
Chen, Xing;Xie, Di;You, Zhu-Hong
通讯作者：
You, Zhu-Hong
DOI：
10.3390/e23010018
发表时间：
2020-12-25
期刊：
Entropy (Basel, Switzerland)
影响因子：
--
作者：
Linardatos P;Papastefanopoulos V;Kotsiantis S
通讯作者：
Kotsiantis S
影响因子：
3
作者：
Gu T;Zhao X;Barbazuk WB;Lee JH
通讯作者：
Lee JH