The findings were according to a new study from the Massachusetts Institute of Technology, funded in part by the National Institutes of Health and the National Cancer Institute.
By distinguishing these harmful driver mutations from the neutral passengers, researchers can identify better targets for drugs. To boost those efforts, an MIT-led team has built a new computer model that can quickly scan the entire genome of cancer cells and identify mutations that are more common than expected, suggesting they stimulate tumor growth. This type of prediction has been challenging because some genomic regions have an extremely high frequency of passenger mutations, drowning out the signal from actual drivers
“We developed a probabilistic deep learning method that allowed us to get a very accurate model of the number of passenger mutations that should occur anywhere in the genome,” said Maxwell Sherman, an MIT graduate student. “Then we can look across the genome at regions where you have an unexpected accumulation of mutations, suggesting that these are driver mutations.”
In their new study, the researchers found additional mutations in the genome that appear to contribute to tumor growth in 5 to 10 percent of cancer patients. The findings could help doctors identify drugs that have a greater chance of successfully treating those patients, the researchers say. Currently, at least 30 percent of cancer patients do not have a detectable driver mutation that can be used to direct treatment.
Sherman, MIT graduate student Adam Yaari and former MIT research assistant Oliver Priebe are the lead authors of the study, which appears today in Nature Biotechnology. Bonnie Berger, the Simons Professor of Mathematics at MIT and head of the Computation and Biology group at the Computer Science and Artificial Intelligence Laboratory (CSAIL), is a senior author of the study, along with Po-Ru Loh, an assistant professor at Harvard Medical School and associate member of the Broad Institute of MIT and Harvard. Felix Dietlein, an associate professor at Harvard Medical School and Boston Children’s Hospital, is also an author of the article.
A new tool
Since the human genome was sequenced two decades ago, researchers have searched the genome to try to find mutations that contribute to cancer by causing cells to grow uncontrollably or evade the immune system. This has successfully yielded targets such as epidermal growth factor receptor (EGFR), which is commonly mutated in lung tumors, and BRAF, a common cause of melanoma. Both mutations can now be targeted by specific drugs.
While those targets have proven useful, protein-coding genes make up only about 2 percent of the genome. The other 98 percent also contain mutations that can occur in cancer cells, but it was much more difficult to figure out whether any of those mutations contribute to cancer development.
“There’s really a lack of computational tools that allow us to look for these driver mutations outside of the protein coding regions,” Berger says. “That’s what we were trying to do here: to design a computational method that would allow us to look not just at the 2 percent of the genome that codes for proteins, but 100 percent of it.”
To do that, the researchers trained a type of computer model known as a deep neural network to search cancer genomes for mutations that are more common than expected. As a first step, they trained the model on genomic data from 37 different cancers, which allowed the model to determine the background mutation rates for each of those types.
“The nice thing about our model is that you train it once for a particular type of cancer, and it learns the mutation rate all over the genome at the same time for that particular type of cancer,” Sherman says. “Then you can query the mutations you see in a patient cohort against the number of mutations you would expect to see.”
The data used to train the models comes from the Roadmap Epigenomics Project and an international collection of data called the Pan-Cancer Analysis of Whole Genomes (PCAWG). The analysis of this data by the model gave the researchers a map of the expected passenger mutation rate across the genome, so that the expected rate in each set of regions (up to the single base pair) can be compared with the observed number of mutations anywhere in the genome. . genome.
Changing the landscape
Using this model, the MIT team was able to contribute to the well-known landscape of mutations that can cause cancer. When cancer patients’ tumors are currently screened for cancer-causing mutations, a known driver will show up about two-thirds of the time. The new results of the MIT study provide possible driver mutations for an additional 5 to 10 percent of the patient pool.
One type of noncoding mutation the researchers focused on is called “cryptic splice mutations.” Most genes are made up of sequences of exons, which encode instructions for building proteins, and introns, which are spacer elements usually excised from messenger RNA before being translated into protein. Cryptic splicing mutations are found in introns, where they can confuse the cellular machinery that splices them. This results in introns being included when they shouldn’t be.
Using their model, the researchers found that many cryptic splicing mutations appear to disrupt tumor suppressor genes. When these mutations are present, the tumor suppressors are mis-spliced and stop working, and the cell loses one of its defense mechanisms against cancer. The number of cryptic splice sites the researchers found in this study accounts for about 5 percent of the driver mutations found in tumor suppressor genes.
Targeting these mutations could provide a new way to potentially treat those patients, the researchers say. One possible approach still under development uses short strands of RNA called antisense oligonucleotides (ASOs) to patch a mutated stretch of DNA with the correct sequence.
“If you could make the mutation disappear in a certain way, then you solve the problem. Those tumor suppressor genes could continue to work and maybe fight the cancer,” Yaari says. “ASO technology is being actively developed and this could be a very good application for that.”
Another region where the researchers found a high concentration of noncoding driver mutations is in the untranslated regions of some tumor suppressor genes. The tumor suppressor gene TP53, which is defective in many cancers, was already known to accumulate many deletions in these sequences, known as 5′ untranslated regions. The MIT team found the same pattern in a tumor suppressor called ELF3.
The researchers also used their model to investigate whether common mutations that were already known can also cause different types of cancer. For example, the researchers found that BRAF, previously associated with melanoma, also contributes to cancer progression in smaller percentages of other cancers, including pancreatic, liver and gastroesophageal cancers.
“That says there’s actually a lot of overlap between the common driver landscape and the rare driver landscape. That opens up the opportunity for therapeutic repurposing,” Sherman says. “These results could help guide the clinical trials we should be building to expand these drugs from approval for just one cancer, to approval for many cancers, and to help more patients.”
#computer #model #helps #identify #mutations #cancer