Added very hackish annotation count reader.

workflows/go_workflow.py

@@ -2,7 +2,7 @@ import gtk
 from fluents import dataset, logger, plots, workflow, fluents
 import geneontology
 #import gostat
-from scipy import array, randn, log, ones
+from scipy import array, randn, log, ones, zeros
 import networkx
 
 EVIDENCE_CODES=[('IMP', 'Inferred from mutant phenotype'),
@@ -22,6 +22,10 @@ DISTANCE_METRICS = [('resnik', 'Resnik'),
                     ('jiang', 'Jiang & Conrath'),
                     ('fussimeg', 'FuSSiMeG')]
 
+GO_DATA_DIR = '/home/einarr/data'
+
+evidence = None
+
 class GoTermView (gtk.Frame):
 
     def __init__(self):
@@ -134,33 +138,27 @@ class LoadAnnotationsFunction(workflow.Function):
         workflow.Function.__init__(self, 'load-go-ann', 'Load Annotations')
         self.annotations = None
     
-    def load_file(self, filename):
-        f = open(filename)
-        self.annotations = Annotations('genes', 'go-terms')
-        logger.log('notice', 'Loading annotation file: %s' % filename)
-
-        for line in f.readlines():
-            val = line.split(' \t')
-
-            if len(val) > 1:
-                val = [v.strip() for v in val]
-                retval.add_annotations('genes', val[0], 
-                                       'go-terms', set(val[1:]))
-            
-    def on_response(self, dialog, response):
-        if response == gtk.RESPONSE_OK:
-            logger.log('notice', 'Reading file: %s' % dialog.get_filename())
-            self.load_file(dialog.get_filename())
-
     def run(self):
-        btns = ('Open', gtk.RESPONSE_OK, \
-                'Cancel', gtk.RESPONSE_CANCEL)
-        dialog = gtk.FileChooserDialog('Open GO Annotation File',
-                                       buttons=btns)
-        dialog.connect('response', self.on_response)
-        dialog.run()
-        dialog.destroy()
-        return [self.annotations]
+        global evidence
+        f = open(GO_DATA_DIR + '/goa-condensed')
+        ev_codes = f.readline().split()
+        go_terms = []
+    
+        lines = f.readlines()
+        m = zeros((len(lines), len(ev_codes)))
+
+        for i, l in enumerate(lines):
+            values = l.split()
+            go_terms.append(values[0])
+            for j, v in enumerate(values[1:]):
+                m[i,j] = float(v.strip())
+        
+        d = dataset.Dataset(m, 
+                            [['go-terms', go_terms], ['evidence', ev_codes]],
+                            name='GO evidence')
+
+        evidence = d
+        return [d]
             
 
 class EvidenceCodeFrame(gtk.Frame):
@@ -249,8 +247,11 @@ class GoDistanceFunction(workflow.Function):
         workflow.Function.__init__(self, 'go-dist', 'GO term distance matrix')
         self.options = GoDistanceOptions()
         
-    def run(self, data):
+    def run(self, selection):
         self.options = self.show_gui(self.options)
+        if not selection.has_key('go-terms') or len(selection['go-terms']) == 0:
+            logger.log('warning', 'No GO terms selected. Cannot make distance matrix.')
+
 
     def show_gui(self, options, edit=True):
         dialog = GoDistanceDialog()