rdworks 0.25.7__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (69) hide show
  1. rdworks/__init__.py +35 -0
  2. rdworks/autograph/__init__.py +4 -0
  3. rdworks/autograph/autograph.py +184 -0
  4. rdworks/autograph/centroid.py +90 -0
  5. rdworks/autograph/dynamictreecut.py +135 -0
  6. rdworks/autograph/nmrclust.py +123 -0
  7. rdworks/autograph/rckmeans.py +74 -0
  8. rdworks/bitqt/__init__.py +1 -0
  9. rdworks/bitqt/bitqt.py +355 -0
  10. rdworks/conf.py +374 -0
  11. rdworks/descriptor.py +36 -0
  12. rdworks/display.py +206 -0
  13. rdworks/ionized.py +170 -0
  14. rdworks/matchedseries.py +260 -0
  15. rdworks/mol.py +1522 -0
  16. rdworks/mollibr.py +887 -0
  17. rdworks/pka.py +38 -0
  18. rdworks/predefined/Asinex_fragment.xml +20 -0
  19. rdworks/predefined/Astex_RO3.xml +16 -0
  20. rdworks/predefined/Baell2010_PAINS/Baell2010A.xml +52 -0
  21. rdworks/predefined/Baell2010_PAINS/Baell2010B.xml +169 -0
  22. rdworks/predefined/Baell2010_PAINS/Baell2010C.xml +1231 -0
  23. rdworks/predefined/Baell2010_PAINS/PAINS-less-than-015-hits.xml +2048 -0
  24. rdworks/predefined/Baell2010_PAINS/PAINS-less-than-150-hits.xml +278 -0
  25. rdworks/predefined/Baell2010_PAINS/PAINS-more-than-150-hits.xml +83 -0
  26. rdworks/predefined/Baell2010_PAINS/makexml.py +70 -0
  27. rdworks/predefined/Brenk2008_Dundee/makexml.py +21 -0
  28. rdworks/predefined/CNS.xml +18 -0
  29. rdworks/predefined/ChEMBL_Walters/BMS.xml +543 -0
  30. rdworks/predefined/ChEMBL_Walters/Dundee.xml +318 -0
  31. rdworks/predefined/ChEMBL_Walters/Glaxo.xml +168 -0
  32. rdworks/predefined/ChEMBL_Walters/Inpharmatica.xml +276 -0
  33. rdworks/predefined/ChEMBL_Walters/LINT.xml +174 -0
  34. rdworks/predefined/ChEMBL_Walters/MLSMR.xml +351 -0
  35. rdworks/predefined/ChEMBL_Walters/PAINS.xml +1446 -0
  36. rdworks/predefined/ChEMBL_Walters/SureChEMBL.xml +501 -0
  37. rdworks/predefined/ChEMBL_Walters/makexml.py +40 -0
  38. rdworks/predefined/Hann1999_Glaxo/Hann1999.xml +168 -0
  39. rdworks/predefined/Hann1999_Glaxo/Hann1999Acid.xml +102 -0
  40. rdworks/predefined/Hann1999_Glaxo/Hann1999Base.xml +6 -0
  41. rdworks/predefined/Hann1999_Glaxo/Hann1999ElPh.xml +6 -0
  42. rdworks/predefined/Hann1999_Glaxo/Hann1999NuPh.xml +6 -0
  43. rdworks/predefined/Hann1999_Glaxo/makexml.py +83 -0
  44. rdworks/predefined/Kazius2005/Kazius2005.xml +114 -0
  45. rdworks/predefined/Kazius2005/makexml.py +66 -0
  46. rdworks/predefined/ZINC_druglike.xml +24 -0
  47. rdworks/predefined/ZINC_fragment.xml +14 -0
  48. rdworks/predefined/ZINC_leadlike.xml +15 -0
  49. rdworks/predefined/fragment.xml +7 -0
  50. rdworks/predefined/ionized/simple_smarts_pattern.csv +57 -0
  51. rdworks/predefined/ionized/smarts_pattern.csv +107 -0
  52. rdworks/predefined/misc/makexml.py +119 -0
  53. rdworks/predefined/misc/reactive-part-2.xml +104 -0
  54. rdworks/predefined/misc/reactive-part-3.xml +74 -0
  55. rdworks/predefined/misc/reactive.xml +321 -0
  56. rdworks/readin.py +312 -0
  57. rdworks/rgroup.py +2173 -0
  58. rdworks/scaffold.py +520 -0
  59. rdworks/std.py +143 -0
  60. rdworks/stereoisomers.py +127 -0
