pathintegrate

PathIntegrate Python package for pathway-based multi-omics data integration

https://github.com/cwieder/pathintegrate

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 6 DOI reference(s) in README
  • Academic publication links
    Links to: biorxiv.org, plos.org, zenodo.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (16.1%) to scientific vocabulary

Keywords

metabolomics multi-omics-integration pathway-analysis reactome sklearn
Last synced: 6 months ago · JSON representation ·

Repository

PathIntegrate Python package for pathway-based multi-omics data integration

Basic Info
  • Host: GitHub
  • Owner: cwieder
  • License: gpl-3.0
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 3.84 MB
Statistics
  • Stars: 16
  • Watchers: 2
  • Forks: 1
  • Open Issues: 1
  • Releases: 1
Topics
metabolomics multi-omics-integration pathway-analysis reactome sklearn
Created over 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

PathIntegrate

PathIntegrate Python package for pathway-based multi-omics data integration

PyPI - Version DOI License: GPL v3 PyPI - Downloads

PathIntegrate graphical abstract

Abstract

As terabytes of multi-omics data are being generated, there is an ever-increasing need for methods facilitating the integration and interpretation of such data. Current multi-omics integration methods typically output lists, clusters, or subnetworks of molecules related to an outcome. Even with expert domain knowledge, discerning the biological processes involved is a time-consuming activity. Here we propose PathIntegrate, a method for integrating multi-omics datasets based on pathways, designed to exploit knowledge of biological systems and thus provide interpretable models for such studies. PathIntegrate employs single-sample pathway analysis to transform multi-omics datasets from the molecular to the pathway-level, and applies a predictive single-view or multi-view model to integrate the data. Model outputs include multi-omics pathways ranked by their contribution to the outcome prediction, the contribution of each omics layer, and the importance of each molecule in a pathway.

Features

  • Pathway-based multi-omics data integration using PathIntegrate Multi-View and Single-View models
    • Multi-View model: Integrates multiple omics datasets using a shared pathway-based latent space
    • Single-View model: Integrates multi-omics data into one set of multi-omics pathway scores and applies an SKlearn-compatible predictive model
    • Pathway importance
    • Sample prediction
    • NEW unsupervised SingleView models (dimensionality reduction and clustering in the pathway space)
  • SKlearn-like API for easy integration into existing pipelines
  • Support for multiple pathway databases, including KEGG, Reactome, PathBank, and custom GMT files
  • Support for multiple pathway scoring methods available via the sspa package
  • Cytoscape Network Viewer app for visualizing pathway-based multi-omics data integration results

PathIntegrate Cytoscape app

System requirements

Hardware

At least 8BG RAM recommended. PathIntegrate models can run on a Google Colab notebook server (see walkthrough tutorial below with example data).

Software

PathIntegrate has been tested on MacOs, Windows 10 and Linux. Python 3.10 or higher is required. Python dependencies are listed in the requirements.txt file.

Installation

bash pip install PathIntegrate

Tutorials and documentation

Please see our Quickstart guide on Google Colab

Full documentation and function reference for PathIntegrate can be found via our ReadTheDocs page

Citing PathIntegrate

If you use PathIntegrate in your research, please consider citing our paper: bibtex @article{Wieder2024, author = {Cecilia Wieder and Juliette Cooke and Clement Frainay and Nathalie Poupin and Russell Bowler and Fabien Jourdan and Katerina J. Kechris and Rachel P.J. Lai and Timothy Ebbels}, doi = {10.1371/JOURNAL.PCBI.1011814}, issue = {3}, journal = {PLOS Computational Biology}, month = {3}, pages = {e1011814}, pmid = {38527092}, publisher = {Public Library of Science}, title = {PathIntegrate: Multivariate modelling approaches for pathway-based multi-omics data integration}, volume = {20}, url = {https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1011814}, year = {2024}, }

PathIntegrate applications

Check out the following papers to see how PathIntegrate has been used in research: - Time-resolved, integrated multi-omic analysis reveals central role of amino acid pathways for defense responses in Arabidopsis thaliana

License

GNU GPL v3

Contributors

Owner

  • Login: cwieder
  • Kind: user
  • Location: London, UK
  • Company: Imperial College London

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Wieder"
  given-names: "Cecilia"
  orcid: "https://orcid.org/0000-0003-1548-4346"
- family-names: "Popham"
  given-names: "Jude"
  orcid: "https://orcid.org/0009-0004-1116-1034"
title: "PathIntegrate Unsupervised"
version: 1.0.0
doi: 10.5281/zenodo.14060723
date-released: 2024-11-09
url: "https://github.com/cwieder/PathIntegrate"

GitHub Events

Total
  • Create event: 1
  • Issues event: 1
  • Release event: 1
  • Watch event: 4
  • Issue comment event: 4
  • Push event: 7
  • Pull request event: 1
  • Fork event: 1
Last Year
  • Create event: 1
  • Issues event: 1
  • Release event: 1
  • Watch event: 4
  • Issue comment event: 4
  • Push event: 7
  • Pull request event: 1
  • Fork event: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 1
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 1
  • Total pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • priyanka-1802 (1)
Pull Request Authors
  • judepops (1)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 40 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 5
  • Total maintainers: 1
pypi.org: pathintegrate

PathIntegrate: multivariate modelling approaches for pathway-based muti-omics integration

  • Versions: 5
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 40 Last month
Rankings
Dependent packages count: 9.6%
Forks count: 29.9%
Average: 36.6%
Stargazers count: 38.9%
Dependent repos count: 67.9%
Maintainers (1)
Last synced: 6 months ago

Dependencies

requirements.txt pypi
  • cmcrameri ==1.6
  • dash ==2.11.1
  • dash_bootstrap_components ==1.4.1
  • dash_cytoscape ==0.3.0
  • matplotlib ==3.5.2
  • mbpls ==1.0.4
  • networkx ==3.1
  • numpy ==1.25.2
  • pandas ==1.5.3
  • plotly ==5.15.0
  • python_datauri ==2.0.0
  • scikit_learn ==1.3.0
  • scipy ==1.11.1
  • scipy ==1.8.1
  • seaborn ==0.12.2
  • setuptools ==68.0.0
  • sspa >=1.0.0
  • statsmodels ==0.13.2
  • svgwrite ==1.4.3
setup.py pypi
  • cmcrameri *
  • dash *
  • dash_bootstrap_components *
  • dash_cytoscape *
  • matplotlib *
  • networkx *
  • numpy *
  • pandas *
  • plotly *
  • scikit-learn *
  • scipy *
  • seaborn *
  • setuptools *
  • sspa *
  • statsmodels *