Deepmind likely solves protein structure prediction

Better link: https://www.nature.com/articles/d41586-020-03348-4

edit: It seems like the answer to my question is actually more or less in this article: https://deepmind.com/blog/article/alphafold-a-solution-to-a-...

"Since DNA specifies the amino acid sequences that comprise protein structures, the genomics revolution has made it possible to read protein sequences from the natural world at massive scale – with 180 million protein sequences and counting in the Universal Protein database (UniProt). In contrast, given the experimental work needed to go from sequence to structure, only around 170,000 protein structures are in the Protein Data Bank (PDB). "

So, basically, less than 0.1% of the proteins we are interested in, have structures determined via lab experiments. The Deep Mind method could fill in the remaining 99.9%

original: Question by someone who knows nothing about molecular biology: How many proteins exist that we are predominantly interested in? How many of those have known structures? And for the remaining, how long would it take humanity to find their structure through experiments instead of these computer models? (Do these questions even make sense?)

Solving protein folding has significant implications for medicine and drug development. If they can reverse the process (i.e., go from a desired 3D structure to an optimal 1D sequence), it will open up even more doors.