homeabout uscontact us


GeneLinkerô Tour - Platinum IBIS Classification



IBIS (Integrated Bayesian Inference System) is a system that is able to predict class membership for a gene expression dataset containing measurements for the same phenomenon as the dataset used to train the IBIS classifier. One of the major strengths of the IBIS method is its ability to reveal nonlinear and non-monotonic associations between pairs of genes and their concerted response to a particular stimulus such as a drug.


Platinum  Classification and Prediction Using IBIS


Please note: these functions are introduced within a conceptual 'workflow' for the purpose of introduction only. Within GeneLinkerô, you are free to apply any appropriate function to your data at any time, in any order.


1. Import Data

A training dataset (expression values with known classes) is required for creating an IBIS classifier. A test dataset can be used to test the classifier. The two datasets must be studies of the same phenomenon (the variable type for both is the same).


2. Import Variable Data

Import the class observations for the training dataset.


3. Preprocess Your Data

GeneLinkerô offers a variety of preprocessing options which can be applied one or more times to a dataset. You can then view the preprocessed data as you would raw data (table viewer or color matrix plot).


4. Optionally, Perform an IBIS Search

The IBIS search process creates a list of proto-classifiers, one for each gene or gene pair. Each proto-classifier consists of the gene/gene pair identifier, an accuracy value, and the MSE value. The proto-classifier list can be viewed in the IBIS search results viewer.


5. Create a Classifier and View Results

You can create a Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), or a Uniform/Gaussian Discriminant Analysis (UGDA) classifier from a proto-classifier (IBIS search results), or from any gene or gene pair. The results can be viewed in an IBIS Gradient plot.


6. Classify Data and Visualize Results

Classification is the process of using a trained classifier to predict the classes of data (of the same type). An IBIS classifier can be applied to a dataset that contains the gene or gene pair used to create the classifier. The results can be viewed in a Classification plot or an IBIS Gradient plot.