Last updated on January 19th, 2022 at 06:59 am
In a significant scientific advancement, DeepMind’s latest version of their AI System, AlphaFold has solved one of Biology’s grand challenges, i.e., predicting the structure of the protein, how they curl up to form amino acid chains into 3D shapes.
In its recent blog AlphaFold: a solution to a 50-year-old grand challenge in biology, Deepmind stated that “This breakthrough demonstrates the impact AI can have on scientific discovery and its potential to dramatically accelerate progress in some of the most fundamental fields that explain and shape our world.”
Table of Contents
CASP Update on Twitter
DeepMind has shared its latest break-through on Twitter in a thread:
We’re excited about the potential impact #AlphaFold may have on the future of biological research and scientific discovery. Thank you to the CASP organisers & the whole community – we look forward to the many years of hard work and discovery ahead: https://t.co/rBuRmgL37h
— DeepMind (@DeepMind) November 30, 2020
Nobel laureate and president of the Royal Society, Professor Venki Ramakrishnan says, “This computational work represents a stunning advance on the protein-folding problem, a 50-year-old grand challenge in biology. It has occurred decades before many people in the field would have predicted. It will be exciting to see the many ways in which it will fundamentally change biological research.”
What is CASP?
This complex problem is called Critical Assessment of protein Structure Prediction (CASP). In 1994, Professor John Moult and Professor Krzysztof Fidelis founded CASP as a biennial blind assessment to catalyze research, monitor progress, and establish the state of the art in protein structure prediction.
Every two years, more than 100 research groups take part in CASP and it is very common to observe that research group suspend their other researches and get ready with a new set of information and the latest tech to perform detailed predictions.
The Scientific Journal, Proteins publish the results of CASP in a special supplement issue. CASP13 came into public attention in 2019 when AlphaFold ( DeepMind’s AI program) had won it.
Version 2 of the program won CASP14 with a score of nearly 90/100 scale of prediction accuracy. You can further check the submission and results of AlphaFold2 on the official website, Prediction Center Results page.
How DeepMind AlphaFold works?
This video by DeepMind Science Engineer Kathryn Tunyasuvunakool precisely explains what protein folding is, why it’s important, and how AlphaFold offers a solution to this grand scientific challenge.
To know the inside story of the DeepMind team of scientists and engineers who created AlphaFold, refer to this video:
More from DeepMind
DeepMind is a dedicated team that works in the field of Artificial Intelligence research and development. DeepMind has been constantly working on providing better solutions to society.
One of the popular research work is “Identifying eye disease faster”. In partnership with Moorfields Eye Hospital, they work on developing quick ways to identify and understand common eye diseases. DeepMind AI system can recommend patient referrals for over 50 sight-threatening diseases.
The next prominent research is used in saving energy at a large scale, i.e. in Google Data Centres where it is necessary to keep the servers cool. Even a small improvement is helpful in a significant reduction of energy use and CO2 emissions.
The most famous one is the AlphaGo that defeated Lee Shedol in the game of GO. Now it is logically the strongest Go player of all time.
This game is considered one of the most challenging classical games for Artificial intelligence because of the complex nature of the game.
There is an interesting video of how the game won .I think this will be a bit scary but a funny end for this blog over the utilities and possibilities of Artificial intelligence.
This is all about the recent scientific advancement, which I love to share. If you have anything which you think we should talk about, please share in the comments or ping me on my social media handles.
This was informative. Thanks for sharing.
Thank you so much.