Home

Welcome to the cmonkey-python Wiki!

Introduction

cMonkey₂ is a machine learning algorithm and data integration framework which aims to discover co-regulated modules, or bicluster in gene expression profiles. It does so by integrating additional prior information such as operons, gene functions, or protein-protein interactions as well as the de novo detection of cis-regulatory DNA sequence motifs, and aggregate these into a combined score for improving the clustering.

Below are details about the usage of cMonkey₂.

Selected Topics

• Quickstart
• Installation
• Walkthrough of a Complete cMonkey_{2 Run}
• cMonkey₂ Principles
• Configuration and run options
• Standardized Input Data File Formats
• Result Database Schema
• MEME Setup
• EC2 Setup
• View statistics in cMonkey₂ Viewer
• More tips for running, debugging, developing
• Source code documentation