Repository files navigation

• Introduction
• Usage: Google Colab Notebooks
• Usage: Running Locally
  • Installation Requirements
  • Steps
• Citation
• License

Mass spectrometry-based phosphoproteomics offers a comprehensive view of protein phosphorylation, yet limited knowledge about the regulation and function of most phosphosites restricts the extraction of meaningful biological insights.CoPheeMap addresses this challenge by combining machine learning with phosphoproteomic data from 1,195 tumor specimens spanning 11 cancer types, creating a co-regulation network of26,280 phosphosites.

Key Features:

• CoPheeMap constructs a co-regulation map of phosphosites.
• CoPheeKSA predicts kinase-substrate associations, revealing associations between 9,399 phosphosites and 104 kinases (including under-studied kinases).
• Highlights biologically significant phosphosites and identifies potential therapeutic targets.

For detailed information, refer to ourbioRxiv preprint.

Component	Description	Notebook
CoPheeMap	Supervised learning model to construct a co-regulated phosphosite network
CoPheeKSA	Predict kinase-substrate associations using CoPheeMap
PSSM	Generate PSSM matrices from gold-standard KSAs

• Python 3.8 or later
• Required Python libraries: numpy, pandas, scikit-learn, matplotlib
• Jupyter Notebook (for running Colab notebooks locally)

1. Clone the repository:

   git clone https://github.com/bzhanglab/CoPheeMap.gitcd CoPheeMap

2. Install dependencies:

   pip install -r requirements.txt

To run the notebooks locally:

1. Install Jupyter Notebook:

   pip install notebook

2. Start Jupyter Notebook:

   jupyter notebook

3. Open the desired.ipynb file and execute the cells. Follow the instructions in each notebook to:
   • Construct the co-regulation map (CoPheeMap).
   • Predict kinase-substrate associations (CoPheeKSA).
   • Generate PSSM matrices.

If you use CoPheeMap or CoPheeKSA in your research, please cite:

@article{jiang2024,title={Illuminating the Dark Cancer Phosphoproteome Through a Machine-Learned Co-Regulation Map of 26,280 Phosphosites},author={Jiang W, Jaehnig EJ, Liao Y, Yaron-Barir TM, Johnson JL, Cantley LC, Zhang B},journal={bioRxiv},year={2024},doi={10.1101/2024.03.19.585786}}

This repository is licensed under the MIT License. See theLICENSE file for details.