### AlphaFold: Revolutionizing Protein Structure Prediction
#### The Breakthrough in Protein Structure Prediction
In 2021, AI research lab DeepMind introduced AlphaFold, a model capable of accurately predicting the 3D structure of proteins. This breakthrough was pivotal because the structure of proteins determines their functions.
“We’re just floating bags of water moving around,” says Pushmeet Kohli, VP of research at DeepMind. “What makes us special are proteins, the building blocks of life. How they interact with each other is what makes the magic of life happen.”
#### Recognition and Impact
AlphaFold was hailed as the breakthrough of the year by the journal Science in 2021. By 2022, it had expanded its capabilities to predict the structures of biomolecules like nucleic acids and ligands. This advancement holds promise for understanding complex diseases such as cancer and neurodegenerative disorders like Parkinson’s and Alzheimer’s.
#### Democratizing Scientific Research
“It has democratized scientific research,” Kohli says. “Scientists working in a developing country on a neglected tropical disease did not have access to the funds to get the structure of a protein computed. Now, at the click of a button, they can go to the AlphaFold database and get these predictions for free.”
One of DeepMind’s early partners, the [Drugs for Neglected Diseases Initiative](https://www.dndi.org/), utilized AlphaFold to develop treatments for diseases like sleeping sickness, Chagas disease, and leishmaniasis, which affect millions but receive limited research attention.
### AlphaMissense: The Next Frontier
#### Understanding Genetic Mutations
DeepMind’s latest innovation, AlphaMissense, focuses on categorizing missense mutations—genetic changes that can produce different amino acids at specific positions in proteins. These mutations can significantly alter protein function. AlphaMissense assigns a likelihood score to determine whether a mutation is pathogenic or benign.
“Understanding and predicting those effects is crucial for the discovery of rare genetic diseases,” Kohli says.
#### Expanding Genetic Classification
Released last year, AlphaMissense has classified around 89 percent of all possible human missense mutations. Previously, only 0.1 percent of these variants had been clinically classified by researchers.
### The Future of AI in Biomedical Research
“This is just the beginning,” Kohli says. Ultimately, he believes AI could eventually lead to the creation of a virtual cell that could radically accelerate biomedical research, enabling biology to be explored in-silico rather than in real-world laboratories. “With AI and machine learning we finally have the tools to comprehend this very sophisticated system that we call life.”
This article appears in the July/August 2024 issue of [WIRED UK magazine](https://www.wired.co.uk/).
1 Comment
Isn’t it risky to let AI decode the secrets of life?