Commit 2b4cfb18 authored by Jacob Durrant's avatar Jacob Durrant

Separated indoles/pyrroles from Aromatic_nitrogen_protonated.

parent df7dd912
......@@ -86,6 +86,13 @@ protonated_mols = dimorphite_dl.run_with_mol_list(
print([Chem.MolToSmiles(m) for m in protonated_mols])
```
Caveats
-------
Dimorphite-DL deprotonates indoles and pyrroles around pH 14.5. But these
substructures can also be protonated around pH -3.5. Dimorphite does not
perform the protonation.
Authors and Contacts
--------------------
......
......@@ -494,6 +494,7 @@ class Protonate(object):
# new_smis_to_perhaps_add = ProtSubstructFuncs.protonate_site(new_smis, site)
new_smis = ProtSubstructFuncs.protonate_site(new_smis, site)
# print(site, new_smis) # Good for debugging.
# Only add new smiles if not already in the list.
# for s in new_smis_to_perhaps_add:
......@@ -812,7 +813,8 @@ class TestFuncs:
["CC(=O)[n+]1ccc(N)cc1", "CC(=O)[n+]1ccc([NH3+])cc1", "CC(=O)[n+]1ccc(N)cc1", "Anilines_primary"],
["CCNc1ccccc1", "CC[NH2+]c1ccccc1", "CCNc1ccccc1", "Anilines_secondary"],
["Cc1ccccc1N(C)C", "Cc1ccccc1[NH+](C)C", "Cc1ccccc1N(C)C", "Anilines_tertiary"],
["BrC1=CC2=C(C=C1)NC=C2", "Brc1ccc2[nH+]ccc2c1", "Brc1ccc2[nH]ccc2c1", "Aromatic_nitrogen_protonated"],
["BrC1=CC2=C(C=C1)NC=C2", "Brc1ccc2[nH]ccc2c1", "Brc1ccc2[nH-]ccc2c1", "Indole_pyrrole"],
["BrC1=CNC=C(C1=O)Br", "O=c1c(Br)c[nH+]cc1Br", "O=c1c(Br)c[nH]cc1Br", "Aromatic_nitrogen_protonated"],
["C-N=[N+]=[N@H]", "CN=[N+]=N", "CN=[N+]=[N-]", "Azide"],
["BrC(C(O)=O)CBr", "O=C(O)C(Br)CBr", "O=C([O-])C(Br)CBr", "Carboxyl"],
["NC(NN=O)=N", "NC(=[NH2+])NN=O", "N=C(N)NN=O", "AmidineGuanidine1"],
......
......@@ -10,12 +10,12 @@ Carboxyl [C:1](=[O:2])-[O:3]-[H] 2 3.456652971502591 1.2871420886834017
Thioic_acid [C,c,N,n:1](=[O,S:2])-[SX2,OX2:3]-[H] 2 0.678267 1.497048763660801
Phenyl_Thiol [c,n:1]-[SX2:2]-[H] 1 4.978235294117647 2.6137000480499806
Thiol [C,N:1]-[SX2:2]-[H] 1 9.12448275862069 1.3317968158171463
Phosphate [PX4:1](=[O:2])(-[OX2:3]-[H])(-[O+0:4])-[OX2:5]-[H] 2 2.4182608695652172 1.1091177991945305 5 6.5055 0.9512787792174668
Phosphonate [PX4:1](=[O:2])(-[OX2:3]-[H])(-[C,c,N,n:4])-[OX2:5]-[H] 2 1.8835714285714287 0.5925999820080644 5 7.247254901960784 0.8511476450801531
Phosphate [PX4:1](=[O:2])(-[OX2:3]-[H])(-[O+0:4])-[OX2:5]-[H] 2 2.4182608695652172 1.1091177991945305 5 6.5055 0.9512787792174668
Phosphonate [PX4:1](=[O:2])(-[OX2:3]-[H])(-[C,c,N,n:4])-[OX2:5]-[H] 2 1.8835714285714287 0.5925999820080644 5 7.247254901960784 0.8511476450801531
