A Machine Learning Approach for Generating Temporal Logic Classifications of Complex Model Behaviours

Decanato - Facoltà di scienze informatiche

Data d'inizio: 5 Dicembre 2012

Data di fine: 6 Dicembre 2012

The Faculty of Informatics is pleased to announce a seminar given by Daniele Maccagnola

DATE: Wednesday, December 5th, 2012
PLACE: USI Università della Svizzera italiana, room 402, Main building (Via G. Buffi 13)
TIME: 15.30

Systems biology aims to facilitate the understanding of complex interactions between components in biological systems. Petri nets (PN), and in particular Coloured Petri Nets (CPN) have been demonstrated to be a suitable formalism for modelling biological systems and building computational models over multiple spatial and temporal scales. To explore the complex and high-dimensional solution space over the behaviours generated by such models, we propose a clustering methodology which combines principal component analysis (PCA), distance similarity and density factors through the application of DBScan. To facilitate the interpretation of clustering results and enable further analysis using model checking we apply a pattern mining approach aimed at generating high-level classificatory descriptions of the clusters' behaviour in temporal logic. We illustrate the power of our approach through the analysis of two case studies: multiple knockdown of the Mitogen-activated protein-kinase (MAPK) pathway, and selective knockout of Planar Cell Polarity (PCP) signalling in Drosophila wing.

Daniele Maccagnola received a bachelor degree in Computer Science in 2009 at University of Milano-Bicocca, with a thesis on the application of clustering algorithms to biomedical datasets, under the supervision of Prof. Enza Messina.

In 2011 he received a master degree in Bioinformatics at University of Milano-Bicocca, after a research period at Brunel University (United Kingdom) where, under the supervision of Prof. David Gilbert, he worked on the development of a machine learning and temporal logic approach for the analysis of biological behaviours.

From March 2012 he is a research fellow at University of Milano-Bicocca under the supervision of Prof. Enza Messina.

His main interests are in data mining, machine learning techniques and, more recently, model checking and temporal logic approaches, in particular their application to systems biology.

HOST: Prof. Natasha Sharygina