|
A set of 42 molecules is stored in the sub-directory 'molecules' of the zip file that can be downloaded here: http://www.talete.mi.it/products/dragon_data.zip. This set of molecules is provided in different multiple structure files generated by different chemical drawing softwares :
.cml (Chemical Markup Language)
.hin (HyperChem)
.mmd (MacroModel)
.mol (Trypos)
.mol2 (Trypos)
.sdf (MDL)
.smi (SMILES)
In the same directory the file 42_molecules_external_variables.txt is also provided. In this file there are three physico-chemical properties (melting point, boiling point and logP) and 2 categorical variables (ClassA and ClassB) of the 42 molecules. The list of the 42 molecules and their properties is shown below.
ID
|
Filename
|
Name
|
mp
|
bp
|
logP
|
ClassA
|
ClassB
|
1
|
M01.hin
|
methane
|
-182.4
|
-161.5
|
1.09
|
alkanes
|
acyclic
|
2
|
M02.hin
|
ethane
|
-182.8
|
-88.6
|
1.81
|
alkanes
|
acyclic
|
3
|
M03.hin
|
propane
|
-187.6
|
-42.1
|
2.36
|
alkanes
|
acyclic
|
4
|
M04.hin
|
n-butane
|
-138.2
|
-0.5
|
2.89
|
alkanes
|
acyclic
|
5
|
M05.hin
|
n-pentane
|
-129.7
|
36.0
|
3.39
|
alkanes
|
acyclic
|
6
|
M06.hin
|
n-hexane
|
-95.3
|
68.7
|
3.90
|
alkanes
|
acyclic
|
7
|
M07.hin
|
isobutane
|
-138.3
|
-11.7
|
2.76
|
alkanes
|
acyclic
|
8
|
M08.hin
|
neopentane
|
-16.6
|
9.4
|
3.11
|
alkanes
|
acyclic
|
9
|
M09.hin
|
2-methylpentane
|
-153.7
|
60.2
|
3.21
|
alkanes
|
acyclic
|
10
|
M10.hin
|
cis-2-butene
|
-105.5
|
0.8
|
2.33
|
unsatured
|
acyclic
|
11
|
M11.hin
|
trans-2-butene
|
-105.5
|
0.8
|
2.33
|
unsatured
|
acyclic
|
12
|
M12.hin
|
2-butyne
|
-32.3
|
26.9
|
1.46
|
unsatured
|
acyclic
|
13
|
M13.hin
|
cyclopropane
|
-127.4
|
-32.8
|
1.72
|
cycloalkanes
|
cyclic
|
14
|
M14.hin
|
cyclobutane
|
-90.6
|
12.6
|
2.19
|
cycloalkanes
|
cyclic
|
15
|
M15.hin
|
cyclopentane
|
-93.8
|
49.3
|
3.00
|
cycloalkanes
|
cyclic
|
16
|
M16.hin
|
cyclohexane
|
6.6
|
80.7
|
3.44
|
cycloalkanes
|
cyclic
|
17
|
M17.hin
|
cyclohexanone
|
-31.0
|
155.4
|
0.81
|
ketones
|
cyclic
|
18
|
M18.hin
|
benzene
|
5.5
|
80.0
|
2.13
|
aromatics
|
cyclic
|
19
|
M19.hin
|
toluene
|
-94.9
|
110.6
|
2.73
|
aromatics
|
cyclic
|
20
|
M20.hin
|
phenol
|
40.9
|
181.8
|
1.46
|
aromatics
|
cyclic
|
21
|
M21.hin
|
benzoic acid
|
122.4
|
249.2
|
1.87
|
aromatics
|
cyclic
|
22
|
M22.hin
|
aniline
|
-6.0
|
184.1
|
0.90
|
aromatics
|
cyclic
|
23
|
M23.hin
|
nitrobenzene
|
5.7
|
210.8
|
1.85
|
aromatics
|
cyclic
|
24
|
M24.hin
|
fluorobenzene
|
-42.2
|
84.7
|
2.27
|
aromatics
|
cyclic
|
25
|
M25.hin
|
chlorobenzene
|
-45.2
|
131.7
|
2.84
|
aromatics
|
cyclic
|
26
|
M26.hin
|
bromobenzene
|
-30.6
|
156.0
|
2.99
|
aromatics
|
cyclic
|
27
|
M27.hin
|
iodobenzene
|
-31.3
|
188.4
|
3.25
|
aromatics
|
cyclic
|
28
|
M28.hin
|
benzamide
|
129.1
|
290.0
|
0.64
|
aromatics
|
cyclic
|
29
|
M29.hin
|
naphthalene
|
80.2
|
217.9
|
3.30
|
aromatics
|
cyclic
|
30
|
M30.hin
|
anthracene
|
215.0
|
339.9
|
4.45
|
aromatics
|
cyclic
|
31
|
M31.hin
|
pyrrole
|
-23.4
|
129.7
|
0.75
|
heterocyclics
|
cyclic
|
32
|
M32.hin
|
furan
|
-85.6
|
31.5
|
1.34
|
heterocyclics
|
cyclic
|
33
|
M33.hin
|
thiophene
|
-39.4
|
84.0
|
1.81
|
heterocyclics
|
cyclic
|
34
|
M34.hin
|
purine
|
216.5
|
344.5
|
-0.37
|
heterocyclics
|
cyclic
|
35
|
M35hin
|
dibenzofuran
|
86.5
|
287.0
|
4.17
|
heterocyclics
|
cyclic
|
36
|
M36.hin
|
ethanol
|
-114.1
|
78.2
|
-0.31
|
alcohols
|
acyclic
|
37
|
M37.hin
|
trifluoro-ethanol
|
-43.5
|
74.0
|
0.41
|
alcohols
|
acyclic
|
38
|
M38.hin
|
2-amino-ethanol
|
10.5
|
171.0
|
-1.31
|
alcohols
|
acyclic
|
39
|
M39.hin
|
1-propanol
|
-126.1
|
97.2
|
0.25
|
alcohols
|
acyclic
|
40
|
M40.hin
|
2-propanone
|
-98.3
|
55.5
|
-0.24
|
ketones
|
acyclic
|
41
|
M41.hin
|
2-propanol
|
-89.5
|
82.3
|
0.05
|
alcohols
|
acyclic
|
42
|
M42.hin
|
2-propylamine
|
-95.1
|
31.7
|
0.26
|
amines
|
acyclic
|
|