Nanopores and AI used to classify respiratory viruses



[ad_1]

Researchers at the University of Osaka have developed a labelless method to identify respiratory viruses, based on dips in electrical current as they pass through silicon nanopores. The method could form the basis of a new rapid test for Covid-19.

Efforts to restrict the transmission of the SARS-CoV-2 virus responsible for the Covid-19 pandemic have emphasized conducting rapid and widespread tests to detect the presence of the new coronavirus and distinguish it from other respiratory viruses.

This new system for the identification of common respiratory pathogens, responsible for conditions such as Covid-19 and influenza, is based on a machine learning algorithm, trained on changes in the current through silicon nanopores.

The technique uses silicon nanopores sensitive enough to detect a single virion when combined with the algorithm.

A 50 nm silicon nitride layer is suspended on a silicon wafer and tiny 300 nm diameter nanopores are added. When a current is applied to the solution on either side of the wafer, the ions travel through the nanopores (a process known as electrophoresis).

The movement of these particles can be controlled by the current they generate. When a viral particle enters a pore, it blocks the passage of some of the ions, causing a drop in current. Each dip reflects the physical characteristics of the particle, such as volume, surface charge, and shape; this makes it possible to distinguish between viruses.

The natural variation in the physical characteristics of viral particles has hampered the implementation of this approach. However, coupling the nanopores with machine learning based on signals from known respiratory viruses allowed the team to build a working tool to distinguish between viruses.

“By combining the detection of single-particle nanopores with artificial intelligence, we were able to achieve highly accurate identification of multiple viral species,” said Professor Makusu Tsutsui, lead author of the ACS sensors study.

The system was tested with the SARS-CoV-2 virus and similar pathogens: respiratory syncytial virus, adenovirus, influenza A and influenza B. It was able to discriminate between waveforms of electrical current, which is impossible for humans. It was performed with very high precision and is faster than other rapid viral tests such as PCR and antibody-based detection, and does not require expensive reagents.

“This work will help with the development of a virus test kit that outperforms conventional viral inspection methods,” said Professor Tomoji Kawai.

According to the researchers, coronaviruses are particularly suitable for this tool due to their spiky outer proteins, which may allow different strains to be classified separately.

Sign up for E&T News email to get great stories like this delivered to your inbox every day.

[ad_2]