An IBM supercomputer directly related to the famous Deep Bluethat battled chess grand master Gary Kasparov in 1997 has recentlybeen recruited to aid Canadian researchers in the fight againstcancer.
One of the biggest challenges in our research is being able tosort through a large volume of data.Igor Jurisicaprofessor ofcomputer science and biophysics at the University ofTorontoText
The Life Sciences Discovery Centre of the University HealthNetwork (UHN) in Toronto is using an IBM eServer p595 supercomputerto analyze protein interactions.
These interactions are vital to the understanding of cancerbiology at the molecular level. The process is crucial to chartinga tumour’s progression and ultimately developing treatment.
The UHN centre received the supercomputer along with IBM’sWebSphere Information Integrator server application and DB2database software under Big Blue’s Shared University Grant program.The package is worth more than US$2.5 million.
“One of the biggest challenges in our research is being able tosort through a large volume of data,” said Igor Jurisica, ascientist with the Ontario Cancer Institute of the UHN. Jurisica isalso a professor of computer science and biophysics at theUniversity of Toronto.
With a lesser computer, Jurisica estimates his calculationswould take months but with the p595, they can be accomplished inweeks or days, shaving wait times by 50 per cent. “With 120,000known proteins and 25,000 to 30,000 we’re looking at millions ofpossible interactions. You can see we have quite a real big hairball.”
The p595 supercomputer used by the UHN “is a descendant of DeepBlue” that famously trounced Kasparov in a series of man versusmachine chess matches in 1997, according to Don Aldridge, IBMCanada’s general manager for higher education, research and lifesciences.
Deep Blue was a 1.4-ton IBM RS/6000 SP high performance computerthat had 256 Power2 processors. It was specifically created to playchess and could explore 200,000,000 positions per second. At thetime of the match Kasparov could explore approximately threepositions per second.
Deep Blue technology was eventually used to tackle other realworld problems such as forecasting weather patterns.
“In the case of Deep Blue it was a natural progression to evolvefrom predicting chess moves to predicting hurricanes because inboth cases you are dealing with multiple variables,” said DaveMarks, consulting director for the research and consulting firm IDCCanada Ltd.
According to Marks, the desktop-sized p595 supercomputerinherited a lot of properties from Deep Blue “but is much faster interms of computing capacity and consumes less power.”
Aldridge said p595 can be configured in different ways to dealwith specific situations, but that the UHN is “stretching it inways we would not have thought possible.”
Learning is a two way street, said Aldridge. “When scientistslike Igor [Jurisica] come to the IBM Lab it gives our researchers achance to work with our equipment in real world situations.”
Marks said IBM is working on another supercomputer projectdubbed Blue Gene with the mission of studying molecular functionsand protein folding.
Proteins react with each other in varied ways. Jurisica’s teamis trying to determine which patterns are disruptive or prone tocause tumours.
Molecular profiles of cancers help detect signs thatpathological tests might have missed at the tissue level, Jurisicasaid. “For instance, it is known that women with mutations in theirBRCA1 and BRCA2 genes are predisposed to breast and ovariancancer.”
However, he cautioned that it is not a black and whitesituation. “By tracing protein patterns and factoring in variablessuch as medical history, habits and environment, we could determinewhether the person is simply predisposed or if cancer is alreadypresent.”
This determination, Jurisica said, could spell the differencebetween providing early aggressive treatment and needlesslylowering the standard of life exposing the person to unneededmedication.