Artificial intelligence and PCA analysis of the electrical activity in cultured human iPS cell-derived neurons for the prediction of convulsive toxicity and action mechanisms of drugs
-
1
Tohoku Institute of Technology, Department of electronics, Japan
[Introduction] Multi-electrode (MEA) assays using human induced pluripotent stem cell (hiPSC)-derived neurons are expected to predict the the convulsion, which is one of severe neurotoxicity in drug development[1,2]. However, an evaluation index of toxicity and differences in responsiveness depending on the convulsant type are not well known. In this study, we aimed to develop an analytical method enabling the evaluation of toxicity and the classification of action mechanism of convulsants.
[Methods] hiPSC-derived cerebral cortical neurons were cultured on MEA chips, and the pharmacological responses of over 12 drugs in spontaneous firings were obtained by the 24-wells MEA system (Presto). Synchronized burst firings (SBFs) were a useful evaluation index of epileptiform activities in cultured neuronal networks. We developed the periodicity analysis, which quantify the periodicity of SBFs using fast fourier transform, and examined the optimal parameter set from more than 10 parameters for choosing the evaluation index of toxicity and the classification of action mechanism using principal component analysis (PCA). We also developed new analysis method for the evaluation index of toxicity and the classification of action mechanism using aritificial intelligence (AI). The 4096 feature quantities of the divided image data were extracted by unsupervised learning. We let AI 4096 feature quantities and drug name learn.
[Results] We analyzed dose-dependent data over 12 drugs including convulsants and negative controls, and found that periodicity analysis is useful parameters for epileptiform activities. We also found the effective parameters for classification of drug responses. In addition, as a result of PCA using these parameters, we have succeeded in separating convulsive drugs and negative control, and classifying the action mechanism of convulsive drugs. We also found the feature quantities set enabling classification of drug responses. Using these feature quantities, we have succeeded in separating the responses between non-convulsive drugs and convulsants and classifying the action mechanism of convulsive drugs.
[Conclusion] The selected analysis parameter including our periodicity analyais using the PCA and AI analysis are useful for an indicator of toxicity and classification of action mechanism in MEA data of in vitro cultured hiPSC-derived neuronal networks.
Acknowledgements
This study was supported by AMED Grant Number 17935517, Astellas aspiring alliance, and JSPS KAKENHI Grant Numbers 17K20111, 17K15577, 16J02472.
References
[1] A. Odawara, H. Katoh, N. Matsuda, I. Suzuki, Physiological maturation and drug responses of human induced pluripotent stem cell-derived cortical neuronal networks in long-term culture, Scientific Reports, 6 (2016) 26181.
[2]Matsuda N, Odawara A, Katoh H, Okuyama N, Yokoi R, Suzuki I. Detection of synchronized burst firing in cultured human induced pluripotent stem cell-derived neurons using a 4-step method. Biochem Biophys Res Commun. (2018) 497(2):612-618.
Keywords:
HiPSC-derived neurons,
Seizures,
AI,
PCA,
Toxicology
Conference:
MEA Meeting 2018 | 11th International Meeting on Substrate Integrated Microelectrode Arrays, Reutlingen, Germany, 4 Jul - 6 Jul, 2018.
Presentation Type:
Poster Presentation
Topic:
Stem cell-derived applications
Citation:
Odawara
A,
Matsuda
N,
Ishibashi
Y,
Yokoi
R and
Suzuki
I
(2019). Artificial intelligence and PCA analysis of the electrical activity in cultured human iPS cell-derived neurons for the prediction of convulsive toxicity and action mechanisms of drugs.
Conference Abstract:
MEA Meeting 2018 | 11th International Meeting on Substrate Integrated Microelectrode Arrays.
doi: 10.3389/conf.fncel.2018.38.00053
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
18 Mar 2018;
Published Online:
17 Jan 2019.
*
Correspondence:
Prof. Ikuro Suzuki, Tohoku Institute of Technology, Department of electronics, Sendai, 9828577, Japan, i-suzuki@tohtech.ac.jp