Chemistry Reference
In-Depth Information
b
a
1
curve
S
3
S
2
Inactives
Se
Actives
S
1
FN
FP
0
Score
Threshold S
3
Threshold S
2
Threshold S
1
1-Sp
1
Fig. 6 (a) A theoretical distribution of compounds in a virtual screen based upon the docking
score. The overlap between active and inactive compounds indicates that the scoring threshold
used to identify a hit by virtual screening is critical. (b) A ROC curve is used to evaluate the
enrichment of a virtual screen and select a scoring threshold. A ROC curve that approaches
Se
¼
1
and 1-
Sp
0 represents perfect enrichment. The area under the ROC curve (AUC) represents the
probability that a true active is identified. (Reprinted with permission from [
131
], copyright 2008
by Springer)
¼
Specificity is the measure of the true negative rate, which represents the ratio of
true negatives (
TN
) to the total number of inactive compounds. The number of
inactive compounds corresponds to both true negatives (
TN
) and false positives (
FP
):
TN
TN
Sp
¼
FP
:
(6)
þ
The enrichment factor is a common method for evaluating the enrichment
capabilities of a virtual screen:
TP
þ
FP
TP
þ
FN
TP
N
tot
:
EF
¼
(7)
The enrichment factor is dependent upon the ratio of active compounds to
the total number of compounds in the library. As a result, enrichment scores are
difficult to compare between virtual screens with different libraries. Also, the
enrichment factor does not distinguish between high and low ranking compounds.
Perhaps the more popular approach for evaluating enrichment is to generate
a receiver operating characteristic (ROC) curve [
133
]. The ROC curve is a plot of
the true positive rate (
Se
) against the false positive rate (1
Sp
) at varying thresholds
for determining a hit. A ROC curve allows for the evaluation of a virtual screening
method without using an arbitrary scoring threshold. Enrichment occurs when the
resulting data point at a particular threshold resides above the diagonal (
Se
¼
1
Sp
), which corresponds to a random selection of compounds. In a perfect virtual
