In this study protein sequences are assigned to functional families using machine learning techniques. The assignment is based on support vector machine classification of binary feature vectors denoting the presence or absence in the protein of highly conserved sequences of amino-acids called motifs. Since the input vectors of the classifier consist of a great number of motifs, feature selection algorithms are applied in order to select the most discriminative ones. Three selection algorithms, embedded within the support vector machine architecture, were considered. The embedded algorithms apart from presenting computational efficiency allowed for ranking the selected features. The experimental evaluation demonstrated the usefulness of the aforementioned approach, whereas the individual ranking for the three selection algorithms presented significant agreement.