AI software can provide a “roadmap” for biological breakthroughs

AI software can provide a

This article was reviewed based on Science X’s editorial process and policies. The editors have highlighted the following attributes ensuring the credibility of the content:


peer-reviewed publication

trusted source


Credit: Nucleic acid research (2023). DOI: 10.1093/nar/gkad374

Predicting the location of a protein within a cell can help researchers unlock a plethora of biological information critical to the development of future scientific breakthroughs related to drug development and the treatment of diseases such as epilepsy. This is because proteins are the “workhorses” of the body, largely responsible for most cellular functions.

Recently, Dong Xu, Curator Distinguished Professor in the Department of Electrical and Computer Engineering at the University of Missouri, and colleagues updated their protein localization prediction model, MULocDeep, with the ability to provide more targeted predictions, including specific models for animals, humans and plants. The model was created 10 years ago by Xu and fellow MU researcher Jay Thelen, a professor of biochemistry, to originally study 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,” Xu said. “A more focused approach saves time. Our tool provides a useful resource for researchers by helping them get to their findings faster because we can help them design more focused experiments from which to advance their research more effectively.”

By harnessing the power of artificial intelligence through a machine learning technique, by training computers to make predictions using existing data, the model can help researchers who are studying the mechanisms associated with irregular protein positions, known as “mislocation” or where a protein goes to a different place than it should. This anomaly is often associated with diseases such as metabolic disorders, tumors and neurological disorders.

“Some diseases are caused by mislocalization, which causes the protein to be unable to perform a function as expected because it cannot reach a target or goes there inefficiently,” Xu said.

Another application of the team’s predictive model is to assist drug design by targeting an incorrectly located protein and moving it to the correct location, Xu said.

In the future, Xu hopes to increase the accuracy of the model and develop more features.

“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 in more precisely,” said Xu. “While we don’t offer any solutions for developing drugs or treatments for various diseases per se, our tool can help others develop medical solutions. Today’s science is like a big business. Different people play different roles and work together we can achieve much good for all”.

Xu is currently working with colleagues to develop a free online course for high school and college students based on the biological and bioinformatics concepts used in the model, and expects the course to be available later this year.

A conflict of interest was also noted by Xu and colleagues: while the online version of MULocDeep is available for use by academic users, a standalone version is also commercially available through a license fee.

“MULocDeep web service for prediction and visualization of protein localization at the subcellular and suborganellar levels,” was published in the journal Nucleic acid research. The co-authors are Yuexu Jiang, Lei Jiang, Chopparapu Sai Akhil, Duolin Wang, Ziyang Zhang and Weinan Zhang of MU.

More information:
Yuexu Jiang et al, MULocDeep web service for prediction and visualization of protein localization at the subcellular and suborganellar levels, Nucleic acid research (2023). DOI: 10.1093/nar/gkad374

About the magazine:
Nucleic acid research

#software #provide #roadmap #biological #breakthroughs

Previous articleAI-generated versions of art history paintings are flooding Google’s top search results | Artnet news
Next articleArtificial intelligence has given Palantir its mystique back


Please enter your comment!
Please enter your name here