General schema of SNPranker 2.0 pipeline. The SNPranker 2.0 reference database collects data from various public data sources using a gene-centric design. This infrastructure represents the core of the SNPranker 2.0 pipeline, which starts with a list of genes (or a biological process or a list of SNPs) as input. If required, the ontological expansion retrieves all genes related to input ones according to a user defined similarity measure and threshold. SNPranker 2.0 performs the score computation using selected features and their corresponding weights, and a final table of SNPs is returned to users with a prioritization score for each SNP.
Merelli et al. BMC Bioinformatics 2013 14(Suppl 1):S9 doi:10.1186/1471-2105-14-S1-S9