pimkl

pathway induced multiple kernel learning for computational biology

Features

The pimkl command:

Usage: pimkl [OPTIONS] NETWORK_CSV_FILE NETWORK_NAME GENE_SETS_GMT_FILE
         GENE_SETS_NAME PREPROCESS_DIR OUTPUT_DIR CLASS_LABEL_FILE [LAM]
         [K] [NUMBER_OF_FOLDS] [MAX_PER_CLASS] [SEED] [MAX_PROCESSES]
         [FOLD]

Console script for a complete pimkl pipeline, including preprocessing and
analysis. For more details consult the following console scripts, which
are here executed in this order. `pimkl-preprocess --help` `pimkl-analyse
run-performance-analysis --help`

Options:
-fd, --data_csv_file PATH       [required]
-nd, --data_name TEXT           [required]
--model_name [EasyMKL|UMKLKNN|AverageMKL]
--help                          Show this message and exit.

Requirements

  • C++14 capable C++ compiler

  • cmake (>3.0.2)

  • Python

Installation

Install the dependencies

pip install -r requirements.txt

Install the package

pip install .

Tutorial

You can find a brief tutorial in the dedicated folder.

Credits

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.