  61. rdworks/tautomers.py +20 -0
  62. rdworks/units.py +63 -0
  63. rdworks/utils.py +495 -0
  64. rdworks/xml.py +260 -0
  65. rdworks-0.25.7.dist-info/METADATA +37 -0
  66. rdworks-0.25.7.dist-info/RECORD +69 -0
  67. rdworks-0.25.7.dist-info/WHEEL +5 -0
  68. rdworks-0.25.7.dist-info/licenses/LICENSE +21 -0
  69. rdworks-0.25.7.dist-info/top_level.txt +1 -0
@@ -0,0 +1,57 @@
1
+ Substructure,SMARTS,Index,Acid_or_base
2
+ Sulfate monoether,[SX4:0](=[O:1])(=[O:2])(-[O:3])-[OX2:4]-[H:5],4,A
3
+ Sulfate monoether,[SX4:0](=[O:1])(=[O:2])(-[O:3])-[O-1:4],4,B
4
+ Sulfonic acid,"[SX4:0](=[O:1])(=[O:2])(-[#6,#7:3])-[OX2:4]-[H:5]",4,A
5
+ Sulfonic acid,"[SX4:0](=[O:1])(=[O:2])(-[#6,#7:3])-[O-1:4]",4,B
6
+ Sulfinic acid,"[SX3:0](=[O:1])(-[#6,#7:2])-[OX2:3]-[H:4]",3,A
7
+ Sulfinic acid,"[SX3:0](=[O:1])(-[0#6,#7:2])-[O-1:3]",3,B
8
+ Seleninic acid,"[SeX3:0](=[O:1])(-[#6,#7:2])-[OX2:3]-[H:4]",3,A
9
+ Seleninic acid,"[SeX3:0](=[O:1])(-[#6,#7:2])-[O-1:3]",3,B
10
+ Selenenic acid,[SeX2:0]-[OX2:1]-[H:2],1,A
11
+ Selenenic acid,[SeX2:0]-[O-1:1],1,B
12
+ Arsonic acid,"[AsX4:0](=[O:1])(-[#6,#7:2])-[OX2:3]-[H:4]",3,A
13
+ Arsonic acid,"[AsX4:0](=[O:1])(-[#6,#7:2])-[O-1:3]",3,B
14
+ Thiosulfuric acid,[S:0]~[SX4:1](~[O:2])(~[O:3])-[O:4]-[H:5],4,A
15
+ Thiosulfuric acid,[S:0]~[SX4:1](~[O:2])(~[O:3])-[O-1:4],4,B
16
+ Phosph(o/i)nic acid,"[PX4:0](=[O:1])(-[OX2:2]-[H:5])(-[#1,#6,#7,#8:3])(-[#1,#6,#7,#8:4])",2,A
17
+ Phosph(o/i)nic acid,"[PX4:0](=[O:1])(-[O-1:2])(-[#1,#6,#7,#8:3])(-[#1,#6,#7,#8:4])",2,B
18
+ Phosphate (mono/di)ether,[PX4:0](=[O:1])(-[O:2])(-[O:3])-[OX2:4]-[H:5],4,A
19
+ Phosphate (mono/di)ether,[PX4:0](=[O:1])(-[O:2])(-[O:3])-[O-1:4],4,B
20
+ Carboxyl acid,"[$([#6]=[#8,#7]),$(C#N):0]-[OX2:1]-[H:2]",1,A
21
+ Carboxyl acid,"[$([#6]=[#8,#7]),$(C#N):0]-[O-1:1]",1,B
22
+ Carboxyl acid enol,[C:0]=[C:1](-[OX2:2]-[H:3])-[OX2:4]-[H:5],4,A
23
+ Carboxyl acid enol,[C:0]=[C:1](-[OX2:2]-[H:3])-[O-1:4],4,B
24
+ Carbo(di)thioic acid,"[CX3:0](=[O,S:1])-[SX2,OX2:2]-[H:3]",2,A
25
+ Carbo(di)thioic acid,"[CX3:0](=[O,S:1])-[S-1,O-1:2]",2,B
26
+ Carboxyl acid vinylogue ,[O:0]=[C:1]-[C:2]=[C:3]-[OX2:4]-[H:5],4,A
27
+ Carboxyl acid vinylogue,[O:0]=[C:1]-[C:2]=[C:3]-[O-1:4],4,B
28
+ Thiol/Thiophenol,"[#6,#7:0]-[SX2:1]-[H:2]",1,A
29
+ Thiol/Thiophenol,"[#6,#7:0]-[S-1:1]",1,B
30
+ Phenol,"[c,n:0]-[OX2:1]-[H:2]",1,A
31
+ Phenol,"[c,n:0]-[O-1:1]",1,B
32
+ Hydroperoxide/Hydroxyl amine,"[O,N:0]-[OX2:1]-[H:2]",1,A
33
+ Hydroperoxide/Hydroxyl amine,"[O,N:0]-[O-1:1]",1,B
34
+ Azole,"[#7:0]1(-[H:5])-,:[#7,#6:1]=,:[#7,#6:2]-,:[#7,#6:3]=,:[#7,#6:4]-,:1",0,A
35
+ Azole,"[#7-1:0]1-,:[#7,#6:1]=,:[#7,#6:2]-,:[#7,#6:3]=,:[#7,#6:4]-,:1",0,B
36
+ Aza-aromatics,[n:0]-[H:1],0,A
37
+ Aza-aromatics,"[n-1,n+0X2:0]",0,B
38
+ Oxime,"[$([#7]:,=[#6,#7]),$([#7]:,=[#6,#7]:,-[#6,#7]:,=[#6,#7]):0]-[OX2,NX3:1]-[H:2]",1,A
39
+ Oxime,"[$([#7]:,=[#6,#7]),$([#7]:,=[#6,#7]:,-[#6,#7]:,=[#6,#7]):0]-[O-1,NX2-1:1]",1,B
40
+ Amine,"[NX4+1:0](-[H:4])(-[CX4,c,#7,#8,#1,S,$(C=C),Cl:1])(-[CX4,c,#7,#8,#1,S,$(C=C):2])(-[CX4,c,#7,#8,#1,S,$(C=C):3])",0,A
41
+ Amine,"[NX3:0](-[CX4,c,#7,#8,#1,S,$(C=C),Cl:1])(-[CX4,c,#7,#8,#1,S,$(C=C):2])(-[CX4,c,#7,#8,#1,S,$(C=C):3])",0,B
