Though it is a cornerstone of virtually every process that occurs in living organisms, the proper folding and transport of biologicalProtein is a notoriously difficult and time consuming process to study.
In a new paper published in eLife, researchers from the School of Biological Sciences and the School of Computer Science show that they can lend a hand.
Building on the models of DeepMind's AlphaFold 2, a machine learning tool can predict the detailed three-dimensional structures of individual proteins. AF2Complex is able to calculate which proteins are likely to interact with each other thanks to these predictions.
Jeffrey Skolnick is a professor and chair in the school of biological sciences and one of the authors. It's like using a computational microscope powered by deep learning and supercomputing with AF2Complex.
In their latest study, the researchers used amputational microscope to examine a complicatedProtein synthesis and transport pathway, hoping to clarify how proteins in the pathway interact to ultimately transport a newly synthesizedProtein from the inside to the outside of thebacteria Insights into this pathway may lead to the identification of new targets for antibiotic and therapeutic design.
The computing complexes are related.
AlphaFold 2 is a deep learning tool that can be used to generate predictions about the three-dimensional structure of single genes. Taking things a step further, AF2Complex uses these structures to predict the likelihood that proteins will interact to form a functional complex, what aspects of each structure are likely interaction sites, and even whatprotein complexes are likely to pair up to create even larger functional groups called supercomplexes
Mu Gao, a senior research scientist at Georgia Tech, said that the successful development of AF2Complex earlier this year made them believe that this approach has tremendous potential in identifying and characterizing the set ofprotein-protein interactions important to life. We had to show it with a high impact application in order to convince the community.
Escherichia coli is a model organisms used in life sciences research due to its simplicity and rapid growth.
In order to demonstrate the tool's power, the team examined the synthesis and transport of OMPs, which are essential for responding to environmental stressors. Gram-negativebacteria have a large family ofbacteria characterized by the presence of inner and outer Membranes. The cells must be moved to their final destinations.
Some of theProtein complexes of key players, but not all of them, have been identified after more than two decades of experiments. Some novel and interesting features of the OMP biogenesis pathway were missed in previous experiments.
Insights that are new.
The team used the Summit supercomputer at the Oak Ridge National Lab to put the project to the test. To see which pairs the tool was most likely to interact with, they compared a few proteins known to be important in the synthesis and transport of OMPs.
The tool's predictions were compared to experimental data to see if they were right. Skolnick said that they found previously known interacting partners. Structural details of those interactions that explain data from previous experiments were highlighted by the tool.
Several unknown pairs were predicted by AF2Complex. What aspects of the pairs might interact to form larger groups of functional proteins, likely active configurations of complexes that have previously been elusive to experimentalists, and new potential mechanisms for how OMPs are synthesised and transported were all revealed.
The key proteins involved in this pathway could be a novel target for new antibiotics since it is vital and unique to gram-negativebacteria. Our work may be useful to new therapeutic design.
The researchers are hoping that AF2Complex will mean big things for biology research.
Predicting the structural model of a supercomplex can be difficult if the components of the complex are not known. "In this regard, AF2Complex could be a new computational tool for biologists to conduct trial experiments of different combinations of genes, potentially speeding up and increasing the efficiency of this type of biology research as a whole."
The public is able to download the open-sourced tool.
More information is available from Mu Gao et al. You can find it in the eLife.
Journal information: eLife
All Rights Reserved © 2024
