May 23, 2012
Using bioinformatics tools, cancer researchers can now search for common protein markers shared among afflicted patients. The process involves tracking thousands of proteins over a course of the disease and identifying the ones that map to patient survival. In a recent study, researchers believe they have a better chance of finding these relationships with a program inspired by Google’s famous PageRank algorithm.
Last week, the Txchnologist covered the scientists’ unconventional method. Christof Winter, one of the study’s researchers and a computational biologist at Lund University in Sweden, explained how cells respond to protein and gene interactions:
“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.”
The researchers attempted creating their own algorithm before realizing that Google’s PageRank algorithm solved essentially the same problem for the web. They modified the algorithm somewhat, and came up with NetRank, a code that analyzes the relationship between proteins and gene expression.
Initially they used it to study pancreatic cancer. They found that out of 20,000 proteins they looked at, seven seemed to correlate most strongly with the how aggressive the cancer became. That information could then be used as criteria for patient treatment.
Significantly, the researchers found that NetRank was able to produce a prognosis that was 6 to 9 percent more accurate than conventional medical practices. Unfortunately, the program only applies to patients already diagnosed with the disease and does not allow for early detection. And more testing is required before the software can be used in real-world clinical environments.
According to their paper, written up in the PloS Computation Biology journal, the scientists view the application as a tool for medical professionals to improve individualized care. The researchers conclude that the technology can be used in a clinical setting to help decide if a cancer patient should receive chemotherapy. “Reliable prediction of survival and response to therapy based on molecular markers bears a great potential to improve and personalize patient therapies in the future,” they write.
Beyond predicting patient outcomes, information gleaned from NetRank could assist in the development of new cancer fighting drugs. For example, the program identified a protein named STAT3, believed to shorten the survival rate of a patient. With the protein identified, pharmaceutical manufacturers can begin to develop and test STAT3-inhibiting drugs, which might slow or reverse the cancer’s progression.
Full story at Txchnologist
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?