The relevance of systems biology in relational learning to annotate human protein with Reactome pathways

Abstract

Aims:  To predict human proteins that could belong to Reactome pathways.  To compare different Representations of proteomic knowledge and Relational Learning techniques.  To take advantages from the interactions and other important biological associations.  To face up to multi-class and multi-label classification, frequent in functional annotations problems.  We propose Machine learning strategies to solve functional annotation tasks.