AI

# AI technologies for waveform, numerical, and image data.

We develop AI models from waveform data, parameters, and imaging pictures obtained through MEA and other techniques to predict the efficacy, toxicity, and mechanisms of action of compounds. We possess multiple AI algorithms, enabling their application in compound screening. Additionally, we have expertise in AI analysis of EEG/ECoG data.

Reference Papers

 N Matsuda, A Odawara, Y Ishibashi, K Kinoshita, A Okamura, T Shirakawa, I Suzuki*. Raster plots machine learning to predict the seizure liability of drugs and to identify drugs. Sci Rep. 2022 12(1):2281. DOI

K. Matsuda, X Han, N. Matsuda, M. Yamanaka, I Suzuki*,  Development of an In Vitro Assessment Method for Chemotherapy-Induced Peripheral Neuropathy (CIPN) by Integrating a Microphysiological System (MPS) with Morphological Deep Learning of Soma and Axonal Images, Toxics 11(10) 848, 2023 DOI

N. Matsuda, Kenichi Kinoshita, Ai Okamura, Takafumi Shirakawa, and I Suzuki*. Histograms of Frequency-Intensity Distribution Deep Learning to Predict the Seizure Liability of Drugs in Electroencephalography. Toxicological Sciences. 2021 182(2):229-242. DOI

AI_Analysis.webp

intellectual property
  • Method, Computer System, and Program for Predicting the Properties of a Target Compound, Patent No. 6567153, PCT Filed
    (Use of the above intellectual property is subject to a license agreement from Tohoku Institute of Technology)