Identifying DNA Sequence Motifs Using Deep Learning

TL;DR

This paper introduces DeepDeCode, an attention-based deep learning model for predicting splice sites in DNA sequences, improving accuracy and interpretability for genomic analysis and healthcare applications.

Contribution

The paper presents a novel deep learning model with visualization techniques for accurate and interpretable splice site prediction in DNA sequences.

Findings

DeepDeCode outperforms existing methods in accuracy.

Visualization techniques improve motif identification.

Model demonstrates efficiency and explainability.

Abstract

Splice sites play a crucial role in gene expression, and accurate prediction of these sites in DNA sequences is essential for diagnosing and treating genetic disorders. We address the challenge of splice site prediction by introducing DeepDeCode, an attention-based deep learning sequence model to capture the long-term dependencies in the nucleotides in DNA sequences. We further propose using visualization techniques for accurate identification of sequence motifs, which enhance the interpretability and trustworthiness of DeepDeCode. We compare DeepDeCode to other state-of-the-art methods for splice site prediction and demonstrate its accuracy, explainability and efficiency. Given the results of our methodology, we expect that it can used for healthcare applications to reason about genomic processes and be extended to discover new splice sites and genomic regulatory elements.