A team has put together a mathematical toolkit combining artificial intelligence and physics that will help in beating cancer.

Man has amassed unimaginable quantities of data. All that data is beginning to become a problem in the fight against cancer. Better and faster gene sequencing techniques mean mountains of new genomic information.

Like Us on Facebook

Within all the noise from the data, there's bound to be some useful information that will assist in their hunt for new and better approaches to beating cancer.

The data problem is not inherent to the fight against cancer alone. It's also evident in astrophysics and climate science as much as it is in medical research.

A group of researchers led by Harvard Medical School's Peter Sorger has found a solution for this conundrum. And it lies outside of medicine.

Sorger and his team have formulated a mathematical toolkit that draws on the techniques of statistical physics and artificial intelligence. This toolkit is capable of identifying the "social networks" of cell proteins.

"[The Cancer Genome Atlas] and similar projects have generated extensive data on the mutational landscape of tumors," Sorger and his team wrote.

"To understand the functional consequences of these mutations, it is necessary to ascertain how they alter the protein-protein interaction networks involved in regulating cellular phenotypes."

He goes on to say the problem with interpreting the data lay in an absence of a unified framework allowing for diverse measurements and the creation of solid models of cancer mutations and their effects.

Soger's work focuses on protein interaction domains (PID), a network that acts as a venue for cell signaling.

The model is based on "statistical mechanics," a way of predicting the likelihood that some system will wind up in a particular state using the thermodynamic energy of a current state.

The new model applies machine learning techniques to the usual principles of statistical machines. Thus, it becomes possible to predict how an individual mutation might propagate through or influence a network.

TagsCancer, Mathematical toolkit, Cancer Genome Atlas