Protein structure modeling can be improved by the use of distance constraints between amino acid residues, provided such data reflects—at least partially—the native tertiary structure of the target system. In fact, only a small subset of the native contact map is necessary to successfully drive the model conformational search, so one important goal is to obtain the set of constraints with the highest true-positive rate, lowest redundancy and greatest amount of information. In this work, we introduce a constraint evaluation and selection method based on the point-biserial correlation coefficient, which utilizes structural information from an ensemble of models to indirectly measure the power of each constraint in biasing the conformational search toward consensus structures.


Residue contact maps obtained by direct coupling analysis are systematically improved by means of discriminant analysis, reaching in some cases accuracies often seen only in modern deep-learning-based approaches. When combined with an iterative modeling workflow, the proposed constraint classification optimizes the selection of the constraint set and maximizes the probability of obtaining successful models. The use of discriminant analysis for the valorization of the information of constraint datasets is a general concept with possible applications to other constraint types and modeling problems.

Availability and implementation

MSA for the targets in this work is available on Modeling data supporting the findings of this study was generated at the Center for Computing in Engineering and Sciences, and is available from the corresponding author LM on request.

Supplementary information

Supplementary data are available at Bioinformatics online.

This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model (