Introduction

BIDEAL is a unified interactive application that allows researchers to use forefront Biclustering algorithms with graphical interface. BIDEAL also facilitates preprocessing of data which includes removing NaN spots, binarization, discretization and normalization. It allows user to visualize and interpret the result using HeatMap, Gene Profile Map and Cluster Plot. Furthermore, it also provides six Bicluster quality indices for Bicluster validation.

Key Features

In our Toolbox there is an option for filtering out the NaN spots in the gene expression data. Data can be binarize (i.e. Can be converted to only 0s and 1s) with respect to any threshold value. BIDEAL Toolbox has the option to binarize the dataset with respect to their median value. Normalization is an important step that can be done over genes and conditions independently or simultaneously.


  • Biclustering

  • BIDEAL facillitates user to opt following state-of-art algorithms for Bicluster formation. Each algorithm has its own set of parameters which can be changed by user though we have already set deafult values of these parameters.

    1. Cheng and Church (CC)
    2. Bipartite Spectral Graph Partitioning (BSGP)
    3. Order Preserving Sub-matrices (OPSM)
    4. Iterative Search Algorithm (ISA)
    5. Spectral Clustering Algorithm (kSpectral)
    6. Information Theoretic Learning (ITL)
    7. xMotif
    8. Plaid
    9. FLexible Overlapped Biclustering (FLOC)
    10. Binary Inclusion Maximal (BiMax)
    11. Large Average Submatrix (LAS)
    12. Factor analysis for Bicluster Information Acquisition (FABIA)
    13. BitBit
    14. BiSim
    15. ROBA
    16. Modular Singular Value Decomposition Multi-Objective Evolutionary Biclustering (MSVD-MOEB)
    17. Qualitative Biclustering (QUBIC)

  • Validation

  • To perform the qualitative assesment of biclusters validation indices are required.There are number of quality indices are available. At present our BIDEAL facilitates following six quality indices to measure the performace of algorithm as well as quality of Biclusters.


    1. Jaccard Coefficient
    2. Chia Score (SB Score)
    3. Constant Variance
    4. Sign variance
    5. Hausdorff Distance
    6. Mean Squared Error (MSE)

  • Visualization

  • Visual analysis is a quick and most intitutive way to analyze the the Bicluster results with minimal efforts. BIDEAL has an option to visualize and interpret the result which is obtained from Biclustering with different algorithms. Four different options are availed to user for visualization of result.


    1. Plot HeatMap: BIDEAL HeatMap can be plotted by loading a particular result.
    2. Plot Cluster: To plot the Bicluster, value, mean, median prestored results can be used. First provide the desired index of Bicluster in the edit box. Then click on the Plot Cluster for plotting. Graph can also be saved as a picture.
    3. Plot Gene Profile: Gene Expression Profile can be plotted by loading a result file and giving particular Bicluster index.
    4. Show Bicluster: To display Bicluster as a numerical matrix load the previously saved .mat file. Put the desired no of index of Bicluster to the edit box. Then click on “Show Bicluster”.

    How to use

    BIDEAL Toolbox is freely available for academic and research purpose under license.

    How to cite?

    Please cite the following paper:

    N. K. Verma, T. Sharma, S. Dixit, P. Agrawal, S. Sengupta, and V. Singh, BIDEAL: A Toolbox for Bicluster Analysis - Generation, Visualization and Validation, SN COMPUTER SCIENCE, Springer Journal, 2, 24 (2021). https://doi.org/10.1007/s42979-020-00411-9






    Back to top

    Copyright © Intelligent Data Engineering and Automation Laboratory
    Web fonts from Google.