AI + Covid-19 Vaccine

How fast can you develop a vaccine? Never has this challenge been put to the test quite so intensely as in 2020.

In fact, Jason Moore, who heads Bioinformatics at UPenn thinks that if the virus had hit 20 years ago, the world might have been doomed. It’s only thanks to modern technology that we now have a safe vaccine. He said, “I think we have a fighting chance today because of AI and machine learning.”

So, how did AI help to make the Covid-19 vaccine a reality? The short answer is a combination of computational analysis and the system of AlphaFold.

Listen to this episode of Short and Sweet AI to learn more or keep reading…

Understanding vaccines

To fully understand how AI helped in the race towards a vaccine, it’s important to understand how vaccines work.

A vaccine works by provoking the body into producing defensive white blood cells and antibodies. It does this by imitating the infection. However, in order to do this, you first need to find a target on the virus.

To find a target on the virus, you need to understand its 3D shape. Naturally, it’s difficult to figure out all the possible shapes the virus could be. That is unless you use the power of AI.

How AI was used to develop the vaccine

In the case of the Covid-19 virus, Google’s machine learning neural network, AlphaFold saved the day.

What AlphaFold managed to do was predict the 3D shape of the virus’ spike protein. This refers to the spikes protruding from the outside of coronaviruses which help them to infect cells.

AlphaFold did this by looking at its genetic sequence, and perhaps more importantly, they did this really fast. AlphaFold did this as early as March 2020, just three months after the pandemic was recorded.

Without AI, it would have taken months and months just to create the best possible target protein. Even after months, it still could have been wrong. That’s how researchers were able to race ahead and develop the mRNA vaccine, all thanks to AI.

Typically, it can take years or even decades to develop a safe vaccine. Before Covid-19, the quickest vaccine development took four years! Despite this, by September 2020, there were a total of 34 different Covid-19 vaccines in development. Many were already being tested on humans. It’s a previously unheard of number in such a short space of time.

AI’s second big contribution to conquering Covid-19

AI’s second contribution to the fight against Covid-19 is through the use of computational analysis.

For some background, neural networks excel at analyzing large amounts of data to find patterns that humans might not spot.

As we can’t spot the patterns ourselves, we have turned to computers which use machine learning to analyze huge amounts of data. By processing all this data, the computers learn more over time by recognizing patterns.

Computational analysis means using AI to gather valuable insights from both experimental and real-world data.

During the outset of the pandemic, The Allen Institute for AI began keeping an online repository of research about Covid-19. This amassed over 30,000 academic articles with invaluable insights into the virus. This, paired with machine learning algorithms, meant that researchers could use this data set to better understand the virus.

In April 2020, computational scientists harnessed neural networks to sort through medical records by the thousands. By doing so, they confirmed that lack of smell and taste were some of the earliest and most common symptoms of Covid. While there were isolated reports of anosmia, (the medical term for loss of smell and taste) the data validated it as a consistent finding.

Thanks to this analysis, the Centers for Disease Control and Prevention (CDC) added these to their list of Covid symptoms. This helped doctors recognize and diagnose patients sooner.

Another example of this is when medical charts from 96 hospitals in several countries were analyzed and compared through machine learning. This revealed other significant findings, one of which being that many Covid patients had off-the-chart readings for blood clotting. This insight alerted doctors to include blood thinners as part of the treatment for infected patients.

AI’s ability to do what we cannot

Without AI and machine learning, where would we be? We would probably still be processing data and testing out target proteins.

That’s because the human brain has a finite capacity and becomes quickly overwhelmed with large amounts of data. To collate and analyse data on Covid from all around the world would take us years.

Thanks to modern technology, we no longer have to wait this long. Computers don’t have these limitations. They can quickly spot patterns we cannot and apply them to findings far more quickly and effectively than we ever could.

We often see AI depicted as evil or something to be afraid of in fiction and social media. Yet AI has revolutionized how vaccines are developed and viruses are studied.

AI has been a workhorse throughout this whole pandemic. It’s only thanks to AI’s ability to process massive amounts of data so efficiently, that we have a working vaccine today.

So, rather than fearing AI, perhaps it’s time to wonder if the machines will save us instead.

If you enjoyed this episode and blog post, subscribe to the Short and Sweet AI podcast. Please leave a rating and a review because it shows others this podcast is worth listening to and gives me encouragement. You can subscribe for free on Apple Podcasts, Spotify, and others!

Leave a Reply

%d bloggers like this: