We are interested in developing and optimising computational approaches and construct novel combinations of mature methodologies.
SpotON implements a robust algorithm with a demonstrated accuracy of 0.95 and sensitivity of 0.98 on an independent test set. The predictor was developed using an ensemble machine learning approach with up-sampling of the minor class. It was trained on 53 complexes using various features, based on both protein 3D structure and sequence.
The web-server is available at http://milou.science.uu.nl/cgi/services/SPOTON/spoton/.
SASA-Based Hot-spot Detection method is a support vector machine learning (SVM) algorithm that determines the binding Hot-Spots at protein-protein and protein-DNA interfaces. A user friendly server is available at http://bio-aims.udc.es/MolStructPred.php.
Computational Alanine Scanning Mutagenesis presents here as a very intuitive plug-in for two widely distributed software (AMBER and Visual Molecular Dynamics – VMD) that allows the user to perform a full Alanine Scanning Mutagenesis (ASM) procedure, requiring only very little user effort. It is composed of two main packages: the Core and Graphical User Interface (GUI). Developed by Dr. João Ribeiro et al. in Theoretical and Computational Biochemistry Research Group from Prof. Maria Ramos.
The web-server is available at http://compbiochem.org/Software/compasm/Home.html.