Designing a protein is a bit like making a cabinet. The first step is building the backbone that holds the protein together. But then comes the hard part: figuring out where to install hinges on the scaffold\u2014that is, finding the best \u201chotspots\u201d\u2014to put on doors, shelves, and other attachments that ultimately make the cabinet fully functional.<\/p>\n
In a way, proteins also have hotspots embedded in their structures. True to their name, \u201cfunctional sites,\u201d these intriguing nooks and crannies form intricate docks for other proteins or drugs to grab onto. The sites are central to performing most of our basic biological processes. They\u2019re also a massive gold mine for designing new treatments and medical drugs.<\/p>\n
The problem? Functional sites are hard to map. Scientists traditionally had to mutate suspecting areas on a protein one by one\u2014switching one amino acid to another\u2014to nail down precise binding spots. Like a detective screening hundreds of suspects, of which there could be many, it\u2019s extremely tedious.<\/p>\n
A new study in Science overthrew the whole gamebook. Led by Dr. David Baker at the University of Washington, a team tapped into an AI\u2019s \u201cimagination\u201d to dream up a myriad of functional sites from scratch. It\u2019s a machine mind\u2019s \u201ccreativity\u201d at its best\u2014a deep learning algorithm that predicts the general area of a protein\u2019s functional site, but then further sculpts the structure.<\/p>\n
As a reality check, the team used the new software to generate drugs that battle cancer and design vaccines against common, if sometimes deadly, viruses. In one case, the digital mind came up with a solution that, when tested in isolated cells, was a perfect match for an existing antibody against a common virus. In other words, the algorithm \u201cimagined\u201d a hotspot from a viral protein, making it vulnerable as a target to design new treatments.<\/p>\n
The algorithm is deep learning\u2019s first foray into building proteins around their functions, opening a door to treatments that were previously unimaginable. But the software isn\u2019t limited to natural protein hotspots. \u201cThe proteins we find in nature are amazing molecules, but designed proteins can do so much more,\u201d said Baker in a press release. The algorithm is \u201cdoing things that none of us thought it would be capable of.\u201d<\/p>\n
The Protein Hotspot
\nBaker\u2019s team are no strangers to predicting proteins with artificial minds. A few years back, they rocked the structural biology field by releasing Rosetta, a software that can predict a protein\u2019s 3D structure based on its amino acid sequence alone. They further mapped protein complexes and designed protein \u201cscrewdrivers\u201d from scratch to pry apart undesirable protein interactions. Late last year, they released a deep learning network dubbed trRosetta, an AI \u201carchitect\u201d that generalizes how strings of amino acids arrange into intricate structures at the nanoscale.<\/p>\n