Skip to main content

AF2BIND for Binding Site Prediction

AF2BIND is a logistic regression model on top of AlphaFold embeddings that predicts the probability that each residue in a protein is in a pocket. Binding site prediction is the problem of detecting where (which residues) on a protein are likely to interact with other molecules. This is also called a binding pocket, pocket, functional site, or sometimes a hotspot. Not all parts of a protein can be easily bound, so identifying where likely sites are can help scientists understand what the function of an unknown protein is, avoid disrupting important sites when engineering a protein, and decide whether or not a candidate protein is a good drug target.

How to Use AF2BIND

Predict pockets in P08100

resip(bind)
2650.925
2680.8773
2120.8214
pocket1

Inputs

PDB File
A single chain protein structure.

Outputs

p(bind) Scores

For each residue in the input structure, a probability score of being in a pocket (0.0-1.0). Higher is better.

Examples

Predict binding pockets of P01889

resip(bind)
330.8715
1230.8211
310.7818
pocket2

Predict binding sites in P32883

resip(bind)
130.8182
150.8126
160.811
pocket3