Supervised approaches for function prediction of proteins contact networks from topological structure information
The role performed by a protein is directly connected to its physico-chemical structure. How the latter affects the behaviour of these molecules is still an open research topic. In this paper we consider a subset of the Escherichia Coli proteome where each protein is represented through the spectral characteristics of its residue contact network and its physiological function is encoded by a suitable class label. By casting this problem as a machine learning task, we aim at assessing whether a relation exists between such spectral properties and the protein’s function. To this end we adopted a set of supervised learning techniques, possibly optimised by means of genetic algorithms. First results are promising and they show that such high-level spectral representation contains enough information in order to discriminate among functional classes. Our experiments pave the way for further research and analysis.