Microsporidia are obligate intracellular parasites infesting many animal groups. Lacking mitochondria and peroxysomes, these unicellular eukaryotes were first considered a deeply branching protist lineage that diverged before the endosymbiotic event that led to mitochondria. The discovery of a gene for a mitochondrial-type chaperone combined with molecular… (More)
To tackle segmentation problems on biological sequences, we advocate the use of a hybrid architecture combining discriminant and generative models in the framework of a hierarchical approach. Multi-class support vector machines and neural networks provide a set of initial predictions. These predictions are post-processed by classifiers estimating the class… (More)
Support vector machines, let them be bi-class or multi-class, have proved efficient for protein secondary structure prediction. They can be used either as sequence-to-structure classifier, structure-to-structure classifier, or both. Compared to the classifier most commonly found in the main prediction methods, the multi-layer perceptron, they exhibit one… (More)
Most of the state-of-the-art methods for protein seconday structure prediction are complex combinations of discriminant models. They apply a local approach of the prediction which is known to induce a limit on the expected prediction accuracy. A priori, the use of generative models should make it possible to overcome this limitation. However, among the… (More)
Prédiction de la structure secondaire des protéines : mise en oeuvre optimisée de l'architecture en cascade Mots-clefs Prédiction de la structure secondaire des protéines, M-SVM, combinaison de modèles.