WHY THIS MATTERS IN BRIEF
If you want to develop a vaccine for a virus you need to be able to analyse and model it, and that’s where protein modelling comes in.
In late December last year, Dr. Li Wenliang began warning officials about a novel coronavirus, now known as COVID-19, in Wuhan, China, but was silenced by the police before tragically succumbing to the disease two months later. Meanwhile, almost simultaneously, a computer server halfway across the world started issuing worrying alerts of a potential new outbreak. The server runs software by BlueDot, a company based in San Francisco that uses AI to monitor infectious disease outbreaks for signs of early trouble.
Not enough people listened to either human expertise or to BlueDot’s Artificial Intelligence (AI). Then cases skyrocketed in Wuhan and spread across the world, and people had to take note.
Hindsight is a wonderful thing, but it is remarkable that BlueDot and other machine learning based services are beginning to catch early signs of infectious disease outbreaks, almost within the same time frame as human health experts.
We often hear about AI as the next second coming of healthcare, where it can catch diseases early, accelerate drug development, and personalise treatment. Yet COVID-19 is the first global pandemic to ever hold healthcare AI’s feet to the flame in a global real world test case. So, in a head to head race, can AI actually accelerate new anti-virals or vaccines for COVID-19, something the world has never previously seen? Or will traditional biotech measures excel, in turn unveiling that AI’s hype massively outstrips reality?
MIT recently reported an excellent piece that comprehensively looks at how AI, at its current ability level, can help us predict, diagnose, and treat novel viral threats, but at the moment, and in the short term at least, don’t expect AI to save the day – it’s simply not ready yet. But that said things, many things, are changing.
The promise of AI for accelerating medical drug discovery is almost a universally supported idea and while AI so far has designed new anti-biotics and flu vaccines so far none of these have completed human trials – mainly because they are still ongoing. But, despite that fact the AI’s responsible for these new breakthroughs did so in just a fraction of the time it would have taken traditional techniques and human experts and it’s clear the technology has great potential in the future.
In very broad strokes, AI could be enormously helpful for initial drug discovery in two main ways. The first is screening through millions of chemical compounds for potential drugs in simulation tests, far faster than any human expert, just as the US Department of Energy’s giant supercomputer Summit is doing right now to try to find COVID-19 vaccines, and the second is identifying targets that new drugs can latch onto, either to reduce their impact, by making people less sick, or to slow their spread.
For COVID-19, DeepMind, Google’s AI superstar, is focusing on the second route. Known mostly for its algorithms that beat human players at Chess, Go, DOTA, and Starcraft, DeepMind has also been working directly on solutions for drug discovery. Their secret sauce? An AI called AlphaFold, a deep learning system that tries to predict protein structures accurately when no similar proteins exist in real lifes.
How a protein “looks” in 3D is essential for developing new drugs, especially for new viruses. COVID-19, for example, has really spikey proteins that jut out from its surface. Normally, human cells don’t care – they won’t let the virus inside. But COVID-19’s spikey proteins also harbour a Trojan Horse that activates it in certain cells with a complementary component. Lung cells have an abundance of these factors, which is why they’re susceptible to invasion.
Bottom line – if a drug is going to “fit” into a protein like a key into a lock to trigger a whole cascade of nasty reactions, then the first step is to figure out the structure of the lock, and that’s what DeepMind’s AlphaFold is doing.
Thanks to a surge of global collaboration, China released the genomic blueprint of the COVID-19 virus in open-access databases, whereas others have posted online the structure of some of its proteins – either determined by experiments or through computational modelling. DeepMind is taking these data to the next level by focusing on a few understudied but potentially important proteins that could become drug or vaccine targets using machine learning.
Protein folding has been a decades-long, fundamental problem in biochemistry and drug discovery. Almost all of our existing drugs grab onto certain proteins to work, so identifying protein structure is akin to surveying the enemy landscape and figuring out best attack point simultaneously. The problem is the genetic code doesn’t translate to how proteins look. When it comes to a new virus, without predicting protein structures we’re basically fighting viruses and diseases as if they were the Invisible Man.
Traditional methods use high-tech microscopes, freezing proteins into crystal-looking entities, and other strange and expensive ways to understand their structure. Under the scope, a protein is basically a chain of chemical “letters” that wrap around itself into intricate structures – kind of like how your headphones always tangle into inconceivable structures while you’re sleeping. For DeepMind and other protein-folding efforts, the key is to predict, and then find methods to decipher drug targets from, those structures.
AlphaFold’s work is guided by expertise from protein structure databases in the public domain. In a nutshell, it uses genome sequences to predict the properties of resulting proteins that actually do the work, by looking at the “distance” of each “letter” or component that makes up a certain protein. It doesn’t predict specific sequences with special powers, such as those that bind to a cell, but offers a quick police sketch of the virus perp in sight.
There’s no doubt that AlphaFold is new to the protein-folding game. Even DeepMind itself stresses that “these structure predictions have not been experimentally verified,” but nonetheless the approach could galvanize efforts at making anti-virals and vaccines.
For now, it’s difficult to judge how much AlphaFold will contribute to the pandemic, if at all, but by automating a critical aspect of drug discovery, it’s also en route to becoming a much larger player in the next epidemic, as and when it comes.