A research group from Nagoya University in Japan has developed a man-made intelligence for analyzing cell images that uses machine learning to predict the therapeutic effect of medication. Called in silico FOCUS, this recent technology may aid in the invention of therapeutic agents for neurodegenerative disorders reminiscent of Kennedy disease.
Current treatments for neurodegenerative diseases often have harsh unwanted side effects, including sexual dysfunction and blocking muscle tissue formation. Nevertheless, researchers searching for brand spanking new, less harmful treatments have been hindered by the dearth of effective screening technologies to discern whether a drug is effective. One promising concept is the ‘anomaly discrimination concept’, meaning neurons that reply to treatment have slight differences in shape compared to those who don’t. Nevertheless, these subtle differences are difficult to discern with the naked eye. Current computer technologies are also too slow to perform the evaluation.
A gaggle of Nagoya University professors, led by Associate Professor Ryuji Kato and Assistant Professor Kei Kanie of the Graduate School of Pharmaceutical Sciences, and Professor Masahisa Katsuno and Assistant Professor Madoka Iida of the Graduate School of Medicine, has developed a recent artificial intelligence technology called in silico FOCUS. It analyzes the cell shape of model neurons and uses that information to evaluate whether or not they reply to therapeutic drugs. They published their leads to the journal Scientific Reports.
The researchers tested the AI on a model of cells being treated for Kennedy disease, a neurodegenerative disorder that results in motor neuron death. in silico FOCUS constructed a sturdy image-based classification model that had 100% accuracy in identifying the state of recovery of the model cells.
This technology enables a highly sensitive and stable evaluation of the results of therapeutic agents through the evaluation of changes in the form of diseased model cells to those of healthy cells, which we couldn’t normally distinguish. That is an ultra-efficient screening technology that may predict drug efficacy by simply capturing images, thus reducing the time required for drug efficacy evaluation and evaluation from several hours with several hundred thousand cells to only a couple of minutes. It allows for a highly accurate prediction of therapeutic effects, without complicated and invasive experiments.”
Ryuji Kato, Associate Professor, Nagoya University
Kato concludes: “These results suggest the potential for accelerating the event of recent drugs and we expect them to be widely applied to the invention of therapeutic drugs for diseases which have been difficult to explore.”
This research was supported by the FY2019 Nagoya University NU Cross-Departmental Innovation Creation Project.