DeepATAC: A deep-learning method to predict regulatory factor binding activity from ATAC-seq signals

Hiranuma, Naozumi; Lundberg, Scott; Lee, Su-In

doi:10.1101/172767

Cited by 12 publications

(19 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep convolutional neural networks (CNNs) have recently been applied to predict transcription factor (TF) binding motifs from genomic sequences [1][2][3][4]. Despite the promise that CNNs bring in replacing methods that rely on k-mers and position weight matrices (PWMs) [5,6], there remains a large gap in our understanding of why CNNs perform well.…”

Section: Introductionmentioning

confidence: 99%

Representation learning of genomic sequence motifs with convolutional neural networks

2019

View full text Add to dashboard Cite

Although convolutional neural networks (CNNs) have been applied to a variety of computational genomics problems, there remains a large gap in our understanding of how they build representations of regulatory genomic sequences. Here we perform systematic experiments on synthetic sequences to reveal how CNN architecture, specifically convolutional filter size and max-pooling, influences the extent that sequence motif representations are learned by first layer filters. We find that CNNs designed to foster hierarchical representation learning of sequence motifs-assembling partial features into whole features in deeper layers-tend to learn distributed representations, i.e. partial motifs. On the other hand, CNNs that are designed to limit the ability to hierarchically build sequence motif representations in deeper layers tend to learn more interpretable localist representations, i.e. whole motifs. We then validate that this representation learning principle established from synthetic sequences generalizes to in vivo sequences.

show abstract

Section: Introductionmentioning

confidence: 99%

Representation learning of genomic sequence motifs with convolutional neural networks

2019

View full text Add to dashboard Cite

show abstract

“…Deep convolutional neural networks (CNNs) have recently been applied to predict transcription factor (TF) binding motifs from genomic sequences (Zhou and Troyanskaya, 2015;Quang and Xie, 2016;Kelley et al , 2016;Hiranuma et al , 2017). Despite the promise that CNNs bring in replacing methods that rely on k -mers and position weight matrices (PWMs) (Ghandi et al , 2016;Foat et al , 2006), there remains a large gap in our understanding of why CNNs perform well.…”

Section: Introductionmentioning

confidence: 99%

Representation Learning of Genomic Sequence Motifs with Convolutional Neural Networks

Koo

Eddy

2018

Preprint

View full text Add to dashboard Cite

Although convolutional neural networks (CNNs) have been applied to a variety of computational genomics problems, there remains a large gap in our understanding of how they work. Here we perform systematic experiments on synthetic sequences to reveal principles of how CNN architecture in uences the internal representations of genomic sequence motifs that are learned. We focus our study on representations learned by rst convolutional layer lters. We nd that deep CNNs tend to learn distributed representations of partial sequence motifs. However, we demonstrate that the architecture of a CNN can be modi ed to predictively learn more interpretable localist representations, i.e. whole motifs. We then validate that the representation learning principles established from synthetic sequences generalize to in vivo sequences.

show abstract

“…Deep neural networks (DNNs) have demonstrated improved performance in many prediction tasks in computational biology (Zhou & Troyanskaya, 2015;Alipanahi et al, 2015;Zeng et al, 2016;Eraslan et al, 2019;Hiranuma et al, 2017;Angermueller et al, 2017;Kelley et al, 2016). Despite their promise, the main drawback of DNNs is the difficulty in understanding why they make any given prediction.…”

Section: Overviewmentioning

confidence: 99%

Interpreting Deep Neural Networks Beyond Attribution Methods: Quantifying Global Importance of Genomic Features

Koo

Ploenzke

2020

Preprint

View full text Add to dashboard Cite

Despite deep neural networks (DNNs) having found great success at improving performance on various prediction tasks in computational genomics, it remains difficult to understand why they make any given prediction. In genomics, the main approaches to interpret a high-performing DNN are to visualize learned representations via weight visualizations and attribution methods. While these methods can be informative, each has strong limitations. For instance, attribution methods only uncover the independent contribution of single nucleotide variants in a given sequence.Here we discuss and argue for global importance analysis which can quantify population-level importance of putative features and their interactions learned by a DNN. We highlight recent work that has benefited from this interpretability approach and then discuss connections between global importance analysis and causality.

show abstract

DeepATAC: A deep-learning method to predict regulatory factor binding activity from ATAC-seq signals

Cited by 12 publications

References 10 publications

Representation learning of genomic sequence motifs with convolutional neural networks

Representation learning of genomic sequence motifs with convolutional neural networks

Representation Learning of Genomic Sequence Motifs with Convolutional Neural Networks

Interpreting Deep Neural Networks Beyond Attribution Methods: Quantifying Global Importance of Genomic Features

Contact Info

Product

Resources

About