Story of AlphaFold

AlphaFold AI program is helping unravel protein structures, which will help build drugs better and faster.

 Story of AlphaFold

---

• The story: DNA makes RNA makes Proteins. While this truth is known to all biologists, the real challenge begins when they try finding the exact structures of various proteins, which are complex molecules.
• On proteins: Proteins are long chains of amino acids linked together like beads on a string. But for a protein to do its job in the cell, it must "fold" – a process of twisting and bending that transforms the molecule into a complex three-dimensional structure that can interact with its target in the cell. If the folding is disrupted, then the protein won't form the correct shape – and it won't be able to perform its job inside the body. This can lead to disease – as is the case in a common disease like Alzheimer's, and rare ones like cystic fibrosis.
• Protein-folding: It is the process by which a protein takes its shape from a string of building blocks to its final three-dimensional structure, which determines its function. By better predicting how proteins take their structure, or "fold," scientists can more quickly develop drugs that, for example, block the action of crucial viral proteins.
• A Himalayan climb: In the field of structural biology, figuring out the constituent structure of organic life forms need to find how the constituent proteins look like. With the coronavirus pandemic hitting the world, its importance was self-evident. It's because the protein structure is known that it's possible to say which are the parts of the virus that bind strongest to human cells or what parts are most vulnerable to vaccines.
• Technical details: In various organisms, the genes code for amino acids which then code for proteins, that are then responsible for the functioning of the cells. But predicting their 3-D structure is quite tough.

1. The traditional method is X-ray crystallography where beams are fired at crystallised proteins and based on how the rays diffract, maps are prepared on how the proteins maybe arranged in three dimensions.
2. Deducing a protein structure involves figuring out how amino acids are arranged and they manner in which they twist and turn and thereby generating insight into their function.
3. With more and more computer power, computer scientists began to work out ways to automate the process. But can a programme successfully predict such shapes?

• AlphaFold arrives: For many years, the answer was no. The first breakthrough came in 2018, when at a competition called Critical Assessment of Structure Prediction (CASP), AlphaFold, an Artificial Intelligence programme that relies on deep learning techniques, came out tops compared to other programs.

1. In 2020, AlphaFold was so good, that some of its structural predictions were indistinguishable from those predicted by Xray crystallography and newer lab methods such as cryo-electron microscopy.
2. AlphaFold is the product of DeepMind, a Google affliated company that every few years makes headlines for outcompeting humans at solving problems that, it was believed, could only be done by human imagination. For instance beating the best human players at the game of Go. DeepMind programmes are self learning and not explicitly programmed—like say early chess programmes—to achieve optimum outcomes.
3. Thus, DeepMind's protein-folding AI has solved the 50-year-old grand challenge of biology. AlphaFold can predict the shape of proteins to within the width of an atom. The breakthrough will help scientists design drugs and understand disease.

• The future: A future in which AlphaFold can solve complex structure opens new ways to understand the organisational structure of living beings, new solutions to disease and maybe unprecedented insight into how we are. Once humanity masters the way to decipher how proteins are folded, the path to drug discovery will be considerably shortened.

 

Join PT courses | PT Youtube | PT App | Contribute |  Testimonials