More secondary - structures almost there

reminder.md

@@ -36,4 +36,48 @@ C=CCN1CCC23C4Oc5c(O)ccc(CC1C3(O)CCC4=O)c25 : logp
 
 C#CCOc1ccccc1OCC(O)CNC(C)(C)C : logp
 C=CCc1ccccc1OCC(O)CNC(C)C : logp
-C=CCOc1ccccc1OCC(O)CNC(C)C : logp
+C=CCOc1ccccc1OCC(O)CNC(C)C : logp
+
+CC(C)(C)C : logp just a bug, don't know how to fix it
+CC(C)C : logp just a bug, don't know how to fix it
+CC(C)C(C)C : logp just a bug, don't know how to fix it
+CC(C)C(C)P(=O)(C)C : logp just a bug, don't know how to fix it
+CC=C(C)C(=O)OC1CCN2CC=C(COC(=O)C(O)(C(C)OC)C(O)(C)C)C12 : logp just a bug, don't know how to fix it
+Cc1nc2ccccc2c(n1)c3ccccc3 : logp just a bug, don't know how to fix it
+CCC(C)N(CC(O)COc1ccccc1)CC(O)COc2ccccc2 : logp just a bug, don't know how to fix it
+CCC1(CC(C)C(C)C)C(=O)NC(=O)NC1=O : logp just a bug, don't know how to fix it
+CCC1OC(=O)C(C)C(OC2OC(C)C(O)C(C)(OC)C2)C(C)C(OC3OC(C)C(O)C(N(C)C)C3O)C(O)(C)CC(C)C(=O)C(C)C(O)C1(O)C : logp just a bug, don't know how to fix it
+CCC1OC(=O)C(C)C(OC2OC(C)C(O)C(C)(OC)C2)C(C)C(OC3OC(C)CC(N(C)C)C3O)C(O)(C)CC(C)C(=O)C(C)C(O)C1(O)C
+CCC1OC(=O)C(C)C(OC2OC(C)C(O)C(C)(OC)C2)C(C)C(OC3OC(C)CC(N(C)C)C3O)C(O)(C)CC(C)C(=O)C(C)C(O)C1C
+CCC1OC(=O)C(C)C(OC2OC(C)C(O)C(C)(OC)C2)C(C)C(OC3OC(C)CC(N(C)C)C3O)C(O)(C)CC(C)C(=O)C(C)C(OC(=O)C)C1(O)C
+CCCN(CCC)C1CCOc2c(O)cccc12
+CCCN(CCC)C1CCOc2ccc(O)cc12
+CCCN(CCC)C1COc2c(O)cccc2C1
+CCCN(CCC)C1COc2ccc(O)cc2C1
+CCCN1CC(C=C2C1CCc3ccc(O)cc23)NS(=O)(=O)N(CC)CC
+CCN(C(=O)SCc1ccccc1)C(C)C(C)C
+CCn1cc(C(=O)O)c(=O)c2cc(F)c(cc12)N3CCN(C)CC3
+CCn1cc(C(=O)O)c(=O)c2cc(F)c(cc12)N3CCNC(C)C3
+CCn1cc(C(=O)O)c(=O)c2cc(F)c(cc12)N3CCNCC3
+CCn1cc(C(=O)O)c(=O)c2cc(F)c(N3CCNC(C)C3)c(F)c12
+CCn1cc(C(=O)O)c(=O)c2cc(F)c(N3CCNCC3)c(F)c12
+CCn1cc(C(=O)O)c(=O)c2cc(F)c(nc12)N3CCNCC3
+CCn1cc(C(=O)O)c(=O)c2cc3OCOc3cc12
+CCn1cc(C(=O)O)c(=O)c2ccc(C)nc12
+CCn1cc(C(=O)O)c(=O)c2cnc(nc12)N3CCNCC3
+CCn1cc(C(=O)OCOC(=O)C)c(=O)c2ccc(C)nc12
+CCNc1nc(SC)nc(n1)NC(C)C(C)C
+CCOC(=O)C1=C2CN(C)C(=O)c3cc(F)ccc3N2C=N1
+CCN(CC)CCCN(c1ccccc1)C2Cc3ccccc3C2
+Clc1ccc(Cl)c(Cl)n1
+Clc1ccc(Cl)c(n1)C(=O)O
+CN(C)c1ccc(O)c2C(=O)C3=C(O)C4(O)C(=O)C(C(=O)N)=C(O)C(N(C)C)C4CC3Cc12
+CN(C)c1ccc2CC3CC4C(N(C)C)C(O)=C(C(=O)N)C(=O)C4(O)C(O)=C3C(=O)c2c1O
+CN1CCN(CC1)c2c(F)cc3c(=O)c(cn4C(C)COc2c34)C(=O)O
+COC1CC(OC(C)C1O)OC2C(C)C(=O)OC(C)C(C)C(O)C(C)C(=O)C3(OC3)CC(C)C(OC4OC(C)CC(N(C)C)C4O)C2C
+COc1ccc(Cc2cnc(N)nc2N)c(OC)n1
+COC2(NC(=O)C(C(=O)O)c1ccc(O)cc1)C(=O)N3C2OCC(CSC4=NN=NN4C)=C3C(=O)O
+CSC(C)=NOC(=O)N(C)SN(C1CC1)C(=O)N(C)C
+CSC1=CC=C2C(=CC1=O)C(CCc3c(C)cc(OC)c(OC)c23)NC4OCC(O)C(O)C4O
+(CHn=CHm)cyc-COOH
+FCCn1cc(C(=O)O)c(=O)c2cc(F)c(N3CCN(C)CC3)c(F)c12