42
+ Imine,"[#6,#7,P,S:0]=[NX3+1:1](-[H:2])",1,A
43
+ Imine,"[#6,#7,P,S:0]=[NX2:1]",1,B
44
+ Amide,"[$([#7]=[#7,#8]),$(c:c:c:c:[#7+1]):0]-[NX3:1]-[H:2]",1,A
45
+ Amide,"[$([#7]=[#7,#8]),$(c:c:c:c:[#7+1]):0]-[NX2-1:1]",1,B
46
+ Amide imine,"[$([#6]-,:[O,S,#7]),N+1:0]=,:[NX2:1]-[H:2]",1,A
47
+ Amide imine,"[$([#6]-,:[O,S,#7]),N+1:0]=,:[NX1-1:1]",1,B
48
+ Sulfamide,[SX4:0](=[O:1])(=[O:2])-[NX3:3]-[H:4],3,A
49
+ Sulfamide,[SX4:0](=[O:1])(=[O:2])-[NX2-1:3],3,B
50
+ Phosphamide,[PX4:0](=[O:1])-[NX3:2]-[H:3],2,A
51
+ Phosphamide,[PX4:0](=[O:1])-[NX2-1:2],2,B
52
+ Enol,"[$([#6]=,:[#7,#8]),$(C#N),#7+1,$([S]=[O]),OH1:0]-[#6:1]:,=[#6:2]-[OX2:3]-[H:4]",3,A
53
+ Enol,"[$([#6]=,:[#7,#8]),$(C#N),#7+1,$([S]=[O]),OH1:0]-[#6:1]:,=[#6:2]-[O-1:3]",3,B
54
+ Hydrocyanic acid,[N:0]#[C:1]-[H:2],1,A
55
+ Hydrocyanic acid,[N:0]#[C-1:1],1,B
56
+ Selenol,[SeX2:0]-[H:1],0,A
57
+ Selenol,[SeX1-1:0],0,B
@@ -0,0 +1,107 @@
1
+ Substructure,SMARTS,Index,Acid_or_base
2
+ Sulfate monoether,[SX4:0](=[O:1])(=[O:2])(-[O:3])-[OX2:4]-[H:5],4,A
3
+ Sulfate monoether,[SX4:0](=[O:1])(=[O:2])(-[O:3])-[O-1:4],4,B
4
+ Sulfonic acid,"[SX4:0](=[O:1])(=[O:2])(-[#6,#7:3])-[OX2:4]-[H:5]",4,A
5
+ Sulfonic acid,"[SX4:0](=[O:1])(=[O:2])(-[#6,#7:3])-[O-1:4]",4,B
6
+ Sulfinic acid,"[SX3:0](=[O:1])(-[#6,#7:2])-[OX2:3]-[H:4]",3,A
7
+ Sulfinic acid,"[SX3:0](=[O:1])(-[0#6,#7:2])-[O-1:3]",3,B
8
+ Seleninic acid,"[SeX3:0](=[O:1])(-[#6,#7:2])-[OX2:3]-[H:4]",3,A
9
+ Seleninic acid,"[SeX3:0](=[O:1])(-[#6,#7:2])-[O-1:3]",3,B
10
+ Selenenic acid,[SeX2:0]-[OX2:1]-[H:2],1,A
11
+ Selenenic acid,[SeX2:0]-[O-1:1],1,B
12
+ Arsonic acid,"[AsX4:0](=[O:1])(-[#6,#7:2])-[OX2:3]-[H:4]",3,A
13
+ Arsonic acid,"[AsX4:0](=[O:1])(-[#6,#7:2])-[O-1:3]",3,B
14
+ Thiosulfuric acid,[S:0]~[SX4:1](~[O:2])(~[O:3])-[O:4]-[H:5],4,A
15
+ Thiosulfuric acid,[S:0]~[SX4:1](~[O:2])(~[O:3])-[O-1:4],4,B
16
+ Phosph(o/i)nic acid,"[PX4:0](=[O:1])(-[OX2:2]-[H:5])(-[#1,#6,#7,#8:3])(-[#1,#6,#7,#8:4])",2,A
17
+ Phosph(o/i)nic acid,"[PX4:0](=[O:1])(-[O-1:2])(-[#1,#6,#7,#8:3])(-[#1,#6,#7,#8:4])",2,B
18
+ Phosphate (mono/di)ether,[PX4:0](=[O:1])(-[O:2])(-[O:3])-[OX2:4]-[H:5],4,A
19
+ Phosphate (mono/di)ether,[PX4:0](=[O:1])(-[O:2])(-[O:3])-[O-1:4],4,B
20
+ Carboxyl acid,"[$([#6]=[#8,#7]),$(C#N):0]-[OX2:1]-[H:2]",1,A
21
+ Carboxyl acid,"[$([#6]=[#8,#7]),$(C#N):0]-[O-1:1]",1,B
22
+ Carboxyl acid enol,[C:0]=[C:1](-[OX2:2]-[H:3])-[OX2:4]-[H:5],4,A
23
+ Carboxyl acid enol,[C:0]=[C:1](-[OX2:2]-[H:3])-[O-1:4],4,B
24
+ Carbo(di)thioic acid,"[CX3:0](=[O,S:1])-[SX2,OX2:2]-[H:3]",2,A
25
+ Carbo(di)thioic acid,"[CX3:0](=[O,S:1])-[S-1,O-1:2]",2,B
26
+ Carboxyl acid vinylogue ,[O:0]=[C:1]-[C:2]=[C:3]-[OX2:4]-[H:5],4,A
27
+ Carboxyl acid vinylogue,[O:0]=[C:1]-[C:2]=[C:3]-[O-1:4],4,B
28
+ Thiol/Thiophenol,"[#6,#7:0]-[SX2:1]-[H:2]",1,A
29
+ Thiol/Thiophenol,"[#6,#7:0]-[S-1:1]",1,B
30
+ Phenol,"[c,n:0]-[OX2:1]-[H:2]",1,A
31
+ Phenol,"[c,n:0]-[O-1:1]",1,B
32
+ Alcohol,"[$([CX4]-[$([#6]=,:[#7,#8]),$([#6]=,:[#6]-,:[#6]=,:[#7,#8]),$(C#N),O,#7+1,$(C-Cl),$(C#C),$(C-O),S:0]),$([CH2]-[#1,CH3]):0]-[OX2:1]-[H:2]",1,A
33
