Scanning Zebrafish Brains In Search Of New Drugs

Researchers have developed a high-throughput method of identifying drug candidates for the treatment of neurological disorders.

AsianScientist (Dec. 13, 2018) – Researchers at the City University of Hong Kong (CityU) have developed a machine learning technique that could accelerate the process of drug discovery for neurological diseases. They reported their method in Nature Communications.

Depression, psychosis, epilepsy and Alzheimer’s disease are common brain disorders. However, drugs designed to treat these serious ailments often have long development timelines and particularly high failure rates.

A ‘shortcut’ for drug discovery has now been found. Scientists led by Associate Professor Shi Peng of CityU have combined brain activity mapping, machine learning and chemical compound libraries to help identify potential drug candidates for the treatment of neurological diseases.

The researchers used zebrafish as a working model to conduct whole-brain activity mapping, showing how and which part of the central nervous system (CNS) reacts to a variety of drugs.

“We have designed an integrative system that makes use of robotics, microfluidics and hydrodynamic force to automatically trap and orient an awake zebrafish in 20 seconds, compared to the preparation time of 20 minutes using conventional methods,” Shi explained.

“Therefore, we can carry out imaging for many zebrafish at one go to collect a large amount of data efficiently. Importantly, our platform is capable of immobilizing the fish without anesthesia. [Anesthesia] may interfere with the brain activity and hence the evaluation of the chemical compounds.”

Using this method, they generated maps of the brains of thousands of zebrafish larvae, each of which had been treated with a different chemical compound. The maps showed the corresponding brain regions that reacted to various drugs.

The scientists then used machine learning algorithms to classify the drugs into ten physiological clusters. To their surprise, some of the drugs were characterized as having anti-epileptic or psychoanaleptic effects. Subsequently, a subset of the compounds belonging to the anti-epileptic category were validated in zebrafish that were induced to experience seizures.

“We showed that 7 out of 14 selected compounds were able to reduce seizures in zebrafish without causing any sedative effects, implying a prediction accuracy of around 50 percent,” said Shi.

He added that the platform can help drug developers identify compounds with a higher therapeutic and clinical translation potential, which would lead to better prioritization of the drug development pipeline. This would in turn speed up the new drug discovery process and save costs.

“Even a one percent increase in the drug development success rate would make a huge difference for patients with CNS disorders,” he added.

The article can be found at: Lin et al. (2018) High-throughput Brain Activity Mapping and Machine Learning as a Foundation for Systems Neuropharmacology.


Source: City University of Hong Kong.
Disclaimer: This article does not necessarily reflect the views of AsianScientist or its staff.

Asian Scientist Magazine is an award-winning science and technology magazine that highlights R&D news stories from Asia to a global audience. The magazine is published by Singapore-headquartered Wildtype Media Group.

Related Stories from Asian Scientist