How artificial intelligence is advancing structural proteomics

This article is based on research findings that have not yet been peer reviewed. The results are therefore considered preliminary and should be interpreted as such. Discover the role of the peer review process in research here. For more information, please contact the quoted source.

Understanding the formation of protein complexes 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 pre-print released earlier this year, a new machine learning model – EquiDock – was introduced that can quickly predict how two proteins will interact. Unlike other approaches, the model does not rely on heavy candidate sampling and has been shown to achieve predictions up to 80 to 500 times faster than popular docking software.

To learn more about EquiDock and how artificial intelligence (AI) methods are advancing the field of structural proteomics, Technology networks spoke to the co-lead author of the article, Octave-Eugen Ganeapostdoctoral researcher at MIT’s Computer Science and Artificial Intelligence Laboratory.

Molly Campbell (MC): For our readers who may not be familiar, 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 biological processes in our body. Two or more proteins with different functions interact and form larger machines, i.e. 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 binding to specific parts of its surface. I am interested in using deep learning to model these interactions and to help and accelerate the research of chemists and biologists by providing better and faster computational tools.

CM: How AI-Based Methods Advance the Field of Proteomics and specifically structural proteomics?

OG: Biological processes are inherently very complicated and have their own mysteries, even for experts in the field. For example, to understand how interacting proteins attach to each other, humans or computers must try all possible combinations of attachment in order to find the most plausible. Intuitively, having two three-dimensional objects with very irregular surfaces, one should rotate them and try to anchor them in every possible way until one could find two complementary regions on both surfaces that would match very well in terms geometric and chemical patterns. . This is a very time consuming process for both manual and computer approaches. In addition, biologists are interested in discovering new interactions across a very large number of proteins such as the human proteome with a size of about 20,000. This is important, for example, to automatically discover side effects unexpected from new treatments. Such a problem now becomes similar to an extremely large 3D puzzle where you have to simultaneously scan pieces to find the ones that match, as well as figure out how each pair attachment occurs by trying all possible combinations and rotations.

MC: Can you explain how you created EquiDock?

OG: EquiDock takes the 3D structures of two proteins and directly identifies areas that might interact, which would otherwise be a complicated problem even for an expert in biology. The discovery of this information is then enough to understand how to rotate and orient the two proteins in their attached positions. EquiDock learns to capture complex docking patterns from a large ensemble of approximately 41,000 protein structures using a geometrically constrained model with thousands of parameters that are dynamically and automatically adjusted until they solve the task very well.

MC: What are the potential applications of EquiDock?

OG: As already mentioned, EquiDock can enable rapid computer analysis of drug side effects. This goes hand in hand with large-scale virtual screening of drugs and other types of molecules (eg, antibodies, nanobodies, peptides). This is necessary in order to significantly reduce an astronomical research space that would otherwise be unfeasible for all of our current experimental capabilities (even aggregated on a global scale). A fast protein-protein docking method like EquiDock combined with a fast protein structure prediction model (like AlphaFold2 developed by DeepMind) would help in drug design, protein engineering, gene antibody or understanding the mechanism of action of a drug, among many other exciting applications. a critical need in our search for better treatments for disease.

Octavian Ganea was speaking to Molly Campbell, Senior Science Writer for Technology Networks.

Previous Electronic tattoo provides continuous and highly accurate blood pressure monitoring
Next How the artistic director of the Moth spends her Sundays