MOTIVATION: Previous studies have shown that accounting for sitespecific amino acid replacement patterns using mixtures of stationary probability profiles offers a promising approach for improving the robustness of phylogenetic reconstructions in the presence of saturation. However, such profile mixture models were introduced only in a Bayesian context, and are not yet available in a Maximum Likelihood framework. In addition, these mixture models only perform well on large alignments, from which they can reliably learn the shapes of profiles, and their associated weights. RESULTS: In this work, we introduce an expectation-maximization algorithm for estimating amino-acid profile mixtures from alignment databases. We apply it, learning on the HSSP database, and observe that a set of 20 profiles is enough to provide a better statistical fit than currently available empirical matrices (WAG, JTT), in particular on saturated data. AVAILABILITY: We have implemented these models into two currently available Bayesian and Maximum Likelihood phylogenetic reconstruction programs. The two implementations, PhyloBayes, and PhyML, are freely available on our web site (http://atgc.lirmm.fr/cat). They run under Linux and MaxOSX operating systems. CONTACT: nicolas.lartillot@lirmm.fr