AI tool inspired by fraud detection pinpoints disease-linked proteins: Study

The tool, called Weighted Graph Anomalous Node Detection (WGAND), uses methods similar to those that detect fraud in social networks to analyse how proteins interact in the body, Xinhua news agency reported.

Published in the journal GigaScience, the algorithm spots unusual proteins that connect heavily with others and play central roles in biological processes -- key to understanding health and disease.

Proteins are essential molecules in our bodies, and they interact with each other in complex networks, known as protein-protein interaction (PPI) networks.

The team from the Ben-Gurion University of the Negev developed the algorithm to analyse these PPI networks to detect "anomalous" proteins -- those that stand out due to their unique pattern of weighted interactions.

This implies that the amount of the protein and its protein interactors is greater in that particular network, allowing them to carry out more functions and drive more processes.

Studying these networks helps scientists understand how proteins function and how they contribute to health and disease, said the team.

"This innovative algorithm has the potential to pinpoint which proteins are important in specific contexts, helping scientists to develop more targeted and effective treatments for various conditions," said Prof. Esti Yeger-Lotem, from the varsity

In tests, WGAND successfully identified proteins linked to brain and heart disorders, as well as those involved in essential functions like nerve signalling and muscle movement. Researchers from the Ben Gurion University (BGU) said it performed more accurately than existing methods.

By combining expertise in biology and cybersecurity, the tool could lead to more targeted medical treatments and provide new insights into how the human body works.

"It's exciting to see how bringing together expertise from bioinformatics and cybersecurity can lead to breakthroughs in understanding human biology. By applying network analysis and machine learning, we have developed a tool that helps uncover key proteins in different tissues -- paving the way for new insights into human health and disease," said Dr. Michael Fire, from the varsity.