To give more flexibility in the analysis of your data set, HPlus allows you to segment your data set and analyse the markers in a number of groups. These groups can be formed using information from your data file that is defined as the 'location data' during the import process.
For example, one form of this data may be the name of the gene where the marker is located:
Gene Name ABCD ABCD ABCD EFGH EFGH marker 1 2 3 4 5 ID 1 1 0 0 1 1 2 1 1 1 0 1 3 0 0 0 0 1 4 0 0 0 0 0In this case, the import assistant would allow you to specify the marker groups data as starting on row 1, ending on row 1 and having the name of the group in column 1. Once the data is imported, 'Gene Name' will be displayed along with a radio button in the bottom left frame. As an example, here is how the frame appears with both Gene Name and Chromosome Location being imported as grouping data:
If you start the analysis without selecting the radio button, all the markers will be included in the analysis and one result set returned. However if you do select the radio button beside 'Gene Name' then the analysis will first be run on the markerss that are in gene ABCD and then it will be run on the markers that are in gene EFGH. You will therefore be presented with two sets of results which can be selected by choosing the gene name in the drop-down box that will appear in the bottom frame.
You can import multiple different sets of location data, but you can only use one at a time during the analysis. By creating your own grouping data information in your data file, you can arbitrarily split up your marker information as you wish.
 Performing an Analysis |
 Including Covariates |