Through a massive speculative effort1– 4, the structures of around 100,000 distinct proteins have been determined5, but this represents a little portion of the billions of known protein sequences6,7. Predicting the 3-D structure that a protein will adopt based entirely on its amino acid series, the structure prediction component of the protein folding issue8, has actually been an essential open research study issue for more than 50 years9. Here we supply the very first computational technique that can regularly predict protein structures with atomic precision even where no comparable structure is known.