Welcome

BiBench is a Python library designed to simplify biclustering tasks. It provides the following features:

• Supports many biclustering algorithms, and it is easy to add more.
• Download gene expression data from the Gene Expression Omnibus.
• Gene Ontology enrichment analysis.
• Synthetic dataset generation.
• Data transformation.
• Results validation and visualization.

Typical usage often looks like this:

      > import bibench.all as bb         # import most commonly used functions
      > data = bb.get_gds_data('GDS181') # download gene expression dataset GDS181
      > data = bb.pca_impute(data)       # impute missing values
      > biclusters = bb.plaid(data)      # cluster with Plaid algorithm
      > bb.enrichment(biclusters[0],     # Gene Ontology enrichment analysis
                      data.annotation,
                      data.genes)

Get BiBench

BiBench is available as an distutils package: BiBench-0.2.tar.gz

BiBench-0.2: Updates to make the library compatible with newer versions of rpy2 (December 28, 2014).

Documentation

Installing BiBench how to install Quick start usage examples

Contents for a complete overview of documentation General Index all functions, classes, terms

Contact

If you have comments or questions, or if you would like to contribute to BiBench, please send us an email: tdalab@REMOVEMEcc.gatech.edu