ugropy/core/frag_classes/abdulelah_gani/abdulelah_gani_pst.py

@@ -192,7 +192,19 @@ def check_ring_aromaticity(self, mol, ring) -> bool:
         """
         # Non-aromatic patterns
         non_aromatic_patterns = [
-            "[nH0]1[cH0][nH0][cH0][cH0][cH0]1",
+            #"[nH0]1[cH0][nH0][cH0][cH0][cH0]1",
+            #"[nH0]1[cH0][nH0][cH0][nH0][cH0]1",
+            "[nH0]1[cH0;$([cH0]=O)][nH0]cn[cH0;$([cH0]=O)]1",
+            "c1ccco1",
+            "n1[nH0][cH0;$([cH0]=O)]ccc1",
+            "[cH0]1[cH0]cc[cH0]cc1",
+            "[nH0;R2]1ccccc1",
+            "n1[cH0;$([cH0]=*)]cccc1",
+            "n1c[cH0;$([cH0]=*)]ccc1",
+            "n1cc[cH0;$([cH0]=*)]cc1",
+            "n1ccc[cH0;$([cH0]=*)]c1",
+            "n1cccc[cH0;$([cH0]=*)]1",
+            "n1cn[cH0;$([cH0]=O)]cc1",
         ]
 
         # Aromatic patterns
@@ -201,9 +213,11 @@ def check_ring_aromaticity(self, mol, ring) -> bool:
             "c1ncncn1",
             "n1ccccc1",
             "n1ccncc1",
-            "[nH0]1c[nH0]ccc1",
+            "[nH0;R1]1[c;R1][nH0]ccc1",
             "[nH0]1[nH0]cccc1",
             "n1ccccc1",
+            "[nX2]1[nX2]c[nX2]cc1",
+            "[nH0]1c[nH0]ccc1",
         ]
 
