Google unveils artificial intelligence to predict the behavior of human molecules

Artificial intelligence is giving machines the power to generate videos, write computer code and even carry on a conversation.

It is also accelerating efforts to understand the human body and fight disease.

On Wednesday, Google DeepMind, the tech giant's core AI lab, and Isomorphic Labs, a sister company, unveiled a more powerful version of AlphaFold, an AI technology that helps scientists understand the behavior of the microscopic mechanisms that drive cells on the planet. Human Body.

An early version of AlphaFold, released in 2020, solved a puzzle that had plagued scientists for more than 50 years. It was called “the protein folding problem”.

Proteins are the microscopic molecules that guide the behavior of all living things. These molecules begin as strings of chemical compounds before twisting and bending into three-dimensional shapes that define how they interact with other microscopic mechanisms in the body.

Biologists have spent years or even decades trying to pinpoint the shape of individual proteins. Then came AlphaFold. When a scientist fed this technology with a series of amino acids that make up a protein, he was able to predict its three-dimensional shape in just a few minutes.

When DeepMind publicly released AlphaFold a year later, biologists began using it to accelerate drug discovery. Researchers at the University of California, San Francisco have used the technology as they worked to understand the coronavirus and prepare for similar pandemics. Others used it as they struggled to find remedies for malaria and Parkinson's disease.

The hope is that this type of technology will significantly simplify the creation of new drugs and vaccines.

“It tells us a lot more about how the machines in the cell interact,” said Google DeepMind researcher John Jumper. “It tells us how it should work and what happens when we get sick.”

The new version of AlphaFold – AlphaFold3 – extends the technology beyond protein folding. In addition to predicting the shape of proteins, it can predict the behavior of other microscopic biological mechanisms, including DNA, where the body stores genetic information, and RNA, which transfers information from DNA to proteins.

“Biology is a dynamic system. You need to understand the interactions between different molecules and structures,” said Demis Hassabis, CEO of Google DeepMind and founder of Isomorphic Labs, also owned by Google. “This is a step in that direction.”

The company offers a website where scientists can use the AlphaFold3. Other labs, notably the University of Washington, offer similar technology. In a paper published Tuesday in the scientific journal Nature, Dr. Jumper and his fellow researchers demonstrate that it achieves a level of precision well beyond the state of the art.

The technology could “save months of experimental work and enable previously impossible research,” said Deniz Kavi, co-founder and chief executive of Tamarind Bio, a start-up developing technology to accelerate drug discovery. “This represents extraordinary promise.”

Leave a Reply

Your email address will not be published. Required fields are marked *