Phenol [c,n,o:1]-[O:2]-[H] 1 7.065359866910526 3.277356122295936
Peroxide1 [O:1]([$(C=O),$(C[Cl]),$(CF),$(C[Br]),$(CC#N):2])-[O:3]-[H] 2 8.738888888888889 0.7562592839596507
Peroxide2 [C:1]-[O:2]-[O:3]-[H] 2 11.978235294117647 0.8697645895163075
O=C-C=C-OH [O:1]=[C;R:2]-[C;R:3]=[C;R:4]-[O:3]-[H] 4 3.554 0.803339458581667
O=C-C=C-OH [O:1]=[C;R:2]-[C;R:3]=[C;R:4]-[O:5]-[H] 4 3.554 0.803339458581667
Vinyl_alcohol [C:1]=[C:2]-[O:3]-[H] 2 8.871850714285713 1.660200255394124
Alcohol [C:1]-[O:2]-[H] 1 14.780384615384616 2.546464970533435
N-hydroxyamide [C:1](=[O:2])-[N:3]-[O:4]-[H] 3 9.301904761904762 1.2181897185891002
......@@ -35,4 +35,5 @@ Phosphinic_acid [PX4:1](=[O:2])(-[C,c,N,n,F,Cl,Br,I:3])(-[C,c,N,n,F,Cl,Br,I:4])-
Phosphate_diester [PX4:1](=[O:2])(-[OX2:3]-[C,c,N,n,F,Cl,Br,I:4])(-[O+0:5]-[C,c,N,n,F,Cl,Br,I:4])-[OX2:6]-[H] 6 2.7280434782608696 2.5437448856908316
Phosphonate_ester [PX4:1](=[O:2])(-[OX2:3]-[C,c,N,n,F,Cl,Br,I:4])(-[C,c,N,n,F,Cl,Br,I:5])-[OX2:6]-[H] 5 2.0868 0.4503028610465036
Primary_hydroxyl_amine [C,c:1]-[O:2]-[NH2:3] 2 4.035714285714286 0.8463816543155368
Aromatic_nitrogen_protonated [n:1]-[H] 0 12.075833333333334 5.09761318117877
*Indole_pyrrole [c;R:1]1[c;R:2][c;R:3][c;R:4][n;R:5]1[H] 4 14.52875 4.06702491591416
Aromatic_nitrogen_protonated [n:1]-[H] 0 7.17 2.94602395490212
*Azide [N+0:1]=[N+:2]=[N+0:3]-[H] 2 4.65 0.07071067811865513
Nitro [C,c,N,n,O,o:1]-[NX3:2](=[O:3])-[O:4]-[H] 3 -1000.0 0
AmidineGuanidine1 [N:1]-[C:2](-[N:3])=[NX2:4]-[H:5] 3 12.025333333333334 1.5941046150769165
AmidineGuanidine2 [C:1](-[N:2])=[NX2+0:3] 2 10.035538461538462 2.1312826469414716
Sulfate [SX4:1](=[O:2])(=[O:3])([O:4]-[C,c,N,n:5])-[OX2:6]-[H] 5 -2.36 1.3048043093561141
Sulfonate [SX4:1](=[O:2])(=[O:3])(-[C,c,N,n:4])-[OX2:5]-[H] 4 -1.8184615384615386 1.4086213481855594
Sulfinic_acid [SX3:1](=[O:2])-[O:3]-[H] 2 1.7933333333333332 0.4372070447739835
Phenyl_carboxyl [c,n,o:1]-[C:2](=[O:3])-[O:4]-[H] 3 3.463441968255319 1.2518054407928614
Carboxyl [C:1](=[O:2])-[O:3]-[H] 2 3.456652971502591 1.2871420886834017
Thioic_acid [C,c,N,n:1](=[O,S:2])-[SX2,OX2:3]-[H] 2 0.678267 1.497048763660801
Phenyl_Thiol [c,n:1]-[SX2:2]-[H] 1 4.978235294117647 2.6137000480499806
Thiol [C,N:1]-[SX2:2]-[H] 1 9.12448275862069 1.3317968158171463
Phosphate [PX4:1](=[O:2])(-[OX2:3]-[H])(-[O+0:4])-[OX2:5]-[H] 2 2.4182608695652172 1.1091177991945305 5 6.5055 0.9512787792174668
