Abstract : Prediction of protein-protein interaction (PPI) types is an important problem in life sciences because of fundamental role of PPIs in many biological processes. In this paper we propose a new classification approach based on the extended classical Fisher linear discriminant analysis (FLDA) to predict obligate and non-obligate protein-protein interactions. To characterize properties of the protein interaction, we proposed to use the binding free energies (total of 282 features). The obtained results are better than in the previous studies.
https://hal.inria.fr/hal-01637469
Contributor : Hal Ifip <>
Submitted on : Friday, November 17, 2017 - 3:43:51 PM Last modification on : Saturday, November 18, 2017 - 1:16:41 AM Long-term archiving on: : Sunday, February 18, 2018 - 3:56:36 PM
Katarzyna Stąpor, Piotr Fabian. Classification of Protein Interactions Based on Sparse Discriminant Analysis and Energetic Features. 15th IFIP International Conference on Computer Information Systems and Industrial Management (CISIM), Sep 2016, Vilnius, Lithuania. pp.530-537, ⟨10.1007/978-3-319-45378-1_47⟩. ⟨hal-01637469⟩