Discrimination of single and multiple human transmembrane proteins using kurtosis and morphological analysis

The identification of transmembrane segments in protein sequences is an important issue in the field of bioinformatics. In this study a method is proposed for the discrimination between proteins with single and multiple transmembrane segments, combining chemical and statistical features of the proteins with higher-order statistics and morphological analysis for protein categorisation. The method was tested on human proteins, extracted from public available databases and the results have shown an efficiency of the proposed algorithm to correctly classify the sequences under study into two classes, for a wide range of transmembrane segment lengths. This paves the way for a more efficient analysis of transmembrane proteins taking into account the individual features and patterns occurring within proteins with single and multiple transmembrane segments.