How do cancerous cells differ from healthy cells? A new machine learning algorithm knows the answer. The program has found a characteristic gene signature.
In order to reliably distinguish cancer cells from healthy cells, the team led by Dr. Altuna Akalin, head of the “Bioinformatics and Omics Data Science” technology platform at the Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC), has developed a machine learning program called “ikarus”. The program found a cross-cancer pattern in the tumor cells, consisting of a characteristic combination of genes. Of the algorithm also discovered types of genes in the pattern that had previously not been clearly identified Krebs the research group writes in the journal Genome Biology.
Machine learning basically means that an algorithm independently learns to answer certain questions using training data. His strategy is to look for patterns in the data that will help him solve the problem. After the training phase, the system can generalize what has been learned and thus assess unknown data. “A major challenge was to obtain suitable learning datasets in which specialists had already made a precise classification of the cells into ‘healthy’ and ‘cancer’,” says Jan Dohmen, first author of the study.
A surprisingly good hit rate
In addition, data sets from single-cell sequencing are often noisy. This means that the information about the molecular properties of the individual cells is not entirely accurate – for example because a different number of genes is recognized in each cell or the samples are not always processed in the same way. Dohmen and his colleague and co-author Dr. Vedran Franke. With data from pulmonary and colon cancer cells Finally, the team trained the algorithm before applying it to datasets from other tumor types.
In the training phase, the AI had to find a list of characteristic genes that the program could use to classify the cells: “We tried and refined different approaches,” says Dohmen. “The decisive factor was that ‘ikarus’ ultimately used two lists: one for cancer genes and one for genes from other cells,” explains Franke.
After the learning period, the algorithm was also able to reliably distinguish between healthy and cancerous cells in other types of cancer, for example in tissue samples from liver cancer or Neuroblastomen. His hit rate was usually only a few percent off. This also surprised the research group: “We did not expect that there would be a common signature that defines tumor cells from different types of cancer so precisely,” says Akalin. “However, we cannot yet say that the method works for all types of cancer,” adds Dohmen. To ensure that the algorithm can reliably help with cancer diagnosis, the researchers want to test it on other types of tumors.
AI as a fully automatic diagnostic aid
The classification of “healthy” versus “cancer” is by no means the end of the project. In initial tests, the AI was able to show that the method can also distinguish between other cell types or certain subtypes of tumor cells. “We want to generalize the approach,” says Akalin, “that is, to further develop it in such a way that it includes all possible cell types in one Biopsy can distinguish.”
|follow the channel cancer sense for more oncology topics.
Are you also interested in news from other medical fields? Discover here other DocCheck channels.
In the clinic, pathologists usually only look at tissue samples from tumors under the microscope and thus identify the different cell types. It’s tedious and takes a lot of time. With the new tool, this step could eventually be fully automated. In addition, one can also derive something from the data about the immediate vicinity of the tumor, says Akalin. This, in turn, could help doctors select the optimal therapy. Because often the composition of the cancer tissue and the microenvironment indicate whether a certain treatment or drug will work or not.
In addition, the AI may help to develop new drugs: “With ‘ikarus’ we can identify genes that are potential drivers of cancer,” says Akalin. Novel active substances could then be applied to these molecular target structures.
Image source: Ty Kent, unsplash