scmkl 0.1.4

Single-cell analysis using Multiple Kernel Learning

Single-cell analysis using Multiple Kernel Learning, scMKL, is a binary classification algorithm utilizing prior information to group features to enhance classification and aid understanding of distinguishing features in multi-omic data sets.

Installation with pip

First, create a virtual environment with a version of python >= 3.11.1 and <3.13.

Then, install scMKL with:

# activate your new env with python>=3.11.1 and <3.13
pip install scmkl

If wheels do not build correctly, ensure gcc and g++ are installed. They can be installed with sudo apt install gcc and sudo apt-get install g++.

Usage

scMKL takes advantage of AnnData objects and can be implemented with just four pieces of data:

1. scRNA and/or scATAC matrices (can be scipy.sparse matrix)

2. An array of cell labels

3. An array of feature names (eg. gene symbols for RNA or peaks for ATAC)

4. A grouping dictionary where {'group_1' : [feature_5, feature_16], 'group_2' : [feature_1, feature_4, feature_9]}

For more information on formatting/creating the grouping dictionaries, see our example for creating an RNA grouping or ATAC grouping.

For implementing scMKL, see our examples for your use case in examples.

Links

Repo: GitHub Repository

PyPI: Python Package Repository

API: scMKL Documentation

Citation

If you use scMKL in your research, please cite using:

To be determined

Our Shiny for Python application for viewing data produced from this work can be found here: scMKL_analysis