In order to use UMD Predictor you need to have a validated account or register.

UMD-Predictor is freely available for non-commercial users. Nevertheless it is not allowed to copy all or part of the database content without specific authorisation from us. If you are a commercial user please contact us to obtain a dedicated license.
For more information please contact Prof. Christophe Béroud or Dr. David Salgado
Login Register

UMD-Predictor: A mutation pathogenicity prediction system

With the development of Next Generation Sequencing technologies, the amount of data generated has reached an unprecedent level.

Approximately half of gene lesions responsible for human inherited diseases are due to an amino acid substitution. Distinguishing neutral sequence variations from those responsible for the phenotype is of major interest in human genetics.

To further differentiate neutral variants from pathogenic nucleotide substitutions, we developed a new tool, UMD-Predictor. This tool provides a combinatorial approach, to identify potential pathogenic variations, that associates the following data: localization within the protein, conservation, biochemical properties of the mutant and wild-type residues, and the potential impact of the variation on mRNA.

Privacy Guaranteed

As underlined by Pabinger et al, legal issues might arise when annotating lists of variants through on-line systems as they do not guarantee data confidentiality. To solve this issue, once batch analyses have been performed, corresponding files are automatically deleted from the UMD-Predictor system and no data are stored.

Get Started

Evaluate the pathogenicity of variations.



  • February 2016 - UMD-Predictor has been accepted for publication in the Human Mutation journal.
    Salgado, D., Desvignes, J.-P., Rai, G., Blanchard, A., Miltgen, M., Pinard, A., Lévy, N., Collod-Béroud, G. and Béroud, C. (2016),
    UMD-Predictor: a High Throughput Sequencing Compliant System for Pathogenicity Prediction of any Human cDNA Substitution. Human Mutation. Accepted Author Manuscript. doi:10.1002/humu.22965 More detail here