Deep neural network (DNN) models have recently obtained state-of-the-art prediction accuracy for the transcription factor binding (TFBS) site classification task. However, it remains unclear how these approaches identify meaningful DNA sequence signals and give insights as to why TFs bind to certain locations. In this paper, we propose a toolkit called the Deep Motif Dashboard (DeMo Dashboard) which provides a suite of visualization strategies to extract motifs, or sequence patterns from deep neural network models for TFBS classification. We demonstrate how to visualize and understand three important DNN models using three visualization methods: saliency maps, temporal output scores, and class optimization. In addition to providing insights as to how each model makes its prediction, the visualization techniques indicate that CNN-RNN makes predictions by modeling both motifs as well as dependencies among them.
Jack Lanchantin (University of Virginia)
Jack Lanchantin is a 4th year PhD student in the department of computer science at the University of Virginia, working with Dr. Yanjun Qi. His interests are primarily in the application of deep learning for biomedical applications.
Ritambhara Singh (University of Virginia)
Beilun Wang (University of Virginia)
More from the Same Authors
2020 : Transfer Learning with Neural Motif Transformer for Predicting Protein-Protein Interactions Between SARS-CoV-2 and Humans »
2017 : Posters »
Reihaneh Rabbany · Tianxi Li · Jacob Carroll · Yin Cheng Ng · Xueyu Mao · Alexandre Hollocou · Jeric Briones · James Atwood · John Santerre · Natalie Klein · Pranamesh Chakraborty · Zahra Razaee · Chandan Singh · Arun Suggala · Beilun Wang · Andrew R. Lawrence · Aditya Grover · FARSHAD HARIRCHI · radhika arava · Qing Zhou · Takatomi Kubo · Josue Orellana · Govinda Kamath · Vivek Kumar Bagaria
2017 Poster: Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin »
Ritambhara Singh · Jack Lanchantin · Arshdeep Sekhon · Yanjun Qi