Using algorithms to track down cancer

Using algorithms to track down cancer
CEO Pe­ter Nestorov's (2nd from right) com­pany now em­ploys over 20 peo­ple (Pho­to­graph: ETH Zurich / Scai­lyte).

Modern medicine is looking for markers that provide early warning of complex diseases. In its quest to discover these "biomarkers," the ETH spinoff Scailyte has developed software capable of analysing millions of single cells very efficiently.

The search for is currently one of the biggest challenges of modern . One of the goals, for example, is for patients to be able to take a blood test to check whether they may have a disease, before the first symptoms make themselves known. If this were possible, patients could receive targeted treatment and in many cases even be cured. However, science is still grappling with the early detection of cancer and other complex diseases.

This is where the ETH spinoff Scailyte comes in. "Our algorithms analyse millions of single cells and identify patterns that point to specific diseases," says Peter Nestorov, CEO of Scailyte. He uses a metaphor to explain how the software works: "Imagine a fruit salad that tastes bad. Instead of trying to guess what the cause of the problem is by looking at the colour or the smell, we isolate every single component and analyse each one." The start-up plans to use this method to track down cancer and other complex diseases. The aim is "to improve and save lives," according to Scailyte's corporate vision.

Efficiency is one of the key strengths of Scailyte's software. While it would take several weeks to churn through the massive amounts of data using conventional methods, the software developed by the start-up is powered by and can complete this task in a few days. This is because the software can learn from data already processed and on this basis identifies abnormal cells associated with certain diseases. This method was developed and scientifically validated at ETH. The underlying algorithms were developed by Manfred Claassen, Professor for Computational Biology at ETH Zurich and his doctoral student, Eirini Arvaniti.

Alongside the decoding of DNA 50 years ago, single cell technology represents one of the biggest breakthroughs in biomedicine. Within the scientific community, extensive basic research is currently being conducted in this field. Scailyte's first step is therefore to bring its software to market for researchers to use—revenues should start to flow this autumn. But basic scientific research seldom leads directly to practical use in medicine. Scailyte wants to fill this gap in the mid-term. "Over the coming years we want to standardise the and offer it for clinical applications," Nestorov says. Services in the field of data analytics will also be part of the business model.

With a view to eventually delivering practical applications, Scailyte has already launched several projects in conjunction with various partners. Working with University Hospital of Zurich and the Inselspital university hospital in Bern, for example, the search is on for biomarkers for cancer—with some encouraging initial results already: "We have already identified certain characteristics," Nestorov says. Research work is still being conducted on the premises of the project partners at present, but Nestorov says they hope to move into their own laboratory soon.

Explore further

AI, robots, data software helping create new approach for planning cities of the future

Provided by ETH Zurich
Citation: Using algorithms to track down cancer (2019, August 5) retrieved 6 December 2019 from
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Feedback to editors

User comments