The Daily Dose: The White House calls on the AI community to tackle SARS-CoV-2 data

Sign up for Scientific Inquirer’s Steady State Newsletter for the week’s top stories, exclusive interviews, and weekly giveaways. Plenty of value added but without the tax.

The United States is the latest government to call on its local Artificial Intelligence industry to use its expertise in the fight against SARS-CoV-2. As per the Next Web, “The White House has urged AI experts to analyze a dataset of 29,000 scholarly articles about coronavirus that could offer insights into how to manage the pandemic. The government wants researchers to use it to develop new text and data mining techniques that can help scientists answer key questions about the origins, transmissions and potential treatment of COVID-19.” A list of the questions have been published on Kaggle.

In the scramble to develop treatments and vaccines against the COVID-19 outbreak, Regeneron has proposed the strategy it feels works best in the short-term. As per STAT, “To battle Covid-19, Regeneron says it wants to select two antibodies against the virus, which is known as SARS-CoV-2. The antibodies target a protein on the virus’ outer shell, called the spike protein. Having two antibodies targeting the spike protein in the treatment, not one, should mean that it is more difficult for the virus to mutate in a way that will allow it to evade both antibodies.” The pharmaceutical company is not the first to try to take advantage of antibodies’ affinity for the coronavirus’ outer spike glycoprotein. Chinese scientists have been using plasma transfers from recovered patients to sick ones in the hopes of eliciting a strong immune response.

European countries are slowly adopting more draconian measures in an attempt to halt new coronavirus infections. As per Deutsche Welle, “A nationwide lockdown began in France at noon local time on Tuesday, requiring people to remain in their homes and only go out for the “bare essentials” like groceries, medicine and going to work. There were reports of many Parisians crowding train stations attempting to leave the French capital for the countryside before the noon deadline. There were also reports of long lines of people outside supermarkets buying supplies in preparation for the lockdown.” Along with Italy and Spain, France has been hit hard by the COVID-19 outbreak.

In the Middle East, Iran accounts for the overwhelming majority of COVID-19 cases. The Associated Press put the scope of the country’s problems in perspective: “Although Iran has one of the Mideast’s best medical services, its hospitals appear to be overwhelmed and authorities have asked for 172 million masks from abroad. It also has asked the International Monetary Fund for $5 billion, the first such loan for Iran since 1962. The Islamic Republic has an opportunity to limit the virus as the Persian New Year, Nowruz, approaches.” Satellite images show evidence of mass graves being dug in the country.

And finally, yet another sports competition has postponed its events indefinitely as a result of the coronavirus outbreak. The marquee football tournament held by the Union of European Football Association, the Euro2020, has been put on hold. As per the Guardian, “This summer’s European Championship has been postponed until the summer of 2021, Uefa has decided, as it contemplates the unprecedented disruption caused by the coronavirus… The proposed new dates are 11 June until 11 July 2021, with decisions on dates for other club and international competitions for men or women to ‘be taken and announced in due course’.” Every domestic league in Europe has postponed their seasons until further notice.

Last week, reports about researchers at the Massachusetts Institute of Technology designing a neural network capable of identifying novel antibiotics gained widespread coverage in the news. Quanta Magazine took an in-depth look at the science behind the development that is well-worth a read. According to the article, the MIT team “trained their network to look for any compound that would inhibit the growth of the bacterium Escherichia coli. They did so by presenting the system with a database of more than 2,300 chemical compounds that had known molecular structures and were classified as “hits” or “non-hits” on tests of their ability to inhibit the growth of E. coli. From that data, the neural net learned what atom arrangements and bond structures were common to the molecules that counted as hits.” Unfortunately, identifying novel antibiotics does little to resolve the financial challenges facing the antibiotics industry.

IMAGE SOURCE: Creative Commons

Words matter. Images matter. The Scientific Inquirer needs your support. Help us pay our contributors for their hard work. Visit our Patreon page and discover ways that you can make a difference.

1 comment

Leave a Reply

%d bloggers like this: