In the last few years, the increasing automation applied to Biology processes has led to a fast accumulation of im- portant biological data. The wide biological implications present in these data makes its analysis unsuitable via con- ventional computing. In this context, Machine Learning (ML) techniques have been showing very promising. One of the ML techniques for analyzing these data is cluster- ing methods. Experimental studies have shown that, often, clusters generated via such methods are biologically mean- ingful. However, in general, the interpretation of the bio- logical meaning of the clusters formed is a very complex task. Thus, this paper invests its efforts in the study of tech- niques that makes the interpretation of clusters formed by clustering techniques more straightforward. In order to do so, unsupervisedML techniques (clustering techniques) will be associated with supervised ML techniques (rule genera- tion). The goal is to generate symbolic structures, such as IF-THEN rules, which are more comprehensible for humans