Researchers at Linköpin University have succeeded in integrating experimental data into the AI tool AlphaFold to efficiently develop new proteins for medical drugs, among other things.

There is a huge variety of proteins in all living organisms that regulate cell functions. Proteins are involved in everything that happens in the body, from controlling muscles and forming hair to transporting oxygen into the blood and digesting food. But proteins are also found outside the body in detergents and medical drugs.

Proteins are large molecules of 20 amino acids that stick together in long rows, much like beads in a necklace. The sequences, or chains, can be anything from 50 to a few thousand amino acids long. This gives rise to several billion different combinations, which determine the protein's three-dimensional shape.

Depending on the shape of the protein chain and the way it is folded, proteins have completely different functions. For over 50 years, researchers have been trying to predict and design different protein structures to gain a deeper understanding of the body's mechanisms and various diseases and to develop new types of medical drugs. This has been a laborious and expensive task involving a lot of manual handling.

But in 2020, the company Deepmind released open-source software called AlphaFold. It is an artificial intelligence based on neural networks that can predict with great accuracy how proteins will fold and thus what functions they will have. This breakthrough also resulted in the Nobel Prize in Chemistry 2024.

However, the program has had its limitations. Among other things, it has not been able to predict very large protein compounds nor draw conclusions from experimental or incomplete data.

Enhancing the model

Researchers at Linköping University have developed AlphaFold further to overcome these shortcomings. The tool, which they call AF_unmasked, can now take in information from experiments and partial data and predict very large and complex protein structures.

The idea behind AF_unmasked is for researchers to refine the experiments by guiding how the researchers could design the protein. This is a step toward an even better understanding of the functions of proteins and designing new types of protein drugs.

The AlphaFold breakthrough was made possible by researchers around the world collecting data on the structure of approximately 200,000 different proteins in a database since the 1970s. This database provided training data for AlphaFold. What finally made it work on a large scale was the technological development of supercomputers that use GPUs for heavy calculations.

Björn Wallner is a professor of bioinformatics at Linköping University and has worked with one of the three Nobel Prize winners.

"The possibilities for protein design are endless; only the imagination sets limits. It's possible to develop proteins inside and outside the body. You always have to find new, more difficult problems when you have solved the old ones. And within our field, finding problems is no problem," says Wallner.

Phys Org

Full Study- Nature