After launching this first phase of data, DeepMind plans to continue to add protein reserves, which will be managed by Europe’s premier life science lab, the European Molecular Biology Laboratory (EMBL).
EMBL director general Edith Heard said DeepMind hopes to release predictions for 100 million protein structures, a dataset that will be transformative for our understanding of how life works.
Understanding the structure of proteins is useful for scientists in many fields. The information can help design new drugs, synthesize new enzymes that break down waste materials, and create plants that are resistant to viruses or extreme weather.
DeepMind protein predictions are already being used for medical research, including studying how SARS-CoV-2, the virus that causes COVID-19, works.
Also Read:
Nasa Will Soon Build a Bigger and More Capable Mars Helicopter
–
–
New data will accelerate these efforts, but the scientists note that it will still take a lot of time to turn this information into real-world results.
In particular, the DeepMind software generates protein structure predictions rather than experimentally defined models, meaning that in some cases, further work will be required to verify the structure.
DeepMind says it has spent a lot of time building accuracy metrics into its AlphaFold software, which ranks how confident each prediction is.
Determining protein structure through experimental methods is expensive, time-consuming, and relies on a lot of trial and error.
Also Read:
That means even low-confidence predictions can save scientists years of work time by pointing them in the right direction for research.
Editor : Good Fit
Writer : Aris N
– .
