Skip to content

Latest commit

 

History

History
24 lines (19 loc) · 1.72 KB

README.md

File metadata and controls

24 lines (19 loc) · 1.72 KB
Raw

Installation procedure

  1. Create a virtualenv most likely like this " create -n name_of_your_env python==3.9 "
  2. Activate the env like this "conda activate name_of_your_env"
  3. Install the requirements: "pip install -R requirements.txt"
  4. Go to the multiomic repo "cd multiomic_predictions"
  5. pip install -e .

multiomic_predictions

This is a the implementation of the model (MOT) submited at BMC. The preprint is available here: [https://doi.org/10.21203/rs.3.rs-1348696/v1]. MOT (Multi-Omic Transformer) is a deep learning based model using the transformer architecture, that discriminates complex phenotypes (herein cancers types) based on five omics data type regardless of their availability: transcriptomics (mRNA and miRNA), epigenomics (DNA methylation), copy number variations (CNVs), and proteomics. The Pancan Dataset is available at [https://xenabrowser.net/datapages/?hub=https://pancanatlas.xenahubs.net:443].

STEPS

Building Dataset

  1. Download the files from The Pancan Dataset at [https://xenabrowser.net/datapages/?hub=https://pancanatlas.xenahubs.net:443].
  2. Run [

    multiomic_predictions/multiomic_modeling/data/build_data.py

    Line 117 in 76430ac

    if __name__ == '__main__':
    ] (Change the path for the dataset)

Models

  1. The normal version (without data augmentation): [https://github.com/dizam92/multiomic_predictions/blob/main/multiomic_modeling/models/models_optuna_version_normal.py]

  2. The version (with data augmentation): [https://github.com/dizam92/multiomic_predictions/blob/main/multiomic_modeling/models/models_optuna_version_data_augmentation.py]

Analysis section

[https://github.com/dizam92/multiomic_predictions/tree/main/multiomic_modeling/analyses_and_paper_figures_section]