TLDRocket
Sign in

Anemo Labs lands £700K to give AI a sense of smell

Tech.eu Tamara Djurickovic

Anemo Labs just raised £700K to build an AI nose for disease screening. It’s aiming for non-invasive tests from smell, starting with urine.

Based on reporting by Tech.eu, Tamara Djurickovic — read the original for the full story.

Summary, retelling and take written by AI under human oversight; images are AI-generated illustrations. How we work · Report an error

Anemo Labs has raised £700,000 in pre-seed funding to build software and hardware that can pick up disease-related compounds by smell. The London deeptech startup says the round was led by Zinc and SFC Capital, with support from Innovate UK.

Founded in 2025 by Koye Sodipo, the company is working on an electronic nose, or e-nose, that combines sensor hardware with AI models. The idea is to detect and classify volatile organic compounds, the VOCs that make up smell. Anemo is starting in healthcare, where changes in the body’s chemical output can reveal useful clinical signals.

Its first focus is urine. The company wants to analyse VOCs from urine to support non-invasive screening and, in some cases, spot signs of disease before symptoms appear. Longer term, it is looking at diagnostic uses for conditions including urinary tract infections and certain cancers, where smell-related changes can be clinically meaningful.

This is not just a sensor project dressed up with machine learning. Anemo says it has an in-house sampling platform built to collect and label up to 5,000 smells a day, feeding training data into its models. Its team includes researchers with PhDs in sensor chemistry and electronics, while clinical advisers are helping with early validation work.

The company says early testing with the Sniffin' Sticks olfactory testing protocol produced 84.15 per cent correct classification across 12 scent categories. The new funding will go into sensor chemistry, smell data collection and labelling, and continued validation of the diagnostics platform with clinical partners.

My take — AI-written commentary, not fact-checked reporting

This is the kind of AI pitch that actually earns its keep: messy biology, real clinical use, and no grand talk of replacing doctors with vibes. The hard part is still the hard part — getting clean data, proving it in clinics, and avoiding the usual startup perfume cloud. But at least this one is aiming at molecules, not marketing slides.

Read more about this at: Tech.eu

Related stories

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.