The human surfaceome: AI flags potential cell surface drug targets overlooked by major databases
More than 65% of approved medicines work by binding to proteins on the surface of human cells. Yet scientists developing new treatments face a fundamental problem: Major biological databases disagree about which proteins are actually found on cell surfaces.
In a groundbreaking study, an AI-powered map of the human surfaceome—proteins found on the surface of human cells—has highlighted potential drug targets previously overlooked by major biological databases. Lead researcher Becca Carlson and her team at the Deliverome Project conducted an exhaustive comparison of five widely-used databases, including UniProt, GO CC, the Human Protein Atlas, the Cell Surface Protein Atlas, and SURFY, which collectively identify only 188 surface proteins out of 5,546.
Utilizing Claude Sonnet 4.6, the AI agent accurately classified 95.7% of proteins in a benchmark test of 147 proteins, significantly outperforming UniProt's 90% accuracy. Among the newly identified candidates are proteins like KLK2, which all five databases classified as absent from the cell surface, but which research has shown to be enriched in prostate cancer.
This AI-assisted analysis could help researchers identify new drug targets, leading to more diverse treatments for various diseases. The team has made the findings accessible through an open, interactive map and free tools, aiming to expand the number of potential drug targets and improve treatment outcomes.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
