Automatic Reverse Engineering Algorithm for Drug Gene Regulating Networks

A.G. Floares (Romania)


gene networks, reverse-engineering, genetic programming, ordinary differential equations, pharmacogenomics.


Automatically inferring gene regulating networks models from microarray time series data is one of the most chal lenging tasks of bioinformatics. The ordinary differential equations models are the most sensible, but very difficult to build. We introduced the more general concept of drug gene regulating networks, where the regulation is exerted also by drugs. We proposed a reverse engineering algo rithm for (drug) gene regulating networks, based on ge netic programming - RODES. RODES automatically dis covers the structure, estimate the parameter, and identify the molecular mechanisms involved. It starts from exper imental or simulated microarray time series data and pro duces systems of ordinary differential equations. We tested RODES on simulated data, and the accuracy and the CPU time of the results were very good. This is mainly due to the possibility of incorporating a priori knowledge, and to reducing the problem of reversing an ordinary differen tial equations system to that of reversing individual alge braic equations. To our knowledge, this is the first realistic reverse engineering algorithm, based on genetic program ming, applicable to large (drug) gene regulating networks. We suggest that the algorithm can reverse engineer systems of ordinary differential equations in any scientific field with a proper use of domain knowledge.

Important Links:

Go Back