updates to metals/ceramics logic

ChemID.py

@@ -19,6 +19,9 @@ METAL_ATOM_SET = set([3,4,11,12,13] + list(range(19,31+1)) + list(range(37,50+1)
 with open('ceramics_list.txt', 'r') as fp:
     lines = fp.readlines()
 CERAMICS_SET = {line.strip() for line in lines}
+with open('salt_list.txt', 'r') as fp:
+    lines = fp.readlines()
+SALT_SET = {line.strip() for line in lines}
 
 ## not sure if this will be possible on pythonanywhere; use this flag to disable related code blocks
 try_dsstox = True
@@ -205,10 +208,12 @@ def CeramicOrMetal(smiles,mp):
     atom_num_list = [a.GetAtomicNum() for a in mol.GetAtoms()]
     is_metal = set(atom_num_list) <= METAL_ATOM_SET
     if not is_metal:
-        # check composition against list of ceramics
+        # check composition against list of ceramics/salts
         elements = ','.join(sorted(set([a.GetSymbol() for a in mol.GetAtoms()])))
         if elements in CERAMICS_SET:
             is_ceramic = True
+        if elements in SALT_SET:
+            is_ceramic = True
         if not is_ceramic:
             # get number of carbon-carbon bonds
             num_CC_bonds = sum([1 if b.GetBeginAtom().GetAtomicNum() == 6 and b.GetEndAtom().GetAtomicNum() == 6 else 0 for b in mol.GetBonds()])

salt_list.txt

@@ -0,0 +1,648 @@
+Ag,Ba,N,O
+Ag,Br
+Ag,Br,Cl
+Ag,Br,Cl,Cs
+Ag,Br,Cl,K
+Ag,Br,Cl,Li
+Ag,Br,Cl,Na
+Ag,Br,Cl,Na
+Ag,Br,Cl,Rb
+Ag,Br,Cs
+Ag,Br,K
+Ag,Br,Li
+Ag,Br,Na
+Ag,Br,Rb
+Ag,Br,Te
+Ag,Ca,N,O
+Ag,Cd,N,O
+Ag,Cl
+Ag,Cl,K
+Ag,Cl,Li,N,O
+Ag,Cl,N,O
+Ag,Cl,O
+Ag,Cl,Pb
+Ag,Cl,S
+Ag,Cl,Se
+Ag,Cl,Te
+Ag,Cs,N,O
+Ag,Hg,I,N,O
+Ag,I
+Ag,I,N,O
+Ag,I,S
+Ag,I,Te
+Ag,K,N,O
+Ag,Li,N,O
+Ag,Li,O,S
+Ag,Mg,N,O
+Ag,N,Na,O
+Ag,N,O
+Ag,N,O,Rb
+Ag,N,O,Tl
+Ag,O,S
+Ag,S
+Ag,Se
+Ag,Te
+Al,Ba,Cl,F,Na
+Al,Ba,F,Na
+Al,Be,F,Na
+Al,Bi,Cl
+Al,Br
+Al,Br,Cl,K
+Al,Br,Cl,K,Li,Na
+Al,Br,Cl,Na
