QCRI scientists highlight the role of AI in vaccine development and prevent future pandemics


Technologies like artificial intelligence (AI) and big data analytics could be the “firewalls” against future disease outbreaks and epidemics and help to develop vaccine candidates faster, according to two scientists from the leading computer research institute in Qatar.
The duo from Hamad Bin Khalifa University’s Qatar Computing Research Institute (QCRI) have also highlighted that AI has played an important role in identifying new variants of Covid-19 such as the Delta.
“When it comes to therapeutics, AI can be used to rapidly develop vaccine candidates. AI has been successfully used to identify segments of the viral genetic code that are most vulnerable to alteration and alteration of its structure, virulence and mechanisms of attack, ”said Dr. Faisal Farooq, senior scientist at QCRI.
“With this information, immunologists can develop vaccines for a more manageable number of targets that can then be tested on animals. This significantly shortens the discovery or candidate generation phase and reduces the overall time a potentially successful vaccine candidate gets into a study, ”he said.
According to Dr. QCRI chief scientist Issa Khalil, modern technologies like AI and big data analytics will be a giant firewall against disease outbreaks and epidemics because of their potential for rapid detection, screening and diagnosis.
“When it comes to outbreak detection, AI-based models can be developed and trained to analyze huge amounts of data from heterogeneous sources and take on a task for which human experts usually work tirelessly around the clock and at incredible speeds. This is the real strength of AI-based methods that make analysis more efficient and scalable, complement each other and learn from human intelligence to support timely decision-making. AI is likely to play a critical role in the early detection of future outbreaks to stop or limit the spread and save lives, ”said Khalil.
He noted that the identification and validation of a new variant like Delta is a classic in vitro study, mostly done manually in a laboratory using sequencers with little to no use of AI techniques.
“However, the AI ​​was very useful in identifying possible clusters and outbreaks that are very different from the expected spread due to the current variant. This can indicate a new variant, which is then confirmed in the laboratory, ”he said.
He cited that the first variant of Covid-19 called Alpha was discovered in Kent, UK because 50% of the samples received for testing were all similar, forming a cluster that after further sequencing was identified as a variant.
“AI techniques are very efficient and accurate in order to detect such anomalous patterns very early on. As such, AI models offer the added value that such variants can be recognized at an early stage. The verification of the actual variant must, however, take place in the laboratory. “
Dr. Farooq said there are AI models that have learned from the evolution of the Covid-19 genome to generate possible future variants and to identify changes in the code that may have consequences, e.g. B. those that can bypass the current vaccines.
“These modeling experiments are in-silico (performed on the computer or via computer simulation) and as such are inexpensive, effective and can be performed in a few hours instead of in-vitro counterparts that would take months. One important thing to note is that this does not eliminate the need for laboratory testing. However, as soon as these strong in-silico candidates have been identified, a significantly smaller set now has to be tested in the laboratory. As such, we can have a huge go-ahead in identifying new vaccines, boosters or therapies, ”he said.
Dr. Khalil said that since the beginning of the pandemic, QCRI scientists have developed AI models for various aspects of Covid-19 – from epidemiology, contact tracing, mobility analysis, self-assessment tools to drug discovery.
“We have developed AI techniques to generate drug candidates that bind to important coronavirus proteins, inhibit replication and thus have the potential to be a therapy. Our work has been especially cited internationally by a company called Innovation Pharma, which makes the drug brilacidin for another disease, ”he said.


Comments are closed.