Skip to content

Explanatory Analysis of Biclustering Algorithm -- CCA over EpiRegioDB

License

Notifications You must be signed in to change notification settings

ShokofehVS/REMBic-CCA

Repository files navigation

REMBic-CCA

This project implements a powerful algorithm for identifying biclusters and co-activation patterns within biological datasets. CCA can help uncover hidden relationships and functional insights in complex biological data.

Table of Contents

Introduction

Biclustering or simultaneous clustering of both genes and conditions as a new paradigm was introduced by Cheng and Church's Algorithm (CCA). The concept of bicluster refers to a subset of genes and a subset of conditions with a high similarity score, which measures the coherence of the genes and conditions in the bicluster. It also returns the list of biclusters for the given data set.

Features

  • Biclustering: Discover patterns of co-activated genes across subsets of conditions.
  • Co-Activation Analysis: Identify relationships and interactions among genes.
  • Evaluation Metrics: Evaluate the algorithm's performance using precision, recall, F1-score, accuracy, and purity metrics.
  • Cross-Validation: Utilize cross-validation for robust evaluation.

Getting Started

Installation

  1. Clone the repository:

    git clone [email protected]:ShokofehVS/REMBic-CCA.git
    cd REMBic-CCA
    python CCA_modified.py

About

Explanatory Analysis of Biclustering Algorithm -- CCA over EpiRegioDB

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages