Data
|
Classifier
|
Bond
| |
Top-3%
| |
Top-2%
|
---|
set
| |
depth
| |
TS1
|
TS2
| |
TS1
|
TS2
|
---|
2C9
|
PRW
|
5
| |
85
|
85
| |
82
|
85
|
6
| |
83
|
85
| |
81
|
85
|
RASCAL
|
5
| |
85
|
85
| |
78
|
85
|
6
| |
81
|
85
| |
77
|
85
|
2D6
|
PRW
|
5
| |
90
|
92
| |
85
|
75
|
6
| |
91
|
94
| |
86
|
79
|
RASCAL
|
5
| |
90
|
90
| |
84
|
75
|
6
| |
87
|
88
| |
84
|
83
|
3A4
|
PRW
|
5
| |
83
|
82
| |
80
|
78
|
6
| |
84
|
81
| |
80
|
79
|
RASCAL
|
5
| |
80
|
76
| |
76
|
67
|
6
| |
79
|
75
| |
72
|
63
|
- Table shows the classification performance in terms of top-2% and top-3% for test set 1 (TS1: 20% of each isoform data set selected at random) and test set 2 (TS2: the 50% of molecules in TS1 most dissimilar to the training data).