Technologies such as Artificial Intelligence (AI) and Big Data Analytics could be the “firewalls” against any future disease outbreaks and epidemics and can help develop vaccine candidates faster, according to two scientists of the premier computing research institute in Qatar.
The duo from Qatar Computing Research Institute (QCRI) at Hamad Bin Khalifa University have also highlighted that AI has had a major role in identifying new variants of Covid-19 such as the Delta.
“As for therapeutics, AI can be used for the rapid development of vaccine candidates. AI has been successfully used to identify segments of the viral genetic code that are most susceptible to change and the change to its structure, virulence, and attack mechanism,” said Dr Faisal Farooq, principal scientist, QCRI.
“With this information, immunologists can design vaccines for a more manageable number of targets which can then be tested in animals. This significantly reduces the discovery or candidate generation phase and reduces the overall time a potentially successful vaccine candidate gets into a trial,” he said.
According to Dr Issa Khalil, principal scientist, QCRI, modern technologies such as AI and Big Data Analytics are going to be a giant firewall against disease outbreaks and epidemics due to their potentials for rapid detection, screening, and diagnosis.
“When it comes to outbreak detections, AI-based models can be developed and trained to analyse massive amounts of data from heterogeneous sources, taking on a task that typically requires human experts to work tirelessly around the clock and with incredible speed. This is the real strength of AI-based methods, making analysis more efficient and scalable, complementing, and learning 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 spread and save lives,” explained Khalil.
He noted that identifying and validating a new variant like Delta is somewhat a classical in-vitro study which is performed mostly manually in a lab using sequencers with little to no use of AI techniques.
“However, where AI has been very useful is to identify possible clusters and outbreaks that present very differently from the expected spread caused by the current variant. This can point to a new variant which is then confirmed in the lab,” he said.
He cited that the first variant of Covid-19 called the Alpha was detected in Kent, UK because 50% of the samples coming in for testing were all similar forming a cluster which after further sequencing were identified to be a variant.
“AI techniques are very efficient and accurate in detecting such anomalous patterns very early. As such AI models provide the added value that such variants can be identified early. However, the verification of the actual variant has to be performed in the lab.”
Dr Farooq said there are AI models that learned from the way the Covid-19 genome has been evolving to generate possible future variants and detect changes in the code that can be consequential e.g. ones that can evade the current vaccines.
“These modelling experiments are in-silico (performed on computer or via computer simulation) and as such cheap, effective, and can be run in a matter of hours instead of the in-vitro counterparts that would take months. One key thing to note is this does not eliminate the need for lab testing. However, once these strong in-silico candidates are identified, now a significantly smaller set needs to be tested in the lab. As such, we can have a huge jumpstart in identifying new vaccines, boosters, or therapies,” he said.
Dr Khalil said that right from the beginning of the pandemic, scientists at QCRI have developed AI models for various aspects of Covid-19 – ranging from epidemiology, contact tracing, mobility analysis, self-assessment tools as well as drug discovery.
“We developed AI techniques to generate drug candidates that can bind to key coronavirus proteins, inhibit replication, and hence have the potential to be a therapy. Our work was cited internationally especially by a company called, Innovation Pharma that produces the drug Brilacidin for some other condition,” he said.
The duo from Qatar Computing Research Institute (QCRI) at Hamad Bin Khalifa University have also highlighted that AI has had a major role in identifying new variants of Covid-19 such as the Delta.
“As for therapeutics, AI can be used for the rapid development of vaccine candidates. AI has been successfully used to identify segments of the viral genetic code that are most susceptible to change and the change to its structure, virulence, and attack mechanism,” said Dr Faisal Farooq, principal scientist, QCRI.
“With this information, immunologists can design vaccines for a more manageable number of targets which can then be tested in animals. This significantly reduces the discovery or candidate generation phase and reduces the overall time a potentially successful vaccine candidate gets into a trial,” he said.
According to Dr Issa Khalil, principal scientist, QCRI, modern technologies such as AI and Big Data Analytics are going to be a giant firewall against disease outbreaks and epidemics due to their potentials for rapid detection, screening, and diagnosis.
“When it comes to outbreak detections, AI-based models can be developed and trained to analyse massive amounts of data from heterogeneous sources, taking on a task that typically requires human experts to work tirelessly around the clock and with incredible speed. This is the real strength of AI-based methods, making analysis more efficient and scalable, complementing, and learning 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 spread and save lives,” explained Khalil.
He noted that identifying and validating a new variant like Delta is somewhat a classical in-vitro study which is performed mostly manually in a lab using sequencers with little to no use of AI techniques.
“However, where AI has been very useful is to identify possible clusters and outbreaks that present very differently from the expected spread caused by the current variant. This can point to a new variant which is then confirmed in the lab,” he said.
He cited that the first variant of Covid-19 called the Alpha was detected in Kent, UK because 50% of the samples coming in for testing were all similar forming a cluster which after further sequencing were identified to be a variant.
“AI techniques are very efficient and accurate in detecting such anomalous patterns very early. As such AI models provide the added value that such variants can be identified early. However, the verification of the actual variant has to be performed in the lab.”
Dr Farooq said there are AI models that learned from the way the Covid-19 genome has been evolving to generate possible future variants and detect changes in the code that can be consequential e.g. ones that can evade the current vaccines.
“These modelling experiments are in-silico (performed on computer or via computer simulation) and as such cheap, effective, and can be run in a matter of hours instead of the in-vitro counterparts that would take months. One key thing to note is this does not eliminate the need for lab testing. However, once these strong in-silico candidates are identified, now a significantly smaller set needs to be tested in the lab. As such, we can have a huge jumpstart in identifying new vaccines, boosters, or therapies,” he said.
Dr Khalil said that right from the beginning of the pandemic, scientists at QCRI have developed AI models for various aspects of Covid-19 – ranging from epidemiology, contact tracing, mobility analysis, self-assessment tools as well as drug discovery.
“We developed AI techniques to generate drug candidates that can bind to key coronavirus proteins, inhibit replication, and hence have the potential to be a therapy. Our work was cited internationally especially by a company called, Innovation Pharma that produces the drug Brilacidin for some other condition,” he said.
