Integrating thermodynamic and sequence contexts improves protein-RNA binding prediction
Integrating thermodynamic and sequence contexts improves protein-RNA binding prediction
复制标题
DOI：
10.1371/journal.pcbi.1007283
复制
发表时间：
2019-09
影响因子：
4.3
通讯作者：
Yufeng Su;Yunan Luo;Xiaoming Zhao;Yang Liu;Jian Peng
中科院分区：
文献类型：
--
作者：
Yufeng Su;Yunan Luo;Xiaoming Zhao;Yang Liu;Jian Peng
预测RNA结合蛋白（RBP）的特异性对于理解基因表达调控和RNA介导的酶促过程非常重要。人们普遍认为，RBP结合特异性由RNA的序列和结构背景决定。现有的方法，包括传统的机器学习算法和最近的深度学习模型，已被广泛应用于整合RNA序列及其预测或实验RNA结构概率，以提高RBP结合预测的准确性。这些模型主要在大规模体外数据集上训练，例如RNAcompete数据集。然而，在RNAcompete中，大多数合成RNA是非结构化的，这使得机器学习方法不能有效地提取RBP结合的结构偏好。此外，根据理论和实验证据，RNA结构可以是可变的或多模态的。在这项工作中，我们提出了ThermoNet，一个热力学预测模型，通过整合一个新的序列嵌入卷积神经网络模型在RNA二级结构的热力学系综。首先，序列嵌入卷积神经网络通过联合学习卷积滤波器和k-mer嵌入来表示RNA序列上下文，从而概括了现有的基于k-mer的方法。其次，深度学习预测的热力学平均值能够探索结构变异性并改进预测，特别是对于结构化RNA。大量的实验表明，我们的方法显着优于现有的方法，包括RCK，DeepBind和其他几个最近的最先进的方法，用于预测体外和体内数据。ThermoNet的实施可在https://github.com/suyufeng/ThermoNet上获得。
Predicting RNA-binding protein (RBP) specificity is important for understanding gene expression regulation and RNA-mediated enzymatic processes. It is widely believed that RBP binding specificity is determined by both the sequence and structural contexts of RNAs. Existing approaches, including traditional machine learning algorithms and more recently, deep learning models, have been extensively applied to integrate RNA sequence and its predicted or experimental RNA structural probabilities for improving the accuracy of RBP binding prediction. Such models were trained mostly on the large-scale in vitro datasets, such as the RNAcompete dataset. However, in RNAcompete, most synthetic RNAs are unstructured, which makes machine learning methods not effectively extract RBP-binding structural preferences. Furthermore, RNA structure may be variable or multi-modal according to both theoretical and experimental evidence. In this work, we propose ThermoNet, a thermodynamic prediction model by integrating a new sequence-embedding convolutional neural network model over a thermodynamic ensemble of RNA secondary structures. First, the sequence-embedding convolutional neural network generalizes the existing k-mer based methods by jointly learning convolutional filters and k-mer embeddings to represent RNA sequence contexts. Second, the thermodynamic average of deep-learning predictions is able to explore structural variability and improves the prediction, especially for the structured RNAs. Extensive experiments demonstrate that our method significantly outperforms existing approaches, including RCK, DeepBind and several other recent state-of-the-art methods for predictions on both in vitro and in vivo data. The implementation of ThermoNet is available at https://github.com/suyufeng/ThermoNet.