SIFTER Protein Function Prediction

Phylogeny-based Protein Function Prediction

SIFTER (Statistical Inference of Function Through Evolutionary Relationships) is a statistical approach to predicting protein function that uses a protein family's phylogenetic tree, as the natural structure for representing protein relationships.

Run SIFTER on your local machine:

SIFTER Pipeline:

You can access the user-friendly pipeline for large-scale protein function prediction using the SIFTER algorithm at the SIFTER GitHub page.

You can download the data required for the pipeline from the following links:

SQL database [34GB]
Pfam families data [25GB]

SIFTER core code:

You can download SIFTER code v2.1.1 here. An older version, v2.0, is also available here.

Complexity Estimation (How long SIFTER will take to run on a local machine):

Learn how long you can expect SIFTER to run on a local machine for your specific input here.

Pre-computed SIFTER Webserver predictions:

Data and scripts for querying the precomputed predictions are available here [27 GB].