Software speeds hunt for cancer triggers

JOHNS HOPKINS (US)—New computer software is sifting through hundreds of genetic mutations to highlight the ones most likely to promote cancer. Results will be posted online to assist researchers worldwide.

The goal of the engineers at Johns Hopkins University who wrote the code is to speed the work of researchers poring over numerous newly discovered mutations in DNA, many of which are harmless or have no connection to cancer. According to its inventors, the new software will enable these scientists to focus more attention on the mutations most likely to trigger tumors.

“It’s very expensive and time-consuming to test a huge number of gene mutations, trying to find the few that have a solid link to cancer,” says Rachel Karchin, an assistant professor of biomedical engineering who supervised the development of the computational sorting approach. “Our new screening system should dramatically speed up efforts to identify genetic cancer risk factors and help find new targets for cancer-fighting medications.”

The new computational method is called CHASM, short for Cancer-specific High-throughput Annotation of Somatic Mutations. A description of the method and details of a test using it on brain cancer DNA were published in the Aug. 15 issue of the journal Cancer Research.

The process focuses on missense mutations, protein sequences that possess single tiny variations from the normal pattern. A small percentage of these genetic errors inhibit proteins that suppress tumors or hyperactivate proteins that make it easier for tumors to grow, thereby allowing cancer to develop and spread. Finding these few genetic offenders can be difficult.

The team first narrowed the field of about 600 potential brain cancer culprits using a computational method that would sort these mutations into “drivers” and “passengers.” Driver mutations initiate or promote the growth of tumors. Passenger mutations are present when a tumor forms but appear to play no role in its formation or growth. The passenger mutations, in other word, are only along for the ride.

The researchers used a machine-learning technique in which about 50 properties associated with cancer-causing mutations were given numerical values and programmed into the system. Karchin and Carter then employed a math technique called a Random Forest classifier to help separate and rank the drivers and the passengers.

In this step, 500 computational “decision trees” considered each mutation to decide whether it possessed the key characteristics associated with promoting cancer. Eventually, each “tree” cast a vote: Was the gene a driver or a passenger?

“It’s a little like the children’s game of ‘Guess Who,’ where you ask a series of yes or no questions to eliminate certain people until you narrow it down to a few remaining suspects,” says Carter, lead author of the Cancer Research paper. “In this case, the decision trees asked questions to figure out which mutations were most likely to be implicated in cancer.”

Karchin and Carter plan to post their system on the Web and will allow researchers worldwide to use it freely to prioritize their studies. Because different genetic characteristics are associated with different types of cancers, they says the method can easily be adapted to rank the mutations that may be linked to different forms of the disease, such as breast cancer or lung cancer.

Funding for the research was provided by the Susan G. Komen Foundation, the Virginia and D. K. Ludwig Fund for Cancer Research, and the National Institutes of Health.

Johns Hopkins University news: