Artificial biosensor measures stress hormone at home

Researchers developed the tool using artificial protein design, a method that uses AI-guided computation to create proteins from scratch, rather than modifying those found in nature.

The team was led by Andy Yeh, assistant professor of biomolecular engineering at the University of California, Santa Cruz.

When cortisol is present, it triggers two designed proteins to move closer together at a molecular level, producing light — with more light indicating higher cortisol. The sensor works across the full range of levels relevant to human health.

Yeh said: “You can read the signal directly — the output of the sensor is light emissions, so essentially you can just take a picture of the test with your smartphone.

“Ideally, that’s really field compatible.”

The test provides quantitative results for healthy, low and elevated cortisol levels. Traditional hospital tests often lack this range of detail, particularly outside the normal range.

Yeh added: “This sensor is very, very sensitive compared to the current standard methods used in the hospital.

“The dynamic range is huge compared to the traditional assay.”

Cortisol imbalance can lead to a number of health issues, but current testing typically requires costly equipment and a clinical setting.

This new diagnostic method uses a simple “mix and read” format — similar to lateral flow tests used during the Covid-19 pandemic — and could support point-of-care testing in clinics or at home without laboratory tools.

According to Yeh, this may be the first biosensor entirely designed using computational techniques to reach such high sensitivity and dynamic range for detecting a small molecule — the term for a substance being analysed in a diagnostic test.

The technology could also support research and drug development aimed at understanding and treating health problems linked to cortisol deficiency or excess.