Uncovering tissue-specific binding features from differential deep learning
Uncovering tissue-specific binding features from differential deep learning
复制标题
DOI：
10.1101/606269
复制
发表时间：
2019-04
影响因子：
14.9
通讯作者：
Mike Phuycharoen;P. Zarrineh;Laure Bridoux;Shilu Amin;Marta Losa;Ke Chen;N. Bobola;M. Rattray
中科院分区：
文献类型：
--
作者：
Mike Phuycharoen;P. Zarrineh;Laure Bridoux;Shilu Amin;Marta Losa;Ke Chen;N. Bobola;M. Rattray
激励转录因子(Tf)可以协同的方式结合DNA，从而使占有率相互增加。通过这种类型的相互作用，可以优先结合不同组织中的替代结合部位，以调节组织特异性表达程序。最近，深度学习模型已经成为各种模式分析任务中的最新技术，包括在基因组学领域的应用。因此，我们研究了卷积神经网络(CNN)模型在发现决定组织间协同和差异TF结合的序列特征方面的应用。结果我们分析了MEI、TF和HOXA2的CHIP-SEQ数据，这些基因广泛表达于小鼠鳃弓中，HOXA2表达于第二和更后鳃弓中。通过开发预测MEIS在所有三种组织中差异结合的模型，我们能够准确地预测HOXA2共同结合部位。我们评估了转移类和多任务方法，以用更大的回归数据集来规范高维分类任务，从而允许创建更深层次和更准确的模型。我们测试了扰动和基于梯度的属性方法在从差异MEI数据中识别HOXA2位点的性能。我们的结果表明，在发现体内结合的组织特异性位点方面，深层正规化模型显著优于浅层CNN和k-mer方法。有关实施和型号的信息，请访问https://doi.org/10.5281/zenodo.2635463.
Motivation Transcription factors (TFs) can bind DNA in a cooperative manner, enabling a mutual increase in occupancy. Through this type of interaction, alternative binding sites can be preferentially bound in different tissues to regulate tissue-specific expression programmes. Recently, deep learning models have become state-of-the-art in various pattern analysis tasks, including applications in the field of genomics. We therefore investigate the application of convolutional neural network (CNN) models to the discovery of sequence features determining cooperative and differential TF binding across tissues. Results We analyse ChIP-seq data from MEIS, TFs which are broadly expressed across mouse branchial arches, and HOXA2, which is expressed in the second and more posterior branchial arches. By developing models predictive of MEIS differential binding in all three tissues we are able to accurately predict HOXA2 co-binding sites. We evaluate transfer-like and multitask approaches to regularising the high-dimensional classification task with a larger regression dataset, allowing for creation of deeper and more accurate models. We test the performance of perturbation and gradient-based attribution methods in identifying the HOXA2 sites from differential MEIS data. Our results show that deep regularised models significantly outperform shallow CNNs as well as k-mer methods in the discovery of tissue-specific sites bound in vivo. Availability For implementation and models please visit https://doi.org/10.5281/zenodo.2635463.