BioNTech and AI Start-Up Develop a Tool to Predict Coronavirus Variants

An AI-based programme developed by BioNTech, the German biotech group behind the leading Covid-19 vaccine, and north African AI start-up InstaDeep, identified more than 90% of high-risk variants based on genetic code, including the highly transmissible Omicron strain, on average two months before their designation by the World Health Organization.

The results from the study show that the programme can evaluate the risks of new variants from their spike proteins within minutes, and monitor them as they evolve nearly in real-time. The early warning system can alert health authorities and vaccine developers to the potential risks months before the spread of concerning variants.

Karim Beguir, co-founder and chief executive officer of InstaDeep, claimed that over 10,000 novel variant sequences were discovered every week and human experts could not cope with complex data at this scale. Using global sequence repositories such as Gisaid, the BioNTech/InstaDeep program can scan hundreds of thousands of registered virus variants and analyse each variant’s potential to spread and its immune escape properties. These two metrics are then combined to create a risk score, and a higher score indicates an increased risk of the variant affecting global health.

Emma Hodcroft, an evolutionary geneticist at the University of Bern, said the early warning system could prove useful to track future variants but we need to pay attention to the quality of input data.

DeepMind Invents AI-Coding Engine to Generate Novel Computer Code

Google’s UK-based AI unit DeepMind has invented a tool that can write computer code at a competitive level to solve open-ended problems that require critical thinking, logic and understanding of language. The system, named AlphaCode, is a sign of the evolution of AI and would allow the automation of computer programming, a powerful and highly prized skill underpinning much of modern science and industry.

DeepMind tested AlphaCode’s performance in coding competitions hosted by Codeforces, a platform that pits the skills of tens of thousands of human software programmers around the world against one another. It found that it performed with the expertise of an average human programmer.

AlphaCode is not the first AI tool to generate computer code. In June 2020, Microsoft released a similar tool to aid programmers with the help of GitHub and OpenAI. The tool, called GitHub Copilot, works more as an intelligent assistant to experienced professionals by analysing existing code and generating new snippets or autocompleting lines of code rather than as an independent problem-solving entity.

AlphaCode currently cannot beat the best human programmers. Critics have also expressed concerns that code generated by machines must be scrutinised particularly closely for bugs, or unforeseen effects including vulnerability to cyberattacks. However, its ability to solve original problems suggests that AI could complement humans, improve productivity and broaden the horizon of people without coding backgrounds.

Robot Surgery Without Human Aid Gets Better Results

US researchers say a robot has successfully performed keyhole surgery on four pigs, all on its own, and they say the robot produced “significantly better” results than humans. The Smart Tissue Autonomous Robot (STAR) carried out laparoscopic surgery to connect two ends of an intestine in the pigs.

According to a paper published in Science Robotics, the robot excelled at the procedure, which requires a high level of precision and repetitive movements. Connecting two ends of an intestine is a challenging procedure in gastrointestinal surgery, requiring a surgeon to apply stitches – or sutures – with high accuracy and consistency. Even a slight hand tremor or misplaced stitch can result in a leak that could result in a patient suffering fatal complications.

It marked the first time a robot had performed laparoscopic surgery without human help according to John Hopkins University. It is normally hard for robots to perform soft-tissue surgery because of how unpredictable it can be, forcing them to be able to adapt quickly to handle unexpected obstacles. The paper set out a novel control system in the STAR that can adjust the surgical plan in real time, just as a human surgeon would.