+Al,Br,Hg
+Al,Br,K
+Al,Br,Na
+Al,Br,Nr
+Al,Br,Sb
+Al,Br,Zn
+Al,Ca,F,Na
+Al,Ca,F,O
+Al,Cl
+Al,Cl,F,Na
+Al,Cl,K
+Al,Cl,Li
+Al,Cl,Li
+Al,Cl,Li,Na
+Al,Cl,Na
+Al,Cl,Nl
+Al,Cl,Rb
+Al,Cs,F
+Al,Cs,F,K
+Al,Cs,F,Li
+Al,Cs,F,Na
+Al,F,K
+Al,F,K,Li
+Al,F,K,Na
+Al,F,K,Na,O
+Al,F,Li
+Al,F,Li,Na
+Al,F,Li,Na
+Al,F,Li,O
+Al,F,Li,Rb
+Al,F,Mg,Na
+Al,F,Na
+Al,F,Na,O
+Al,F,Na,O,Si
+Al,F,Na,Rb
+Al,F,Rb
+Al,Hg,I
+Al,I
+Al,I,K
+Al,I,Sb
+Al,O
+B,Bi,K,O
+B,Bi,Na,O
+B,C,F,N
+B,C,N
+B,Ca,F,Na,O
+B,Cl,K,Na,O
+B,Cl,Li,Na,O
+B,Cs,F
+B,F,K
+B,F,K,Na,O
+B,F,Li
+B,F,Na
+B,F,Na,O
+B,F,Na,O,Zr
+B,F,Rb
+B,K,Ni,O
+B,K,O
+B,K,O,P
+B,K,O,Pb
+B,Na,Ni,O
+B,Na,O
+B,Na,O,P
+B,Na,O,Pb
+B,Na,O,W
+B,O
+Ba,Br
+Ba,Br,K
+Ba,Ca,F,O
+Ba,Cd,Cl
+Ba,Cl
+Ba,Cl,Cs
+Ba,Cl,F
+Ba,Cl,F,K
+Ba,Cl,K
+Ba,Cl,La
+Ba,Cl,Li
+Ba,Cl,Mg
+Ba,Cl,Na
+Ba,Cl,Pb
+Ba,Cl,Zn
+Ba,Cs,F
+Ba,F
+Ba,F,K
+Ba,F,Li
+Ba,F,Na
+Ba,I
+Ba,K,N,O
+Ba,N,Na,O
+Ba,N,O
+Ba,N,O,Rb
+Ba,O,P
+Be,Cl
+Be,Cl,K
+Be,Cl,Na
+Be,F
+Be,F,Li
+Be,F,Li,Th
+Be,F,Li,U,Zr
+Be,F,Li,Zr
+Be,F,Na
+Be,F,Rb
+Be,F,U
+Bi,Br
+Bi,Cl
+Bi,I
+Bi,K,O,P
+Bi,Mo,O
+Bi,Mo,O,Pb
+Bi,Na,O,P
+Bi,O,Pb,W
+Bi,O,W
+Bi,S
+Br,C,N
+Br,Ca
+Br,Cd
+Br,Cd,Cl
+Br,Cd,Cl,K
+Br,Cd,Cl,Zn
+Br,Cd,K
+Br,Cd,Na
+Br,Cd,Tl
+Br,Cd,Zn
+Br,Cl,Cs
+Br,Cl,Cs,K
+Br,Cl,Cs,Na
+Br,Cl,Cs,Na
+Br,Cl,K
+Br,Cl,K,Li
+Br,Cl,K,Na
+Br,Cl,K,Na
+Br,Cl,K,Rb
+Br,Cl,Li
+Br,Cl,Na
+Br,Cl,Pb
+Br,Cl,Rb
+Br,Cl,Tl
+Br,Co,K,N,O
+Br,Cr,Na,O
+Br,Cs
+Br,Cs,F
+Br,Cs,I
+Br,Cs,K
+Br,Cs,Li
+Br,F,K
+Br,F,Li
+Br,Ga
+Br,Hg
+Br,Hg,I
+Br,I,K
+Br,I,Li
+Br,I,Na
+Br,I,Rb
+Br,I,Sb
+Br,I,Tl
+Br,In
+Br,K
+Br,K,Li
+Br,K,N,O
+Br,K,Na
+Br,K,O,S,Zn
+Br,K,Pb
+Br,K,Rb
+Br,K,Tl
+Br,K,Zn
+Br,La
+Br,Li
+Br,Li,Na
+Br,Li,Rb
+Br,Mg
+Br,Na
+Br,Na,Pb
+Br,Na,Rb
+Br,Na,Tl
+Br,Nd
+Br,Pb
+Br,Rb
+Br,Rb,Tl
+Br,Sb
+Br,Sr
+Br,Tl
+Br,Zn
+C,Ca,K,O
+C,Ca,Na,O
+C,Cl,K,Li,O
+C,Cl,K,Na,O
+C,Cl,K,O
+C,Cl,Li,O
+C,Cl,Na,O
