The most popular and comprehensive Open Source ECM platform
Understanding the proteins in living organisms is vital for developing drugs/medicines and understanding how organisms function. Every protein is made from a chain of amino acids. Scientists have been able to determine the amino acids in a protein but to determine the 3D structure of what the protein looks like typically was very time consuming. Until recently only about 17 percent of known proteins had 3D maps of their structure. The 3D structures of proteins are quite complex. They wrap and fold, forming creases similar to origami folding. Because of that, sometimes protein folding is called ‘paper folding’.
Last year, Google’s DeepMind group announced that they had developed an AI algorithm that could quickly determine the paper-folding structure of a protein given the constituent amino acid information. DeepMind released the information as a free on-line searchable database consisting of more than 350,000 different proteins. The biology community was amazed at the announcement. Many said that the information should speed up biological research by a factor of years.
Christine Orengo, a computational biologist at University College London (UCL), said that “it’s totally transformative from my perspective. Having the shapes of all these proteins really gives you insight into their mechanisms.”
Demis Hassabis, co-founder and chief executive of DeepMind, said that “this is the biggest contribution an AI system has made so far to advancing scientific knowledge. I don’t think it’s a stretch to say that.”
Hassabis told TechCrunch that “structural biologists are not yet used to the idea that they can just look up anything in a matter of seconds, rather than take years to experimentally determine these things. And I think that should lead to whole new types of approaches to questions that can be asked and experiments that can be done. Once we start getting wind of that, we may start building other tools that cater to this sort of serendipity: What if I want to look at 10,000 proteins related in a particular way? There isn’t really a normal way of doing that, because that isn’t really a normal question anyone would ask currently. So I imagine we’ll have to start producing new tools, and there’ll be demand for that once we start seeing how people interact with this.”