Skip to main content
. 2013 Jun 19;29(13):i217–i226. doi: 10.1093/bioinformatics/btt245

Table 5.

Pairwise model performance of MTPL

Pairwise tasks F1
Task-1, Task-2 Task-1 Task-2
B.anthracis, F.tularensis 31.4 30.1
B.anthracis, S.typhi 32 76.3
B. anthracis, Y.pestis 31.6 32
F.tularensis, S.typhi 30.3 73
F.tularensis, Y.pestis 30 32.1
S.typhi, Y.pestis 74.2 32.3

Note: F1 computed during 10-fold CV of various pairwise models from MTPL. Positive: negative class ratio was 1:100. The best F1 achieved for each task (i.e. for each bacterial species) is shown in bold. For example, B.anthracis has the best performance of 32 when it is coupled with S.typhi.