+C,Cs
+C,Cs,N,S
+C,Cs,Na
+C,Cs,O
+C,Cu,N,S
+C,F,K,Li,O
+C,F,N,P
+C,I,N
+C,K,Li,Na,O
+C,K,Li,O
+C,K,Li,O,S
+C,K,N,Na,S
+C,K,N,S
+C,K,Na,O
+C,K,O
+C,K,O,Si
+C,Li,N,S
+C,Li,Na,O
+C,Li,O
+C,N,Na,S
+C,N,Rb,S
+C,N,S
+C,Na
+C,Na,O
+C,Na,O,Si
+C,Na,Rb
+C,O,Rb
+C,Rb
+Ca,Cl
+Ca,Cl,Cs
+Ca,Cl,Dy
+Ca,Cl,K
+Ca,Cl,K,Mg
+Ca,Cl,La
+Ca,Cl,La,Na
+Ca,Cl,Li
+Ca,Cl,Mg
+Ca,Cl,Mg,Na
+Ca,Cl,Mn
+Ca,Cl,Mo,O
+Ca,Cl,Na
+Ca,Cl,Nd
+Ca,Cl,O
+Ca,Cl,Pr
+Ca,Cl,Rb
+Ca,Cl,Sr
+Ca,Cs,N,O
+Ca,F
+Ca,F,Li
+Ca,F,Mg,O
+Ca,F,Na
+Ca,F,O
+Ca,F,O,Si
+Ca,F,O,Ti
+Ca,F,O,V
+Ca,F,O,Zr
+Ca,I
+Ca,K,N,Na,O
+Ca,K,N,O
+Ca,N,Na,O
+Ca,Na,O,S
+Ca,O
+Ca,O,Si
+Cd,Cl
+Cd,Cl,Cs
+Cd,Cl,I
+Cd,Cl,K
+Cd,Cl,Li
+Cd,Cl,Na
+Cd,Cl,Pb
+Cd,Cl,Rb
+Cd,Cl,Tl
+Cd,Cl,Zn
+Cd,Cs,I
+Cd,I
+Cd,I,K
+Cd,I,Na
+Cd,K,N,O
+Cd,O,P
+Ce,Cl
+Ce,Cl,K
+Ce,Cl,K,Na
+Ce,F
+Ce,F,K
+Ce,F,Li
+Ce,F,Na
+Cl,Cr,K,Li,O
+Cl,Cr,K,O
+Cl,Cr,Li,O
+Cl,Cs
+Cl,Cs,F
+Cl,Cs,I
+Cl,Cs,I,K
+Cl,Cs,K
+Cl,Cs,La
+Cl,Cs,Li
+Cl,Cs,Li,O
+Cl,Cs,Mg
+Cl,Cs,Mn
+Cl,Cs,Na
+Cl,Cs,Pb
+Cl,Cs,Rb
+Cl,Cs,U
+Cl,Cs,Zn
+Cl,Cu
+Cl,Cu,K
+Cl,Cu,S
+Cl,Dy
+Cl,F,I,Na
+Cl,F,K
+Cl,F,K,Na
+Cl,F,K,Na,Zr
+Cl,F,K,Zr
+Cl,F,Li
+Cl,F,Na
+Cl,F,Na,Ti
+Cl,F,Na,Zr
+Cl,Fe
+Cl,Fe,S
+Cl,Ga
+Cl,Gd
+Cl,H,Li,O
+Cl,H,Na,O
+Cl,Hg
+Cl,Hg,N,O,Tl
+Cl,I,K
+Cl,I,K,Na
+Cl,I,K,Na
+Cl,I,Li
+Cl,I,Na
+Cl,I,Rb
+Cl,In
+Cl,K
+Cl,K,La
+Cl,K,La,Na
+Cl,K,Li
+Cl,K,Li,N,O
+Cl,K,Li,O
+Cl,K,Li,Pb
+Cl,K,Mg
+Cl,K,Mn
+Cl,K,N,Na,O
+Cl,K,N,O
+Cl,K,Na
+Cl,K,Na,Nd
+Cl,K,Na,Pb
+Cl,K,Na,Pr
+Cl,K,Na,Sm
+Cl,K,Na,Y
+Cl,K,Nd
+Cl,K,O,S
+Cl,K,O,S,Zn
+Cl,K,Pb
+Cl,K,Pr
+Cl,K,Rb
+Cl,K,Sr
+Cl,K,Th
+Cl,K,U
+Cl,K,Y
+Cl,K,Zn
+Cl,La
+Cl,La,Li
+Cl,La,Na
+Cl,Li
+Cl,Li,Mg
+Cl,Li,Mn
+Cl,Li,N,Na,O
+Cl,Li,N,O
+Cl,Li,Na
+Cl,Li,Na,O
+Cl,Li,O
+Cl,Li,Pb
+Cl,Li,Rb
+Cl,Li,Sr
+Cl,Li,U
+Cl,Li,Zn
+Cl,Mg
+Cl,Mg,Na
+Cl,Mg,Rb
+Cl,Mn
+Cl,Mn,Na
+Cl,Mn,Rb
+Cl,N,Na,O
+Cl,Na
+Cl,Na,Nd
+Cl,Na,O
+Cl,Na,O,P
+Cl,Na,Pb
+Cl,Na,Pr