+ Alcohol,"[$([CX4]-[$([#6]=,:[#7,#8]),$([#6]=,:[#6]-,:[#6]=,:[#7,#8]),$(C#N),O,#7+1,$(C-Cl),$(C#C),$(C-O),S:0]),$([CH2]-[#1,CH3]):0]-[O-1:1]",1,B
34
+ Hydroxypyridine,[n:0]:[c:1]-[OH2+1:2]-[H:3],2,A
35
+ Hydroxypyridine,[n:0]:[c:1]-[OX2H1:2],2,B
36
+ Methylpyridine,[n:0](-[C:1]=[O:2]):[c:3]:[c:4]:[c:5]-[CX4:6]-[H:7],6,A
37
+ Methylpyridine,[n:0](-[C:1]=[O:2]):[c:3]:[c:4]:[c:5]-[CX3-1:6],6,B
38
+ Hydroperoxide/Hydroxyl amine,"[O,N:0]-[OX2:1]-[H:2]",1,A
39
+ Hydroperoxide/Hydroxyl amine,"[O,N:0]-[O-1:1]",1,B
40
+ Azole,"[#7:0]1(-[H:5])-,:[#7,#6:1]=,:[#7,#6:2]-,:[#7,#6:3]=,:[#7,#6:4]-,:1",0,A
41
+ Azole,"[#7-1:0]1-,:[#7,#6:1]=,:[#7,#6:2]-,:[#7,#6:3]=,:[#7,#6:4]-,:1",0,B
42
+ Aza-aromatics,[n:0]-[H:1],0,A
43
+ Aza-aromatics,"[n-1,n+0X2:0]",0,B
44
+ N-substitute aza-aromatics,[n+1:0]-[CX4:1]-[H:2],1,A
45
+ N-substitute aza-aromatics,[n+1:0]-[CX3-1:1],1,B
46
+ Oxime,"[$([#7]:,=[#6,#7]),$([#7]:,=[#6,#7]:,-[#6,#7]:,=[#6,#7]):0]-[OX2,NX3:1]-[H:2]",1,A
47
+ Oxime,"[$([#7]:,=[#6,#7]),$([#7]:,=[#6,#7]:,-[#6,#7]:,=[#6,#7]):0]-[O-1,NX2-1:1]",1,B
48
+ Amine,"[NX4+1:0](-[H:4])(-[CX4,c,#7,#8,#1,S,$(C=C),Cl:1])(-[CX4,c,#7,#8,#1,S,$(C=C):2])(-[CX4,c,#7,#8,#1,S,$(C=C):3])",0,A
49
+ Amine,"[NX3:0](-[CX4,c,#7,#8,#1,S,$(C=C),Cl:1])(-[CX4,c,#7,#8,#1,S,$(C=C):2])(-[CX4,c,#7,#8,#1,S,$(C=C):3])",0,B
50
+ Imine,"[#6,#7,P,S:0]=[NX3+1:1](-[H:2])",1,A
51
+ Imine,"[#6,#7,P,S:0]=[NX2:1]",1,B
52
+ Amide,"[$([#6]=,:[O,S,#7:0]),$([#7]=[#7,#8]),$([#6]:,=[#6]:,-[#7]=[#7,#8]),$(c:c:c:c:[#7+1]):0]-[NX3:1]-[H:2]",1,A
53
+ Amide,"[$([#6]=,:[O,S,#7:0]),$([#7]=[#7,#8]),$([#6]:,=[#6]:,-[#7]=[#7,#8]),$(c:c:c:c:[#7+1]):0]-[NX2-1:1]",1,B
54
+ Amide imine,"[$([#6]-,:[O,S,#7]),N+1:0]=,:[NX2:1]-[H:2]",1,A
55
+ Amide imine,"[$([#6]-,:[O,S,#7]),N+1:0]=,:[NX1-1:1]",1,B
56
+ Sulfamide,[SX4:0](=[O:1])(=[O:2])-[NX3:3]-[H:4],3,A
57
+ Sulfamide,[SX4:0](=[O:1])(=[O:2])-[NX2-1:3],3,B
58
+ Phosphamide,[PX4:0](=[O:1])-[NX3:2]-[H:3],2,A
59
+ Phosphamide,[PX4:0](=[O:1])-[NX2-1:2],2,B
60
+ Amide vinylogue,"[NX3:0](-[H:5])-,:[#6:1]=,:[#6:2]-,:[$([#6]=,:[#7,#8]),$(C#N):3]",0,A
61
+ Amide vinylogue,"[NX2-1:0]-,:[#6:1]=,:[#6:2]-,:[$([#6]=,:[#7,#8]),$(C#N):3]",0,B
62
+ Di Carbonyl βH,"[$([#6,#7]=,:[#7,#8]),$(C#N),$([#6]=,:[#6]-,:[$([#6]=,:[#7,#8]),$(C#N)]),$(P=O),$(S=O),S+1,Cl,F,O,c:0]-,:[#6X4:1](-[H:3])-,:[$([#6]=,:[#7,#8]),$(C#N),$(P=O),$(S=O):2]",1,A
63
+ Di Carbonyl βH,"[$([#6,#7]=,:[#7,#8]),$(C#N),$([#6]=,:[#6]-,:[$([#6]=,:[#7,#8]),$(C#N)]),$(P=O),$(S=O),S+1,Cl,F,O,c:0]-,:[#6X3-1:1]-,:[$([#6]=,:[#7,#8]),$(C#N),$(P=O),$(S=O):2]",1,B
64
+ Carbonyl βH,"[$([#6](=O)(-,:[#7+1,#6,#1])(-,:[#6,#1])),$([N](=O)(-O)),$(P=O),$(C=C-C(=O)-[#6,#1]):0]-,:[#6X4:1]-[H:2]",1,A
65
+ Carbonyl βH,"[$([#6](=O)(-,:[#7+1,#6,#1])(-,:[#6,#1])),$([N](=O)(-O)),$(P=O),$(C=C-C(=O)-[#6,#1]):0]-,:[#6X3-1:1]",1,B
66
+ Carbonyl allene,[O:0]=[C:1]-[C:2]=[C:3]=[CX3:4]-[H:5],4,A
67
+ Carbonyl allene,[O:0]=[C:1]-[C:2]=[C:3]=[CX2-1:4],4,B
68
+ Enol,"[$([#6]=,:[#7,#8]),$(C#N),#7+1,$([S]=[O]),c,$(C=C),OH1:0]-[#6:1]:,=[#6:2]-[OX2:3]-[H:4]",3,A
69
+ Enol,"[$([#6]=,:[#7,#8]),$(C#N),#7+1,$([S]=[O]),c,$(C=C),OH1:0]-[#6:1]:,=[#6:2]-[O-1:3]",3,B
70
+ Enol,"[#6:0]=[#6:1](-[$(C=O),$(C(=C)-[OH1]):2])-[OX2:3]-[H:4]",3,A
71
