Sovereign 8s.is mirror of standardgalactic/scDiffEq
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Michael Vinyard d0c3c20cc6
Some checks failed
Build and Deploy Docs / build (push) Has been cancelled
Build and Deploy Docs / deploy (push) Has been cancelled
Revise software dependencies and manuscript link
Updated links and clarified software dependencies.
2025-12-23 08:04:17 -07:00
.github/workflows Add note about enabling GitHub Pages in repository settings 2025-12-21 09:38:44 -07:00
docs Update install docs 2025-12-21 12:29:54 -07:00
src/scdiffeq Update version for release 2025-12-21 09:08:13 -07:00
tests Enhance PyPI smoke test to validate package version attribute and its format 2025-12-18 09:24:34 -07:00
.gitignore Update git ignore 2025-12-21 09:43:01 -07:00
CNAME Create CNAME 2025-12-21 10:55:10 -07:00
LICENSE Create LICENSE 2022-11-23 00:08:37 -05:00
pyproject.toml bug fixes; updated quickstart nb for docs 2025-12-19 11:23:50 -07:00
README.md Revise software dependencies and manuscript link 2025-12-23 08:04:17 -07:00

scdiffeq_logo

PyPI pyversions PyPI version DOI

An analysis framework for modeling dynamical single-cell data with neural differential equations, most notably stochastic differential equations allow us to build generative models of single-cell dynamics.

Quickstart

Please see the scDiffEq website for a quickstart notebook: link

Install the development package

Install generally only takes a few seconds.

git clone https://github.com/scDiffEq/scDiffEq.git; cd ./scDiffEq;

# Install uv if you haven't already: curl -LsSf https://astral.sh/uv/install.sh | sh
uv sync

Using pip

git clone https://github.com/scDiffEq/scDiffEq.git; cd ./scDiffEq;

pip install -e .

With documentation dependencies

# Using uv
uv sync --extra docs

# Using pip
pip install -e ".[docs]"

Main API

import scdiffeq as sdq

model = sdq.scDiffEq(adata=adata)

model.fit(train_epochs = 1500)

Built on

pytorch_logopytorch_lightning_logo neural_diffeqs_logo

System requirements

  • Developed on linux20.04 and MacOS (with Apple Silicon), using Python3.11.
  • Software dependencies are listed in pyproject.toml.
  • Tested with NVIDIA GPUs (A100, T4) and Apple Silicon. Most datasets likely only require an NVIDIA Tesla T4 (free in Google Colab).

Reproducibility

  • All results described in the manuscript detailing scDiffEq can be reproduced using notebooks in the companion repository: scdiffeq-analyses