School of Information Engineering, Xijing University, Xi'an, China.
School of Computer Science, Northwestern Polytechnical University, Xi'an, China.
Brief Funct Genomics. 2024 May 15;23(3):276-285. doi: 10.1093/bfgp/elad030.
Recently, the role of competing endogenous RNAs in regulating gene expression through the interaction of microRNAs has been closely associated with the expression of circular RNAs (circRNAs) in various biological processes such as reproduction and apoptosis. While the number of confirmed circRNA-miRNA interactions (CMIs) continues to increase, the conventional in vitro approaches for discovery are expensive, labor intensive, and time consuming. Therefore, there is an urgent need for effective prediction of potential CMIs through appropriate data modeling and prediction based on known information. In this study, we proposed a novel model, called DeepCMI, that utilizes multi-source information on circRNA/miRNA to predict potential CMIs. Comprehensive evaluations on the CMI-9905 and CMI-9589 datasets demonstrated that DeepCMI successfully infers potential CMIs. Specifically, DeepCMI achieved AUC values of 90.54% and 94.8% on the CMI-9905 and CMI-9589 datasets, respectively. These results suggest that DeepCMI is an effective model for predicting potential CMIs and has the potential to significantly reduce the need for downstream in vitro studies. To facilitate the use of our trained model and data, we have constructed a computational platform, which is available at http://120.77.11.78/DeepCMI/. The source code and datasets used in this work are available at https://github.com/LiYuechao1998/DeepCMI.
最近，竞争内源性 RNA 通过 microRNA 的相互作用调节基因表达的作用与环状 RNA（circRNA）在生殖和凋亡等各种生物过程中的表达密切相关。虽然已经确认的 circRNA-miRNA 相互作用（CMI）数量不断增加，但传统的体外发现方法昂贵、劳动强度大且耗时。因此，迫切需要通过适当的数据建模和基于已知信息的预测来有效预测潜在的 CMIs。在这项研究中，我们提出了一种名为 DeepCMI 的新模型，该模型利用 circRNA/miRNA 的多源信息来预测潜在的 CMIs。对 CMI-9905 和 CMI-9589 数据集的综合评估表明，DeepCMI 成功推断出了潜在的 CMIs。具体来说，DeepCMI 在 CMI-9905 和 CMI-9589 数据集上的 AUC 值分别达到 90.54%和 94.8%。这些结果表明，DeepCMI 是一种预测潜在 CMIs 的有效模型，有潜力显著减少对下游体外研究的需求。为了方便使用我们训练好的模型和数据，我们构建了一个计算平台，网址为 http://120.77.11.78/DeepCMI/。本工作中使用的源代码和数据集可在 https://github.com/LiYuechao1998/DeepCMI 上获取。
