'Scientific Breakthrough': AI program solves decades-long ‘protein folding problem’

An artificial intelligence (AI) created in UK has cracked deces-long 'protein folding problem’ after it mapped out ir 2D structures and distinguished between different s of proteins. For more than 50-years, scientists were unable to decode biology’s one of biggest challenges that could help in development of treatments and drug effectiveness. On vember 30, however, a London-based Google-owned artificial lab DeepMind anunced that its program AlphaFold was w able to detect many shapes of proteins that could accelerate research in fields of drug design, treating diseases, and environmental sustainability. 

“Figuring out what shapes proteins fold into is kwn as  protein folding problem, and has stood as a grand challenge in biology for past 50 years,” AI lab informed in a release.

It ded, that large complex molecules composed of ami acids were comprised in all life forms’ supporting systems, including in COVID-19 disease-causing viruses SRAS-coV-2 and in cancer cells.

In a breakthrough, DeepMind’s biennial Critical Assessment of protein Structure Prediction (CASP) was able to detect how proteins fold up by thorough assessment of several experimentally determined protein structures. In total, re are approximately 200 million kwn proteins that exist. Researchers from 14th Community Wide Experiment on Critical Assessment of Techniques for Protein Structure Prediction (CASP14) solved 1994 riddle by creating an attention-based neural network system that was trained end-to-end to interpret structures using latest version of AI AlphaFold. 

Re: 'Super Planet' Discovered By Scientists Using Rio Telescope For First Time

Re: Scientists Create Diamonds In Lab At Room Temperature By Mimicking Asteroid Collision

[Two examples of targets in free modelling category. Credit: Deepmind site]

'Trained' on 170,000 protein structures

“AI system developed strong predictions of underlying physical structure of protein and is able to determine highly-accurate structures in a matter of days,” scientists informed in a release. y ded, that AlphaFold could also predict “which parts of each predicted protein structure were reliable.” AlphaFold was trained on 170,000 protein structures, generated an aver accuracy score of 92.4 out of 100 in prediction. “This computational work represents a stunning vance on protein-folding problem, a 50-year-old grand challenge in biology,” said President of Royal Society Venki Ramakrishnan. “It will be exciting to see many ways in which it will fundamentally change biological research,” he ded.

Re: Israeli Scientists Claim To Biologically Reverse Human ing Process For First Time Ever

Re: British Scientists 'fine Tuning' Process To Extract Oxygen From Moon Dust 'Lunar Regolith'