         # Ring as set to compare

ugropy/core/get_rdkit_object.py

@@ -8,7 +8,6 @@
 from rdkit import Chem
 
 
-@cache
 def instantiate_mol_object(
     identifier: Union[str, Chem.rdchem.Mol], identifier_type: str = "name"
 ) -> Chem.rdchem.Mol:
@@ -34,15 +33,7 @@ def instantiate_mol_object(
         chem_object = Chem.MolFromSmiles(smiles)
 
     elif identifier_type.lower() == "name":
-        try:
-            pcp_object = pcp.get_compounds(identifier, identifier_type)[0]
-            smiles = pcp_object.canonical_smiles
-            chem_object = Chem.MolFromSmiles(smiles)
-        except IndexError:
-            raise ValueError(
-                f"Could not find a molecule with the name '{identifier}' on "
-                "PubChem"
-            )
+        chem_object = instantiate_mol_from_name(identifier)
 
     elif identifier_type.lower() == "mol":
         chem_object = identifier
@@ -52,11 +43,41 @@ def instantiate_mol_object(
                 "If 'mol' identifier type is used, the identifier must be a "
                 "rdkit.Chem.Chem.rdchem.Mol object."
             )
-
     else:
         raise ValueError(
             f"Identifier type: {identifier_type} not valid, use: 'name', "
             "'smiles' or 'mol'"
         )
 
     return chem_object
+
+
+@cache
+def instantiate_mol_from_name(name: str) -> Chem.rdchem.Mol:
+    """Instantiate a RDKit Mol object from molecule's name.
+    
+    The funcion uses `pubchempy` to get the molecule's SMILES representation
+    from the molecule's name and then instantiate a RDKit Mol object.
+
+    Parameters
+    ----------
+    name : str
+        Name of the molecule.
+
+    Returns
+    -------
+    rdkit.Chem.rdchem.Mol
+        RDKit Mol object.
+    """
+
+    try:
+        pcp_object = pcp.get_compounds(name, "name")[0]
+        smiles = pcp_object.canonical_smiles
+        chem_object = Chem.MolFromSmiles(smiles)
+    except IndexError:
+        raise ValueError(
+            f"Could not find a molecule with the name '{name}' on "
+            "PubChem"
+        )
+
+    return chem_object

ugropy/groupscsv/abdulelah_gani/secondary/info.csv

@@ -27,7 +27,7 @@ H2NCOCHnCHmCONH2 (m,n in 1..2)|245
 CHm(NHn)-COOH (m,n in 0..2)|246
 HOOC-CHn-COOH (n in 1..2)|247
 HOOC-CHn-CHm-COOH (n, m in 1..2)|248
-HO-CHn-COOH (n in 1..2)|249
+HO-CHn-COOH (n in 0..2)|249
 NH2-CHn-CHm-COOH (n, m in 1..2)|250
 CH3-O-CHn-COOH (n in 1..2)|251
 HS-CH-COOH|252
@@ -51,7 +51,7 @@ CHm=CHn-COOH (m,n in 0..2)|269
 aC-CHn-X (n in 1..2) X: Halogen|270
 aC-CHn-NHm (n in 1..2; m in 0..2))|271
 aC-CHn-O- (n in 1..2)|272
-aC-CHn-OH (n in 0..2)|273
+aC-CHn-OH (n in 1..2)|273
 aC-CHn-CN (n in 1..2)|274
 aC-CHn-CHO (n in 1..2)|275
 aC-CHn-SH (n in 1..2)|276

