Data set
|
A.U.C
|
---|
3_08_1506
|
79%
|
3_07_551
|
77%
|
3_06_116
|
76%
|
4_08_1226
|
76%
|
4_07_447
|
78%
|
4_06_102
|
77%
|
5_08_778
|
77%
|
5_07_280
|
77%
|
5_06_62
|
75%
|
6_08_544
|
76%
|
6_07_202
|
76%
|
6_06_62
|
76%
|
Li_849
|
76%
|
LiFlank_849
|
80%
|
- The AUC score is shown for each of the 14 PSWM sets when predicting operons using the positive and negative examples of operon members of E. coli. Data set nomenclature x_y_z refers to: x, Poisson distribution dimer significance threshold (-log10 P >) or Data set, y, Clustering threshold, and z, the number of clusters/PSWMs in data set (see also methods and text).