How AI and Crowdsourcing Can Advance mRNA Vaccine Thermo-stability - NVIDIA's podcast

Artificial intelligence (AI) and crowdsourcing are being used to improve the thermostability of mRNA vaccines, making distribution more accessible worldwide, according to Bojan Tunguz, a physicist and senior system software engineer, and Johnny Israeli, senior manager of AI and cloud software, at #NVIDIA. They were interviewed by the NVIDIA AI Podcast about AI's potential in drug discovery and Stanford’s OpenVaccine competition, which uses machine learning and crowdsourcing to tackle mRNA vaccine thermostability challenges. OpenVaccine was hosted by Kaggle, an online machine-learning competition platform that now encompasses datasets, code and discussions in addition to competitions, with participants earning points, rankings and status achievements across four areas. AI, crowdsourcing and machine learning are opening up new possibilities in drug discovery and vaccine distribution, enabling better problem-solving for complex challenges like thermostability by tapping into the collective wisdom and skills of participants worldwide. Based on this competition on Kaggle - A paper was recently published in Nature . The mRNA design space is prohibitively large (e.g., ~10632?candidates for the SARS-CoV-2 Spike protein), which poses insurmountable computational challenges. The new algorithm?LinearDesign?takes only 11 minutes for the Spike protein, and can jointly optimize stability and codon usage. A very timely tool - not only for vaccines but also for mRNA medicine encoding all therapeutic proteins (e.g., monoclonal antibodies and anti-cancer drugs. #Sanofi's mRNA CoE has licensed this platform from Baidu to develop mRNA therapeutics.