Machine learning-based prediction of adverse drug effects: An example of seizure-inducing compounds

J Pharmacol Sci. 2017 Feb;133(2):70-78. doi: 10.1016/j.jphs.2017.01.003. Epub 2017 Jan 28.


Various biological factors have been implicated in convulsive seizures, involving side effects of drugs. For the preclinical safety assessment of drug development, it is difficult to predict seizure-inducing side effects. Here, we introduced a machine learning-based in vitro system designed to detect seizure-inducing side effects. We recorded local field potentials from the CA1 alveus in acute mouse neocortico-hippocampal slices, while 14 drugs were bath-perfused at 5 different concentrations each. For each experimental condition, we collected seizure-like neuronal activity and merged their waveforms as one graphic image, which was further converted into a feature vector using Caffe, an open framework for deep learning. In the space of the first two principal components, the support vector machine completely separated the vectors (i.e., doses of individual drugs) that induced seizure-like events and identified diphenhydramine, enoxacin, strychnine and theophylline as "seizure-inducing" drugs, which indeed were reported to induce seizures in clinical situations. Thus, this artificial intelligence-based classification may provide a new platform to detect the seizure-inducing side effects of preclinical drugs.

Keywords: Artificial intelligence; Clinical; Epilepsy; Side effect; Toxicity.

MeSH terms

  • Animals
  • CA1 Region, Hippocampal / drug effects
  • Diphenhydramine / adverse effects
  • Enoxacin / adverse effects
  • In Vitro Techniques
  • Male
  • Mice
  • Mice, Inbred ICR
  • Seizures / chemically induced*
  • Strychnine / adverse effects
  • Support Vector Machine*
  • Theophylline / adverse effects


  • Enoxacin
  • Diphenhydramine
  • Theophylline
  • Strychnine