CooPPS - A system for the Cooperative Prediction of Protein Structures

CooPPS is a system for the cooperative prediction of protein structures. It allows a suitable set of prediction tools to be chosen, out of a given set of available ones, so as to maximize the overall performances on the given prediction problem.
It works in three phases:
- Definition of the Application Domain; it is a set of proteins whose structure is known which define the domain of interest
- Team Building; in this phase, all the prediction tools are required to provide a prediction for the proteins in the Application Domain; each of them is evaluated and some precision measures are computed. Finally, the best team for the Application Domain is composed by considering the set of predictors best performing, cooperatively, on the Application Domain (The two phases above must be carried out only once until the user wants to change the application domain)
- Prediction; after the team is composed, CooPPS is able to predict proteins whose structure is not known. It first queries the predictors in the team for their predictions and, then, integrates their results by considering their accordance and their precision

For any question, please contact

Referencing this work, please cite:

L. Palopoli and G. Terracina, CooPPS: A System for the Cooperative Prediction of Protein Structures, Journal of Bioinformatics and Computational Biology, 2(3), 471-496, 2004

The code is made freely available for academic and non-commercial uses only.

To download and use CooPPS:

Click here for a Windows version (tested)

System requirements:

- Java Virtual Machine 1.4.1 ( )


Unzip the files and run CooPPS.exe

Click here for a platform independent version (not completely tested)

System requirements:

- Java virtual machine 1.4.1 ( )


- If you have installed java in the directory /java you must set the path to /java/bin

- Unzip the CooPPS files

- If you unzipped the CooPPS files in the directory /CooPPS, the classpath must contain the following entries:






- run java Show

We gratefully thank Francesco Strangio for his efforts in the software development