Skip to main content
Figure 7 | BMC Bioinformatics

Figure 7

From: Integrating phenotype and gene expression data for predicting gene function

Figure 7

Recall. In contrast to recall, as the cutoff is increased, the recall decreases. Recall is defined as (tp)/(tp + fn) [16]. Since false negatives indicate negative predictions of known positive annotations, it is not surprising that the values would decrease as the cutoff is increased since that results in fewer predictions. The gene expression data set has the highest recall, but the integrated data set is only slightly lower. The generalized predictions have a better recall than the exact predictions. Figure 7a shows the results for the generalized predictions. Figure 7b shows the results for the exact predictions.

Back to article page