Skip to main content

A Python package for UNAGI

Project description

UNAGI

UNAGI: Deep Generative Model for Deciphering Cellular Dynamics and In-Silico Drug Discovery in Complex Diseases

Full documentations and tutorials can be accessed at UNAGI-docs.

Overview

Alt text UNAGI is a comprehensive unsupervised in-silico cellular dynamics and drug discovery framework. UNAGI adeptly deciphers cellular dynamics from human disease time-series single-cell data and facilitates in-silico drug perturbations to earmark therapeutic targets and drugs potentially active against complex human diseases. All outputs, from cellular dynamics to drug perturbations, are rendered in an interactive visual format within the UNAGI framework. Nestled within a deep learning architecture Variational Autoencoder-Generative adversarial network (VAE-GAN), UNAGI is tailored to manage diverse data distributions frequently arising post-normalization. It also innovatively employs disease-informed cell embeddings, harnessing crucial gene markers derived from the disease dataset. On achieving cell embeddings, UNAGI fabricates a graph that chronologically links cell clusters across disease stages, subsequently deducing the gene regulatory network orchestrating these connections. UNAGI is primed to leverage time-series data, enabling a precise portrayal of cellular dynamics and a superior capture of disease markers and regulators. Lastly, the deep generative prowess of UNAGI framework powers an in-silico drug perturbation module, simulating drug impacts by manipulating the latent space informed by real drug perturbation data from the CMAP database. This allows for an empirical assessment of drug efficacy based on cellular shifts towards healthier states following drug treatment. The in-silico perturbation module can similarly be utilized to investigate therapeutic pathways, employing an approach akin to the one used in drug perturbation analysis.

Key Capabilities

  • Learning disease-specific cell embeddings through iterative training processes.

  • Constructing temporal dynamic graphs from time-series single-cell data and reconstructing temporal gene regulatory networks to decipher cellular dynamics.

  • Identifying dynamic and hierarchical static markers to profile cellular dynamics, both longitudinally and at specific time points.

  • Performing in-silico perturbations to identify potential therapeutic pathways and drug/compound candidates.

Installation

Create a new conda environment

conda create -n unagi python=3.9
conda activate unagi

UNAGI installation

Option 1: Install from pip

pip install scUNAGI

Option 2: Install from Github

Installing UNAGI directly from GitHub ensures you have the latest version. (Please install directly from GitHub to use the provided Jupyter notebooks for tutorials and walkthrough examples.)

git clone https://github.com/mcgilldinglab/UNAGI.git
cd UNAGI
pip install .

Prerequisites

  • Python >=3.9 (Python3.9 is recommanded)
  • pyro-ppl>=1.8.6
  • scanpy>=1.9.5
  • anndata==0.8.0
  • torch >= 2.0.0
  • matplotlib>=3.7.1

Required files

Preprocessed CMAP database: One Drive

  • Mandatory data to run UNAGI perturbation function.

Preprocessed IPF snRNA-seq dataset: One Drive

  • UNAGI outcomes to reproduce the figures and tables generated for the manuscript.

Example dataset: Link.

  • The dataset for UNAGI walktrhough demonstration.

iDREM installation:

git clone https://github.com/phoenixding/idrem.git

iDREM prerequisites:

Install the iDREM to the source folder of UNAGI

  • Java To use iDREM, a version of Java 1.7 or later must be installed. If Java 1.7 or later is not currently installed, please refer to http://www.java.com for installation instructions.

  • JavaScript To enable the interactive visualization powered by Javascript, please make sure that you have Internet connection. (The users are still able to run the software off-line, but Internet access is needed to view the result interactively.)

Tutorials:

Dataset preparation

Prepare datasets to run UNAGI.

Training and analysis on example dataset

UNAGI training and analysis on an example dataset.

Visualize the results of UNAGI method

Visualization on an example dataset.

Using UNAGI with a customized pathway or drug database for in-silico perturbation

Run UNAGI on Customized drug/compound database and Customized pathway database.

Predicting post-treatment gene expressions

Predict the post-treatment gene expression changes using the PCLS data.

Please visit UNAGI-docs for more examples and tutorials.

Contact

Yumin Zheng, Naftali Kaminski, Jun Ding

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

scUNAGI-0.4.0.tar.gz (5.2 MB view details)

Uploaded Source

Built Distribution

scUNAGI-0.4.0-py3-none-any.whl (5.2 MB view details)

Uploaded Python 3

File details

Details for the file scUNAGI-0.4.0.tar.gz.

File metadata

  • Download URL: scUNAGI-0.4.0.tar.gz
  • Upload date:
  • Size: 5.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.12

File hashes

Hashes for scUNAGI-0.4.0.tar.gz
Algorithm Hash digest
SHA256 3b09218749b1b0ccc1a6e161b2d087be8f3f20d0d4167b5678aa6488aecf60c9
MD5 b8e096e8759d9701a7867260717100ae
BLAKE2b-256 e76e9e42231afa1a42dc43fff926d723ee50f98192adafc0e65f40ae4d218521

See more details on using hashes here.

File details

Details for the file scUNAGI-0.4.0-py3-none-any.whl.

File metadata

  • Download URL: scUNAGI-0.4.0-py3-none-any.whl
  • Upload date:
  • Size: 5.2 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.12

File hashes

Hashes for scUNAGI-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 4907087588759df29d698c0a71cf026a6cc48befd44f34bd90be1dfe462054be
MD5 c8ca85039ef5581ba18c09411a47b54c
BLAKE2b-256 b0ecbb93d0e406214ab78c670676962f30691f31f7c1964d1d0410dd95b00e70

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page