作者: Zujian Wu , Wei Pang , George M. Coghill
DOI: 10.1109/UKCI.2013.6651284
关键词: Machine learning 、 Biochemical systems theory 、 Model learning 、 Artificial intelligence 、 Set (psychology) 、 Model composition 、 Evolutionary computation 、 Topology (chemistry) 、 Computer science
摘要: Modelling of biochemical pathways in a computational way has received considerable attention over the last decade from biochemistry, computing sciences, and mathematics. In this paper we present an approach to evolutionarily stepwise constructing models by qualitative model learning methodology. Given set reactants involved target pathway, atomic components can be generated preserved library for further composition. These synthetic are then reused compose which qualitatively evaluated referring experimental states given reactants. Simulation results show that our evolutionary learn relationships among exploring topology space alternative models. addition, complex obtained as hidden composed The inferred topologies investigated biologists environment understanding biological principles.