Deep Motif: Visualizing Genomic Sequence Classifications

Jack Lanchantin, Ritambhara Singh, Zeming Lin, Yanjun Qi
5/4/2016
cs.LG

Official code: QData/DeepMotif (46 stars, MIT, last commit 2019-04-19).

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.

View on arXivView PDF

Code Implementations(1)

QData/DeepMotifOfficial100%
MIT

Deep Motif (ICLR16)/ Deep Motif Dashboard (PSB17): Visualizing Genomic Sequence Classifications

4614R, LuaMar 26, 20167 years agoMIT
deep-learninggenomicstorch

Similar Papers

A mechanistically interpretable neural network for regulatory genomics

84% match1 repo132024

A Multi-Label Temporal Convolutional Framework for Transcription Factor Binding Characterization

84% match2026

Explainable AI in Genomics: Transcription Factor Binding Site Prediction with Mixture of Experts

83% match2025

GCBLANE: A graph-enhanced convolutional BiLSTM attention network for improved transcription factor binding site prediction

82% match1 repo2025

Predicting Transcription Factor Binding Sites using Transformer based Capsule Network

82% match1 repo42023

A Benchmark Dataset for Multimodal Prediction of Enzymatic Function Coupling DNA Sequences and Natural Language

80% match1 repo72024

Cite this paper

@article{lanchantin2016deep,
  title  = {Deep Motif: Visualizing Genomic Sequence Classifications},
  author = {Jack Lanchantin and Ritambhara Singh and Zeming Lin and Yanjun Qi},
  year   = {2016},
  eprint = {1605.01133},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1605.01133}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1605.01133.svg)](https://codeofpaper.com/paper/1605.01133)

Discussion