Convolutional neural network architectures for predicting DNA–protein binding

By Haoyang Zeng, Matthew D. Edwards, Ge Liu, David K. Gifford. 2016

477 citations recorded by the source corpus.

Motivation: Convolutional neural networks (CNN) have outperformed conventional methods in modeling the sequence specificity of DNA–protein binding. Yet inappropriate CNN architectures can yield poorer performance than simpler models. Thus an in-depth understanding of how to match CNN architecture to a given task is needed to fully harness the power of CNNs for computational biology applications. Results: We present a systematic exploration of CNN architectures for predicting DNA sequence binding using a large compendium of transcription factor datasets. We identify the best-performing architectures by varying CNN width, depth and pooling designs. We find that adding convolutional kernels to a network is important for motif-based tasks. We show the benefits of CNNs in learning rich higher-order sequence features, such as secondary motifs and local sequence context, by comparing network performance on multiple modeling tasks ranging in difficulty. We also demonstrate how careful construction of sequence benchmark datasets, using approaches that control potentially confounding effects like positional or motif strength bias, is critical in making fair comparisons between competing methods. We explore how to establish the sufficiency of training data for these learning tasks, and we have created a flexible cloud-based framework that permits the rapid exploration of alternative neural network architectures for problems in computational biology. Availability and Implementation: All the models analyzed are available at http://cnn.csail.mit.edu. Contact: gifford@mit.edu Supplementary information: Supplementary data are available at Bioinformatics online.

Subfields: Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Forecasting Crude Oil Prices: a Deep Learning based Model (2017, methodology): “[10] applied the convolution neural network to the biological aspects of DNA-protein transcription prediction.”
Training GANs with Optimism (2017, methodology): “matrix. Both the discriminator and generator of the WGAN used in this analysis were chosen to be convolutional neural networks (CNN), given the recent success of CNNs in modeling DNA-protein binding (Zeng et al., 2016; Alipanahi et al., 2015). The detailed structure of the chosen CNNs can be found i”
Biological Sequence Modeling with Convolutional Kernel Networks (2017, positive): “Both supervised and unsupervised versions of CKN-seq show performance similar to DeepBind-based CNN models (Figure 2), on either the Deep-Bind Zeng et al. [2016] datasets.”
Strong mixed-integer programming formulations for trained neural networks (2018, background): “For example, neural networks have proven well-suited for predicting the propensity for a given DNA sequence to bind with a given protein [2,83], where the”
Maximum entropy methods for extracting the learned features of deep neural networks (2017, methodology): “constructed by [2] from ENCODE CTCF ChIP-seq data [11].”
Deep Learning and Its Applications in Biomedicine (2018, result): “Subsequently, Lanchantin et al. [148] and Zeng et al. [149] also applied CNN to predict transcription factor binding sites (TFBSs), and both studies demonstrated an improvement over the performance of DeepBind (AUC of 0.894).”
Machine learning in protein engineering (2018, background): “…large labeled datasets with examples from many protein families, such as protein-nucleic acid binding (Zhang et al., 2015; Alipanahi et al., 2015; Zeng et al., 2016), protein-MHC binding (Hu & Liu, 2017), binding site prediction (Jim ´ enez et al., 2017), protein-ligand binding (Gomes et al.,…”
Efficient Processing of Deep Neural Networks: A Tutorial and Survey (2017, background): “• Medical DNNs: They have played an important role in genomics to gain insight into the genetics of diseases such as autism, cancers, and spinal muscular atrophy [24]–[27].”
Sequence-based prediction of protein protein interaction using a deep-learning algorithm (2017, methodology): “This phenomenon was also observed by Zeng et al. on predicting the protein binding motif on DNA using a convolutional neural network (CNN) method [23].”
Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, methodology): “employed CNN to predict the binding between DNA and protein [95].”
Mut2Vec: distributed representation of cancerous mutations (2018, background): “…learning techniques has been making remarkable improvements in various applications such as text mining [1], speech recognition [2], image classification [3] and even the prediction tasks in biomedical domain such as protein secondary structure prediction [4] and DNA-protein binding prediction [5].”
Deep learning in bioinformatics (2016, unknown): “[102] performed a systematic exploration of CNN”