Machine learning helps to determine leukaemia subtypes

Australian researchers have developed machine learning software that is helping patients diagnosed with acute lymphoblastic leukaemia (ALL) to determine what subtype they have.

ALL is the most common childhood cancer in the world, and also affects adults. Over 300 people are diagnosed with the disease in Australia each year, and over half of those are young children under the age of 15. Determining what subtype of ALL a patient has provides valuable information about their prognosis, and how they should best be treated.

“Figuring out what genetic changes are driving a patient’s cancer is key to working out how intense their treatment should be and what drugs get used,” noted Associate Professor Paul Ekert, from the Peter MacCallum Cancer Centre and the Children’s Cancer Institute. But up until the advent of genomic technologies like RNA sequencing, methods for doing so were not as precise.

“Previously, genetic abnormalities were detected by looking down a microscope at individual chromosomes and looking for four or five main defects,” Ekert said.

“But we now know there are at least 23 subtypes for ALL.”

Researchers from Peter Mac, the Children’s Cancer Institute, the Murdoch Children’s Research Institute and The University of Melbourne have now developed ALLSorts — software that uses RNA sequencing data to identify a patient’s ALL subtype. Their work has been published in the journal Blood Advances.

“ALLSorts adds a different way of finding these genetic drivers, and classifying what subtype of ALL a patient has,” said Peter Mac’s Professor Alicia Oshlack, the senior author on the paper.

“And it can be used with even a single patient sample, so testing centres regardless of their size will be able to use it.”

Oshlack explained that the researchers used a machine learning approach, and validated the accuracy of the software on children’s cancer samples from The Royal Children’s Hospital and adult cancer samples from Peter Mac. In machine learning, it is the computer that puts all the information from a large dataset together to use the most informative features of the dataset, rather than relying on the human researchers to determine what the important pieces of the data are.

The researchers believe that ALLSorts is the first publicly available and open source tool of its kind, available for anyone to access at https://github.com/Oshlack/ALLSorts. Oshlack hopes the software can be used across the world in testing ALL and informing treatment choices for patients.

“It’s also a nice example of the importance of computational biology in cancer research,” she said.

Image caption: Two young girls with acute lymphocytic leukaemia (ALL) receiving chemotherapy. Image credit: National Cancer Institute.

Please follow us and share on Twitter and Facebook. You can also subscribe for FREE to our weekly newsletters and bimonthly magazine.