+ Enol,"[#6:0]=[#6:1](-[$(C=O),$(C(=C)-[OH1]):2])-[O-1:3]",3,B
72
+ Acyl group,"[#6:0](-[O,N:1])=[OX2+1:2]-[H:3]",2,A
73
+ Acyl group,"[#6:0](-[O,N:1])=[OX1:2]",2,B
74
+ Sulfoxide,[S+1:0](-[OX2:1]-[H:4])(-[#6:2])(-[#6:3]),1,A
75
+ Sulfoxide,[S+1:0](-[O-1:1])(-[#6:2])(-[#6:3]),1,B
76
+ Sulfoxide,[S:0](=[OX2+1:1]-[H:4])(-[#6:2])(-[#6:3]),1,A
77
+ Sulfoxide,[S:0](=[OX1:1])(-[#6:2])(-[#6:3]),1,B
78
+ Sulfoxide,[S:0](=[OX2+1:1]-[H:3])(=[#6:2]),1,A
79
+ Sulfoxide,[S:0](=[OX1:1])(=[#6:2]),1,B
80
+ Hydrocyanic acid,[N:0]#[C:1]-[H:2],1,A
81
+ Hydrocyanic acid,[N:0]#[C-1:1],1,B
82
+ Phosphoryl group,[PX4:0]=[OX2+1:1]-[H:3],1,A
83
+ Phosphoryl group,[PX4:0]=[OX1:1],1,B
84
+ Selenonyl group,[Se:0]=[OX2+1:1]-[H:3],1,A
85
+ Selenonyl group,[Se:0]=[OX1:1],1,B
86
+ Arsenyl group,[AsX4:0]=[OX2+1:1]-[H:2],1,A
87
+ Arsenyl group,[AsX4:0]=[OX1:1],1,B
88
+ Carboxyl group,"[#6X3:0](:,-[O,#7,S:1])=[OX2+1,SX2+1:2]-[H:3]",2,A
89
+ Carboxyl group,"[#6X3:0](:,-[O,#7,S:1])=[OX1,SX1:2]",2,B
90
+ Carboxyl group vinylogue,"[#6X3:0](:,-[#6:1]:,=[#6:2]:,-[O,#7,S:3])=[OX2+1,SX2+1:4]-[H:5]",4,A
91
+ Carboxyl group vinylogue,"[#6X3:0](:,-[#6:1]:,=[#6:2]:,-[O,#7,S:3])=[OX1,SX1:4]",4,B
92
+ Carbonyl group,"[#6X3:0](:,-[#1,#6:1])(:,-[#1,#6:2])=[OX2+1:3]-[H:4]",3,A
93
+ Carbonyl group,"[#6X3:0](:,-[#1,#6:1])(:,-[#1,#6:2])=[OX1:3]",3,B
94
+ Cyano group,[C:0]#[N:1]-[H:2],1,A
95
+ Cyano group,[C:0]#[NX1:1],1,B
96
+ Hydroxyl group,"[CX4:0](-[#6,#1:1])(-[#6,#1:2])(-[#6,#1:3])-[OH2+1:4]",4,A
97
+ Hydroxyl group,"[CX4:0](-[#6,#1:1])(-[#6,#1:2])(-[#6,#1:3])-[OX2:4]-[H:5]",4,B
98
+ Selenol,[SeX2:0]-[H:1],0,A
99
+ Selenol,[SeX1-1:0],0,B
100
+ Borate,[BX3:0]-[OX2:1]-[H:2],1,A
101
+ Borate,[BX3:0]-[O-1:1],1,B
102
+ Bromomethane,[Br:0]-[CH3:1]-[H:2],1,A
103
+ Bromomethane,[Br:0]-[CH2-1:1],1,B
104
+ Cyclopentadiene,"[#6X4:0](-[#1:5])1-,:[#6:1]=,:[#6:2]-,:[#6:3]=,:[#6:4]-,:1",0,A
105
+ Cyclopentadiene,"[#6X3-1:0]1-,:[#6:1]=,:[#6:2]-,:[#6:3]=,:[#6:4]-,:1",0,B
106
+ Tin alkyl,[N+:0]-[CX4:1](-[H:3])-[SnX4:2],1,A
107
+ Tin alkyl,[N+:0]-[CX3-1:1]-[SnX4:2],1,B
@@ -0,0 +1,119 @@
1
+ from xml.etree.ElementTree import Element,SubElement,Comment,tostring,parse
2
+ from xml.dom import minidom
3
+
4
+ count= 0
5
+ A= Element('reactive')
6
+
7
+ for (name, smarts) in [
8
+ ["4-Nitrophenyl Ester","[O-][N+](=O)c1ccc(OC=O)cc1"],
9
+ ["Acid Chloride","C(=O)Cl"],
10
+ ["Acid Bromide","C(=O)Br"],
11
+ ["Acid Iodide","C(=O)I"],
12
+ ["Acid Fluoride","C(=O)F"],
13
+ ["Acyl Cyanide","N#CC(=O)"],
14
+ ["Acyl hydrazine","NNC=O"],
15
+ ["Anhydride","C(=O)OC(=O)"],
16
+ ["Allyl Bromide","BrCC=C"],
17
+ ["Allyl Chloride","ClCC=C"],
18
+ ["Allyl Fluoride","FCC=C"],
19
+ ["Allyl iodide","ICC=C"],
20
+ ["Alpha_HaloCarbonyl","[F,Cl,Br,I]CC=O"],
21
+ ["Beta_HaloCarbonyl","[F,Cl,Br,I]CCC=O"],
22
+ ["Azide","N=[N+]=[N-]"],
23
+ ["Aziridine","C1CN1"],
24
+ ["Azo","[N;X2]=[N;X2]"],
25
+ ["Benzyl Bromide","[H]C([H])(Br)c"],
26
+ ["Benzyl Chloride","[H]C([H])(Cl)c"],
27
+ ["Benzyl Iodide","[H]C([H])(I)c"],
28
+ ["Beta ammonium carbonyl","C[N+](C)(C)CCC=O"],
29
+ ["Carbazide","O=*N=[N+]=[N-]"],
30
+ ["Carbodimide","N=C=N"],
31
+ ["Chloramine","[N;X3](Cl)"],
32
+ ["Chloro Silane","Cl[Si]"],
33
+ ["Cyanohydrin","N#CC[OH]"],
34
+ ["cyanamides","N[CH2]C#N"],
35
+ ["Cyanate","O=C=N"],
36
+ ["diazo","cN=Nc"],
37
+ ["Diazonium","[N+]#N"],
38
+ ["Dichloramine","[N;X3](Cl)Cl"],
39
+ ["Disulphide","SS"],
40
+ ["Epoxide","C1CO1"],
41
+ ["HaloAmine","[F,Cl,Br,I]N"],
42
+ ["Beta_HaloAmine","[F,Cl,Br,I]CCN"],
43
+ ["HaloMethylEther","[F,Cl,Br,I]C[OH0;X2]"],
44
+ ["HaloMethylThioEther","[F,Cl,Br,I]C[SH0;X2]"],
45
+ ["HydroxyBenzoylTriazole","C(=O)Onnn"],
46
+ ["Imidoyl Chloride","ClC=N"],
47
+ ["Imidoyl Bromide","BrC=N"],
48
+ ["Iodoso","I(=O)"],
49
+ ["Iodoxy","O=I=O"],
50
+ ["Isocyanate","N=C=O"],
51
+ ["Isothiocyanate","N=C=S"],
52
+ ["isonitriles","[N+]#[C-]"],
53
+ ["Ketene","C=C=O"],
54
+ ["Lawesson's_reagents","P(=S)(S)S"],
55
+ ["Nitroso","[N;X2]=O"],
56
+ ["Oxaziridine","C1NO1"],
57
+ ["Pentafluorophenyl Ester","Fc1c(F)c(F)c(OC=O)c(F)c1F"],
58
+ ["Peroxide","OO"],
59
+ ["Phosphine Chloride","PCl"],
60
+ ["Phosphine Bromide","PBr"],
61
+ ["Phosphine Fluoride","PF"],
62
+ ["Phosphine Iodide","PI"],
63
+ ["Cationic Br","[Br+]"],
64
+ ["Cationic Cl","[Cl+]"],
65
+ ["Cationic I","[I+]"],
66
+ ["Cationic O","[O+,o+]"],
67
+ ["Cationic P","[P+]"],
68
+ ["Cationic S","[S+]"],
69
+ ["Sulphonyl Chloride","S(=O)(=O)[Cl]"],
70
+ ["Sulphonyl Bromide","S(=O)(=O)[Br]"],
71
+ ["Sulphonyl Fluoride","S(=O)(=O)[F]"],
72
+ ["Sulphonate Ester","COS(c)(=O)=O"],
73
+ ["Sulphonyl Cyanide","S(=O)(=O)C#N"],
74
+ ["Thioacyl Chloride","C(=S)Cl"],
75
+ ["Thioacyl Bromide","C(=S)Br"],
76
+ ["Thio Halides","[S][Cl,Br,F,I]"],
77
+ ["Thiocyanate","SC#N"],
78
+ ["Triflate","OS(=O)(=O)C(F)(F)F"],
79
+ ["Vinylous Acid Chloride","ClC=CC=O"]
80
+ ]:
81
+ count += 1
82
+ entry= SubElement (A, 'group')
83
+ entry.set('name', '('+str(count)+') '+name)
84
+ node= SubElement(entry, "SMARTS")
85
+ node.text= smarts
86
+
87
+ with open('reactive-part1.xml','rt') as f :
88
+ treeA= parse(f)
89
+
90
+ with open('reactive-part2.xml','rt') as g :
91
+ treeB= parse(g)
92
+
93
+
94
+ for node in treeA.iter() :
95
+ if node.tag == 'SMART' :
96
+ smarts= node.text.strip()
97
+ if node.tag == 'name' :
98
+ name= node.text.strip()
99
+ count += 1
100
+ entry= SubElement (A, 'group')
101
+ entry.set('name', '('+str(count)+') '+name)
102
+ node= SubElement (entry, "SMARTS")
103
+ node.text= smarts
104
+
105
+ for node in treeB.iter() :
106
+ if node.tag == 'SMART' :
107
+ smarts= node.text.strip()
108
+ if node.tag == 'name' :
109
+ name= node.text.strip()
110
+ count += 1
111
+ entry= SubElement (A, 'group')
112
+ entry.set('name', '('+str(count)+') '+name)
113
+ node= SubElement (entry, "SMARTS")
114
+ node.text= smarts
115
+
116
+ g=open('reactive.xml','wt')
117
+ coarse= tostring(A,'utf-8')
118
+ g.write( minidom.parseString( coarse ).toprettyxml(indent=" ") )
119
+ g.close()
@@ -0,0 +1,104 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <SMARTPatterns>
3
+ <pattern active="true">
4
+ <SMART>[F,Cl,Br,I]-[SX4](=[OX1])(=[OX1])-[#6]</SMART>
5
+ <name>sulfonyl-alide</name>
6
+ <desc>sulfonyl-alide</desc>
7
+ </pattern>
8
+ <pattern active="true">
9
