Google goes cancer: Researchers use search engine algorithm to find cancer biomarkers

May 17, 2012

The strategy used by Google to decide which pages are relevant for a search query can also be used to determine which proteins in a patient's cancer are relevant for the disease progression. Researchers from Dresden University of Technology, Germany, have used a modified version of Google's PageRank algorithm to rank about 20,000 proteins by their genetic relevance to the progression of pancreatic cancer. In their study, published in PLoS Computational Biology, they found seven proteins that can help to assess how aggressive a patient's tumor is and guide the clinician to decide if that patient should receive chemotherapy or not.

The researcher's own version of the algorithm has been used in this study to find new , which are molecules produced by . Biomarkers can help to detect cancer earlier in body fluids or directly in the obtained in an operation or biopsy. Finding these biomarkers is often difficult and time consuming. Another problem is that markers found in different studies for the same almost never overlap.

This problem has been circumvented using the Google strategy, which takes into account the content of a web page and also how these pages are connected via hyperlinks. With this strategy as the model, the authors made use of the fact that proteins in a cell are connected through a network of physical and regulatory interactions; the 'protein Facebook' so to speak.

"Once we added the network information in our analysis, our biomarkers became more reproducible," said Christof Winter, the paper's first author. Using this network information and the Google Algorithm, a significant overlap was found with an earlier study from the University of North Carolina. There, a connection was made with a protein which can assess aggressiveness in pancreatic cancer.

Although the new biomarkers seem to mark an improvement over currently used diagnostic tools, they are far from perfect and still need to be validated in a larger follow-up study before they can be used in clinical practice. It remains an open problem to turn these insights into novel drugs which slow down cancer progression. A first step in this direction is the group's cooperation with the Dresden-based biotech company RESprotect, who are running a clinical trial on a pancreas cancer drug.

TU Dresden is a leading German university, whose Center for Regenerative Therapies was awarded excellence status in the national excellence initiative. The work was a cooperation between the bioinformatics group of Prof. Dr. Michael Schroeder and the medical groups of Dr. Christian Pilarsky and Prof. Robert Grützmann.

Explore further: Biomarker family found for chemo resistant breast cancers

More information: Winter C, Kristiansen G, Kersting S, Roy J, Aust D, et al. (2012) Google Goes Cancer: Improving Outcome Prediction for Cancer Patients by Network-Based Ranking of Marker Genes. PLoS Comput Biol 8(5): e1002511. doi:10.1371/journal.pcbi.1002511

Related Stories

Biomarker family found for chemo resistant breast cancers

April 12, 2012
Biomarkers which could help to predict resistance to chemotherapy in breast cancer patients have been identified by researchers from the University of Hull, UK.

New prostate cancer biomarkers move closer to clinical use

June 17, 2011
Conway Fellow, Professor William Watson and Professor John Fitzpatrick, UCD School of Medicine and Medical Science and Mater Misericordiae University Hospital recently received a translational research award for the validation ...

Singling out the real breast cancer among the lumps

October 25, 2011
(Medical Xpress) -- Early detection of breast cancer saves thousands of lives each year. But screening for breast cancer also produces false alarms, which can cause undue stress and costly medical bills. Now, a recent study ...

Recommended for you

What does hair loss have to teach us about cancer metastasis?

December 15, 2017
Understanding how cancer cells are able to metastasize—migrate from the primary tumor to distant sites in the body—and developing therapies to inhibit this process are the focus of many laboratories around the country. ...

Cancer immunotherapy may work better in patients with specific genes

December 15, 2017
Cancer cells arise when DNA is mutated, and these cells should be recognized as "foreign" by the immune system. However, cancer cells have found ways to evade detection by the immune system.

Scientists pinpoint gene to blame for poorer survival rate in early-onset breast cancer patients

December 15, 2017
A new study led by scientists at the University of Southampton has found that inherited variation in a particular gene may be to blame for the lower survival rate of patients diagnosed with early-onset breast cancer.

'Bet hedging' explains the efficacy of many combination cancer therapies

December 14, 2017
The efficacy of many FDA-approved cancer drug combinations is not due to synergistic interactions between drugs, but rather to a form of "bet hedging," according to a new study published by Harvard Medical School researchers ...

Scientists unlock structure of mTOR, a key cancer cell signaling protein

December 14, 2017
Researchers in the Sloan Kettering Institute have solved the structure of an important signaling molecule in cancer cells. They used a new technology called cryo-EM to visualize the structure in three dimensions. The detailed ...

Liquid biopsy results differed substantially between two providers

December 14, 2017
Two Johns Hopkins prostate cancer researchers found significant disparities when they submitted identical patient samples to two different commercial liquid biopsy providers. Liquid biopsy is a new and noninvasive alternative ...

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.