ugropy/groupscsv/abdulelah_gani/secondary/secondary.csv

@@ -1,105 +1,105 @@
 group|smarts
-(CH3)2CH|[CH;!R]([CH3])[CH3]
+(CH3)2CH|[CH;!R;!$([CH][cH0])]([CH3])[CH3]
 (CH3)3C|[CH0;!R;!$([CH0][cH0])]([CH3])([CH3])[CH3]
-?CH(CH3)CH(CH3)|
-?CH(CH3)C(CH3)2|
+CH(CH3)CH(CH3)|[CH;!R]([CH3])[CH;!R]([CH3])
+CH(CH3)C(CH3)2|[CH;!R](*)([CH3])[CH0;!R](*)([CH3])[CH3]
 ????C(CH3)2C(CH3)2|
 CHn=CHm-CHp=CHk (k,m,n,p in 0..2)|[CH0,CH1,CH2;!R]=[CH0,CH1;!R][CH0,CH1;!R]=[CH0,CH1,CH2;!R]
 CH3-CHm=CHn (m,n in 0..2)|[CH3][CH0,CH1;!R]=[CH0,CH1,CH2;!R]
 CH2-CHm=CHn (m,n in 0..2)|[CH2;!R][CH0,CH1;!R]=[CH0,CH1,CH2;!R]
 CHp-CHm=CHn (m,n in 0..2; p in 0..1)|[CX4H0,CX4H1;!R][CH0,CH1,CH2;!R]=[CH0,CH1,CH2;!R]
 ?CHCHO or CCHO|
 CH3COCH2|[CX4H3][CH0;!R](=[OH0])[CX4H2;!R]
-?CH3COCH or CH3COC|
-?CHCOOH or CCOOH|
+CH3COCH or CH3COC|[CX4H3][CH0;!R](=[OH0])[CX4H,CX4H0;!R]
+CHCOOH or CCOOH|[CX4H,CX4H0;!R;!$([C][a,OH]);!$([C][N;!R])][CH0;!R](=[OH0])[OH]
 CH3COOCH or CH3COOC|[CX4H3][CH0;!R](=[OH0])[O][CX4H,CX4H0;!R]
 ?CO-O-CO|
-CHOH|[CH;!R;$([CH]([C;!$([C][OH]);!$([C][NH])])[C;!$([C][OH]);!$([C][NH])])][OH]
+CHOH|[CX4H;!R;!$([CH][C;!R][OH]);!$([CH][cH0]);!$([CH][CH2,CH][NH])][OH]
 COH|[CX4H0;!R;$([CX4H0](C)(C)C)][OH]
 ????CH3COCHnOH (n in 0..2)|
 ?NCCHOH or NCCOH|
-?OH-CHn-COO (n in 0..2)|
-CHm(OH)CHn(OH) (m,n in 0..2)|[CX4H0,CX4H1,CX4H2]([OH])[CX4H0,CX4H1,CX4H2][OH]
-CHm(OH)CHn(NHp) (m,n,p in 0..2)|[CX4H0,CX4H1,CX4H2;!R]([OH])[CX4H0,CX4H1,CX4H2;!R][NH0,NH1,NH2;!R]
+OH-CHn-COO (n in 0..2)|[OH][CH0,CH1,CH2;!R][CH0]([OH0])=O
+CHm(OH)CHn(OH) (m,n in 0..2)|[CX4H0,CX4H1,CX4H2;!R]([OH])[CX4H0,CX4H1,CX4H2;!R][OH]
+CHm(OH)CHn(NHp) (m,n,p in 0..2)|[CX4H0,CX4H1,CX4H2;!R]([OH])[CX4H0,CX4H1,CX4H2;!R][NH1,NH2;!R;!$([N][Cl,a])]
 ?CHm(NH2)CHn(NH2) (m,n in 0..2)|
-?CHm(NH)CHn(NH2) (m,n in 1..2)|
-?H2NCOCHnCHmCONH2 (m,n in 1..2)|
