Probabilistic in Silico Prediction of Protein-Peptide Interactions

Abstract. Peptide recognition modules (PRMs) are specialised compact protein domains that mediate many important protein-protein interactions. They are responsible for the assembly of critical macromolecular complexes and biochemical pathways (Pawson and Scott, 1997), and they have been implicated in carcinogenesis and various other human diseases (Sudol and Hunter, 2000). PRMs recognise and bind to peptide ligands that contain a specic structural motif. This paper introduces a novel discriminative model which models these PRMs and allows prediction of their behaviour, which we compare with a recently proposed generative model. We nd that on a yeast two-hybrid dataset, the generative model performs better when background sequences are included, while our discriminative model performs better when the evaluation is focused on discirminating between the SH3 domains. Our model is also evaluated on a phage display dataset, where consistantly out-performed the generative model. 

• Type: Conference
• Year: 2005
• Where: RECOMB
• Authors: Wolfgang P. Lehrach, Dirk Husmeier, Christopher K. I. Williams
• Keywords: Computational Biology, Discriminative Model, Generative Model, Generative Model Performs, RECOMB 2005