March 5, 2021

Join us for our next breakfast insight event with VMware on 24 Feb 2021 - click here for more details

We are creating some awesome events for you. Kindly bear with us.

AI to determine which overlooked animals could host new coronavirus

A new AI study has identified many more potential host species for new coronaviruses than are currently known. Scientists from the University of Liverpool used machine learning to predict which mammals could be sources for new strains of the virus. They detected several species implicated in previous outbreaks, including horseshoe bats, and pangolins — as well as some new candidates.

The study also predicted that hedgehogs, rabbits, and domestic cats could host SARS-CoV-2, as well as numerous other coronaviruses. They noted that their results demonstrate the large underappreciation of the potential scale of novel coronavirus generation in wild and domesticated animals.

Finding the sources

The researchers used machine learning to predict the relations between 411 coronavirus strains and 876 potential mammal host species. This helped them identify animals that were most likely to be co-infected with different strains of the virus — which could cause a new one to emerge.

The researchers found at least 11 times more associations between mammal species and coronavirus strains than were previously known. They also estimate that there are over 40 times more species that can be infected with four or more coronaviruses than have been observed to date.

A co-lead on the study stated, “Given that coronaviruses frequently undergo recombination when they co-infect a host, and that SARS-CoV-2 is highly infectious to humans, the most immediate threat to public health is a recombination of other coronaviruses with SARS-CoV-2.”

The research suggests there could be 30 times more host species for SARS-CoV-2 recombination than are currently recognized. They include the dromedary camel, African green monkey, and the lesser Asiatic yellow bat. The researchers note that their results draw on limited data and that there are study biases for certain species. Nonetheless, they believe the findings could help reduce the risk of new coronaviruses spreading to people.

Armed with this knowledge, the scientists may be able to reduce the chance of emergence into human populations, such as by the strict monitoring and enforced separation of the identified hosts, in live animal markets, farms, and other close-quarters environments; or they may be able to develop potential mitigations in advance.

AI aids in the fight against COVID-19

According to another article, a new software tool that reveals the severity of lung infections in COVID-19 patients has been developed by researchers from the Indian Institute of Science, in collaboration with Oslo University Hospital and the University of Adger in Norway.

It has been described in a recent study published in the journal “IEEE Transactions on Neural Networks and Learning Systems”, Bengaluru-based IISc said in a statement. COVID-19 can cause severe damage to the respiratory systems, especially the lung tissues. Image-based methods such as X-ray or CT scans can prove helpful in determining how bad the infection is, the statement noted.

The software tool, developed by the Departments of Computational and Data Science and Instrumentation and Applied Physics at IISc, called AnamNet, can ‘read’ the chest CT scans of COVID-19 patients, and, using a special kind of neural network, estimate how much damage has been caused in the lungs, by searching for specific abnormal features, it said.

AnamNet employs deep learning and other image processing techniques, which have now become integral to biomedical research and applications. The software can identify infected areas in a chest CT scan with a high degree of accuracy, it said.

The researchers trained AnamNet to look for abnormalities and classify areas of the lung scan as either infected or not infected – this is called segmentation. The tool can judge the severity of the disease by comparing the extent of the infected area with a healthy area.

Another significant advantage of AnamNet is that the software is lightweight with a small memory footprint. This has enabled the team to develop an app called CovSeg that can be run on a mobile phone and hence potentially be used by healthcare professionals.  AnamNet holds promise beyond merely identifying lung infections in COVID-19 patients. The software tool is freely available to the public, IISc added.

Send this to a friend