This article introduces SVMcon, a new contact map predictor that uses support vector machines (SVMs) to predict medium- and long-range protein residue-residue contacts. SVMcon integrates a large set of informative features, including profiles, secondary structure, relative solvent accessibility, contact potentials, and other useful features. The method outperforms the latest version of the CMAPpro contact map predictor by 4% in accuracy on the same test dataset. In the seventh edition of the Critical Assessment of Techniques for Protein Structure Prediction (CASP7) experiment, SVMcon was ranked as one of the top predictors, yielding the second best coverage and accuracy for contacts with sequence separation >= 12 on 13 de novo domains. The authors conclude that SVMcon is a promising method for improving contact map predictions and can be modularly incorporated into a structure prediction pipeline.This article introduces SVMcon, a new contact map predictor that uses support vector machines (SVMs) to predict medium- and long-range protein residue-residue contacts. SVMcon integrates a large set of informative features, including profiles, secondary structure, relative solvent accessibility, contact potentials, and other useful features. The method outperforms the latest version of the CMAPpro contact map predictor by 4% in accuracy on the same test dataset. In the seventh edition of the Critical Assessment of Techniques for Protein Structure Prediction (CASP7) experiment, SVMcon was ranked as one of the top predictors, yielding the second best coverage and accuracy for contacts with sequence separation >= 12 on 13 de novo domains. The authors conclude that SVMcon is a promising method for improving contact map predictions and can be modularly incorporated into a structure prediction pipeline.