Back to catalogue >>

Reference: Capriotti E., Calabrese R., Casadio R. Predicting the insurgence of human genetic diseases associated to single point protein mutations with support vector machines and evolutionary information. Bioinformatics.(2006) 22 (22) 2729-2734.
Hosted: The Biocomputing group at the University of Bologna. (http://gpcr2.biocomp.unibo.it/cgi/predictors/PhD-SNP/PhD-SNP.cgi)

Summary:
PhD-SNP uses a combination of support vector machines (SVMs) trained on different sequence and evolutionary information to predict variant pathogenicity.

Methodology:
The SVMs used are:
• SVM-sequence: classifies disease-related and neutral SNPs from the sequence change in association with local sequence environment.
• SVM-profile: This classifies SNPs based on a sequence profile in an alignment with BLAST hits.

Input:
• The user needs to provide the protein sequence or alternatively its Swiss-Prot code.
• Either the sequence-based SVM, the sequence and profile-based SVM or a hybrid method (as implemented in an older version of PhD-SNP) must be selected.
• The user can also choose to perform a 20-fold cross validation prediction.