Large quantities of metabolic profiling data are being gathered intensively in the rapidly growing field of Metabolomics. However, such data, in order to provide knowledge, must be machine-explored by robust methods that deal with complexity and uncertainty. Symbolic machine learning methods have the power to model structural and relational complexity while statistical machine learning ones provide principled approaches to uncertainty modeling. In this paper, we apply a hybrid symbolic-statistical framework to mine timeseries sequences of reactions for biologically active paths in metabolic networks. We show through experiments that our approach provides a robust methodology for knowledge discovery in Systems Biology.
Mining time-series sequences of reactions for biologically active patterns in metabolic pathways
Esposito, F;FERILLI, Stefano;DI MAURO, NICOLA;BASILE, TERESA MARIA
2007-01-01
Abstract
Large quantities of metabolic profiling data are being gathered intensively in the rapidly growing field of Metabolomics. However, such data, in order to provide knowledge, must be machine-explored by robust methods that deal with complexity and uncertainty. Symbolic machine learning methods have the power to model structural and relational complexity while statistical machine learning ones provide principled approaches to uncertainty modeling. In this paper, we apply a hybrid symbolic-statistical framework to mine timeseries sequences of reactions for biologically active paths in metabolic networks. We show through experiments that our approach provides a robust methodology for knowledge discovery in Systems Biology.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.