A Harvard Medical School scientist has used end-to-end differentiable deep learning to predict the 3D structure of effectively any protein based on its amino acid sequence. He achieved accuracy comparable to current state-of-the-art methods but at speeds upward of a million times faster.

See the source article by following the link below:
A Harvard Medical School scientist has used end-to-end differentiable deep learning to predict the 3D structure of effectively any protein based on its amino acid sequence. He achieved accuracy comparable to current state-of-the-art methods but at speeds upward of a million times faster.