Researchers could have access to a wealth of biological knowledge by predicting where proteins will be found within a cell. This knowledge is essential for generating future scientific discoveries connected to medication development and treating conditions like epilepsy. That is because proteins serve as the body’s “workhorses,” in charge of most cellular operations.
Dong Xu. Image Credit: University of Missouri
The University of Missouri’s Dong Xu, Curators Distinguished Professor in the Department of Electrical Engineering and Computer Science, and colleagues recently updated their protein localization prediction model, MULocDeep, to be able to make more precise predictions, including models specifically for plants, animals, and humans.
Xu and Jay Thelen, a professor of biochemistry at MU, developed the model ten years ago with the intention of originally examining proteins in mitochondria.
Many biological discoveries need to be validated by experiments, but we don’t want researchers to have to spend time and money conducting thousands of experiments to get there. A more targeted approach saves time. Our tool provides a useful resource for researchers by helping them get to their discoveries faster because we can help them design more targeted experiments from which to advance their research more effectively.
Dong Xu, Curators Distinguished Professor, Department of Electrical Engineering and Computer Science, University of Missouri
The model can assist researchers who are looking at the mechanisms underlying irregular protein locations, also known as “mislocalization,” or when a protein goes to a different place than it is intended to, by harnessing the power of artificial intelligence through a machine learning technique.
This anomaly is frequently linked to diseases, including cancer, neurological disorders, and metabolic disorders.
Xu stated, “Some diseases are caused by mislocalization, which causes the protein to be unable to perform a function as expected because it either cannot go to a target or goes there inefficiently.”
The team’s predictive model can also be used to help with drug design by focusing on misplaced proteins and relocating them, according to Xu.
Currently, the National Science Foundation is funding the work. To assist in improving the model’s accuracy and include more features, Xu wants to get more money in the future.
“We want to continue improving the model to determine whether a mutation in a protein could cause mislocalization, whether proteins are distributed in more than one cellular compartment, or how signal peptides can help predict localization more precisely. While we don’t offer any solutions for drug development or treatments for various diseases per se, our tool may help others for their development of medical solutions. Today’s science is like a big enterprise. Different people play different roles, and by working together we can achieve a lot of good for all, Xu further stated.
Xu is also working with collaborators to create a free online course for high school and college students that will be based on the biological and bioinformatics ideas utilized in the model, and he anticipates that the course will be accessible later this year.
Xu and colleagues also point out a conflict of interest: MULocDeep has an online version that academic users can access, but a standalone version is also offered commercially in exchange for a licensing charge.
Journal Reference
Jiang, Y., et al. (2023) MULocDeep web service for protein localization prediction and visualization at subcellular and suborganellar levels. Nucleic Acids Research. doi:10.1093/nar/gkad374