Artificial intelligence just revealed a potential concern for COVID vaccine makers
Machine learning and artificial intelligence solve problems we never thought possible. This week alone, a unit of Alphabetowned by Google – DeepMind – used this approach to solve a mystery about how proteins fold, which has upset scientists for 50 years.
Another use of powerful algorithms that doesn’t get as much publicity is to simulate complex systems to avoid problems we didn’t even know existed. This appears to be what researchers at the Massachusetts Institute of Technology (MIT) did. And this raises questions about the reported effectiveness of the famous Vaccines against covid-19 of Pfizer (NYSE: PFE) and BioNTech (NASDAQ: BNTX), Modern (NASDAQ: mRNA), AstraZeneca (NASDAQ: AZN), and others.
Focus on the tip
Everyone is grateful that we seem close to having several vaccines approved for COVID-19, and most are surprised at how quickly the vaccines have been developed. What once took a decade or more – the fastest vaccine ever developed was for mumps, which took four years – was accomplished in less than 12 months.
In addition to the deluge of funding and attention, the record pace has been hit by focusing on the spike protein that the SARS-CoV-2 virus uses to invade human cells. While not the only one, the spike protein is the most common way for the virus to bind outside cell membranes, allowing the virus genome to invade the cell and turn it into a virus-producing plant. It was natural for the researchers to focus on this unusual attribute in an attempt to prevent attachment and subsequent invasion. However, this focus may have inadvertently prioritized certain groups of people over others. It turns out that we do not all react to spike protein the same way.
Demographics have always been a problem
The story of the 2020 pandemic has always been about demographics – whether it was the disproportionate effect on the health of minorities or the discrepancy between knowledge workers who could connect remotely and those who had to continue to report to work. The virus has exposed two different realities for many Americans.
A study released in September by NPR found that black Americans accounted for more than 21% of COVID-19 deaths in the United States, compared to only 12.3% of the population. Conversely, White Americans make up 61% of the American population, but only 51% of deaths. A variable rarely explains a result, but the differences are striking. Likewise, the unemployment rate for black Americans is 10.3%, compared to 5.9% for whites. While the gap is narrowing, this is another statistic that tells the story of different America 2020 experiences depending on race.
Vaccines to the rescue
The negative effect on our health and daily life is why most people are so happy to finally have approved vaccines on the horizon. With Pfizer, Moderna and AstraZeneca, all of the published data that shows their vaccine candidates could be at least 90% effective in preventing COVID-19, the assumption is that life could soon return to normal. In response to the good news, the stock market rebounded nearly 11% in November, its best month in over 30 years.
That’s why it surprised me when MIT’s Computer and Artificial Intelligence Laboratory (CSAIL) modeled a vaccine like those approved and found it to be significantly less effective for some groups than others. It turns out that people have different versions of genes – called alleles – that determine how cells behave. When a virus invades, it enters the grooves of cell membranes, triggering an immune response. This is how vaccines work. Using pieces of the SARS-CoV-2 virus – especially the spike protein – the vaccines that have been developed introduce those pieces of the virus that bind to the cell and trigger a response. For people who self-identified as black or Asian, the alleles caused less reliable binding to the spike protein, which increased the potential for the vaccine to be ineffective for them. While ineffectiveness is likely to occur in less than one percent of white people, CSAIL predicts that it could affect 10% of people of Asian descent.
Genes aren’t the biggest obstacle
Although it sounds scary, the vaccines are still far superior to the seasonal flu shot and will offer great protection to most who take them. Additionally, MIT’s research is not yet peer-reviewed and is only a prediction, albeit based on a very good model. One way around the problem is to create future vaccines with fragments of viruses other than the spike protein. It was a good target for the quick turnaround we needed in 2020, but some drugmakers should take note for future releases.
Moreover, it is not just the genes that will limit the effect of the vaccine. A recent study found that the percentage of Americans who say they will get vaccinated rose from 72% in April to 48% in October. To allay security concerns among minority groups, it will be particularly important for companies to highlight the racial diversity of participants in clinical tests for their COVID-19 vaccines.
The stock market recovery, and the return to a normal life, depend on two things: an effective vaccine and a majority of people receiving it. As we get closer to the first box, it is more important than ever to address the factors that may limit anyone’s willingness to get vaccinated. If CSAIL’s prediction stands up to peer review, it may add another reason people most vulnerable to COVID-19 will rationalize not getting the vaccine. As an investor, I will carefully monitor all distribution and administration statistics made public to confirm that the recovery is coming for everyone in the economy.
This article represents the opinion of the author, who may disagree with the “official” recommendation position of a premium Motley Fool consulting service. We are heterogeneous! Challenging an investment thesis – even one of our own – helps us all to think critically about investing and make decisions that help us become smarter, happier, and richer.