In the world of biology, a great problem has stumped scientists for 50 years: how do you accurately predict the shape that a protein will fold into? For scientists, this question is important because predicting the shape that a protein will fold into determines their function. In fact, nearly all diseases, including cancer and dementia, are related to how proteins fold.

After half a century, scientists finally have an answer to this scientific problem thanks to the artificial intelligence program called AlphaFold, which was developed by the Alphabet-owned intelligence group DeepMind. The company, which Google bought for $600 million in 2014, is most famous for its AI systems that can play games like chess and the ancient Chinese board game Go (it doesn’t just play, but actually wins against the best players in the world). Those games, in hindsight, were just a warm-up for the real challenge of predicting how proteins will fold.

To learn how proteins fold, the researchers trained their algorithm on a public database containing about 170,000 protein sequences and their shapes. As the Guardian reports, DeepMind then put AlphaFold through its paces by entering it for a biennial “protein olympics” known as Casp, the Critical Assessment of Protein Structure Prediction. Entrants to the international competition are given the amino acid sequences for about 100 proteins and challenged to work them out.

The results from teams that use computers are compared with those based on lab work. Not only did AlphaFold outperform other computer programs, but it also reached an accuracy comparable to the laborious and time-consuming lab-based methods.

Now that the 50-year-old scientific problem has been solved, scientists say it could pave the way for better understandings of disease and drug discovery. “This is a problem that I was beginning to think would not get solved in my lifetime,” said Janet Thorton, a director emeritus of EMBL’s European Bioinformatics Institute near Cambridge. “Knowing these structures will really help us to understand how human beings operate and function, how we work.”