Using AI to make cancer evolution more predictable

September 4, 2018 by Bob Yirka, Medical Xpress report
cancer
Killer T cells surround a cancer cell. Credit: NIH

A team of researchers affiliated with several institutions in the U.K. and one in the U.S. has developed a way to use artificial intelligence to predict how cancer might change and spread in patients. The results are published in Nature Methods.

Over many years of , scientists have discovered that tumors actually evolve, allowing them to change their form and the way they spread. Understanding how this evolutionary process works is considered by many in the field to be a key part of learning how to prevent it from happening. As part of this effort, scientists have collected from patients hoping to find a pattern in how they change. But this method has proven to be difficult, because when tumors grow, they also tend to develop mutations that have no impact on their ability to spread. In this new effort, the researchers sought to add machine learning to the process in an effort to track evolutionary changes that are involved in spreading. They have named their new system Revolver.

The new application uses a machine learning algorithm to study mutation data and detect patterns. They fed their system data describing 768 tumors from 178 patients—each of whom had breast, kidney, bowel or lung cancer. The system sought mutation patterns between patients that appeared to be related to changes that allowed the tumor to spread. Next, they applied what the system had learned to new patients as a way to assess the state of newly developing tumors—it was correctly identified gene mutations in 95 colorectal patients who had mutations that had been previously identified as drivers of evolution in breast, kidney and lung cancers.

The researchers note that Revolver is just one of the first steps toward developing computer-based tools to better predict how tumors will evolve—such tools should make it easier for doctors to formulate the best treatment plan for a given patient, hopefully, improving their prognosis.

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

More information: Giulio Caravagna et al. Detecting repeated cancer evolution from multi-region tumor sequencing data, Nature Methods (2018). DOI: 10.1038/s41592-018-0108-x

Abstract
Recurrent successions of genomic changes, both within and between patients, reflect repeated evolutionary processes that are valuable for the anticipation of cancer progression. Multi-region sequencing allows the temporal order of some genomic changes in a tumor to be inferred, but the robust identification of repeated evolution across patients remains a challenge. We developed a machine-learning method based on transfer learning that allowed us to overcome the stochastic effects of cancer evolution and noise in data and identified hidden evolutionary patterns in cancer cohorts. When applied to multi-region sequencing datasets from lung, breast, renal, and colorectal cancer (768 samples from 178 patients), our method detected repeated evolutionary trajectories in subgroups of patients, which were reproduced in single-sample cohorts (n = 2,935). Our method provides a means of classifying patients on the basis of how their tumor evolved, with implications for the anticipation of disease progression.

Related Stories

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

March 15, 2018
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 ...

Two teams independently tease out gene expression patterns in tumor-infiltrating lymphocytes using RNA sequencing

June 27, 2018
Two teams working independently of each other have found that it is possible to tease out gene expression patterns in tumor-infiltrating lymphocytes using single-cell RNA sequencing. The first team, based in Australia, sequenced ...

Researchers apply computing power to track the spread of cancer

June 29, 2018
Princeton researchers have developed a new computational method that increases the ability to track the spread of cancer cells from one part of the body to another.

Machine learning finds tumor gene variants and sensitivity to drugs in The Cancer Genome Atlas

April 9, 2018
Matching unique genetic information from cancer patients' tumors with treatment options - an emerging area of precision medicine efforts - often fails to identify all patients who may respond to certain therapies. Other molecular ...

New approach to immunotherapy leads to complete response in breast cancer patient

June 4, 2018
A novel approach to immunotherapy developed by researchers at the National Cancer Institute (NCI) has led to the complete regression of breast cancer in a patient who was unresponsive to all other treatments. This patient ...

New technique predicts gene resistance to cancer treatments

February 21, 2018
Yale School of Public Health researchers have developed a new method to predict likely resistance paths to cancer therapeutics, and a methodology to apply it to one of the most frequent cancer-causing genes.

Recommended for you

Eating foods with low nutritional quality ratings linked to cancer risk in large European cohort

September 18, 2018
The consumption of foods with higher scores on the British Food Standards Agency nutrient profiling system (FSAm-NPS), reflecting a lower nutritional quality, is associated with an increased risk of developing cancer, according ...

CRISPR screen reveals new targets in more than half of all squamous cell carcinomas

September 18, 2018
A little p63 goes a long way in embryonic development—and flaws in p63 can result in birth defects like cleft palette, fused fingers or even missing limbs. But once this early work is done, p63 goes silent, sitting quietly ...

Could the zika virus fight the brain cancer that killed john McCain?

September 18, 2018
(HealthDay)—Preliminary research in mice suggests that the Zika virus might be turned from foe into friend—enlisted to curb deadly glioblastoma brain tumors.

Enlarged genotype-phenotype correlation for a three-base pair deletion in neurofibromatosis type 1

September 18, 2018
International collaborative research led by Ludwine Messiaen, Ph.D., shows that while a three-base pair, in-frame deletion called p.Met992del in the NF1 gene has a mild phenotype for people with the genetic disorder neurofibromatosis ...

Your teen is underestimating the health risks of vaping

September 17, 2018
Teens today are more reluctant to smoke cigarettes than their counterparts nearly three decades ago, according to a study released this summer. But parents should hold their collective sigh of relief. The study, carried out ...

Artificial intelligence can determine lung cancer type

September 17, 2018
A new computer program can analyze images of patients' lung tumors, specify cancer types, and even identify altered genes driving abnormal cell growth, a new study shows.

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.