Min Seonwoo, Lee Byunghan, Yoon Sungroh
Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, South Korea.
LG AI Research, Seoul 07796, South Korea.
Bioinformatics. 2022 Jan 12;38(3):671-677. doi: 10.1093/bioinformatics/btab733.
MicroRNAs (miRNAs) play pivotal roles in gene expression regulation by binding to target sites of messenger RNAs (mRNAs). While identifying functional targets of miRNAs is of utmost importance, their prediction remains a great challenge. Previous computational algorithms have major limitations. They use conservative candidate target site (CTS) selection criteria mainly focusing on canonical site types, rely on laborious and time-consuming manual feature extraction, and do not fully capitalize on the information underlying miRNA-CTS interactions.
In this article, we introduce TargetNet, a novel deep learning-based algorithm for functional miRNA target prediction. To address the limitations of previous approaches, TargetNet has three key components: (i) relaxed CTS selection criteria accommodating irregularities in the seed region, (ii) a novel miRNA-CTS sequence encoding scheme incorporating extended seed region alignments and (iii) a deep residual network-based prediction model. The proposed model was trained with miRNA-CTS pair datasets and evaluated with miRNA-mRNA pair datasets. TargetNet advances the previous state-of-the-art algorithms used in functional miRNA target classification. Furthermore, it demonstrates great potential for distinguishing high-functional miRNA targets.
The codes and pre-trained models are available at https://github.com/mswzeus/TargetNet.
微小RNA（miRNA）通过与信使核糖核酸（mRNA）的靶位点结合，在基因表达调控中发挥关键作用。虽然识别miRNA的功能靶点至关重要，但其预测仍然是一项巨大挑战。先前的计算算法存在重大局限性。它们使用主要关注典型位点类型的保守候选靶位点（CTS）选择标准，依赖费力且耗时的手动特征提取，并且没有充分利用miRNA - CTS相互作用背后的信息。
在本文中，我们介绍了TargetNet，一种基于深度学习的新型功能性miRNA靶标预测算法。为解决先前方法的局限性，TargetNet有三个关键组件：（i）放宽的CTS选择标准，以适应种子区域的不规则性；（ii）一种新颖的miRNA - CTS序列编码方案，纳入扩展的种子区域比对；（iii）基于深度残差网络的预测模型。所提出的模型使用miRNA - CTS对数据集进行训练，并使用miRNA - mRNA对数据集进行评估。TargetNet改进了先前用于功能性miRNA靶标分类的最先进算法。此外，它在区分高功能性miRNA靶标方面显示出巨大潜力。
代码和预训练模型可在https://github.com/mswzeus/TargetNet获取。
