Updated: May 11
Let’s take a trip back in time to July of last year to help answer that question. In July researchers in Australia who used AI to develop a vaccine. Dr. Petrosvky at Flinders University lead a development team to develop a ligand vaccine independently. The program’s directive was to search all current knowledge for all conceivable compounds to find a good human drug.
"We had to teach the AI program on a set of compounds that are known to activate the human immune system, and a set of compounds that don't work. The job of the AI was then to work out for itself what distinguished a drug that worked from one that doesn't," Petrovsky said in a press conference. (http://vaxine.net/)
"We then developed another program, called the synthetic chemist which generated trillions of different chemical compounds that we then fed to the AI so that it could sift through all of these to find candidates that it thought might be good human immune drugs."
Once the AI provided top candidates, the team took over and synthesised the ligands, tested them in human blood cells to see if they would work. Not only did the AI provide excellent candidates but it also, according to Petrovsky, create better treatment outcomes than was currently available. What did the team do next?
"So we then took these drugs into development with animal testing to confirm their ability to boost influenza vaccine effectiveness." Petrovsky said. "We already know from animal testing that the vaccine is highly protective against flu, outperforming the existing vaccines. Now we just need to confirm this in humans."
This vaccine has received funding for it’s clinical trials and continues to be under development.
Is this company using it’s AI to work on a vaccine for COVID-19 – you bet! If you are interesting in reading it’s press release:
This pandemic has shone a light on the use of technology in the race to find a vaccine and return the world to “normal”. There are two key roles AI is playing are (1) recommendations for vaccine components using big data to analyze viral protein structures and (2) helping researchers to review the scores of peer-reviewed information being published about the virus. Computer science teams have been creating AI tools and sharing them with the scientific community.
Vaccines mimic the infection, causing the body to produce protective white-blood cells and antigens. There are several typs of vaccines that can be developed. Three types are: killed or attenuated vaccines, like those for the flu or MMR, that use killed pathogens to create an immune response; subunit vaccines, (e.g., pertussis, shingles) use only part of the pathogen, such as a protein; and nucleic acid vaccines inject genetic material of the pathogen into human cells to stimulate an immune response.
Viral proteins are made up of a sequence of amino acids. This sequence will its unique shape which is key to understanding how the virus works. Once the shape is understood, scientists can develop drugs that work with the protein’s unique shape. Without computer technology, it would take a long time to examine the possible shapes of a protein before finding its three-dimensional structure.
According to Wired:
Earlier this year, Google DeepMind introduced AlphaFold, a system that predicts the folding structure of a protein based on its genetic sequence. In early March, the system was put to the test on Covid-19. DeepMind released protein structure predictions of several under-studied proteins associated with SARS-CoV-2, the virus that causes Covid-19, to help the research community better understand the virus.
At the same time, researchers from The University of Texas at Austin and the National Institutes of Health used a popular biology technique to create the first 3D atomic scale map of the part of the virus that attaches to and infects human cells—the spike protein. The team responsible for this critical breakthrough had spent years working on other coronaviruses, including SARS-CoV and MERS-CoV. One of the predictions released by AlphaFold provided an accurate prediction for this spike structure.
In the first few months of 2020 several thousand papers were published on COVID-19. Keeping up with the information can be overwhelming. Using big data and AI can save months or even years of work by moving past a blind alley, avoiding reinventing the wheel, or suggesting a shortcut.
How else is AI helping epidemiologists? It was an AI startup Bluedot that detected a cluster of unusual pneumonia cases in Wuhan China late in 2019 and accurately predicted where the virus might spread. AI has been used to track and map the spread of infection in real time, diagnose infections, predict mortality risk, and contact racing among many others.
AI has emerged as a powerful tool for processing enormous amounts of information. As such, it can be used beneficially but also to forge documents, images, videos, or even identities, to perpetuate biases, for surveillance, and worse. Wondering what is meant by this, check out DeepFake:
Our use of AI to fight COVID-19 reminds us that this is a tool with potential to speed us on our way back to “normal”.
Follow us on the Social Media links below
Youtube Channel: Scaling for Success
Scaling For Success
Visit our Facebook Page:
Follow me on Linkedin: