Tumor Phylogeny Topology Inference via Deep Learning

Getting started

You can get the code for different parts of this project using the following command.

git clone https://github.com/algo-cancer/PhyloM.git

The list of packages and their versions installed on our system for running these codes is provided in the packages.txt file.

Outline

• Data
• Branching Inference
• Noise Inference
• Noise Elimination

System configs

All the experiments in this work are performed using Carbonate, a computer cluster at Indiana University. We used deep learning (DL) nodes in Carbonate. These nodes features 12 GPU-accelerated Lenovo ThinkSystem SD530 , each equipped with two Intel Xeon Gold 6126 12-core CPUs, two NVIDIA GPU accelerators (eight with Tesla P100s; four with Tesla V100s), and 192 GB of RAM. A Red Hat Enterprise 7.x is running on these nodes and we used Python 3.7.3 :: Anaconda, Inc., Tensorflow 1.13.1, and Keras 2.2.4.

License

This code is published under Apache 2.0 license.

Contact

Please email us at esadeqia@iu.edu or mhaghir@iu.edu for any questions.