+CHm(NH)CHn(NH2) (m,n in 1..2)|[CX4H0,CX4H,CX4H2;!R]([NH;!R])[CX4H0,CX4H,CX4H2;!R][NH2]
+H2NCOCHnCHmCONH2 (m,n in 1..2)|[NH2][CH0](=O)[CX4H,CX4H2;!R][CX4H,CX4H2;!R][CH0](=O)[NH2]
 CHm(NHn)-COOH (m,n in 0..2)|[CH0,CH1,CH2;!R]([NH0,NH1,NH2;!R])[CH0]([OH])=[OH0]
 ?HOOC-CHn-COOH (n in 1..2)|
 ?HOOC-CHn-CHm-COOH (n, m in 1..2)|
-?HO-CHn-COOH (n in 1..2)|
+HO-CHn-COOH (n in 0..2)|[OH][CH0,CH1,CH2;!R][CH0]([OH])=O
 ?NH2-CHn-CHm-COOH (n, m in 1..2)|
-?CH3-O-CHn-COOH (n in 1..2)|
+CH3-O-CHn-COOH (n in 1..2)|[CX4H3][O][CX4H0,CX4H,CX4H2;!R][CH0]([OH])=O
 ?HS-CH-COOH|
 ?HS-CHn-CHm-COOH (n, m in 1..2)|
 ?NC-CHn-CHm-CN (n, m in 1..2)|
 ?OH-CHn-CHm-CN (n, m in 1..2)|
 ????HS-CHn-CHm-SH (n, m in 1..2)|
-?COO-CHn-CHm-OOC (n, m in 1..2)|
-?OOC-CHm-CHm-COO (n, m in 1..2)|
+COO-CHn-CHm-OOC (n, m in 1..2)|[CH0;!R](=[OH0])[OH0;!R][CX4H,CX4H2;!R][CX4H,CX4H2;!R][OH0;!R][CH0;!R](=[OH0])
+OOC-CHm-CHm-COO (n, m in 1..2)|[OH0;!R][CH0](=O)[CH,CH2;!R][CH,CH2;!R][CH0;!R](=O)[OH0;!R]
 ?NC-CHn-COO (n in 1..2)|
-?COCHnCOO (n in 1..2)|
+COCHnCOO (n in 1..2)|[CH0;!R;!$([CH0][OH0]);$([CH0]([CX4;!R])[CX4;!R])](=[OH0])[CX4H,CX4H2;!R][CH0;!R](=[OH0])[OH0;!R]
 CHm-O-CHn=CHp (m,n,p in 0..3)|[CH0,CH1,CH2,CH3;!R;!$([CH0,CH1,CH2,CH3;!R]=[OH0])][OH0;!R][CH0,CH1;!R]=[CH0,CH1,CH2;!R]
 CHm=CHn-F (m,n in 0..2)|[CH0,CH1,CH2;!R]=[CH0,CH1;!R][F]
 CHm=CHn-Br (m,n in 0..2)|[CH0,CH1,CH2;!R]=[CH0,CH1,CH2;!R][Br]
 ????CHm=CHn-I (m,n in 0..2)|
 CHm=CHn-Cl (m,n in 0..2)|[CH0,CH1,CH2;!R]=[CH0,CH1;!R][Cl]
-?CHm=CHn-CN (m,n in 0..2)|
+CHm=CHn-CN (m,n in 0..2)|[CH0,CH1,CH2;!R]=[CH0,CH1;!R][CH0;!R]#N
 CHn=CHm-COO-CHp (m,n,p in 0..3)|[CH0,CH1,CH2;!R]=[CH0,CH1][CH0](=[OH0])[OH0][CH0,CH1,CH2,CH3;!R,R1]
 ?CHm=CHn-CHO (m,n in 0..2)|
 CHm=CHn-COOH (m,n in 0..2)|[CH0,CH1,CH2;!R]=[CH0,CH1;!R][CH0]([OH])=[OH0]
-aC-CHn-X (n in 1..2) X: Halogen|[cH0][CH1,CH2;!R][F,Cl,Br,I]
