search

gregbellan / Stabl

BSD 3-Clause Clear License
48 stars 15 forks source link

readme

STABL

Discovery of sparse, reliable omic biomarkers with Stabl

DOI Python version BSD 3-Clause Clear license BSD 3-Clause Clear license

Last full release Last light-weight release GitHub latest commit

GitHub forks GitHub stars GitHub watchers

This is a scikit-learn compatible Python implementation of Stabl, coupled with useful functions and example notebooks to rerun the analyses on the different use cases located in the sample data folder

Abstract

Adoption of high-content omic technologies in clinical studies, coupled with computational methods, has yielded an abundance of candidate biomarkers. However, translating such fndings into bona fde clinical biomarkers remains challenging. To facilitate this process, we introduce Stabl, a general machine learning method that identifes a sparse, reliable set of biomarkers by integrating noise injection and a data-driven signal-to- noise threshold into multivariable predictive modeling. Evaluation of Stabl on synthetic datasets and fve independent clinical studies demonstrates improved biomarker sparsity and reliability compared to commonly used sparsity-promoting regularization methods while maintaining predictive performance; it distills datasets containing 1,400–35,000 features down to 4–34 candidate biomarkers. Stabl extends to multi-omic integration tasks, enabling biological interpretation of complex predictive models, as it hones in on a shortlist of proteomic, metabolomic and cytometric events predicting labor onset, microbial biomarkers of pre-term birth and a pre-operative immune signature of post-surgical infections.

Full content: https://rdcu.be/du2gB

Cite us

Hédou, J., Marić, I., Bellan, G. et al. Discovery of sparse, reliable omic biomarkers with Stabl. Nat Biotechnol (2024). https://doi.org/10.1038/s41587-023-02033-x

or by following this link

Light-weight version

Requirements

Python version : from 3.7 up to 3.12

Python packages:

Installation

In order to install the light-weight version of the library, you have two options:

  1. Install directly from github:
pip install git+https://github.com/gregbellan/Stabl.git@v1.0.1-lw

  1. Clone the repository and install the library:

    a. Download Stabl:

    git clone https://github.com/gregbellan/Stabl.git@stabl_lw

    b. Install requirements and Stabl:

    cd Stabl
pip install .

The general installation time is less than 10 seconds, and have been tested on mac OS and linux system.

You may need to install CMake to fully use the library. Please refer to the section CMake installation in full version installation for more details.

Full version

Requirements

Python version : from 3.7 up to 3.10

Python packages:

Julia package for noise generation (version 1.9.2) :

Installation

Julia installation

To install Julia, please follow these instructions:

  1. Download Julia from here.
  2. Follow the instructions for your operating system here.

  3. Install the required julia packages :

    
julia -e 'using Pkg; Pkg.add(name="Bigsimr", version="0.8.7"); Pkg.add(name="Distributions", version="0.25.98"); Pkg.add(name="PyCall", version="1.96.1"); Pkg.add("IJulia")'
  4. Finally, install Julia for python: 
    pip install julia
python -c "import julia; julia.install()"

CMake installation

In order to install the python libraries required to generate the noise, we need to install :

You can install this module by :

Python installation (>= 3.7 and < 3.11)

Install Directly from github (install latest release):

pip install git+https://github.com/gregbellan/Stabl.git
pip install numpy==1.23.2

or

Download Stabl:

git clone https://github.com/gregbellan/Stabl.git

Install requirements and Stabl:

cd Stabl
pip install .
pip install numpy==1.23.2

The general installation time is less than 10 seconds, and have been tested on mac OS and linux system.

NOTE: There is a behavior with Julia library:

  • you can run the script in a notebook, but you need to run the import block two times. The first will throw an error and the second one will finalize the import.
  • It is not possible to run the script in command line if you are installing the library with conda To resolve this issue, either you install the library without conda or you run the script into a notebook.

If there is still an issue with Julia in a notebook, run the following command in the first cell of the notebook:

from julia.api import Julia
jl = Julia(compiled_modules=False)

Use of the library

To use the library and the associated benchmark in the folder Notebook examples, you need to download the repository :

git clone https://github.com/gregbellan/Stabl.git
cd Stabl/
unzip Sample\ Data/data.zip -d Sample\ Data/

Benchmarks

NOTE: The different scripts may take some time to begin because of the dependence with julia. However, once started, the time to run should come back to normal.

Input data

When using your own data, you have to provide

Sample Data

The "Sample Data" folder contains data for the following use cases:

Onset of Labor

Training

COVID-19

Training

CFRNA Preeclampsia

Training

Surgical Site Infections (SSI)

Training

Dream

Training