The folded form of proteins dictate their function within the human bodies. The ability to predict a protein’s structure on the basis of its components will have vast implications for drug discovery and design.
Artificial intelligence is impacting novel drug discovery, and new deep learning techniques are now tacking on the the historical “protein folding problem.” DeepMind recently built a deep neural network, named AlphaFold system, which uses big genomic data to predict protein structure, and generate 3D models of folded proteins. DeepMind’s AlphaFold has predicted the distances between amino acid pairs and the angles between their chemical bonds with tremendous accuracy.