Identifying Splice Junctions in Primate DNA using Time Series Classification

In this project, the aim is to develop a method of classifying whether a given section of primate DNA contains a splice junction or not. Furthermore, determining whether the splice junction is exon-intron, or intron-exon. This will be accomplished using a Time Series Classification model, specifically using Dynamic Time Warping.

Getting Started

To run this file, make sure you have Python 3.7.2, Jupyter Notebook, and (optionally) Anaconda installed.

Prerequisites

• Numpy >= 1.16.2
• Pandas >= 0.24.2
• Scikit-learn >= 0.20.3
• Matplotlib >= 3.0.3
• DTW >= 1.0.4

Most of these, except DTW, can be installed automatically using the requirements.txt file:

pip install -r requirements.txt

or if you're using Anaconda, create a virtual environment:

conda create --name splice_junction --file requirements.txt

Running

Navigate to the directory with the ipynb file, and then launch Jupyter:

jupyter notebook

Authors

Eli Halpern, Abolfazl Saghafi

License

This project is licensed under the GNU General Public License - see the LICENSE.md file for details

Acknowledgments

• Dr. Abolfazl Saghafi, my research advisor who guided me through this project
• Dr. Zhijun Li, head of the Bioinformatics department at USciences