ups

scripts/lpls/rpy_go.py

@@ -2,7 +2,7 @@
 import scipy
 import rpy
 silent_eval = rpy.with_mode(rpy.NO_CONVERSION, rpy.r)
-
+import collections
 
 def goterms_from_gene(genelist, ontology='BP', garbage=None):
     """ Returns the go-terms from a specified genelist (Entrez id).
@@ -18,7 +18,7 @@ def goterms_from_gene(genelist, ontology='BP', garbage=None):
               "IDA" : "inferred from direct assay",
               "IEP" : "inferred from expression pattern",
               "IEA" : "inferred from electronic annotation",
-              "TAS" : "traceable author statement",
+               "TAS" : "traceable author statement",
               "NAS" : "non-traceable author statement",
               "ND" : "no biological data available",
               "IC" : "inferred by curator"
@@ -167,3 +167,47 @@ def gene_GO_hypergeo_test(genelist,universe="entrezUniverse",ontology="BP",chip
     result = rpy.r.summary(rpy.r.hyperGTest(params))
     
     return rpy.r.summary(result), params
+
+def data_aff2loc_hgu133a(X, aff_ids, verbose=False):
+    aff_ids = scipy.asarray(aff_ids)
+    if verbose:
+        print "\nNumber of probesets in affy list: %s" %len(aff_ids)
+    import rpy
+    rpy.r.library("hgu133a")
+    trans_table = rpy.r.as_list(rpy.r.hgu133aENTREZID)
+    if verbose:
+        print "Number of entrez ids: %d" %(scipy.asarray(trans_table.values())>0).sum()
+    enz2aff = collections.defaultdict(list)
+    #aff2enz = collections.defaultdict(list)
+    for aff, enz in trans_table.items():
+        if int(enz)>0 and (aff in aff_ids):
+            enz2aff[enz].append(aff)
+            #aff2enz[aff].append(enz)
+    if verbose:
+        print "\nNumber of translated entrez ids: %d" %len(enz2aff)
+    aff2ind = dict(zip(aff_ids, scipy.arange(len(aff_ids))))
+    var_x = X.var(0)
+    new_data = []
+    new_ids = []
+    m = 0
+    s = 0
+    for enz, aff_id_list in enz2aff.items():
+        index = [aff2ind[aff_id] for aff_id in aff_id_list]
+        if len(index)>1:
+            m+=1
+            if verbose:
+                pass
+                #print "\nEntrez id: %s has %d probesets" %(enz, len(index))
+                #print index
+            xsub = X[:,index]
+            choose_this = scipy.argmax(xsub.var(0))
+            new_data.append(xsub[:,choose_this].ravel())
+        else:
+            s+=1
+            new_data.append(X[:,index].ravel())
+        new_ids.append(enz)
+    if verbose:
+        print "Ids with multiple probesets: %d" %m
+        print "Ids with unique probeset: %d" %s
+    X = scipy.asarray(new_data).T
+    return X, new_ids