Vaishnavi Kardale, Bioinformatics Centre, Savitribai Phule Pune University
For the past one and a half years, we have been struggling with COVID19. The deadly pandemic has taken millions of lives all over the world. Meanwhile, the huge demand has deaccelerated the vaccine rollout. The plan to deal with COVID19 includes extensive testing, contact tracing, quarantining, and medical supervision for those in need. When it comes to testing rapid antigen tests and RT-PCR tests are widely carried out. RT-PCR tests are the gold standard when it comes to COVID testing at the moment. Although the tests are accurate it takes quite a long time this is because of the time that goes into the process of RNA extraction from the virus. The exposure increases the chances of the inspector contracting the viral infection. A team of researchers at Osaka University have come up with a method that would allow faster and accurate COVID testing in mere 5 minutes with the help of artificial intelligence. This test is not just accurate but it is also highly sensitive, so much so that it can identify different types of coronaviruses that cause the common cold, SARS, MERS, and COVID which is not possible with RT-PCR.
Where do we use AI in biology?
By no way artificial intelligence can be replaced with biological intelligence. But AI has only aided in solving problems that human intelligence has found complex. From a biological point of view, AI has proved to be useful in dealing with big data generated in genomics, protein structure prediction, drug development, and much more. This research has shown that sky is not the limit for AI and its applications.
What is Nanopore technology?
The researchers at Osaka University combined nanopore technology with AI to get the results. They devised an AI-assisted nanopore-based device to accurately detect the virus. In nanopore technology, genetic material (DNA or RNA) is passed through a pore of very small diameter in an electrostatic environment. As each base of the nucleic acid pass through the pore, the current fluctuates. These fluctuations are recorded. Each base in the nucleic acid creates a different unique fluctuation in the current and therefore the exact base that is passing can be detected. This in fact is a very popular and widely used sequencing method practiced by molecular biologists across the globe. In this work, the researchers replaced the genetic material with the virus itself and thus no need for RNA extraction was required thereby speeding up the process.
How did they do that?
The scientists made a device with a 300nm pore in a silicon nitride membrane. When a virus passes through this pore it temporarily blocks the passage disrupting the flow of charge. This disruption in charge is detected as an electric current. Even a single coronavirus particle can be detected successfully. The signals generated can be as small as a few nano-ampere and therefore to detect these machine learning is used. The current as a function of time gave information on the volume, structure, and surface charge of the target being analyzed. This method helped researchers achieve a sensitivity of 90% and a specificity of 96% in just 5 minutes using saliva samples.
The researchers have described the method as user-friendly and non-invasive. The test platform requires the machine learning software on a server, a high precision current measuring instrument, and a cost-effective semiconducting nanopore module. This study can prove to be beneficial in detecting emerging infectious diseases and it may further revolutionize public health care and disease control.
Also read: NUCOME: The new Database for nucleosome organisation
References
- Taniguchi, M., Minami, S., Ono, C. et al. Combining machine learning and nanopore construction creates an artificial intelligence nanopore for coronavirus detection. Nat Commun 12, 3726 (2021). https://doi.org/10.1038/s41467-021-24001-2
- The Corrosion Prediction from the Corrosion Product Performance
- Nitrogen Resilience in Waterlogged Soybean plants
- Cell Senescence in Type II Diabetes: Therapeutic Potential
- Transgene-Free Canker-Resistant Citrus sinensis with Cas12/RNP
- AI Literacy in Early Childhood Education: Challenges and Opportunities
7 thoughts on “Artificial Intelligence (AI) for efficient COVID Testing”