A team led by Dr Altuna Akalin, Head of the Bioinformatics and Omics Data Science Platform, Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC) has developed a machine learning programme called 'ikarus.' The programme found a pattern in tumour cells that is common to different types of cancer, consisting of a characteristic combination of genes. According to the team’s paper in the journal Genome Biology, the algorithm also detected types of genes in the pattern that had never been linked to cancer before. “It was a major challenge to get suitable training data where experts had already distinguished clearly between ‘healthy’ and ‘cancerous’ cells,” relates Jan Dohmen, the first author of the paper.

Dohmen and his colleague Dr Vedran Franke, co-head of the study, sifted through countless publications and contacted quite a few research groups to get adequate data sets. The team ultimately used data from lung and colorectal cancer cells to train the algorithm before applying it to data sets of other kinds of tumours.

The project aims to go far beyond the classification of 'healthy' versus 'cancerous' cells. In initial tests, ikarus already demonstrated that the method can also distinguish other types (and certain subtypes) of cells from tumour cells. “We want to make the approach more comprehensive,” Akalin says, “developing it further so that it can distinguish between all possible cell types in a biopsy.”

A remarkable aspect of the publication is that it was prepared entirely during the covid pandemic. All those involved were not at their usual desks at the Berlin Institute for Medical Systems Biology (BIMSB), which is part of the MDC.