Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/core-bioinformatics/clustassesspy

https://github.com/core-bioinformatics/clustassesspy

Science Score: 26.0%

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

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 2 DOI reference(s) in README
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.2%) to scientific vocabulary

Keywords

bioinformatics clustering genomics machine-learning parameter-optimisation robustness single-cell unsupervised-learning
Last synced: 5 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: Core-Bioinformatics
  • License: mit
  • Language: C++
  • Default Branch: main
  • Homepage:
  • Size: 1.82 MB
Statistics
  • Stars: 3
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
bioinformatics clustering genomics machine-learning parameter-optimisation robustness single-cell unsupervised-learning
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme License

README.md

ClustAssessPy

Downloads Downloads

ClustAssessPy offers a data-driven approach for optimizing parameter values across all stages of graph-based community detection clustering in single-cell datasets. This Python package is a lighter adaptation of ClustAssess (R) [1], incorporating its main functions and can be used by the Scanpy community to guide robust clustering through data-driven selection in all community detection clustering steps:

  • Dimensionality Reduction: Selection of the base embedding (UMAP vs PCA) and the number and type of features (e.g., highly-variable vs most abundant).
  • Graph Type: Choice of graph type for the adjacency matrix (nearest neighbors vs shared nearest neighbors) and the number of neighbors.
  • Clustering: Identification of the most stable algorithm (Leiden or Louvain) and the appropriate resolution value.

Installation

ClustAssessPy requires Python 3.7 or newer.

Dependencies

  • numpy
  • pandas
  • scanpy
  • umap-learn
  • seaborn
  • matplotlib
  • scipy
  • networkx
  • plotnine
  • pynndescent
  • leidenalg
  • louvain
  • igraph

User Installation

We recommend that you download ClustAssessPy on a virtual environment (venv or Conda).

sh pip install ClustAssessPy

Getting Started

Documentation for the main functions is available here. For a detailed tutorial, click here.

References

[1] Shahsavari, A., Munteanu, A., & Mohorianu, I. (2022). ClustAssess: Tools for Assessing the Robustness of Single-Cell Clustering. https://doi.org/10.1101/2022.01.31.478592

Owner

  • Name: Cambridge Stem Cell Institute Core Bioinformatics group
  • Login: Core-Bioinformatics
  • Kind: organization

GitHub Events

Total
  • Watch event: 1
  • Push event: 4
  • Create event: 1
Last Year
  • Watch event: 1
  • Push event: 4
  • Create event: 1

Dependencies

.github/workflows/wheels.yml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
  • actions/upload-artifact v4 composite
pyproject.toml pypi
requirements.txt pypi
  • igraph *
  • leidenalg *
  • louvain *
  • matplotlib *
  • networkx *
  • numpy *
  • pandas *
  • plotnine *
  • pynndescent *
  • scanpy *
  • scipy *
  • seaborn *
  • umap-learn *
setup.py pypi
  • igraph *
  • leidenalg *
  • louvain *
  • matplotlib *
  • networkx *
  • numpy *
  • pandas *
  • plotnine *
  • pynndescent *
  • scanpy *
  • scipy *
  • seaborn *
  • umap-learn *