The RAISE-GENIC research network aims to identify models that allow predicting the drug therapy with the best chances of success for individual epilepsy patients for an individualized selection of anti-epileptic drugs. In our sub-project, we analyze RNA expression data of drug-treated cells and DNA sequencing data of affected patients and carry out the bioinformatic evaluation of the transcriptome networks and their processing for big data and machine learning analyses.

Valproate is known to activate a broad network of genes via transcriptomic regulation. We hypothesize that the transcriptomic response mediates success of valproate treatment and that thus alterations of the network properties are predictors of treatment outcome in patients with epilepsy.

We aim at developing a recommendation system for Valproate, integrating patients’ genetic information and the drug’s transcriptomic profile. For each patient in the study, we estimated how the genetic network properties are altered based on the individual’s mutational burden. We confirmed that the alteration of network properties are significant predictors of treatment outcome, although with moderate accuracy. In addition, we identified stable subgroups. The clinical association is currently under investigation.