Disease gene prioritization through semi-supervised transductive methods
Disease gene prioritization is the process of ranking genes with respect of their likelihood to be involved in specific disorders.
We propose novel methods to rank genes with respect to Cancer Modules (CMs), that is sets of genes coordinately under or overexpressed in cancer diseases obtained from the Molecular Signatures Database (Re and Valentini 2011).
We used both protein-protein and domain-domain interaction networks enforced through the predictions of a classifier, and functional interaction networks constructed with comparative genomics techniques to rank genes with respect to CMs, by applying classical random walk techniques (Re and Valentini, 2012), label propagation algorithms and kernelized score functions (Re and Valentini, 2012). In particular kernelized score functions compare favorably to state-of-the-art semi-supervised machine learning methods, both in terms of average AUC and precision at a fixed recall (Re and Valentini, 2012).
We showed also that the integration of multiple sources of information plays a key role to improve the performance of methods for gene prioritization, by exploiting a large analysis of gene - disease associations over more than 700 diseases, using both unweighted and weighted network integration methods (Valentini et al., 2014).
G. Valentini, A. Paccanaro, H. Caniza, A. Romero, M. Re, An extensive analysis of disease-gene associations using network integration and fast kernel-based gene prioritization methods, Artificial Intelligence in Medicine, 2014 (accepted for publication)
M. Re and G. Valentini Cancer module genes ranking using kernelized score functions
BMC Bioinformatics 13 (Suppl 14): S3, 2012.
M. Re and G. Valentini Random walking on functional interaction networks to rank genes involved in cancer
2nd Artificial Intelligence Applications in Biomedicine Workshop, in: AIAI 2012 - Artificial Intelligence Applications and Innovations, pp. 66-75, IFIP AICT Series, Springer, 2012
M. Re, G. Valentini Genes prioritization with respect to Cancer Gene Modules using functional interaction network data , NETTAB 2011 Workshop on Clinical Bioinformatics, Pavia 12-14 October, 2011.