+aC-CHn-X (n in 1..2) X: Halogen|[cH0][CX4H0,CX4H1,CX4H2;!R;!$([CH0](F)(F)F)][F,Cl,Br,I]
 aC-CHn-NHm (n in 1..2; m in 0..2))|[cH0][CH1,CH2;!R][NH0,NH1,NH2;!R]
-aC-CHn-O- (n in 1..2)|[cH0][CX4H,CX4H2;!R][OH0;!R;!$([OH0][CH0]=[OH0])]
-aC-CHn-OH (n in 0..2)|[cH0][CX4H0,CX4H,CX4H2;!R][OH]
-?aC-CHn-CN (n in 1..2)|
+aC-CHn-O- (n in 1..2)|[cH0][CX4H0,CX4H,CX4H2;!R][OH0;!R;!$([OH0][CH0]=[OH0])]
+aC-CHn-OH (n in 1..2)|[cH0][CX4H0,CX4H,CX4H2;!R][OH]
+aC-CHn-CN (n in 1..2)|[cH0][CX4H0,CX4H,CX4H2;!R][CH0]#N
 ?aC-CHn-CHO (n in 1..2)|
 ????aC-CHn-SH (n in 1..2)|
-aC-CHn-COOH (n in 1..2)|[cH0][CX4H,CX4H2;!R][CH0;!R]([OH])=O
-aC-CHn-CO- (n in 1..2)|[cH0][CX4H,CX4H2;!R][CH0;!R;!$([CH0][OH,OH0])]=O
-aC-CHn-S- (n in 1..2)|[cH0][CX4H,CX4H2;!R][SX2H0;!R]
+aC-CHn-COOH (n in 1..2)|[cH0][CX4H0,CX4H,CX4H2;!R][CH0;!R]([OH])=O
+aC-CHn-CO- (n in 1..2)|[cH0][CX4H0,CX4H,CX4H2;!R][CH0;!R;!$([CH0][OH,OH0,NH2]);!$([CH0][NH][CH0;!R](=O))]=O
+aC-CHn-S- (n in 1..2)|[cH0][CX4H0,CX4H,CX4H2;!R][SX2H0;!R]
 ????aC-CHn-OOC-H (n in 1..2)|
-?aC-CHm-NO2 (n in 1..2)|
-?aC-CHn-CONH2 (n in 1..2)|
-aC-CHn-OOC (n in 1..2)|[cH0][CX4H,CX4H2;!R]O[CH0;!R]=O
-aC-CHn-COO (n in 1..2)|[cH0][CX4H,CX4H2;!R][CH0;!R]([OH0])=[OH0]
+aC-CHm-NO2 (n in 1..2)|[cH0][CX4H0,CX4H,CX4H2;!R][N+](=O)[O-]
+aC-CHn-CONH2 (n in 1..2)|[cH0][CX4H0,CX4H,CX4H2;!R][CH0;!R](=[O])[NH2]
+aC-CHn-OOC (n in 1..2)|[cH0][CX4H0,CX4H,CX4H2;!R]O[CH0;!R]=O
+aC-CHn-COO (n in 1..2)|[cH0][CX4H0,CX4H,CX4H2;!R][CH0;!R]([OH0])=[OH0]
 ?aC-SO2-OH|
-?aC-CH(CH3)2|
+aC-CH(CH3)2|[cH0][CH;!R]([CH3])([CH3])
 aC-C(CH3)3|[cH0][CH0;!R]([CH3])([CH3])[CH3]
-?aC-CF3|
-?(CHn=C)(cyc)-CHO (n in 0..2)|
-(CHn=C)cyc-COO-CHm (n,m in 0..3)|[CH0,CH1;R]=[CH0;R][CH0;!R](=[OH0])[OH0;!R][CH0,CH1,CH2,CH3]
-(CHn=C)cyc-CO- (n in 0..2)|[CH0,CH1;R]=[CH0;R][CH0;!R;!$([CH0][OH0])](=[OH0])
