Ricerc@Sapienza

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.

This paper investigates a novel graph embedding procedure based on simplicial complexes. Inherited from algebraic topology, simplicial complexes are collections of increasing-order simplices (e.g., points, lines, triangles, tetrahedrons) which can be interpreted as possibly meaningful substructures (i.e., information granules) on the top of which an embedding space can be built by means of symbolic histograms. In the embedding space, any Euclidean pattern recognition system can be used, possibly equipped with feature selection capabilities in order to select the most informative symbols.

Multiple kernel learning is a paradigm which employs a properly constructed chain of kernel functions able to simultaneously analyse different data or different representations of the same data. In this paper, we propose an hybrid classification system based on a linear combination of multiple kernels defined over multiple dissimilarity spaces. The core of the training procedure is the joint optimisation of kernel weights and representatives selection in the dissimilarity spaces.