Format

Send to

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

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

Author information

1
Graduate School of Pharmaceutical Sciences, The University of Tokyo, Tokyo 113-0033, Japan; iPS-non Clinical Experiments for Nervous System (iNCENS) Project, Japan.
2
Graduate School of Pharmaceutical Sciences, The University of Tokyo, Tokyo 113-0033, Japan.
3
iPS-non Clinical Experiments for Nervous System (iNCENS) Project, Japan; Division of Pharmacology, National Institute of Health Sciences, Tokyo 158-8501, Japan.
4
Graduate School of Pharmaceutical Sciences, The University of Tokyo, Tokyo 113-0033, Japan; iPS-non Clinical Experiments for Nervous System (iNCENS) Project, Japan; Center for Information and Neural Networks, National Institute of Information and Communications Technology, Osaka 565-0871, Japan. Electronic address: yuji@ikegaya.jp.

Abstract

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

PMID:
28215473
DOI:
10.1016/j.jphs.2017.01.003
[Indexed for MEDLINE]
Free full text

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center