Protein Allosteric Sites Server


This tutorial shows the major functions of PASSer, helps to understand the requirements for the input data and explain the output results.


PASSer is a server to predict the probabilities of protein pockets being allosteric sites. For a given protein, FPocket[1] is used to detect potential pockets. For each pocket, physical properties are calculated and predicted using XGBoost[2]; while an atomic graph is constructed and fed into a graph convolutional neural network[3]. The final probability is given by averaging results from both models.

Input Data

Two options are provided for input. If there is an existing PDB ID in the Protein Data Bank, the user can enter the four-letter PDB ID. The user can also upload a customed PDB file which name ends with ".pdb". Please refer to this link to understand the PDB format.

A chain ID is needed if the user want to analyze specific chain, and is also recommended. The chain ID can be either single letter, such as "A", or multiple letters separated with comma, such as "A,B". Please notice that there is no space between comma and chain ID. The chain ID can be left blank. If so, all chains in the PDB file will be used in calculation and analysis.

Output Results

The result page shows the top three pockets that are most likely to be allosteric sites with corresponding predicted probabilities. A result table is provided to show the residues in each pocket. Click "Show Residues" to see those residues and click again to close the popup window. A link is provided to download the full reports generated by FPocket.

Pocket Number Probability Residues
1 89.65% Show Residues
2 20.23% Show Residues
3 16.84% Show Residues

The user can interact with the protein in the window powered by JSmol. The complete tutorial of JSmol can be found here. Top 3 pockets are colored as red, orange and gold. Pockets can be seen upon clicking "Load Pocket" button. To hide pockets, the user can either click "Hide Pocket" for specific pocket or "Reset" to hide all currently shown pockets.


Video Example

A short video describing the basic usage of this server is shown below:


1. Le Guilloux, V., Schmidtke, P. and Tuffery, P., 2009. Fpocket: an open source platform for ligand pocket detection. BMC bioinformatics, 10(1), pp.1-11.
2. Chen, T. and Guestrin, C., 2016, August. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
3. Kipf, T.N. and Welling, M., 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.