-(CHn=C)cyc-CH3 (n in 0..2)|[CH0,CH1;R]=[CH0][CH3]
-(CHn=C)cyc-CH2 (n in 0..2)|[CH0,CH1;R]=[CH0;R][CH2;!R]
-?(CHn=C)cyc-CN (n in 0..2)|
-?(CHn=C)cyc-Cl (n in 0..2)|
-CHcyc-CH3|[CX4H;R1][CX4H3]
-CHcyc-CH2|[CX4H;R1][CX4H2;!R]
+aC-CF3|[cH0][CH0;!R]([F])([F])[F]
+(CHn=C)(cyc)-CHO (n in 0..2)|[CH0,CH1;R]=[CH0;R][CH;!R]=[OX1H0]
+(CHn=C)cyc-COO-CHm (n,m in 0..3)|[CH0,CH1;R]=[CH0;R][CH0;!R](=[OH0])[OH0;!R][CH0,CH1,CH2,CH3,cH0]
+(CHn=C)cyc-CO- (n in 0..2)|[CH0,CH1;R;x2]=[CH0;R][CH0;!R;!$([CH0][OH0,OH])](=[OH0])
+(CHn=C)cyc-CH3 (n in 0..2)|[CH0,CH1;R;x2]=[CH0;R][CH3]
+(CHn=C)cyc-CH2 (n in 0..2)|[CH0,CH1;R;x2]=[CH0;R][CH2;!R]
+(CHn=C)cyc-CN (n in 0..2)|[CH0,CH1;R;x2]=[CH0;R][CH0;!R]#N
+(CHn=C)cyc-Cl (n in 0..2)|[CH0,CH1;R]=[CH0;R][Cl]
+CHcyc-CH3|[CX4H;R][CX4H3]
+CHcyc-CH2|[CX4H;R][CX4H2;!R]
 CHcyc-CH|[CX4H;R][CX4H;!R]
-CHcyc-C|[CX4H;R1][CX4H0;!R]
+CHcyc-C|[CX4H;R][CX4H0;!R]
 CHcyc-CH=CHn (n in 0..2)|[CX4H;R][CH;!R]=[CH0,CH1,CH2;!R]
 CHcyc-C=CHn (n in 1..2)|[CX4H;R][CH0;!R]=[CH0,CH1,CH2;!R]
-?CHcyc-Cl|
+CHcyc-Cl|[CX4H;R][Cl]
 CHcyc-F|[CX4H;R][F]
 CHcyc-OH|[CX4H;R][OH]
-?CHcyc-NH2|
-CHcyc-NH-CHn (n in 0..3)|[CX4H;R][NH;!R][CH0,CH1,CH2,CH3;!R]
-?CHcyc-N-CHn (n in 0..3)|
+CHcyc-NH2|[CX4H;R][NH2]
+CHcyc-NH-CHn (n in 0..3)|[CX4H;R][NH;!R][CH0,CH1,CH2,CH3,cH0]
+CHcyc-N-CHn (n in 0..3)|[CX4H;R][NH0;!R][CX4H0&!R,CX4H1&!R,CX4H2&!R,CX4H3&!R,cH0]
 ????CHcyc-SH|
-?CHcyc-CN|
+CHcyc-CN|[CX4H;R][CH0;!R]#N
 CHcyc-COOH|[CX4H;R][CH0;!R]([OH])=O
-?CHcyc-CO|
+CHcyc-CO|[CX4H;R][CH0;!R;!$([CH0][OH,OH0])]=O
 CHcyc-NO2|[CX4H;R][N+](=O)[O-]
-?CHcyc-S-|
+CHcyc-S-|[CX4H;R][SX2H0;!R]
 ????CHcyc-CHO|
-CHcyc-O-|[CX4H;R1][OH0;!R;!$([OH0][CH0]=[OH0])]
+CHcyc-O-|[CX4H;R;x2][OH0;!R;!$([OH0][CH0]=[OH0])]
 ?CHcyc-OOCH|
-CHcyc-COO|[CX4H;R1][CH0]([OH0;!R])=[OH0]
-CHcyc-OOC|[CX4H;R1][OH0;!R][CH0]=[OH0]
-Ccyc-CH3|[CX4H0;R1][CH3]
