scEPS

scEPS (single-cell Expression exPlainability Statistics)

This repo contains the code of the method, scEPS, for integrating GWAS and single-cell disease cell atlas data to identify disease-associated cell neighborhoods. scEPS calculates a $d$ statistic at each cell neighborhood, representing the difference between the variance in disease explained by variations in the expression of each GWAS vs. each mean-expression matched control gene. An illustration of the scEPS method is shown below:

Reference

The current draft of the manuscript is available here. The code we used to create the figures in the manuscript is available here. We also implemented CNA*, a simple extension of CNA, for estimating the variance in disease attributable to variations in cell abundance at each cell neighborhood.

We also provide a web UI for visualizing the results in the scEPS manuscript here.

Manual

We provide a detailed manual of scEPS in the Wiki page.

Installation

Option 1: using pip

The easiest way to install scEPS is from PyPI:

pip install sceps

This installs the sceps Python package along with the four command-line tools described under Usage.

Option 2: using Anaconda or Miniforge

scEPS may also be installed into a dedicated environment through Anaconda or Miniforge. To do this, please first install Anaconda or Miniforge on your machine. You may then install scEPS using the following commands:

git clone git@github.com:Genentech/sceps.git
cd sceps
conda env create -f sceps.yml
conda activate sceps
pip install .

The sceps.yml file installs the dependencies through conda; the final pip install . installs scEPS itself and its command-line tools. Use pip install -e . instead if you intend to modify the scEPS source.

Option 3: manually install required packages

The user may also manually install the required packages to run scEPS. scEPS requires Python 3.9 or newer and the following packages:

These can be installed with a single command:

conda install -c conda-forge python=3.9 numpy=1.26.2 pandas=1.5.3 scipy=1.13.1 \
    anndata=0.10.7 scanpy=1.10.3 scikit-learn=1.3.2 statsmodels=0.14.5 \
    tqdm=4.67.1 packaging=25.0 matplotlib-base=3.9.4 seaborn=0.13.2

The pinned versions are those used for the analyses in the manuscript, and sceps.yml reproduces that environment exactly. The minimums are the floors declared in pyproject.toml; scEPS has also been verified to reproduce identical output on numpy 2.x, pandas 2.x, anndata 0.12 and scanpy 1.11.

The optional preprocessing helper script misc/preprocess_scdata.py additionally requires harmonypy for batch integration. This is also available as an extra:

pip install "sceps[preprocess]"

Once the required packages to run scEPS are installed, the user may then install scEPS using:

git clone git@github.com:Genentech/sceps.git
cd sceps
pip install --no-deps .

Usage

Installing scEPS provides four command-line tools, corresponding to the four steps of the scEPS workflow:

Pass --help to any of them for the full list of options, e.g. sceps --help. A detailed description of each step is available in the Wiki page.

scEPS can also be driven from Python rather than the command line:

from sceps.sceps_core import *

See misc/run_sceps_from_python.py for a worked example.

Testing scEPS

We provide examples script to test the scEPS workflow here.

Contact

Please create a GitHub issue if you experience any issue with running scEPS.