Deep Motif: Visualizing Genomic Sequence Classifications

TL;DR

Deep Motif introduces a deep learning approach for classifying genomic sequences and visualizing learned motifs, achieving comparable or better motif extraction and classification performance than existing methods.

Contribution

The paper presents Deep Motif, a novel deep learning framework that visualizes genomic motifs and demonstrates improved classification accuracy over previous models.

Findings

Deep Motif extracts motifs similar to known motifs.

Deeper models outperform shallower ones in classification.

The system achieves competitive motif visualization results.

Abstract

This paper applies a deep convolutional/highway MLP framework to classify genomic sequences on the transcription factor binding site task. To make the model understandable, we propose an optimization driven strategy to extract "motifs", or symbolic patterns which visualize the positive class learned by the network. We show that our system, Deep Motif (DeMo), extracts motifs that are similar to, and in some cases outperform the current well known motifs. In addition, we find that a deeper model consisting of multiple convolutional and highway layers can outperform a single convolutional and fully connected layer in the previous state-of-the-art.