Welcome to the updated version of Pmut (Beta), you can find the old version here.

Predict the pathology of mutations

Enter a list of mutations on any protein or sequence, and find out their pathology score using PMut predictor.

Analyze mutations »

Do you have lots of mutations? Submit a batch analysis!

If you want to predict lots of mutations on different proteins, you can submit a batch query.

Browse our repository

We have a repository of 725,596,928 variants on 106,407 proteins that have been analyzed and are predicted to be either pathological or neutral.

e.g. BRCA2, 2vgb, ENSG00000133110, Q04917

Train your own predictor

Train a specific predictor using your own annotated variants and get more precise predictions for your research.

Train custom predictor »

Server status

19 queued jobs

0 running jobs

2850 completed jobs

725,596,928 variants

  106,407 proteins

25 registered users

V. López-Ferrando, A. Gazzo, X. de la Cruz, M. Orozco, J.L. Gelpí;
PMut: a web-based tool for the annotation of pathological variants on proteins, 2017 update.
Nucleic Acids Research 2017.
PubMed   DOI
Download PyMut to work locally
The PyMut Python module brings all the PMut funtionality to your computer, allowing you to customize and tinker the machine learning process. Check the PyMut tutorial as an example of how to use it.
If you have any question or request about this service, contact us at pmut@mmb.irbbarcelona.org