Tralala ...

scripts/lpls/rpy_go.py

@@ -4,7 +4,7 @@ import rpy
 silent_eval = rpy.with_mode(rpy.NO_CONVERSION, rpy.r)
 import collections
 
-def goterms_from_gene(genelist, ontology='BP', garbage=None):
+def goterms_from_gene(genelist, ontology='BP', garbage=None, ic_cutoff=2.0):
     """ Returns the go-terms from a specified genelist (Entrez id).
 
     Recalculates the information content if needed based on selected evidence codes.
@@ -37,38 +37,30 @@ def goterms_from_gene(genelist, ontology='BP', garbage=None):
         ic = rpy.r('get("IC", envir=GOSimEnv)')
     print "loading GO definitions environment"
     
-    gene2terms = {}
+    gene2terms = collections.defaultdict(list)
     cc = 0
     dd = 0
     ii = 0
-    for gene in genelist:
-        info = rpy.r('GOENTREZID2GO[["' + str(gene) + '"]]')
-        #print info
-        if info:
-            skip=False
-            for term, desc in info.items():
-                if ic.get(term)==scipy.isinf:
-                    print "\nIC is Inf on this GO term %s for this gene: %s" %(term,gene)
-                    skip=True
-                if ic.get(term)==None:
-                    #print "\nHave no IC on this GO term %s for this gene: %s" %(term,gene)
-                    skip=True
-                    ii += 1
-                if desc['Ontology']!=ontology:
-                    #print "\nThis GO term %s belongs to: %s:" %(term,desc['Ontology'])
-                    skip = True
-                    dd += 1
-                if not skip:
-                    if gene2terms.has_key(gene):
-                        gene2terms[gene].append(term)
-                    else:
-                        gene2terms[gene] = [term]
+    jj = 0
+    all = rpy.r.mget(gene_ids, rpy.r.GOENTREZID2GO,ifnotfound="NA")
+    for gene, terms in all.items():
+        if terms!="NA":
+            for term,desc in terms.items():
+                if desc['Ontology'].lower() == ontology and term in ic:
+                    if ic[term]>.88:
+                        jj+=1
+                        continue
+                    cc+=1
+                    gene2terms[gene].append(term)
+                else:
+                    dd+=1
         else:
-            cc += 1
-
-    print "\nNumber of genes without annotation: %d" %cc 
+            ii+=1
+                    
+        
+    print "\nNumber of genes without annotation: %d" %ii 
     print "\nNumber of genes not in %s : %d " %(ontology, dd)
-    print "\nNumber of genes with infs : %d " %ii
+    print "\nNumber of genes with too high IC : %d " %jj
     
     return gene2terms
 
@@ -220,3 +212,15 @@ def data_aff2loc_hgu133a(X, aff_ids, verbose=False):
         print "Ids with unique probeset: %d" %s
     X = scipy.asarray(new_data).T
     return X, new_ids
+
+def R_PLS(x,y,ncomp=3, validation='"LOO"'):
+    rpy.r.library("pls")
+    rpy.r.assign("X", x)
+    rpy.r.assign("Y", y)
+    callstr = "plsr(Y~X, ncomp=" + str(ncomp) + ", validation=" + validation + ")"
+    print callstr
+    result = rpy.r(callstr)
+    return result
+
+
+def gogene()