+ <SMART>[F,Cl,Br,I]-[CX3](=[OX1])-[#6]</SMART>
10
+ <name>acyl-halide</name>
11
+ <desc>acyl-halide</desc>
12
+ </pattern>
13
+ <pattern active="true">
14
+ <SMART>[F,Cl,Br,I]-[CX4H2]-[#6]</SMART>
15
+ <name>alkyl-halide</name>
16
+ <desc>alkyl-halide</desc>
17
+ </pattern>
18
+ <pattern active="true">
19
+ <SMART>[F,Cl,Br,I]-c1ncccn1</SMART>
20
+ <name>halopyrimidine</name>
21
+ <desc>halopyrimidine</desc>
22
+ </pattern>
23
+ <pattern active="true">
24
+ <SMART>[#6]-[CX3](=[OX1])-[OX2]-[CX3](=O)-[#6]</SMART>
25
+ <name>anhydride</name>
26
+ <desc>anhydride</desc>
27
+ </pattern>
28
+ <pattern active="true">
29
+ <SMART>[#6]-[CX3](=[OX1])-[CX3](=[OX1])-[#6]</SMART>
30
+ <name>1,2-dicarbonyl</name>
31
+ <desc>1,2-dicarbonyl</desc>
32
+ </pattern>
33
+ <pattern active="true">
34
+ <SMART>[F,Cl,Br,I]-[CX4]([F,Cl,Br,I])([F,Cl,Br,I])-[CX3](=[OX1])-[CX4H2]-[#6]</SMART>
35
+ <name>perhalo-ketone</name>
36
+ <desc>perhalo-ketone</desc>
37
+ </pattern>
38
+ <pattern active="true">
39
+ <SMART>[CH3]-[CX3](=[OX1])([CH2])-[#6]</SMART>
40
+ <name>aliphatic ketone</name>
41
+ <desc>aliphatic ketone</desc>
42
+ </pattern>
43
+ <pattern active="true">
44
+ <SMART>[#6]-[CX4]1-[OX2]-[CX4]1</SMART>
45
+ <name>epoxide</name>
46
+ <desc>epoxide</desc>
47
+ </pattern>
48
+ <pattern active="true">
49
+ <SMART>[#6]-[CX4]1-[NX3](-[#6])-[CX4]1-[#6]</SMART>
50
+ <name>aziridine</name>
51
+ <desc>aziridine</desc>
52
+ </pattern>
53
+ <pattern active="true">
54
+ <SMART>[#6]-[CX4H2]-[CX3](=[OX1])-[OX2]-[#6]</SMART>
55
+ <name>aliphatic ester</name>
56
+ <desc>aliphatic ester</desc>
57
+ </pattern>
58
+ <pattern active="true">
59
+ <SMART>[#6]-[CX4H2]-[CX3](=[OX1])-[SX2]-[#6]</SMART>
60
+ <name>aliphatic thioester</name>
61
+ <desc>aliphatic thioester</desc>
62
+ </pattern>
63
+ <pattern active="true">
64
+ <SMART>[#6]-[CX4H2]-[SX4](=[OX1])(=[OX1])-[OX2]-[#6]</SMART>
65
+ <name>sulphonate ester</name>
66
+ <desc>sulphonate ester</desc>
67
+ </pattern>
68
+ <pattern active="true">
69
+ <SMART>[#6]-[CX4H2]-[PX4](=[OX1])(-O)-[OX2]-[#6]</SMART>
70
+ <name>phosphonate ester</name>
71
+ <desc>phosphonate ester</desc>
72
+ </pattern>
73
+ <pattern active="true">
74
+ <SMART>[#6]-[CX4H2]-[CX3](=[NX2]-[#6])-[#6]</SMART>
75
+ <name>imine</name>
76
+ <desc>imine</desc>
77
+ </pattern>
78
+ <pattern active="true">
79
+ <SMART>[CX3H1](=[OX1])-[#6]</SMART>
80
+ <name>aldehyde</name>
81
+ <desc>aldehyde</desc>
82
+ </pattern>
83
+ <pattern active="true">
84
+ <SMART>[*]-[C](-[#1])=[C](-[#1,C])-[CX3](=O)-[#6]</SMART>
85
+ <name>Michael acceptor</name>
86
+ <desc>Michael acceptor</desc>
87
+ </pattern>
88
+ <pattern active="true">
89
+ <SMART>[*]-[CX4H1](-[F,Cl,Br,I])-[CX4H2]-[CX3](=O)-[#6]</SMART>
90
+ <name>b-heterosubstitued carbonyl</name>
91
+ <desc>b-heterosubstitued carbonyl</desc>
92
+ </pattern>
93
+ <pattern active="true">
94
+ <SMART>[#6]-[#7,#8,#16;X2]-[#7,#8,#16;X2]-[#6]</SMART>
95
+ <name>heteroatom-heteroatom single bonds</name>
96
+ <desc>heteroatom-heteroatom single bonds</desc>
97
+ </pattern>
98
+ <pattern active="true">
99
+ <SMART>[$([#16X4](=[OX1])(=[OX1])-[C](-[#1,C])=[C](-[#1,C])),$([#16X4+2]([OX1-])([OX1-])-[C](-[#1,C])=[C](-[#1,C]))]</SMART>
