In many biological processes, N6-methyladenosine (m6A) plays a critical role. Experimental methods for identifying m6A sites have proven to be costly, and existing computational methods still require improvement. To address these challenges, we develop a novel computational method called structured sparse regularization-based fuzzy hierarchical echo state network (SSR-FHESN) to identify m6A sites in mammals. We apply fuzzy systems to deep learning. Compared with traditional fuzzy inference systems (FISs), this deep fuzzy network has the ability to generate feature representations. Echo state network (ESN) is a special type of recurrent neural network (RNN), which consists of an input layer, a randomly generated large fixed hidden layer (called a reservoir), and an adaptive output layer. The advantages of our method over ESNs are that it is capable of mining and capturing hidden features layer by layer within reservoirs and has better approximation performance. In order to remove redundancy, the output layer weights are trained by structured sparse learning, which enhances the generalizability and robustness of the method. Evaluation of our method by testing it on tissue-specific datasets shows that it outperforms existing tools.

中文翻译：

---

基于结构化稀疏正则化的深度模糊网络用于 RNA N6-甲基腺苷位点预测


在许多生物过程中，N6-甲基腺苷 (m6A) 起着至关重要的作用。事实证明，识别 m6A 位点的实验方法成本高昂，现有的计算方法仍需要改进。为了应对这些挑战，我们开发了一种新颖的计算方法，称为基于结构化稀疏正则化的模糊分层回声状态网络（SSR-FHESN）来识别哺乳动物中的 m6A 位点。我们将模糊系统应用于深度学习。与传统的模糊推理系统（FIS）相比，这种深度模糊网络具有生成特征表示的能力。回声状态网络（ESN）是一种特殊类型的循环神经网络（RNN），由输入层、随机生成的大型固定隐藏层（称为存储层）和自适应输出层组成。我们的方法相对于ESN的优点在于它能够逐层挖掘和捕获储层内的隐藏特征，并且具有更好的逼近性能。为了去除冗余，通过结构化稀疏学习来训练输出层权重，增强了方法的泛化性和鲁棒性。通过在组织特异性数据集上测试我们的方法来评估我们的方法，结果表明它优于现有工具。