Artificial intelligence and machine learning are among the latest tools used by cancer researchers to help detect and treat the disease.
One of the scientists working on this new frontier of cancer research is Ryan Layer, PhD, a member of the University of Colorado Cancer Center, who recently published a study detailing his research that uses big data to find cancerous mutations. in the cells.
Identifying the genetic changes that make healthy cells become malignant can help doctors select therapies specifically targeted at the tumor. For example, about 25% of breast cancers are HER2 positive, meaning cells in this type of tumor have mutations that cause them to produce more than one protein called HER2 that helps them grow. HER2-specific treatments have drastically increased survival rates for this type of breast cancer. “
Ryan Layer, Assistant Professor of Computer Science, CU Boulder
Scientists can evaluate cellular DNA to identify mutations, Layer says, but the challenge is that the human genome is massive and mutations are a normal part of evolution.
“The human genome is long enough to fill a 1.2 million-page book, and any two people can have about 3 million genetic differences,” he says. “Finding a mutation that leads to cancer in a tumor is like finding a needle in a stack of needles.”
Scanning the data
The ideal method for determining what type of cancer mutation a patient has is to compare two samples from the same patient, one from the tumor and one from healthy tissue. These tests can be complicated and expensive, however, Layer found another idea -; using massive public DNA databases to search for common cell mutations that tend to be benign, so that researchers can identify rarer mutations that have the potential to be cancerous.
“There was a project called the Genome Aggregation Database, or gnomAD, from the Broad Institute, where they put together a bunch of different studies that were going on in Broad into the largest genetic database that anyone has ever thought of. “says Layer. “At first there were 65,000 individuals, and now there are about half a million individuals. At the time I was at the University of Utah doing research at the Rare Disease Clinic undiagnosed, and the usefulness of this database was more beyond belief “.
Even if he was able to sequence a child with cancer and his parents, Layer says, there were often so many genetic mutations that it was difficult to determine which one was causing the disease. Using gnomAD, he was able to see how often a given variant occurred in a larger population, greatly reducing the number of therapeutic targets.
Verification of variants
Inspired by this experience, Layer began looking for other ways to use big data to identify potentially cancerous mutations. Knowing that the detection of complex DNA mutations called structural variants (SVs) can often lead to false negatives, he and his colleagues developed a process that focuses on verification rather than detection. This method searches through raw data from thousands of DNA samples for any evidence to support a specific structural variant.
“We scanned the SVs identified in previous cancer studies and found that thousands of SVs previously associated with cancers also appear in normal healthy samples,” Layer says. “This indicates that these variants are more likely to be benign and inherited sequences than disease-causing ones.”
The team also found that their method worked just as well as the traditional strategy that requires tumor and healthy samples, opening the door to reduce cost and increase accessibility to high-quality cancer mutation analysis. .
“With all the existing data on cancer, we were able to show that this method is really powerful in identifying not necessarily the mutation that leads to cancer, but which variants are unique to the tumor, compared to the rest of your body,” he says. . “In this way, the treatment of the tumor can become superpersonalized. We can say,” If you have this mutation, use this drug; if you do not have this mutation, do not use this drug “.
Sharing research
Layer’s lab has now deployed a website where doctors can enter information about structural variants found in a patient’s tumor to see how common -; and potentially dangerous -; they are. He is also looking to create a larger cancer-focused dataset to help better understand how and where tumors form.
“Our job so far has been to take a structural variant and look at how common it is in a healthy population,” he says. “But what if we do indices that allow you to look for our populations? Suppose you take a sample of a tumor in a lung and find structural variants; now you can look for those against prostate cancer and breast cancer and all other cancers., and can help you identify: “What is the origin of the tumor?” ‘Did it metastasize or originate in the lung?’ We can search the tumor databases to try to find other matching tumors for more personalized medicine-inspired treatments. “
Source:
Anschutz Medical Campus, University of Colorado