Exploring around your hypotheses
Although the interactive Discovery Map provides an effective way of exploring the results sometimes we need a more advanced method to focus on the complex relationships that were found related to our a-priori exploratory questions.
The Hypo Booster tool allows us to specify these hypotheses in terms of which variables are involved in them so that only these relationships are shown.
To start the Hypo Booster tool:
Configure and execute a discovery process.
Wait for the discovery process to finish.
Select the "Explore" tab and click the "Hypo Booster" button.
THE HYPO BOOSTER
The Hypo Booster tool complements the interactive Discovery Map to focus the exploration on the most relevant relationships for you.
Defining your exploratory question
To define a question to explore:
Express your exploratory question in terms of "what variables or group of variables" are part of the relationship and "in which conditions" do you expect it to happen. Take a look at this blog post on the typical exploratory questions you may be asking yourself to be inspired.
Select the variables or groups (data sources) that are part of your hypothesis in the two lists located at the left side of the window. If more than one item is to be selected, keep the Ctrl key pressed as you click on them.
3. If you need to refine even more, specify the value of the subject grouping variables in which you expect the association to happen.
Following our example, we'd like to focus specifically on associations that may be identified in the group of patients under the stage III of the illness.
In this example, our exploratory question is "is there any potential association between two of our main biomarkers (ki67 and 4epb1) and the prognosis of the patients under study?". As it is an exploratory hypothesis, we cannot still determine the particular associations but just an approximation.
5. Press the "Explore It" button.
The whole list of associations registered and the Discovery Map are automatically filtered to show only those around the exploratory question defined.
4. Additionally, select the degree of relevance of the associations you would like to explore among the following options:
All relationships matching the conditions.
Relationships with high significance only.
Exploratory relationships to be confirmed only.
Relationships exclusive of a group of samples.
Relationships identified in the whole population.