Audio version of the article
Scratching the surface in terms of scientific progress to be made.
It is quite difficult to determine the three-dimensional shapes of biological molecules, especially in modern biology and medical discoveries. The task often requires millions of dollars and even enormous efforts. Stanford University scientists have now developed an approach that overcomes this problem due to the prediction of computationally accurate structures. The new approach uses new machine learning techniques.
During testing, it was found that the approach accurately predicts the 3D shapes of drug targets and other important biological molecules, even when limited data are available, making it applicable to types of molecules whose structures are more difficult to determine experimentally. Using predictions, the algorithm enables scientists to explain how various molecules work, with applications ranging from basic biological research to well-founded drug development practices.
Stanford University Ph.D. student Raphael Townshend said, “Structural biology, which is the study of the shapes of molecules, has this mantra that structure determines function.”
Stanford University Ph.D. student Stephan Eismann said, “Proteins are molecular machines that perform all sorts of functions. To execute their functions, proteins often bind to other proteins. If you know that a pair of proteins is implicated in disease and you know how they interact in 3D, you can try to target this interaction very specifically with a drug.”
Rather than determining what an underlying forecast makes fairly accurate, the analysts let the algorithm discover these molecular features for itself, since they found that the conventional way of providing such knowledge can affect a computation for certain elements and prevent it from others Discover educational opportunities.
Eismann said, “The problem with these hand-crafted features in an algorithm is that the algorithm becomes biased towards what the person who picks these features thinks is important, and you might miss some information that you would need to do better.”
Townshend said, “The network learned to find fundamental concepts that are key to molecular structure formation, but without explicitly being told to. The exciting aspect is that the algorithm has clearly recovered things that we knew were important, but it has also recovered characteristics that we didn’t know about before.”
The scientists then applied their algorithm to another class of critical biological molecules, RNAs. They tested their algorithm on a series of “RNA puzzles” from a long-term competition in their field. In all cases the tool outperformed all other puzzle participants and did so, without being explicitly designed for RNA structures.
Ron Dror, associate professor of computer science, said, “Most of the dramatic recent advances in machine learning have required a tremendous amount of data for training. The fact that this method succeeds given very little training data suggests that related methods could address unsolved problems in many fields where data is scarce.”
Townshend said, “Once you have this fundamental technology, then you’re increasing your level of understanding another step and can start asking the next set of questions. For example, you can start designing new molecules and medicines with this kind of information, which is an area that people are very excited about.”