An extensive analysis of disease-gene associations using network integration and fast kernel-based gene prioritization methods
Conclusions: Network integration is necessary to boost the performances of gene prioritization methods. Moreover the methods based on kernelized score functions can further enhance disease gene ranking results, by adopting both local and global learning strategies, able to exploit the overall topology of the network.
Source: Artificial Intelligence in Medicine - Category: Bioinformatics Authors: Giorgio Valentini, Alberto Paccanaro, Horacio Caniza, Alfonso E. Romero, Matteo Re Tags: Research Articles Source Type: research