corrections for 4 CAs w/ lookup problems

ChemID.py

@@ -1,4 +1,6 @@
 import sys,os,glob,re,string
+from collections import Counter
+from operator import itemgetter
 import nltk
 import pandas as pd
 import numpy as np

color2_module/colors.py

@@ -27,7 +27,7 @@ else:
     polymers, categories, params = Polymers2()
 
 # Named color additives, TI values, and Mw
-nCA = 14
+nCA = 13
 caData = np.zeros((nCA,), dtype=[('name', 'a75'), ('TI', 'd'), ('MW', 'd'),('CAS', 'a75')])
 caData[0] = ('Titanium dioxide (CAS#:13463-67-7)', 1.0, 1100., '13463-67-7')
 caData[1] = ('Carbon black (CAS#:1333-86-4)', 2.0, 1100., '1333-86-4')
@@ -37,8 +37,8 @@ caData[4] = ('Pigment Red 101 (CAS#: 1309-37-1)', 1.0, 1100., '1309-37-1')
 caData[5] = ('Solvent violet 13 (CAS#:81-48-1)', 0.0013, 319.4, '81-48-1')
 caData[6] = ('Manganese phthalocyanine (CAS#:14325-24-7)', 0.15, 567.5, '14325-24-7')
 caData[7] = ('Pigment blue 15 (CAS#:147-14-8)', 0.15, 576.1, '147-14-8')
-caData[8] = ('Phthalocyanine green (CAS#:1326-53-6)', 0.15, 1092.8, '1326-53-6')
-caData[9] = ('Ultramarine blue (CAS#:57445-37-5)', 3.3, 1100., '57445-37-5')
+caData[8] = ('Phthalocyanine green (CAS#:1328-53-6)', 0.15, 1092.8, '1328-53-6')
+caData[9] = ('Ultramarine blue (CAS#:57455-37-5)', 3.3, 1100., '57455-37-5')
 caData[10] = ('Pigment Yellow 138 (CAS#:30125-47-4)', 1.0, 693.96, '30125-47-4')
 caData[11] = ('Other color additive', 1.0, 1100.0, ' ')
 caData[12] = ('Other color additive associated compound', 1.0, 1100.0, ' ')
@@ -79,9 +79,14 @@ def app_post():
     chemName = ''
 
     if caIndex <= 10:
-        IDtype = "CAS"
+        IDtype = 'CAS'
         chemName = caData[caIndex][3].decode('UTF-8')
         impurity = float(request.form["impurity"]) * amount * 1e-2
+        # problems:
+        # o C.I. Pigment Brown 24 = 68186-90-3, kludge "works"
+        # o Manganese(II) phthalocyanine = 14325-24-7, kludge "works"
+        # o Phthalocyanine green = 1326-53-6 -> 1328-53-6, corrected CAS works
+        # o Ultramarine blue = 57445-37-5 -> 57455-37-5, corrected CAS works
     if caIndex > 10:
         chemName = request.form["chemName"]
         IDtype = request.form["IDtype"]
@@ -90,8 +95,24 @@ def app_post():
         isCA = False
 
