ups

scripts/lpls/rpy_go.py

@@ -3,32 +3,14 @@ import scipy
 import rpy
 silent_eval = rpy.with_mode(rpy.NO_CONVERSION, rpy.r)
 
-def get_term_sim(termlist, method = "JiangConrath", verbose=False):
-    """Returns the similariy matrix between go-terms.
 
-    Arguments:
-        termlist: character vector of GO terms
-        method: one of
-        ("JiangConrath","Resnik","Lin","CoutoEnriched","CoutoJiangConrath","CoutoResnik","CoutoLin")
-        verbose: print out various information or not
-    """
-    _methods = ("JiangConrath","Resnik","Lin","CoutoEnriched","CoutoJiangConrath","CoutoResnik","CoutoLin")
-    assert(method in _methods)
-    assert(termlist[0][:2]=='GO')
-    rpy.r.library("GOSim")
-    return rpy.r.getTermSim(termlist, method = method, verbose = verbose)
-
-def get_gene_sim(genelist, similarity='OA',
-                 distance="Resnick"):
-    rpy.r.library("GOSim")
-    rpy.r.assign("ids", genelist)
-    silent_eval('a<-getGeneSim(ids)', verbose=FALSE)
-
-def goterms_from_gene(genelist, ontology=['BP'], garbage = ['IEA', 'ISS', 'ND']):
+def goterms_from_gene(genelist, ontology='BP', garbage=None):
     """ Returns the go-terms from a specified genelist (Entrez id).
+
+    Recalculates the information content if needed based on selected evidence codes.
     
     """
-    rpy.r.library("GO")
+    rpy.r.library("GOSim")
     _CODES = {"IMP" : "inferred from mutant phenotype",
               "IGI" : "inferred from genetic interaction",
               "IPI" :"inferred from physical interaction",
@@ -42,25 +24,46 @@ def goterms_from_gene(genelist, ontology=['BP'], garbage = ['IEA', 'ISS', 'ND'])
               "IC" : "inferred by curator"
               }
     _ONTOLOGIES = ['BP', 'CC', 'MF']
-    assert(scipy.all([(code in _CODES) for code in garbage]))
-    assert(scipy.all([(ont in _ONTOLOGIES) for ont in ontology]))
-    have_these = rpy.r('as.list(GOTERM)').keys()
-    goterms = {}
+    #assert(scipy.all([(code in _CODES) for code in garbage]) or garbage==None)
+    assert(ontology in _ONTOLOGIES)
+    dummy = rpy.r.setOntology(ontology)
+    ddef = False
+    if ontology=='BP' and garbage!=None:
+        # This is for ont=BP and garbage =['IEA', 'ISS', 'ND']
+        rpy.r.load("ICsBPIMP_IGI_IPI_ISS_IDA_IEP_TAS_NAS_IC.rda")
+        ic = rpy.r.assign("IC",rpy.r.IC, envir=rpy.r.GOSimEnv)
+        print len(ic)
+    else:
+        ic = rpy.r('get("IC", envir=GOSimEnv)')
+    print "loading GO definitions environment"
+    
+    gene2terms = {}
     for gene in genelist:
-        goterms[gene] = []
         info = rpy.r('GOENTREZID2GO[["' + str(gene) + '"]]')
         #print info
         if info:
+            skip=False
             for term, desc in info.items():
-                if term not in have_these:
-                    print "GO miss:"
-                    print term
-                if desc['Ontology'] in ontology and desc['Evidence'] not in garbage:
-                        goterms[gene].append(term)
+                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
+                if desc['Ontology']!=ontology:
+                    #print "\nThis GO term %s belongs to: %s:" %(term,desc['Ontology'])
+                    skip = True
+                if not skip:
+                    if gene2terms.has_key(gene):
+                        gene2terms[gene].append(term)
+                    else:
+                        gene2terms[gene] = [term]
+        else:
+           print "\nHave no Annotation on this gene: %s" %gene 
 
-    return goterms
+    return gene2terms
 
-def genego_matrix(goterms, tmat, gene_ids, term_ids, func=min):
+def genego_matrix(goterms, tmat, gene_ids, term_ids, func=max):
     ngenes = len(gene_ids)
     nterms = len(term_ids)
     gene2indx = {}
@@ -71,23 +74,46 @@ def genego_matrix(goterms, tmat, gene_ids, term_ids, func=min):
         term2indx[id]=i
     #G = scipy.empty((nterms, ngenes),'d')
     G = []
-    newindex = []
+    new_gene_index = []
     for gene, terms in goterms.items():
         g_ind = gene2indx[gene]
         if len(terms)>0:
             t_ind = []
-            newindex.append(g_ind)
+            new_gene_index.append(g_ind)
             for term in terms:
                 if term2indx.has_key(term): t_ind.append(term2indx[term])
-            print t_ind
             subsim = tmat[t_ind, :]
             gene_vec = scipy.apply_along_axis(func, 0, subsim)
             G.append(gene_vec)
 
-    return scipy.asarray(G), newindex
+    return scipy.asarray(G), new_gene_index
+
+def genego_sim(gene2go, gene_ids, all_go_terms, STerm, go_term_sim="OA", term_sim="Lin", verbose=False):
+    """Returns go-terms x genes similarity matrix.
+
+    :input:
+           - gene2go: dict: keys: gene_id, values: go_terms
+           - gene_ids: list of gene ids (entrez ids)
+           - STerm: (go_terms x go_terms) similarity matrix
+           - go_terms_sim: similarity measure between a gene and multiple go terms (max, mean, OA)
+           - term_sim: similarity measure between two go-terms
+           - verbose
+    """
+    rpy.r.library("GOSim")
+
+    #gene_ids = gene2go.keys()
+    GG = scipy.empty((len(all_go_terms), len(gene_ids)), 'd')
+    for j,gene in enumerate(gene_ids):
+        for i,go_term in enumerate(all_go_terms):
+            if verbose:
+                print "\nAssigning similarity from %s to terms(gene): %s" %(go_term,gene)
+            GG_ij = rpy.r.getGSim(go_term, gene2go[gene], similarity=go_term_sim,
+                                  similarityTerm=term_sim, STerm=STerm, verbose=verbose)
+            GG[i,j] = GG_ij
+    return GG
 
 def goterm2desc(gotermlist):
-    """Returns the go-terms description keyed by go-term
+    """Returns the go-terms description keyed by go-term.
     """
     rpy.r.library("GO")
     term2desc = {}