AI that identifies the location and expression of proteins could provide boost to drug development

In a study published in Communications Biology, researchers at Surrey University's Institute for People-Centred AI demonstrate how the HCPL (Hybrid subCellular Protein Localiser) requires partially labelled data to learn how to decipher the locations of proteins within cellular structures and their behaviour in different cells.

The team tested the HCPL on the Human Protein Atlas and found it to be the most accurate tool for identifying the location of proteins within individual cells.

In a statement, Professor Miroslaw Bober, HCPL project leader, said: "To understand how proteins work inside cells, scientists need to study where they are located, but this can be a time-consuming and complicated process. HCPL makes this process easier.

"This program uses a deep-learning model to quickly and accurately identify subcellular structures where proteins are present inside individual cells. We are hopeful that HCPL can help scientists study how proteins work and develop new treatments for diseases."