Fold Assessment Software



General Description

This web site contains a fold assessment software that relies on the GA341 multivariate scoring function. A benchmark of the performance of this scoring function in fold assessment has been recently described (Melo and Sali, 2007).

The general working pipeline of this scoring function is shown in Figure 1. The GA341 scoring function depends on three independent variables: 1) The compactness of the model, 2) a combined statistical potential z-score of the model, and 3) the percentage sequence identity of the target-template alignment that was used to build the model.





Figure 1: Fold assessment scheme.

The GA341 score depends on three variables: the percentage sequence identity is calculated from the alignment that was used to build the model, while the compactness (Methods) and the combined statistical potential z-score (Melo et al. 2002) are calculated from the 3D model itself. Next, the length of the model and the GA341 score are plugged into a naive Bayesian classifier to obtain the conditional probability that the model is correct, pC(GA341, length). Typically, pC of at least 0.7 predicts that the model is correct; otherwise it is classified as incorrect.

The software is distributed as a bunch of executable programs for LINUX OS. The programs can be easily integrated with a simple script. The software is distributed with no warranties and it is responsibility of the user how the software is used and how the results are interpreted.



Raw data


File name


File format

General description



Binary files

This archive contains all the executable programs for LINUX OS and the required data libraries.


Help file

Plain text

README file that explains how to run each program and what each program does.






Melo, F. and Sali, A. (2007)
Fold Assessment for Comparative Protein Structure Modeling.
Protein Science 16, 2412-2426.

Melo, F., Sánchez, R., and Sali, A. (2002)
Statistical potentials for fold assessment.
Protein Science 11, 430-448.

Sali, A., Fiser, A., Sanchez, R., Marti-Renom, M.A., Jerkovic, B., Badretdinov, A., Melo, F., Overington, J., and Feyfant, E. (2001).

MODELLER, A Protein Structure Modeling Program, Release 6v0.