     print(chemName)
-    iupac, cas, smiles, MW, LogP, rho, mp, molImage, error = ResolveChemical(chemName, IDtype,
-                                                                                 get_properties=get_properties)
+    if chemName == '68186-90-3':
+        #IDtype = 'SMILES'
+        #chemName = 'O=[Ti]=O.O=[Sb]O[Sb](=O)=O.O=[Cr]O[Cr]=O'
+        #iupac, cas, smiles, MW, LogP, rho, mp, molImage, error = ResolveChemical(chemName, IDtype, get_properties=get_properties)
+        iupac, cas, smiles, MW, LogP, rho, mp, molImage, error = None, chemName, 'O=[Ti]=O.O=[Sb]O[Sb](=O)=O.O=[Cr]O[Cr]=O', 1100, None, None, 1001, None, 0
+    elif chemName == '14325-24-7':
+        IDtype = 'SMILES'
+        chemName = 'C1=CC=C2C(=C1)C3=NC4=NC(=NC5=C6C=CC=CC6=C([N-]5)N=C7C8=CC=CC=C8C(=N7)N=C2[N-]3)C9=CC=CC=C94.[Mn+2]'
+        iupac, cas, smiles, MW, LogP, rho, mp, molImage, error = ResolveChemical(chemName, IDtype, get_properties=get_properties)
+        #iupac, cas, smiles, MW, LogP, rho, mp, molImage, error = None, chemName, 'C1=CC=C2C(=C1)C3=NC4=NC(=NC5=C6C=CC=CC6=C([N-]5)N=C7C8=CC=CC=C8C(=N7)N=C2[N-]3)C9=CC=CC=C94.[Mn+2]', 567.5, None, None, 500, None, 0
+    #elif chemName == '1326-53-6':
+    #    IDtype = 'SMILES'
+    #    chemName = 'C1=C2C(=C(C(=C1Cl)Cl)Cl)C3=NC4=NC(=NC5=NC(=NC6=C7C(=C([N-]6)N=C2[N-]3)C(=C(C(=C7Cl)Cl)Cl)Cl)C8=C5C(=C(C(=C8Cl)Cl)Cl)Cl)C9=C4C(=C(C(=C9Cl)Cl)Cl)Cl.[Cu+2]'
+    #    iupac, cas, smiles, MW, LogP, rho, mp, molImage, error = ResolveChemical(chemName, IDtype, get_properties=get_properties)
+    else:
+        iupac, cas, smiles, MW, LogP, rho, mp, molImage, error = ResolveChemical(chemName, IDtype, get_properties=get_properties)
+        ## XXX
+        print(iupac, cas, smiles, MW, LogP, rho, mp, error)
 
     if error > 0:
         # TODO output more useful info
@@ -99,22 +120,22 @@ def app_post():
 
     # metals/ceramics logic
     mol = Chem.MolFromSmiles(smiles)
+    mol = Chem.AddHs(mol)
     natoms = mol.GetNumAtoms()
+    metal_nums = [3,4,11,12,13] + list(range(19,31+1)) + list(range(37,50+1)) + list(range(55,84+1)) + list(range(87,114+1)) + [116]
     ceramic = False
-    if natoms == 1 and smiles != '[C]':
-
+    if all(a.GetAtomicNum() in metal_nums for a in mol.GetAtoms()):
+        # if all atoms are metals -> this is a metal
+    #if natoms == 1 and smiles != '[C]':
         # only one atom, except for carbon -> assumed metal
         # return render_template('chemError.html')
         return render_template('metalError.html', show_properties=show_properties, chemName=chemName, MW=MW,
                                LogP=LogP, rho=rho, mp=mp, iupac=iupac,
-                               cas=cas, smiles=smiles, molImage=molImage,
-                               LogP_origin=LogP_origin, rho_origin=rho_origin, mp_origin=mp_origin)
+                               cas=cas, smiles=smiles, molImage=molImage)
+                               #LogP_origin=LogP_origin, rho_origin=rho_origin, mp_origin=mp_origin)
     else:
         if (type(mp) is float or type(mp) is int) and mp > 1000.:
-            # more than one atom, or carbon -> assumed ceramic
-            # TODO say something about what we're doing on report? (e.g. 'detected ceramic, setting MW = 1100')
-            # I added something to address this, edit as needed
-            # We can perhaps increase the mp limit to 1000 C, just in case
+            # if not a metal but melting point > 1000, assume ceramic
             MW = 1100.
             ceramic = True
 

exposure2_module/exposure.py

@@ -71,7 +71,7 @@ def exp_post():
     # metals/ceramics logic
     mol = Chem.MolFromSmiles(smiles)
     mol = Chem.AddHs(mol)
-    natoms = mol.GetNumAtoms()
+    #natoms = mol.GetNumAtoms()
     metal_nums = [3,4,11,12,13] + list(range(19,31+1)) + list(range(37,50+1)) + list(range(55,84+1)) + list(range(87,114+1)) + [116]
     ceramic = False
     if all(a.GetAtomicNum() in metal_nums for a in mol.GetAtoms()):