Figure 12
From: EVEREST: automatic identification and classification of protein domains in all protein sequences
Performance of the regression function in iteration 1. Data points correspond to a random set of ~13,000 of the clusters created in step 5 of iteration 1 of EVEREST release 1, and intersecting with Pfam. x-axis: score of the cluster according to Pfam. y-axis: score of cluster according to the regression function learned in step 6 of iteration 1. See section Evaluating a Suggested Domain Family for the definition of a domain family score.