Mayo, University of Illinois tap genomic data with new informatics tool

A newly developed tool combines different types of genomic data to predict patients’ specific responses to therapeutic drugs.

The application, developed by the University of Illinois and the Mayo Clinic, is based on information contained in human genomes and enables researchers to predict patient reactions.

“We all know treatment outcomes for complex diseases like cancers vary dramatically among individuals, from lacking of efficacy resulting in disease recurring to severe toxicity resulting in noncompliance in patients who cannot tolerate these life-saving drugs,” says Leiwei Wang, professor of pharmacology at the Mayo Clinic. “Therefore, it is extremely important for us to understand better of how and why patients respond differently, so that we can truly individualize their therapies by choosing the right drug at the right dose.”

Funded under the National Institutes of Health’s Big Data to Knowledge (BD2K) initiative, the University of Illinois in partnership with the Mayo Clinic has created a Center of Excellence to tap the wealth of information contained in genomic data.

Also See: NIH awards will tackle challenges of big data

The Knowledge Engine (KnowEnG) researchers created is an analytical platform that leverages algorithms used successfully in other data mining activities—including Google’s search functions—but which have not been previously applied to the interpretation of genomic data.

“A cloud-based infrastructure was constructed as well as a portal to enable genomic researchers to analyze their data using state-of-the-art machine learning and data mining,” says Saurabh Sinha, who co-directs the KnowEnG Center of Excellence at the University of Illinois and is professor of computer science. “In parallel, we developed new algorithms for such genomic data analysis.”

In particular, Sinha and graduate student Casey Hanson developed an algorithm that utilizes gene expression data, genomic factors that help control gene expression, and resulting traits such as drug response in order to predict which genes are most important in determining the latter.

“We have generated tools that can be used broadly by the research community. These tools will be open to anyone who might have the right data sets to both help generate hypothesis and also to help refine the algorithms,” adds Mayo Clinic’s Wang. “This is a perfect example of how expertise in complementary research areas, in this case, computational science and pharmacoproteomics, come together to make a difference.”