Polina Brangel is using tools such as artificial intelligence to strengthen pandemic preparedness.
More than five years after the start of the COVID-19 pandemic, researchers continue to try to anticipate the next global disease outbreak that could cost millions of lives and cause economic chaos. Polina Brangel, a research-and-development data-innovation lead at the Coalition for Epidemic Preparedness Innovations (CEPI), headquartered in Oslo, is trying to prevent this.
Brangel began studying biotechnology engineering at Ben-Gurion University of the Negev in Israel in 2007, graduating from her combined programme with both bachelor’s and master’s degrees in 2012. Later that year, she began her PhD in bioengineering and biomedical engineering at Imperial College London.
Nature Spotlight: Infectious diseases
Her role was originally focused on biosensor development for oncology diagnostics, but Brangel became involved in developing rapid diagnostic (lateral flow) tests to detect various cancer biomarkers. When Ebola broke out in West Africa in 2014 and the World Health Organization (WHO) called for rapid, simple and accurate tests for the disease, Brangel realized that she had the right tools but was using them for a different purpose.
The decision to repurpose her work to tackle Ebola led to a career in pandemic preparedness, and she joined CEPI in 2023. She has developed tests to understand the immunological biomarkers found in people who have recovered from Ebola, has studied the immune response elicited by COVID-19 and now focuses on protecting people from ‘Disease X’.
Brangel spoke to Nature about her work in the field, what she has learnt from the COVID-19 pandemic that could help prevent future pandemics and the part artificial intelligence is playing in preparedness efforts.
What is Disease X?
Disease X is the term, coined by the WHO in its 2018 Research & Development Blueprint for Epidemics, for a hypothetical pathogen that infects humans. The WHO created a list of priority pathogens deemed likely to cause a pandemic that have no available countermeasures, such as vaccines, diagnostics and therapeutics. The list includes the viruses that cause Ebola, Lassa fever and Rift Valley fever.
What did the COVID-19 pandemic teach you about pandemic preparedness?
As serology technical officer at the WHO, I was trying to understand the immune response elicited by COVID-19. With infectious diseases, you do a sero-epidemiology study: drawing blood from a small cohort of people, looking at immune-response antibodies to work out how many individuals had been infected and extrapolating to derive the prevalence in the population.
The infection numbers we estimated went from almost zero to around 90% between different countries because we had so many different tests that could look for these antibodies. The problem is that the tests were all accurate, but the different set-ups were not comparable. We worked with the former agency Public Health England to introduce an international standard for benchmarking assays1. Before this, each laboratory would choose its own assay and the results couldn’t be compared.
This taught me the importance of harmonizing data if we are to use them as evidence for decision-making. Sound, strong science isn’t enough.
How do you prepare for an unknown pathogen?
CEPI has a methodological programme focused on Disease X. We’re working with the 25 known families of virus that can infect humans, most of which come from animals. These include filoviruses (the family that includes Ebola), coronaviruses (such as SARS-CoV-2, which causes COVID-19) and orthoflaviviruses (including those that cause dengue, yellow fever and Zika). We can’t develop vaccines for all 25 so we prioritize the pathogens considered most likely to infect humans, then generate as much knowledge as possible about their genomic sequence.
How does technology support your work?
Pathogens must mutate to jump from animals to humans, so we use computer simulations to predict which ones will undergo mutation. Feeding the most likely ones into AI tools enables us to start developing and testing vaccine sequences and designing clinical trials.
AI models are being used to track zoonotic diseases. Will they prevent the next pandemic?
AI gives us three things: speed (extremely important in a pandemic response); the ability to integrate data from disparate sources; and federated access that enables us to learn from source information even when it’s retained by the owner, whether that’s a government agency or commercial company.
You’ve proposed a pandemic-preparedness engine. What is that?
CEPI’s Pandemic Preparedness Engine for Disease X is our idea for a collaborative scientific tool that will integrate fragmented knowledge bases — such as information on genomic sequences from various sources — and enable researchers around the world to build vaccines and medical interventions. It will be a bit like a chatbot. Imagine that a researcher in Malaysia identifies a new Nipah virus and wants to build a vaccine. They could input the genomic sequence of the virus and its location, and the AI agent could suggest how to create or tweak specific molecules (antigens) to trigger the correct immune response.