AlphaFold and the End of the Protein Folding Problem
John Jumper et al. (DeepMind) · 2021
"For fifty years, going from a protein's amino-acid sequence to its three-dimensional shape took months or years of experiment per protein. In 2020 a neural network did it in minutes at near-experimental accuracy, and two years later the predicted structure of nearly every catalogued protein was free to download."
By 2020, after decades of X-ray crystallography, NMR and cryo-electron microscopy, biologists had determined the structures of roughly 100,000 unique proteins. Sequencing had by then catalogued billions. The gap existed because a protein's shape — the thing that decides what it does — is encoded in its sequence in a way nobody could compute: Christian Anfinsen showed in the 1960s that sequence alone determines the fold, and Cyrus Levinthal pointed out that a chain trying its conformations at random would take longer than the age of the universe to find the right one. At the 2020 CASP14 blind assessment, DeepMind's AlphaFold produced predictions competitive with experimental structures for a majority of targets, with a median accuracy score of 92.4 GDT. The organizers said the problem was, in essence, solved.
Read more about the topic
Prime Editing and the Reprogrammable Human Genome
"CRISPR 2.0 (Prime Editing) elevates genetic modification from a crude cutting tool to a precise word processor, unlocking the capability to cure most genetic diseases and propelling humanity into an era of directed, non-Darwinian evolution."