Does deep learning induce a strategic inflection point in how we study disease?

[agitter]

The partner issue #93 defines the term "strategic inflection point", and here we can organize the discussion of methods that could be used to study disease. These are biological applications that do not have an immediate connection to disease or health.

As an example, I'll nominate #91. What stood out was that they can correctly fold 224 of 579 test proteins when previous methods, including the CASP11 winner, can do 79 or 62.