-Ccyc-CH2|[CX4H0;R1][CH2;!R]
-Ccyc-OH|[CX4H0;R][OH]
+CHcyc-COO|[CX4H;R;x2][CH0]([OH0;!R])=[OH0]
+CHcyc-OOC|[CX4H;R;x2][OH0;!R][CH0]=[OH0]
+Ccyc-CH3|[CX4H0;R;x2][CH3]
+Ccyc-CH2|[CX4H0;R;x2][CH2;!R]
+Ccyc-OH|[CX4H0;R;x2][OH]
 >Ncyc-CH3|[NH0X3;R][CH3;!R]
 >Ncyc-CH2|[NH0X3;R][CH2;!R]
 AROMRINGs1s2|[cH0;R1;D3]1[cH0;R1;D3][c;D2][c;D2][c;D2][c;D2]1
@@ -108,7 +108,7 @@ AROMRINGs1s4|[cH0;R1;D3]1[c;D2][c;D2][cH0;R1;D3][c;D2][c;D2]1
 AROMRINGs1s2s3|[cH0;R1;D3]1[cH0;R1;D3][cH0;R1;D3][c;D2][c;D2][c;D2]1
 AROMRINGs1s2s4|[cH0;R1;D3]1[cH0;R1;D3][c;D2][cH0;R1;D3][c;D2][c;D2]1
 AROMRINGs1s3s5|[cH0;R1;D3]1[c;D2][cH0;R1;D3][c;D2][cH0;R1;D3][c;D2]1
-?AROMRINGs1s2s3s4|
+AROMRINGs1s2s3s4|[cH0;R1;D3]1[cH0;R1;D3][cH0;R1;D3][cH0;R1;D3][c;D2][c;D2]1
 AROMRINGs1s2s3s5|[cH0;R1;D3]1[cH0;R1;D3][cH0;R1;D3][c;D2][cH0;R1;D3][c;D2]1
 AROMRINGs1s2s4s5|[cH0;R1;D3]1[cH0;R1;D3][c;D2][cH0;R1;D3][cH0;R1;D3][c;D2]1
 PYRIDINEs2|[nH0;R1]1[cH0;R1;D3][c;D2][c;D2][c;D2][c;D2]1
@@ -121,11 +121,11 @@ PYRIDINEs2s6|[nH0;R1]1[cH0;R1;D3][c;D2][c;D2][c;D2][cH0;R1;D3]1
 PYRIDINEs3s4|[nH0;R1]1[c;D2][cH0;R1;D3][cH0;R1;D3][c;D2][c;D2]1
 PYRIDINEs3s5|[nH0;R1]1[c;D2][cH0;R1;D3][c;D2][cH0;R1;D3][c;D2]1
 PYRIDINEs2s3s6|[nH0;R1]1[cH0;R1;D3][cH0;R1;D3][c;D2][c;D2][cH0;R1;D3]1
-?(CHn=CHm)cyc-COOH|
-AROMRINGs1s2s3s4s5|[cH0;R1]1(*)[cH0;R1](*)[cH0;R1](*)[cH0;R1](*)[cH0;R1](*)[a;D2]1
-?aC-NHCOCH2N|
+(CHn=CHm)cyc-COOH|[CH0,CH1;R]=[CH0,CH1;R][CH0]([OH])=O
+AROMRINGs1s2s3s4s5|[cH0;R1]1(*)[cH0;R1](*)[cH0;R1](*)[cH0;R1](*)[cH0;R1](*)[c;D2]1
+aC-NHCOCH2N|[cH0][NH;!R][CH0](=O)[CH2][NH0;!R]
 (N=C)cyc-CH3|[N;R]=[CH0;R][CH3]
-?aC-CONH(CH2)2N|
+aC-CONH(CH2)2N|[cH0][CH0;!R](=O)[NH;!R][CH2;!R][CH2;!R][NH0;!R]
 aC-SO2NH|[cH0][S;!R](=O)(=O)[NH]
-aC-SO2N|[cH0][S;!R](=O)(=O)[NH0]
+aC-SO2N|[cH0][S;!R](=O)(=O)[NH0;!R]
 aC-SO2NH2|[cH0][S;!R](=O)(=O)[NH2]