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

Citation data:

Journal of pharmacological sciences, ISSN: 1347-8648, Vol: 133, Issue: 2, Page: 70-78

Publication Year:
Usage 27
Abstract Views 25
Link-outs 2
Captures 41
Readers 41
Mentions 1
Blog Mentions 1
Social Media 158
Shares, Likes & Comments 138
Tweets 20
Citations 3
Citation Indexes 3
Gao, Mengxuan; Igata, Hideyoshi; Takeuchi, Aoi; Sato, Kaoru; Ikegaya, Yuji
Elsevier BV
Biochemistry, Genetics and Molecular Biology; Pharmacology, Toxicology and Pharmaceutics
Most Recent Tweet View All Tweets
Most Recent Blog Mention
article description
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.