 |
|
|
|
| HAL : hal-00616640, version 1 |
| Fiche détaillée |  Récupérer au format |
|
|
| PRIB 2011, Pays-Bas (2011) |
|
|
|
|
| Estimating the Class Posterior Probabilities in Protein Secondary Structure Prediction |
|
|
| Yann Guermeur 1Fabienne Thomarat 1 |
|
|
| (11/2011) |
|
|
|
| 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 single drawback: their outputs are not class posterior probability estimates. This paper addresses the problem of post-processing the outputs of multi-class support vector machines used as sequence-to-structure classifiers with a structure-to-structure classifier estimating the class posterior probabilities. The aim of this comparative study is to obtain improved performance with respect to both criteria: prediction accuracy and quality of the estimates. |
|
|
|
|
|
|
|
|
|
|
|
| 1 : | ABC (Apprentissage et Biologie Computationnelle) (LORIA) |
|
|
|
CNRS : UMR7503 – INRIA – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine (INPL) |
|
|
|
|
|
|
|
|
|
| Domaine | : | Informatique/Bio-informatique Sciences du Vivant/Bio-Informatique, Biologie Systémique |
|
|
| protein secondary structure prediction – multi-class support vector machines – class membership probabilities |
|
| hal-00616640, version 1 | |
| http://hal.archives-ouvertes.fr/hal-00616640 | |
| oai:hal.archives-ouvertes.fr:hal-00616640 | |
| Contributeur : Yann Guermeur | |
| Soumis le : Mardi 23 Août 2011, 15:38:15 | |
| Dernière modification le : Mardi 23 Août 2011, 15:38:15 | |
