Hassabis and Jumper created AlphaFold, an AI tool that in 2020 solved an issue scientists have been wrestling with for many years: predicting the three-dimensional structure of a protein from a sequence of amino acids. The tool has since been used to predict the shapes of all proteins known to science. Their latest model, AlphaFold 3, can predict the structures of DNA, RNA, and molecules like ligands, that are essential to drug discovery. DeepMind has also released the source code and database of its results to scientists totally free.
Baker has created several AI tools for designing and predicting the structure of proteins, corresponding to a family of tools called Rosetta. In 2022, his lab created an open-source AI tool called ProteinMPNN that might help researchers discover previously unknown proteins and design entirely recent ones. It helps researchers who’ve a precise protein structure in mind find amino acid sequences that fold into that shape. Most recently in late September, Baker’s lab unveiled that they’d developed custom molecules that allow scientists to exactly goal and eliminate proteins which can be related to diseases in living cells.
“[Proteins] evolved over the course of evolution to unravel the issues that organisms faced during evolution. But we face recent problems today, like covid. If we could design proteins that were nearly as good at solving recent problems because the ones that evolved during evolution are at solving old problems, it might be really, really powerful,” Baker told in 2022.
