Friday, May 18, 2012

Googling Cancer: Search Algorithms Can Scan Disease for Patient Risk | Txchnologist

Math baby! I love it :D

Googling Cancer: Search Algorithms Can Scan Disease for Patient Risk

  • May 17th, 2012
  • By Charles Q. Choi
  • No Comments

The algorithm Google uses to rank search results can now scan cancers to see which molecules best reveal the risks patients face, researchers say.

By seeing how proteins are linked in a kind of molecular Facebook, search engine algorithms could also help unearth new targets for drugs to help combat tumors, investigators added.

Scientists worldwide currently aim to learn more about cancers by analyzing the behavior of thousands of proteins. The hope is to uncover which of these “biomarkers” might help detect a cancer earlier or reveal how a tumor might progress. The major challenge is spotting which of the thousands of changes that take place during cancer are most important to, say, patient survival.

The algorithm Google uses to rank which results pop up first in search queries, PageRank, orders results based on how other web pages are connected to them via hyperlinks. Researchers modified PageRank to develop NetRank, which scans how genes and proteins in a cell are similarly connected through a network of interactions with their neighbors — “‘friends’ in the social network analogy,” said researcher Christof Winter, a medical doctor and computational biologist at Lund University in Sweden.

“We have to consider the interactions between proteins in a cell,” Winter explained in an interview. “A cell integrates many different inputs from the inside and outside and makes decisions based on them — grow, divide, migrate, differentiate, and so on. These decisions are mostly the result of proteins talking to each other, and if we want to predict what the cell does next, we have to, besides measuring the protein levels, take into account and better understand these networks of interactions.”

“We first experimented with our own ideas on network algorithms until we realized that what we needed existed already with the PageRank algorithm, so why reinvent the wheel?” Winter recalled.

The investigators focused on pancreatic cancer, the most common form of which, pancreatic ductal adenocarcinoma, accounts for approximately 130,000 deaths each year in Europe and the United States. Very few tests exist to find out a prognosis for the disease — how it might progress, whether a patient might live or die.

The researchers used NetRank on about 20,000 proteins to see which ones were the best indicators for survival. They identified seven proteins that could help assess how aggressive a patient’s tumor is and guide clinicians to decide if the prognosis was worth trying chemotherapy or not.

“Most exciting for me is that solutions to problems in one domain, such as computer science, hyperlinks in the World Wide Web, can be often successfully used in a completely different domain, such as medicine, cancer protein networks,” Winter said.

As to how accurate prognoses based on these seven markers were, roughly speaking, “our markers are right in two-thirds of cases, and wrong in one-third,” Winter said. These markers were 6 to 9 percent more accurate at prognoses compared with those relying on conventional clinical parameters.

The researchers noted these findings needed validation in a larger follow-up study before they can be used in clinical practice. Winter also cautioned this work “is not about early detection of cancer. It only applies to patients that are already diagnosed with cancer.”

Not everyone might want better knowledge of whether the cancer they have might kill them, Winter admitted.

“When I talk to people about my work, some say ‘I would rather not like to know what my prognosis is if I have cancer,’” he said. “I think it’s important to realize that are ethical issues about such prognostic tests that need to be openly discussed in the public.”

In addition to improving prognoses of cancer, this research could also help identify new targets to help destroy tumors.

“Our PageRank-based algorithm singles out proteins in the cancer cells that seem to either promote or suppress disease progression,” Winter said. “An example is STAT3, where we find high levels in the tumor clearly associated with shorter survival of the patient.”

As far as Winter knows, no officially approved STAT3 inhibitor drug exists yet. “We provide a list of proteins that should be targeted by drugs, and then others can use and try if they can develop such a drug,” Winter said.

Currently Winter and his colleagues are analyzing DNA and RNA data from breast cancer. The hope is “to develop a DNA-based prognostic blood test for breast cancer patients,” he said.

The scientists detailed their findings online May 17 in the journal PLoS Computational Biology.

Top image: Cancerous human oral tissues. Courtesy Flickr user Libertas Academica.

Subscribe to Txchnologist’s daily email

Charles Q. Choi has written for Scientific American, The New York Times, Wired, Science and Nature, among others. In his spare time, he has traveled to all seven continents, including scaling the side of an iceberg in Antarctica, investigating mummies from Siberia, snorkeling in the Galapagos, climbing Mt. Kilimanjaro, camping in the Outback, avoiding thieves near Shaolin Temple and hunting for mammoth DNA in Yukon.


Related Txchnologist Articles

What do you think?

Posted via email from Tony Burkhart

No comments:

Post a Comment