Predicting transcription factor binding sites using DNA shape features based on shared hybrid deep learning architecture.
Predicting transcription factor binding sites using DNA shape features based on shared hybrid deep learning architecture.
复制标题
基于共享混合深度学习架构使用 DNA 形状特征预测转录因子结合位点
DOI：
10.1016/j.omtn.2021.02.014
复制
发表时间：
2021-06-04
期刊：
影响因子：
--
通讯作者：
Huang DS
中科院分区：
文献类型：
--
作者：
Wang S;Zhang Q;Shen Z;He Y;Chen ZH;Li J;Huang DS
转录调控的研究仍然是分子生物学研究中的难点和基础。最近的研究表明，核苷酸的双螺旋结构在提高转录因子结合位点(TFBSS)的准确性和可解释性方面发挥着重要作用。虽然已经设计了多种计算方法来同时考虑DNA序列和DNA形状特征，但如何设计一个有效的模型仍然是一个棘手的课题。本文提出了一种结合DNA序列和DNA形状特征的混合卷积递归神经网络(CNN/RNN)结构CRPTS来预测TFBSS。该方法的新颖性依赖于三个关键方面：(1)共享的混合CNN和RNN的应用能够有效地从通过高通量技术获得的大规模基因组序列中提取特征；(2)从DNA序列及其对应的DNA形状特征中找到共同的模式；(3)我们提出的CRPTS能够在不完全依赖DNA形状数据的情况下捕获DNA序列的局部结构信息。在来自通用蛋白质结合微阵列(UPBM)的66个体外数据集上的一系列综合实验表明，我们提出的方法CRPTS明显优于最先进的方法。转录调控的研究仍然是分子生物学研究中的难点和基础。提出了一种结合DNA序列和DNA形状特征预测TFBSS的混合卷积递归神经网络结构CRPTS。实验结果表明，CRPTS的性能明显优于目前最先进的方法。
The study of transcriptional regulation is still difficult yet fundamental in molecular biology research. Recent research has shown that the double helix structure of nucleotides plays an important role in improving the accuracy and interpretability of transcription factor binding sites (TFBSs). Although several computational methods have been designed to take both DNA sequence and DNA shape features into consideration simultaneously, how to design an efficient model is still an intractable topic. In this paper, we proposed a hybrid convolutional recurrent neural network (CNN/RNN) architecture, CRPTS, to predict TFBSs by combining DNA sequence and DNA shape features. The novelty of our proposed method relies on three critical aspects: (1) the application of a shared hybrid CNN and RNN has the ability to efficiently extract features from large-scale genomic sequences obtained by high-throughput technology; (2) the common patterns were found from DNA sequences and their corresponding DNA shape features; (3) our proposed CRPTS can capture local structural information of DNA sequences without completely relying on DNA shape data. A series of comprehensive experiments on 66 in vitro datasets derived from universal protein binding microarrays (uPBMs) shows that our proposed method CRPTS obviously outperforms the state-of-the-art methods. The study of transcriptional regulation is still difficult yet fundamental in molecular biology research. A hybrid convolutional recurrent neural network architecture, CRPTS, to predict TFBSs by combining DNA sequence and DNA shape features was proposed. Experimental results show that CRPTS obviously outperforms the state-of-the-art methods.
登录
查看更多内容
影响因子：
14.9
作者：
Li J;Sagendorf JM;Chiu TP;Pasi M;Perez A;Rohs R
通讯作者：
Rohs R
影响因子：
14.8
作者：
Berger, Michael F.;Bulyk, Martha L.
通讯作者：
Bulyk, Martha L.
影响因子：
30.5
作者：
Kidder, Benjamin L.;Hu, Gangqing;Zhao, Keji
通讯作者：
Zhao, Keji
DOI：
10.1109/tcbb.2013.10
发表时间：
2013-03-01
影响因子：
4.5
作者：
Huang, De-Shuang;Yu, Hong-Jie
通讯作者：
Yu, Hong-Jie
径向基概率神经网络的构造性混合结构优化方法
影响因子：
--
作者：
Huang, De-Shuang;Du, Ji-Xiang
通讯作者：
Du, Ji-Xiang