Computational model predicts cancer survival rates

A new computational model highly predictive of breast cancer survival has been developed by Columbia University engineering researchers. Their work is outlined in a study published this week in Science Translational Medicine

Lead researcher Dimitris Anastassiou--a professor of engineering at Columbia's Fu Foundation School of Engineering and Applied Science--and his team identified "attractor metagenes," which are gene signatures present in identical form among many types of cancer, according to an announcement from the school.

Anastassiou and two Ph.D. students tested the signatures in the Sage Bionetworks/DREAM Breast Cancer Prognosis Challenge, a "crowd-sourced effort for accurate breast cancer prognosis" using molecular and clinical data. A prognostic model was developed showing that these certain signatures of cancer, when combined, were "strong predictors for breast cancer survival," according to the announcement.

"These signatures manifest themselves in specific genes that are turned on together in the tissues of some patients in many different cancer types," Anastassiou said. "And if these general cancer signatures are useful in breast cancer, as we proved in this Challenge, then why not in other types of cancer as well? I think that the most significant--and exciting--implication of our work is the hope that these signatures can be used for improved diagnostic, prognostic, and eventually, therapeutic products, applicable to multiple cancers."

He noted that currently, widely used biomarker products look at specific genes in cancer patient biopsies to decide if certain treatments are appropriate, and some of those genes are related to the tested signatures, so it's "worth finding out if replacing such genes with our specific 'pan-cancer' signatures will improve the accuracy of these products."

Added Anastassiou: "The hallmarks of cancer are unifying biological capabilities present in all cancers, as described in some seminal papers. We think that we have now reached the point where systems biology can also identify such hallmarks."

To  learn more:
- read the announcement from Columbia
- read the study in Science Translational Medicine

Related Articles:
New technologies altering care standards for breast imagers
UCLA, IBM team to use big data to prevent brain swelling
Cloud storage to enable massive cancer cell database
Future of data analytics is predictive, actionable


The Real Payback of Healthcare Analytics

Tuesday, April 6 | 2pm ET / 11am PT

With the unpredictability of healthcare today, organizations are sharpening their focus on analytics to make more data-informed decisions. Join us for a roundtable session in which thought leaders will discuss how they are maximizing their analytics investments.