Abstract
Background
Proteins are generally composed of one or more functional regions, which are called domains. These regions are independent folding units and can evolve, function, and exist independently of the rest of the protein chain.
Motivation
In this paper we describe using HMM to model the Kunitz domain. This model will be later validated and compared with the automatically curated Pfam database to understand benefits of manual model building.
Results
Regarding the comparison with the Pfam database model of a relatively good quality was built with the sensitivity of 0.994, specificity of 1, 0.927 precision and accuracy of almost 1.