Today’s Solutions: October 24, 2021

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.”

Solutions News Source Print this article
More of Today's Solutions

Algae wrapped in droplets improves efficiency of artificial photosynthesis

In our quest for the most sustainable, most renewable sources of energy, humanity continues to look to nature for inspiration. One of nature’s most efficient energy systems is photosynthesis, which is how plants convert sunlight, ... Read More

Evidence shows Vikings arrived in Americas nearly 500 years before Columbus

Researchers have known for a while that Vikings from Greenland founded the village of L’Anse aux Meadows in Newfoundland around the turn of the millennium, but now, a study published in Nature has finally pinpointed ... Read More

Egypt’s State Council swears-in the nation’s first female judges

Egypt’s State Council was established in 1946 and is an independent judicial body that deals with administrative disputes, disciplinary cases, appeals, reviews draft laws, decisions, and contracts that involve the government or a government-run body. ... Read More

Is group or individual work more productive? Here’s what science says

Are you a group project person or do you prefer to fly solo? We all have our work preferences, but what does science say about teamwork and productivity? A new study conducted by Quartz aims ... Read More

Wildlife filmaker provides a unique insight into the daily lives of bees

You may have seen bees flying around your backyard or local park, but it can be difficult for the naked human eye to grasp the full complexity of the lives of these pollinators. During the ... Read More