Machine-learning algorithm used to identify specific types of brain tumors

March 15, 2018 by Bob Yirka, Medical Xpress report
Credit: CC0 Public Domain

An international team of researchers has used methylation fingerprinting data as input to a machine-learning algorithm to identify different types of brain tumors. In their paper published in the journal Nature, the team describes studying DNA methylation fingerprinting to create a system that is able to identify central nervous system (CNS) tumors and report on its accuracy.

Accurately identifying a patient's specific tumor type is difficult for doctors because of the limited number of tests available and the large number of types—there are over 100 known, with some yet to be identified. In this new effort, the researchers studied methylation, in which methyl groups are added to DNA—the process induces changes in function, typically by repressing gene transcription. Methylation is a normal process, and one of its hallmarks is that it leaves a unique signature. Noting that the process also occurs in cancer cells, the researchers set out to use such signatures as fingerprints to identify the presence of in a sample. They created a system based on a that uses methylation fingerprinting data as its learning material.

To teach the system to recognize and then identify tumor types, the researchers entered data from 2,800 cancer patients and report that it is now capable of identifying 91 types of CNS tumors. They tested the system with tumor data from 1,104 patients with previously identified tumors. The system found that approximately 12 percent of the tumors had been misdiagnosed.

The researchers note that in addition to providing a new tool for tumor identification in new patients, the system is also able to discern whether a given tumor is one that has not been previously identified, circumventing the common occurrence of doctors feeling pressured into classifying tumors as belonging to known types. To make the system more approachable, the team has put their system online free of charge. As of the publication of their paper, the system had been accessed over 4,500 times, suggesting people are finding it useful. Such widespread use, the note, will only improve the accuracy of the system and hopefully aid in discovering new types.

Explore further: Novel classification can lead to new ways to diagnose and treat cancer

More information: David Capper et al. DNA methylation-based classification of central nervous system tumours, Nature (2018). DOI: 10.1038/nature26000

Abstract
Accurate pathological diagnosis is crucial for optimal management of patients with cancer. For the approximately 100 known tumour types of the central nervous system, standardization of the diagnostic process has been shown to be particularly challenging—with substantial inter-observer variability in the histopathological diagnosis of many tumour types. Here we present a comprehensive approach for the DNA methylation-based classification of central nervous system tumours across all entities and age groups, and demonstrate its application in a routine diagnostic setting. We show that the availability of this method may have a substantial impact on diagnostic precision compared to standard methods, resulting in a change of diagnosis in up to 12% of prospective cases. For broader accessibility, we have designed a free online classifier tool, the use of which does not require any additional onsite data processing. Our results provide a blueprint for the generation of machine-learning-based tumour classifiers across other cancer entities, with the potential to fundamentally transform tumour pathology.

Press release

Related Stories

Novel classification can lead to new ways to diagnose and treat cancer

February 12, 2018
A novel approach to studying cancer has enabled researchers to group about 10,000 human cancers of 32 different types into 10 classes based on the molecular pathways that drive tumor growth. A better understanding of these ...

Study suggests colon cancer cells carry bacteria with them when they metastasize

November 24, 2017
(Medical Xpress)—A team of researchers working at Harvard University has found evidence that suggests a certain type of bacteria found in colon cancer tumors makes its way to tumors in other body parts by traveling with ...

AZD6738 found to slow some types of children's tumor growth in mouse models

November 2, 2017
(Medical Xpress)—A team of researchers from the U.S., Germany and Japan has found that the chemical AZD6738 was able to slow some childhood type tumor growths in mouse models. In their paper published in the journal Science ...

New blood test could help detect and locate cancer early on

March 6, 2017
Bioengineers at the University of California San Diego have developed a new blood test that could detect cancer—and locate where in the body the tumor is growing.

New marker could detect fatal breast cancer up to one year earlier than current methods

December 21, 2017
A new marker that could be used to diagnose fatal breast cancer up to one year ahead of current methods has been described in a study published in the open access journal Genome Medicine this week. A team of researchers led ...

Molecular fingerprint of breast tumors linked to immune response in bloodstream

September 28, 2017
Using newly developed software, researchers have shown that genes and molecular processes in breast cancer tumor cells are tightly linked to genes and processes in blood cells, including immune system cells. The findings ...

Recommended for you

Pushing closer to a new cancer-fighting strategy

December 11, 2018
A molecular pathway that's frequently mutated in many different forms of cancer becomes active when cells push parts of their membranes outward into bulging protrusions, Johns Hopkins researchers report in a new study. The ...

Scientists have identified and modelled a distinct biology for paediatric AML

December 11, 2018
Scientists have identified and modelled a distinct biology for paediatric acute myeloid leukaemia, one of the major causes of death in children.

HER2 mutations can cause treatment resistance in metastatic ER-positive breast cancer

December 11, 2018
Metastatic breast cancers treated with hormone therapy can become treatment-resistant when they acquire mutations in the human epidermal growth factor receptor 2 (HER2) that were not present in the original tumor, reports ...

Loss of two genes drives a deadly form of colorectal cancer, reveals a potential treatment

December 11, 2018
Colorectal cancers arise from earlier growths, called polyps, found on the inner surface of the colon. Scientists are now learning that polyps use two distinct molecular pathways as they progress to cancer, called the "conventional" ...

Successful anti-PD-1 therapy requires interaction between CD8+ T cells and dendritic cells

December 11, 2018
A team led by a Massachusetts General Hospital (MGH) investigator has found that successful cancer immunotherapy targeting the PD-1 molecule requires interaction between cytotoxic CD8+ T cells, which have been considered ...

Taking uncertainty out of cancer prognosis

December 11, 2018
A cancer diagnosis tells you that you have cancer, but how that cancer will progress is a terrifying uncertainty for most patients. Researchers at Cold Spring Harbor Laboratory (CSHL) have now identified a specific class ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.