Viruses are sneaky little pathogens that can wreak havoc on the human body before our immune system knows how to destroy them. Armed with machine learning tools, we can outsmart them by speeding up the process of developing antibodies.

In his laboratory at Carnegie Mellon University’s Department of Mechanical Engineering, Amir Barati Farimani develops algorithms that can infer, learn, and predict mechanical systems based on data. While he investigates a range of topics from fluid mechanics and heat transfer to material discovery and robotics, he also researches human health and bioengineering challenges.

With the outbreak of the COVID-19 pandemic, Barati Farimani quickly shifted his lab’s focus to SARS-CoV-2. Having used machine learning tools previously to study antibodies for viruses like Ebola and HIV, he wanted to take a closer look at the novel coronavirus.

Currently, scientists use computational and physics-based models to screen thousands of antibody sequences. Expensive and time consuming, these models also require information that we do not yet have about SARS-CoV-2.

“This is where machine learning can do the heavy lifting,” said Barati Farimani. “Not only can it ‘learn’ the complex antigen-antibody interactions much more quickly than the current screening methods, it can also beat the human immune system in response time.”

The research team combined available biological data on other infectious viruses into a dataset they named VirusNet. They then used this set to train machine learning models, selecting the best-performing model to screen thousands of potential antibody candidates.

The model ultimately identified eight stable antibodies that were highly efficient in neutralizing SARS-CoV-2. The findings were posted in a preliminary report on the biology pre-print server bioRxiv so that other researchers would have access to the

Suppose we wanted to estimate how many car owners there are in the UK and how many of those own a Ford Fiesta, but we only have data on those people who visited Ford car showrooms in the last year. If 10% of the showroom visitors owned a Fiesta, then, because of the bias in the sample, this would certainly overestimate the proportion of Ford Fiesta owners in the country.

Estimating death rates for people with COVID-19 is currently undertaken largely along the same lines. In the UK, for example, almost all testing of COVID-19 is performed on people already hospitalized with COVID-19 symptoms. At the time of writing, there are 29,474 confirmed COVID-19 cases (analogous to car owners visiting a showroom) of whom 2,352 have died (Ford Fiesta owners who visited a showroom). But it misses out all the people with mild or no symptoms.

Concluding that the death rate from COVID-19 is on average 8% (2,352 out of 29,474) ignores the many people with COVID-19 who are not hospitalized and have not died (analogous to car owners who did not visit a Ford showroom and who do not own a Ford Fiesta). It is therefore equivalent to making the mistake of concluding that 10% of all car owners own a Fiesta.

There are many prominent examples of this sort of conclusion. The Oxford COVID-19 Evidence Service have undertaken a thorough statistical analysis. They acknowledge potential selection bias, and add confidence intervals showing how big the error may be for the (potentially highly misleading) proportion of deaths among confirmed COVID-19 patients.

They note various factors that can result in wide national differences—for example the UK’s 8% (mean) “death rate” is very high compared

A team of Spanish researchers have designed and validated a simulator to enable study of the evolution of the COVID-19 illness in Spain and in all Europe, based on parameters such as climate, social distancing policies and transportation. This research work has been carried out by scientists and technologists from Universidad Carlos III de Madrid (UC3M), the Centro Nacional de Epidemiología (CNE) and the Consorcio Centro de Investigación Biomédica en Red (CIBER) from the Instituto de Salud Carlos III (ISCIII), in conjunction with the Barcelona Supercomputing Center—Centro Nacional de Supercomputación (BSC-CNS).

This large scale simulator, called Epigraph, allows the evolution of the spread of the SARS-CoV-2 virus to be studied and the curve of the illness to be modeled, including the isolation measures, to predict its evolution depending on the activities that are permitted, and to assess the possible effect of a vaccination on the epidemic’s spread.

According to the first results obtained, the researchers point out that the possible number of cases in Spain could be greater than those detected at the national level, which would situate Spain as currently having more than three million people affected, including asymptomatic cases.

Another scenario that has been simulated is reincorporation to the workplace, finding that if workplace reincorporation is not accompanied by social distancing and personal protection, the epidemic would very likely be reproduced, with between three and fourteen million people being infected during the second curve, depending on the social distancing policy applied.

This simulator is able to recreate the social characteristics of diverse groups in the population (students, workers, seniors,

In the battle against COVID-19, The University of Texas at Austin’s supercomputers are at the front lines.

Historically, the Texas Advanced Computing Center (TACC) has served the state when called upon, using resources such as Frontera—the world’s most powerful computing system on a university campus—to work on improved models for chemical attacks, Hurricane Harvey, the West Nile virus and swine flu.

Now, TACC has turned its efforts to stopping COVID-19. It’s an arms race to flatten the curve and TACC is providing the supercomputing power needed to better understand the virus and its spread, expose its underlying weaknesses, and ultimately, fight back.

Supercomputers are essential when trying to combat a pandemic quickly. Calculations or simulations that take regular computers days, months or even years to complete can be done by supercomputers in mere minutes or hours.

For example, TACC supercomputing resources were used to predict the speed of the coronavirus outbreak when it was first labeled as an epidemic. It aided a key study that swiftly discovered the virus spreads more quickly than anticipated and sometimes even before people have symptoms.

Even before COVID-19, the computing center was set up to help at a time of crisis.

TACC has an existing tool that uses supercomputers to optimize emergency health care response, the Texas Pandemic Flu Toolkit. It was first developed in 2012 in response to H1N1 swine flu and was created by a group of expert UT biologists, mathematicians, statisticians, engineers and computer scientists. This service simulates the spread of pandemic flu through the state, forecasts the number of hospitalizations, and determines where and when to place health care resources to maximize lives saved.