+ extended docu
[qpalma.git] / scripts / qpalma_pipeline.py
index 6730974..4df1500 100644 (file)
@@ -61,16 +61,21 @@ class System:
       """
       logwrite('Begin of training.\n',self.settings)
 
-      # 
+      print '#'*80
+      print '\t\t\tStarting approximation...\n'
+      print '#'*80
+
+      # When we are given only genomic reads we first generate artificially spliced
+      # ones in order to generate a training set
       pre_task = TrainingPreprocessingTask(self.settings)
       pre_task.createJobs()
       pre_task.submit() 
       pre_task.checkIfTaskFinished()
 
-      # 
+      # Collect the data and create a pickled training set
       generateTrainingDataset(self.settings)
 
-      # Now that we have a dataset we can perform accurate trainments
+      # Now that we have a dataset we can perform training
       train_task = TrainingTask(self.settings)
       train_task.CreateJobs()
       train_task.Submit()
@@ -78,6 +83,7 @@ class System:
 
       logwrite('End of training.\n',self.settings)
 
+
    def prediction(self):
       """
       This function encapsulates all steps needed to perform a prediction. Given
@@ -87,6 +93,10 @@ class System:
 
       logwrite('Begin of prediction.\n',self.settings)
 
+      print '#'*80
+      print '\t\t\tStarting approximation...\n'
+      print '#'*80
+
       # Before creating a candidate spliced read dataset we have to first filter
       # the matches from the first seed finding run.
 
@@ -98,11 +108,15 @@ class System:
       # After filtering combine the filtered matches from the first run and the
       # found matches from the second run to a full dataset
 
+      print '#'*80
+      print '\t\t\tStarting dataset generation...\n'
+      print '#'*80
+
       generatePredictionDataset(self.settings)
-      #pre_task = PreprocessingTask(self.settings)
-      #pre_task.CreateJobs()
-      #pre_task.Submit() 
-      #pre_task.CheckIfTaskFinished()
+
+      print '#'*80
+      print '\t\t\tStarting alignments...\n'
+      print '#'*80
 
       # Now that we have a dataset we can perform accurate alignments
       align_task = AlignmentTask(self.settings)
@@ -110,6 +124,10 @@ class System:
       align_task.Submit()
       align_task.CheckIfTaskFinished()
 
+      print '#'*80
+      print '\t\t\tPostprocessing...\n'
+      print '#'*80
+
       # The results of the above alignment step can be converted to a data format
       # needed for further postprocessing.
       post_task = PostprocessingTask(self.settings)