DeepMind gives scientists a voice using AlphaFold

AlphaFold, the artificial intelligence system that can accurately predict 3D models of protein structures from their amino acid sequences developed by DeepMind, has revolutionized proteomics research. Since its creation, it has accelerated research in many fields: drug discovery, vaccine development, food safety, bioinformatics, ecology, etc.

Deepmind proposed a first version of AlphaFold at CASP (Critical Assessment of protein Structure Prediction) in 2018, it got 1st place just like AlphaFold 2, the second version to which we also dedicated an article in our ActuIA magazine n. 3, did so in 2020.

In 2021, the company released the scientific paper and source code explaining how it created this artificial intelligence system and partnered with the European Bioinformatics Institute EMBL (EMBL-EBI) to create the AlphaFold DB platform to make these forecasts are freely available to the scientific community. The latest version of the database contains over 200 million entries, providing broad coverage of UniProt, the standard repository for protein sequences and annotations.

Some of the advances made with AlphaFold shared by DeepMind

DeepMind shared the progress of the work of several scientists.

Matthew Higgins and his team: development of an effective drug to eradicate malaria

Malaria, or malaria, killed an estimated 627,000 people in 2020, mostly children under five, with Africa by far the hardest hit.

the Plasmodium, the parasite responsible for malaria, is transmitted to humans by an infected female mosquito, then infects liver cells, then circulates in the blood by colonizing red blood cells. It produces proteins that attach to the surface of the host cell, only one at a time appearing on the surface of the red blood cells, preventing the immune system from responding correctly.

Biochemist Matthew Higgins, a professor of molecular parasitology at Oxford University, created a research team in 2006 with a desire to discover a truly effective vaccine, but faced the challenge of the metamorphic nature of malaria parasites.

Currently, RTS, S, better known as Mosquirix, is the only approved inoculation. It is a vaccine based on recombinant proteins active against Plasmodium falciparum, the main parasite responsible for malaria. Designed for children and approved by the WHO in October 2021, it only targets the first stage of infection, when the malaria parasite is transported to the liver and its effectiveness rate is only around 30%.

The Jenner Institute, another team from the University of Oxford, recently reported promising results from another similar vaccine. His approach, which consists of three doses followed by a booster one year later, has an efficacy rate of 77%. However, like Mosquirix, this vaccine targets the early prehepatic stage of the malaria parasite’s life cycle.

The goal of Matthew Higgins and his Oxford-based collaborators Simon Draper and Sumi Biswas was to develop vaccine immunogens for a multiphase vaccine that could function simultaneously at each stage of the infection cycle, targeting the invasion of blood cells that infection follows, but also the final reproductive phase of the parasite’s life cycle. This step is very important because infected humans can in turn transmit the parasite to previously uninfected mosquitoes if they are bitten again, thus continuing the cycle.

Until the arrival of AlphaFold, their models were flawed and incomplete, but according to Matthew Higgins “AlphaFold has allowed us to take our project to the next level, from basic science to preclinical and clinical development.. “

He also said:

“I’m sure AlphaFold’s predictions will get better and better. But for now, combining experimental knowledge with AlphaFold models is the optimal approach, because it allows us to put it all together. This is the approach we take for many of our projects. “

Zhong Yan Gan uncovers crucial information on the molecular basis of Parkinson’s disease

More than 10 million people worldwide are living with Parkinson’s disease, 4% of them diagnosed before age 50, while early-stage Parkinson’s disease symptoms affect 10 to 20%.

The doctoral research of Zhong Yan Gan, a doctoral student in Professor David Komander’s laboratory, co-supervised by Associate Professor Grant Dewson, at WEHI (Walter and Eliza Hall Institute of Medical Research) in Melbourne, Australia, focuses on understanding the PINK1 protein and how it works in our cells to trigger the recycling of damaged mitochondria, a process known as mitophagy. Mitophagy is essential for maintaining the health of our cells, and when PINK1 is defective, it leads to the death of neurons in our brains and the development of early-stage Parkinson’s disease.

Understanding PINK1 and its role

A 2004 study showed that PINK1 could cause Parkinson’s disease, although finding that its structure became a crucial problem, human PINK1 was too unstable to be produced in the laboratory, so scientists opted for versions of insects (such as human lice), more stable, to study it.

Komander’s lab team published the PINK1 structure in 2017, other researchers published different structures for the same protein from a different insect (meal beetle).

Zhon Yan Gan wondered if the published structure was actually a snapshot of PINK1 during a single phase of a longer process and decided, as part of his doctoral project, to determine PINK1 at each stage of his process. activation. His work showed that PINK1’s published structures were not a mistake and that they were different shapes the protein takes on at different stages of its activation process.

To understand the implications of their findings for humans with Parkinson’s, David Komander and his team had to determine whether their findings extended to the human version of the protein and turned to AlphaFold.

Zhon Yan Gan inserted two protein sequences into AlphaFold to predict the structure of a PINK1 dimer in humans, the result being nearly indistinguishable from his experimental work with the insect protein.

David Komander said:

“We were able to immediately generate real information for people who have these particular mutations. We can start thinking, “What kind of drugs do we need to develop to repair the protein, rather than just dealing with the fact that it is broken. “

Melissa Formosa: predicting and fighting the onset of osteoporosis

According to the National Institute of Health and Medical Research (INSERM), osteoporosis is the cause of nearly 400,000 fractures each year in France. Almost 40% of women over 65 are affected by this disease. Although osteoporosis has a strong genetic component, little scientific research has focused on its causes.

Bone is a living tissue that is constantly rebuilding itself to maintain its strength. The old damaged bone is replaced with new healthy bone. Mutations in the WNT1 gene (an osteoblast, or bone-making cell), disrupt the bone-building process so that carriers have brittle bones and suffer from early osteoporosis. This tends to show that osteoporosis cannot be considered a disease that affects only the elderly.

A fracture is still often the first indication of the presence of osteoporosis. According to Melissa Formosa, it is necessary to find biomarkers: a blood test, a gene or a protein to look for a predisposition or a high risk of developing osteoporosis and thus begin to fight the disease before it even begins.

To this end, his team used AlphaFold to try to better understand the genetic causes: When we insert the amino acid sequence into the AlphaFold software, it creates a 3D image of what the protein structure looks like and allows us to compare the protein structures encoded by normal and faulty genes. With AlphaFold, we can visualize the impact of specific genetic mutations, some of which can cause only subtle structural changes. Others induce significant deformations of the protein, reducing its ability to function properly, contributing to the disease. “

The goal is to develop simple blood tests for young adults to better predict the disease and find new genes and proteins associated with the disease in order to develop better drugs to treat it. Early diagnosis and the introduction of personalized medicine could mean that osteoporosis can be managed much more effectively, millions of lives could be vastly improved.

These three use cases of AlphaFold are far from the only ones presented by DeepMind citing Drugs for Neglected Diseases (DNDi) for example advancing drug discovery for neglected diseases, such as Chagas disease and leishmaniasis, which affect millions of people in poverty and vulnerable communities; or the Center for Enzyme Innovation (CEI), where researchers discover and design enzymes to break down single-use plastics …

Leave a Reply

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