finalizing exercises

lecturers/morten/README.md

@@ -26,8 +26,14 @@ validation and, if possible, to extract discriminating genes.
   above for all the samples that have been left out.
 * Do the above multiple times and find the probability of the
   prediction beeing correct.
+* Find the gene ids with the highest coefficient in the components for
+  the PCA. Do they discriminate the samples for different exposures?
+  Take a look at sparse PCA and discuss how it can be used to find
+  more relevant gene ids.
+* Figure out how to translate he gene ids to gene names.
 * Execute the remaining notebooks in the morten/python folder.
-* Analyze a new data set. Are you able to learn the exposures of the samples?
+* Analyze a data set of your own. Are you able to learn the exposures
+  of your samples? 
   
 
 
@@ -56,7 +62,7 @@ inform me if you figure out a way to do that.
 
 Follow these [instructions](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git) 
 
-### Install dependincies
+### Install dependencies
 
 Navigate to this folder with the terminal or the Anaconda Promt. In the terminal/Promt type