/snp-compression

Primary LanguagePythonBSD 3-Clause "New" or "Revised" LicenseBSD-3-Clause

SNP-Compression

Note: This is a work in progress

TODO:

  1. Generalize data read function to include xarrays metadata.
    1. reformat the dataset into .zarr (started)
    2. create code for doing the forward pass with metadata
  2. Get doug a txt with chr 1, 2, 6 as a N part.

This project seeks to compress snp's using deep neural networks.

Plan of action

  • Run model to test speed
    • check profiler
  • run w/o profiler
  • set up sweep
  • run sweep
  • select best model

Project Organization

├── LICENSE
├── README.md          <- The top-level README for developers using this project.
├── data
│   └── interim        <- The .zarr files created using src/data/plink_to_dask.py
│
├── models             <- Trained and serialized models, model predictions, or model summaries
│
├── references         <- Data dictionaries, manuals, and all other explanatory materials.
│
├── reports            <- Generated analysis as HTML, PDF, LaTeX, etc.
|   ├── slurm-output   <- slurm .out files
│   └── figures        <- Generated graphics and figures to be used in reporting
│
├── requirements.txt   <- The requirements file for reproducing the analysis environment.
│
├── src                <- Source code for use in this project.
│   ├── __init__.py    <- Makes src a Python module
│   │
│   ├── data           <- Scripts to download or generate data
│   │
│   └── models         <- Scripts to train models and then use trained models to make
│       │                 predictions
│       ├── predict_model.py
│       └── train_model.py