finished update with textbook chapter release

bayespairing/src/Rfam_to_module.py

@@ -24,7 +24,7 @@ def get_consensus(module_seqs):
         consensus.append([x/tot for x in scores])
     return consensus
 
-def rfam_to_module(positions, family_file,output_name, as_list=False, seqs=[]):
+def rfam_to_module(positions=[], family_file="",output_name="module_seqs.fasta", as_list=False, seqs=[]):
     alph = ["A","C","G","U"]
 
 
@@ -43,6 +43,7 @@ def rfam_to_module(positions, family_file,output_name, as_list=False, seqs=[]):
                 if str(s[col]) != "-":
                     this_mod = this_mod + str(s[col])
                 else:
+                    #print("CONSENSUS:", cons, "CURRENT COLUMN", col)
                     this_mod = this_mod + alph[choice(np.array([0,1,2,3]),p=cons[col])]
 
             fmodule_seqs.append(this_mod)

bayespairing/src/find_rna3dmotif_modules.py

@@ -29,14 +29,39 @@ def number_of_strands(nodelist):
     return (n_breaks+1)
 
 def match_pos(input_pos,module_pos):
-	if len(input_pos)==0:
-		return True
+    if len(input_pos)==0:
+        return True
+
+    for i in input_pos:
+        if i in module_pos:
+            return True
+    return False
+
+
+def get_carnaval_graph(file):
+    n = []
+    e = []
+    with open(file) as f:
+        g = nx.DiGraph()
+        lines = f.readlines()
+        for line in lines:
+            if "+++" in line:
+                continue
+            else:
+                n1,nuc1,bp, n2, nuc2 = line.replace("\n","").split(" ")
+                if (int(n1),{"nuc": nuc1 }) not in n:
+                    n.append((int(n1),{"nuc": nuc1 }))
+                if (int(n2),{"nuc": nuc2 }) not in n:
+                    n.append((int(n2),{"nuc": nuc2 }))
+                if (int(n1),int(n2),{"label" : bp}) not in e:
+                    e.append((int(n1),int(n2),{"label" : bp}))
+    n = sorted(n)
+    e = sorted(e)
+    g.add_nodes_from(n)
+    g.add_edges_from(e)
+    return g
+
 
-	for i in input_pos:
-		if i in module_pos:
-			return True
-	return False
-	
 def parse_dataset_for_modules(dataset,source_PDBs, n_strands=-1,bp=["None"],input_positions=[]):
     modules_in_PDB = []
     full_ids = []