A team led by Joseph Brown, an assistant professor at the University of Toronto’s Leslie Dan Faculty of Pharmacy, is building OpenPep, an open-access database and artificial intelligence model to identify peptides with therapeutic potential. The project is supported by US$2.3 million from the Google.org Impact Challenge: AI for Science.
Peptides are short chains of amino acids and already make up eight per cent of newly approved drugs, but discovering them is still slow because data is scattered across labs. The team will produce up to 500 disease-relevant proteins, test large peptide libraries against them and use the results to train AI to predict new binding.
Researchers at hospitals and institutes will be able to nominate target proteins, with a particular focus on paediatric and rare diseases, cancer, neurodegeneration and cardiovascular disease. The database will remain open so other scientists can use and improve it.
