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/mvinyard/sc-neural-diffeqs.git; cd ./sc-neural-diffeqs;

pip install -e .

Main API

import scdiffeq as sdq

model = sdq.scDiffEq(
    adata=adata, potential_type="fixed", train_lr=1e-4, train_step_size=1200
)
model.fit(train_epochs = 1500)

Built on:

System requirements

• Developed on linux20.04 and MacOS (with Apple Silicon), using Python3.9.
• Software dependencies are listed in requirements.txt
• Tested with NVIDIA GPUs (A100, T4) and Apple Silicon. Most datasets likely only require an NVIDIA Tesla T4 (free in Google Colab).

Reproducibiliuty

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