How artificial intelligence promotes structural proteomics

How artificial intelligence promotes structural proteomics

This article is based on research findings that have not yet been reviewed. The results are therefore considered preliminary and should be interpreted as such. Find out what role the peer review process plays in research here. For further information, please contact the cited source.

Understanding protein complex formation is crucial in drug design and the development of therapeutic proteins such as antibodies. However, proteins can attach to each other in millions of different combinations and current docking solutions used to predict these interactions can be very slow. Faster and more accurate solutions are needed to streamline the process.

In a oppression published earlier this year, a new machine learning model was introduced – EquiDock – that can quickly predict how two proteins will interact. Unlike other approaches, the model does not rely on heavy candidate sampling and was found to reach predictions up to 80-500 times faster than popular docking programs.

To learn more about EquiDock and how artificial intelligence (AI) methods advance the field of structural proteomics, Technology network talked to the lead author of the newspaper, Octavian-Eugen Ganeaa postdoctoral fellow at the MIT Computer Science and Artificial Intelligence Laboratory.

Molly Campbell (MC): For our readers who may be unfamiliar, can you describe your current research focus in proteomics?

Octavian Ganea (OG): My research uses AI (specifically, deep learning) to model aspects of molecules that are important in various applications such as drug discovery.

Proteins are involved in most of the biological processes in our bodies. Two or more proteins with different functions interact and form larger machines, ie complexes. They also bind to smaller molecules such as those found in drugs. These processes alter the biological functions of individual proteins, for example, an ideal drug would inhibit a carcinogenic protein by attaching to specific parts of its surface. I am interested in using in-depth learning to model these interactions and to help and accelerate the research of chemists and biologists by providing better and faster computational tools.

MC: How AI-based methods promote the proteomics field and specifically structural proteomics?

AND: Biological processes are by nature very complicated and have their own mysteries, even for domain experts. For example, to understand how interacting proteins attach to each other, humans or computers must try all possible binding combinations to find the most reasonable one. Intuitively, with two three-dimensional objects with very irregular surfaces, you have to rotate them and try to dock them in every possible way until you can find two complementary regions on both surfaces that would match very well in terms of their geometric and chemical patterns. This is a very time consuming process for both manual and computational. In addition, biologists are interested in discovering new interactions over a very large set of proteins such as the human proteome in the size of ~ 20,000. This is important, for example, to automatically detect unexpected side effects of new treatments. Such a problem now resembles an extremely large 3D puzzle where you must simultaneously scan pieces to find matching, and understand how each individual paired fortress is done by trying all possible combinations and rotations.

MC: Can you explain how you created EquiDock?

AND: EquiDock takes the 3D structures of two proteins and directly identifies which areas are likely to interact, which would otherwise be a complicated problem even for a biology expert. Discovering this information is then sufficient to understand how to rotate and orient the two proteins in their fixed positions. EquiDock learns to capture complex docking patterns from a large set of ~ 41,000 protein structures using a geometrically limited model with thousands of parameters that are adjusted dynamically and automatically until they solve the task very well.

MC: What are the potential applications of EquiDock?

AND: As already mentioned, EquiDock can enable rapid computational screening of drug side effects. This goes hand in hand with massive scale virtual screening of drugs and other types of molecules (eg antibodies, nanobodies, peptides). This is needed to significantly reduce an astronomical search space that would otherwise be impossible for all of our current experimental capabilities (even globally aggregated). A fast protein-protein docking method like EquiDock combined with a fast protein structure prediction model (like AlphaFold2 developed by DeepMind) would help drug design, protein technology, antibody generation or understand a drug’s mechanism of action, among many other exciting applications needed in our search for better disease therapies.

Octavian Ganea spoke with Molly Campbell, Senior Science Writer for Technology Networks.

#artificial #intelligence #promotes #structural #proteomics

Leave a Comment

Your email address will not be published.