+Cl,Na,Rb
+Cl,Na,Sr
+Cl,Na,Th
+Cl,Na,U
+Cl,Na,Y
+Cl,Na,Zn
+Cl,Nb
+Cl,Nb,Ta
+Cl,Nd
+Cl,Ni
+Cl,O,S,Tl,Zn
+Cl,Pb
+Cl,Pb,Rb
+Cl,Pb,S
+Cl,Pb,Tl
+Cl,Pb,Zn
+Cl,Pr
+Cl,Rb
+Cl,Rb,U
+Cl,Rb,Zn
+Cl,Sb
+Cl,Sn
+Cl,Sn,Ti
+Cl,Sn,Zn
+Cl,Sr
+Cl,Ta
+Cl,Th
+Cl,Ti
+Cl,Tl
+Cl,Tl,Zn
+Cl,U
+Cl,Y
+Cl,Zn
+Cl,Zr
+Co,Cu,S
+Co,Fe,S
+Co,Ni,S
+Co,O,P
+Co,S
+Cr,K,Li,O
+Cr,K,N,Na,O
+Cr,K,O
+Cr,Li,O
+Cr,Na,O
+Cr,O
+Cs,F
+Cs,F,I
+Cs,Gd,I
+Cs,I
+Cs,I,La
+Cs,I,Li
+Cs,I,Nd
+Cs,K,N,O
+Cs,Li,N,O
+Cs,N,Na,O
+Cs,N,O
+Cs,N,O,Rb
+Cs,O,P
+Cs,O,S
+Cu,Fe,S
+Cu,Ni,S
+Cu,S
+F,I,K
+F,I,Li
+F,K
+F,K,La
+F,K,Li
+F,K,Li,Na
+F,K,Na
+F,K,Sm
+F,K,Th
+F,K,U
+F,K,Y
+F,K,Zr
+F,La
+F,La,Li
+F,La,Na
+F,Li
+F,Li,Na
+F,Li,Rb
+F,Li,Sm
+F,Li,Th
+F,Li,U
+F,Li,Y
+F,Mg
+F,Na
+F,Na,O,Ti
+F,Na,Sm
+F,Na,Th
+F,Na,Ti
+F,Na,U
+F,Na,Y
+F,Na,Zr
+F,Rb
+F,Sr
+F,Th
+F,U
+Fe,Ni,S
+Fe,S
+Ga,I
+Gd,I
+Gd,I,K
+H,K,N,O
+H,K,O
+H,Li,N,O
+H,Li,O
+H,N,Na,O
+H,Na,O
+Hg,I
+I,In
+I,K
+I,K,La
+I,K,Li
+I,K,Na
+I,K,Nd
+I,K,Pb
+I,K,Rb
+I,K,Tl
+I,La
+I,Li
+I,Li,Na
+I,Li,Rb
+I,Mg
+I,Na
+I,Na,Nd
+I,Na,Rb
+I,Nd
+I,Pb
+I,Rb
+I,Sb
+I,Sr
+I,Tl
+I,Zn
+K,Li,Mo,O
+K,Li,N,O
+K,Li,O,S
+K,Li,O,W
+K,Mg,N,O
+K,Mo,N,O
+K,Mo,O
+K,N,Na,O
+K,N,O
+K,N,O,Pb
+K,N,O,Rb
+K,N,O,Sr
+K,N,O,Tl
+K,N,O,W
+K,Na,O,S
+K,Ni,O,P
+K,O
+K,O,P
+K,O,P,Pb
+K,O,P,W
+K,O,P,Zn
+K,O,P,Zn
+K,O,S
+K,O,S,Zn
+K,O,V
+K,O,W
+Li,Mo,Na,O
+Li,Mo,O
+Li,N,Na,O
+Li,N,O
+Li,N,O,Rb
+Li,N,O,Tl
+Li,Na,O,P,S
+Li,Na,O,S
+Li,Na,O,W
+Li,O
+Li,O,P
+Li,O,S
+Li,O,S,Tl
+Li,O,S,Zn
+Li,O,W
+Mg,O
+Mo,N,Na,O
+Mo,Na,O
+Mo,O
+Mo,O,Pb
+N,Na,O
+N,Na,O,Pb
+N,Na,O,Rb
+N,Na,O,Tl
+N,Na,O,W
+N,O,P
+N,O,Rb
+N,O,Rb,Tl
+N,O,S
+N,O,Tl
+Na,Ni,O,P
+Na,O
+Na,O,P
+Na,O,P,Pb
+Na,O,P,Rb,S
+Na,O,P,S
+Na,O,P,S,U
+Na,O,P,W
+Na,O,P,Zn
+Na,O,S
+Na,O,S,Zn
+Na,O,V
+Na,O,W
+Na,S
+Ni,S
+O,P,Zn
+O,Pb
+O,Pb,W
+O,Rb,S
+O,S,Tl
+O,S,Zn
+O,Th
+O,Ti
+O,V
+O,Zr
+Pb,S
+S,Sb
+S,Sn
+S,Tl