Phosphonate [PX4:1](=[O:2])(-[OX2:3]-[H])(-[C,c,N,n:4])-[OX2:5]-[H] 2 1.8835714285714287 0.5925999820080644 5 7.247254901960784 0.8511476450801531
Phenol [c,n,o:1]-[O:2]-[H] 1 7.065359866910526 3.277356122295936
Peroxide1 [O:1]([$(C=O),$(C[Cl]),$(CF),$(C[Br]),$(CC#N):2])-[O:3]-[H] 2 8.738888888888889 0.7562592839596507
Peroxide2 [C:1]-[O:2]-[O:3]-[H] 2 11.978235294117647 0.8697645895163075
O=C-C=C-OH [O:1]=[C;R:2]-[C;R:3]=[C;R:4]-[O:3]-[H] 4 3.554 0.803339458581667
Vinyl_alcohol [C:1]=[C:2]-[O:3]-[H] 2 8.871850714285713 1.660200255394124
Alcohol [C:1]-[O:2]-[H] 1 14.780384615384616 2.546464970533435
N-hydroxyamide [C:1](=[O:2])-[N:3]-[O:4]-[H] 3 9.301904761904762 1.2181897185891002
*Ringed_imide1 [O,S:1]=[C;R:2]([$([#8]),$([#7]),$([#16]),$([#6][Cl]),$([#6]F),$([#6][Br]):3])-[N;R:4]([C;R:5]=[O,S:6])-[H] 3 6.4525 0.5555627777308341
*Ringed_imide2 [O,S:1]=[C;R:2]-[N;R:3]([C;R:4]=[O,S:5])-[H] 2 8.681666666666667 1.8657779975741713
*Imide [F,Cl,Br,S,s,P,p:1][#6:2][CX3:3](=[O,S:4])-[NX3+0:5]([CX3:6]=[O,S:7])-[H] 4 2.466666666666667 1.4843629385474877
*Imide2 [O,S:1]=[CX3:2]-[NX3+0:3]([CX3:4]=[O,S:5])-[H] 2 10.23 1.1198214143335534
*Amide_electronegative [C:1](=[O:2])-[N:3](-[Br,Cl,I,F,S,O,N,P:4])-[H] 2 3.4896 2.688124315081677
*Amide [C:1](=[O:2])-[N:3]-[H] 2 12.00611111111111 4.512491341218857
*Sulfonamide [SX4:1](=[O:2])(=[O:3])-[NX3+0:4]-[H] 3 7.9160326086956525 1.9842121316708763
Anilines_primary [c:1]-[NX3+0:2]([H:3])[H:4] 1 3.899298673194805 2.068768503987161
Anilines_secondary [c:1]-[NX3+0:2]([H:3])[!H:4] 1 4.335408163265306 2.1768842022330843
Anilines_tertiary [c:1]-[NX3+0:2]([!H:3])[!H:4] 1 4.16690685045614 2.005865735782679
Aromatic_nitrogen_unprotonated [n+0&H0:1] 0 4.3535441240733945 2.0714072661859584
Amines_primary_secondary_tertiary [C:1]-[NX3+0:2] 1 8.159107682388349 2.5183597445318147
Phosphinic_acid [PX4:1](=[O:2])(-[C,c,N,n,F,Cl,Br,I:3])(-[C,c,N,n,F,Cl,Br,I:4])-[OX2:5]-[H] 4 2.9745 0.6867886750744557
Phosphate_diester [PX4:1](=[O:2])(-[OX2:3]-[C,c,N,n,F,Cl,Br,I:4])(-[O+0:5]-[C,c,N,n,F,Cl,Br,I:4])-[OX2:6]-[H] 6 2.7280434782608696 2.5437448856908316
Phosphonate_ester [PX4:1](=[O:2])(-[OX2:3]-[C,c,N,n,F,Cl,Br,I:4])(-[C,c,N,n,F,Cl,Br,I:5])-[OX2:6]-[H] 5 2.0868 0.4503028610465036
Primary_hydroxyl_amine [C,c:1]-[O:2]-[NH2:3] 2 4.035714285714286 0.8463816543155368
Aromatic_nitrogen_protonated [n:1]-[H] 0 12.075833333333334 5.09761318117877
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment