In this paper we propose an automatic protein family expansion approach for recruitment of new members among the protein-coding genes in newly sequenced genomes. The criteria for adding a new member to a family depends on the structure of each individual family versus being globally uniform. The detection of a threshold in the ROC space of all sorted iterative profile sets defines the alignments selection criteria for each family. Furthermore, the statistical estimation of most-frequent optimal sorting criteria generates the optimal filtering strategy in a learning-parameter set for profile-based homology search.