100
+ <name>vinyl sulfone</name>
101
+ <desc>vinyl sulfone</desc>
102
+ </pattern>
103
+ </SMARTPatterns>
104
+
@@ -0,0 +1,74 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <SMARTPatterns>
3
+ <pattern active="true">
4
+ <SMART>[*]-C(=[OX1])-[NH]-C(=[CH1]-*)-C(=[OX1])-[CH2]-[F,Cl,Br,I]</SMART>
5
+ <name>alpha-Haloketones</name>
6
+ <desc>alpha-Haloketones</desc>
7
+ </pattern>
8
+ <pattern active="true">
9
+ <SMART>[*]-C(=[OX1])-[NH]-C(=[CH1]-*)-[BX3](-[OX2]-[*,#1])-[OX2]-[*,#1]</SMART>
10
+ <name>boronic acids boronic esters</name>
11
+ <desc>boronic acids boronic esters</desc>
12
+ </pattern>
13
+ <pattern active="true">
14
+ <SMART>[*]-C(=[OX1])-[NH]-C(=[CH1]-*)-[CH1]=[OX1]</SMART>
15
+ <name>aldehydes</name>
16
+ <desc>aldehydes</desc>
17
+ </pattern>
18
+ <pattern active="true">
19
+ <SMART>[*]-C(=[OX1])-[NH]-C(=[CH1]-*)-C(=[OX1])-C(-F)(-F)F</SMART>
20
+ <name>TFMKs</name>
21
+ <desc>TFMKs</desc>
22
+ </pattern>
23
+ <pattern active="true">
24
+ <SMART>[*]-C(=[OX1])-[NH]-C(=[CH1]-*)-C(=[OX1])-C(=[OX1])-*</SMART>
25
+ <name>1,2-dicarbonyls</name>
26
+ <desc>1,2-dicarbonyls</desc>
27
+ </pattern>
28
+ <pattern active="true">
29
+ <SMART>[*]-C(=O)N-C(=C-*)c1cc2c(cc1)S(N(C2=O)*)(=O)=O</SMART>
30
+ <name>saccharinoids</name>
31
+ <desc>saccharinoids</desc>
32
+ </pattern>
33
+ <pattern active="true">
34
+ <SMART>[*]-C(=[OX1])-[NH]-C(=C-O-[P](=[OX1])(-[O-])-[O-])-C(=[OX1])-[NH]-*</SMART>
35
+ <name>phosphoryl-serine phosphoryl-threonine</name>
36
+ <desc>phosphoryl-serine phosphoryl-threonine</desc>
37
+ </pattern>
38
+ <pattern active="true">
39
+ <SMART>[*]-C(=[OX1])-[NH]-C(=C-c1ccc(-O-[PX4](=[OX1])(-[O-])-[O-])cc1)-C(=[OX1])-[NH]-*</SMART>
40
+ <name>phosphoryl-tyrosine</name>
41
+ <desc>phosphoryl-tyrosine</desc>
42
+ </pattern>
43
+ <pattern active="true">
44
+ <SMART>[*]-C(=[OX1])-[NH]-C(=C-c1ccc(-O-[PX4](=[OX1])(-[O-])-[OX2]-*)cc1)-C(=[OX1])-[NH]-*</SMART>
45
+ <name>phosphate esters as "in vitro prodrugs"</name>
46
+ <desc>phosphate esters as "in vitro prodrugs"</desc>
47
+ </pattern>
48
+ <pattern active="true">
49
+ <SMART>[*]-C(=[OX1])-[NH]-C(=C-c1ccc(-O-[*X4-3;!#6;!#7;!#8;!#9;!#15;!#16;!#17;!#34;!#35;!#53](=[OX1])(-[O-])-[O])cc1)-C(=[OX1])-[NH]-*</SMART>
50
+ <name>various metal substitutes for phosphorous</name>
51
+ <desc>various metal substitutes for phosphorous</desc>
52
+ </pattern>
53
+ <pattern active="true">
54
+ <SMART>[*]-C(=[OX1])-[NH]-C(=[CH1]-*)-C(=[OX1])-[NH]-[O-,OH]</SMART>
55
+ <name>Hydroxamates</name>
56
+ <desc>Hydroxamates</desc>
57
+ </pattern>
58
+ <pattern active="true">
59
+ <SMART>[*]-C(=[OX1])-[NH]-C(=[CH1]-[SH])-C(=[OX1])-[NH]-*</SMART>
60
+ <name>thiols</name>
61
+ <desc>thiols</desc>
62
+ </pattern>
63
+ <pattern active="true">
64
+ <SMART>[*]-C(=[OX1])-[NH]-C(=[CH1]-[SH])-C(=[OX1])-[NH]-[OH]</SMART>
65
+ <name>double trouble</name>
66
+ <desc>double trouble</desc>
67
+ </pattern>
68
+ <pattern active="true">
69
+ <SMART>[*]-C(=[OX1])-[NH]-C(=[CH1]-*)-C(=N-[OH])-*</SMART>
70
+ <name>oximes</name>
71
+ <desc>oximes</desc>
72
+ </pattern>
73
+ </SMARTPatterns>
74
+