coded other IDtypes

ChemID.py

@@ -18,6 +18,10 @@ def ResolveChemical(chemName, IDtype):
 
     if IDtype == 'CAS':
         cas = chemName
+        if not is_cas(cas):
+            name = 'INVALID CAS'
+            error = 3
+            return (name, cas, None, None, None, error)
         smiles = None
         name = None
         Mw = None
@@ -28,12 +32,62 @@ def ResolveChemical(chemName, IDtype):
 
         if smiles:
             name = cas2name(cas)
+            try:
+                mol = Chem.MolFromSmiles(smiles)
+                Mw = Descriptors.MolWt(mol)
+                im = ImageFromSmiles(smiles)
+                im64 = Imageto64(im)
+            except:
+                error = 2
+        else:
+            error = 1
+    elif IDtype == 'SMILES':
+        smiles = chemName
+        cas = None
+        name = None
+        Mw = None
+        im64 = None
+        error = 0
+
+        name = smiles2name(smiles)
+        cas = name2cas(name)
+
+        try:
             mol = Chem.MolFromSmiles(smiles)
             Mw = Descriptors.MolWt(mol)
             im = ImageFromSmiles(smiles)
             im64 = Imageto64(im)
+        except:
+            error = 2
+    elif IDtype == 'common':
+        name = chemName
+        smiles = None
+        cas = None
+        Mw = None
+        im64 = None
+        error = 0
+
+        cas = name2cas(name)
+        smiles = cas2smiles(cas)
+
+        if smiles:
+            try:
+                mol = Chem.MolFromSmiles(smiles)
+                Mw = Descriptors.MolWt(mol)
+                im = ImageFromSmiles(smiles)
+                im64 = Imageto64(im)
+            except:
+                error = 2
         else:
             error = 1
+    else:
+        ## should never be here
+        name = None
+        smiles = None
+        cas = None
+        Mw = None
+        im64 = None
+        error = 4
 
     return (name, cas, smiles, Mw, im64, error)
 
@@ -69,6 +123,47 @@ def Imageto64(img):
 
     return pngImageB64String
 
+# function to convert SMILES to name
+def smiles2name(smiles):
+    name = None
+    # first try chemicals package
+    try:
+        cm = chemicals.search_chemical(smiles)
+        if cm.common_name:
+            name = cm.common_name
+        elif cm.iupac_name:
+            name = cm.iupac_name
+    except:
+        name = None
+    # then try pubchem for compounds
+    if not name:
+        try:
+            compounds = pcp.get_compounds(smiles, namespace='smiles')
+            c = compounds[0]
+            name = c.iupac_name
+        except:
+            name = None
+    # next try cirpy
+    if not name:
+        try:
+            name = cirpy.resolve(smiles, 'iupac_name')
+        except:
+            name = None
+    if type(name) is list:
+        name = name[0]
+    # finally try it as a pubchem substance
+    if not name:
+        try:
+            compounds = pcp.get_substances(smiles, namespace='smiles')
+            # sometimes there are multiple substances, and multiple synonyms per substance
+            allsyns = [syn for c in compounds for syn in c.iupac_name if cas not in syn]
+            # choose the most common synonym
+            fd = nltk.FreqDist(allsyns)
+            name = fd.most_common(1)[0][0]
+        except:
+            name = None
+    return name
+
 # function to convert CAS to SMILES
 def cas2smiles(cas):
     smiles = None