Data mining holds potential for biology breakthroughs

Data mining holds potential for biology breakthroughs

on Aug 12, 14 • by Chris Bubinas • with No Comments

The Cancer Genome Atlas research project uses these resources to explore molecular information, eventually hoping to effectively translate biological data into clinical use...

Home » Analytics and Data Mining » Data mining holds potential for biology breakthroughs

Data mining tools continue to demonstrate their tremendous potential. Organizations around the world are constantly developing new strategies to leverage this technology, mining data to discover trends, patterns and insights that would otherwise remain invisible.

One of the fields for which data mining may prove most valuable is biology. For example, The Cancer Genome Atlas research project uses these resources to explore molecular information, eventually hoping to effectively translate biological data into clinical use, as Health Canal reported.

Mining for cancer
The Cancer Genome Atlas represents a joint effort between the National Cancer Institute and National Human Genome Research Institute, both of which exist within the National Institutes of Health. According to the news source, these groups are examining genomic changes among more than 20 cancer types in a process known as molecular profiling.

"We hope that molecular profiling of tumors will one day advance the clinical management of cancer, but the benefits of integrating molecular and clinical data have not been studied in depth," said Han Liang, an assistant professor in Bioinformatics and Computational Biology at The University of Texas MD Anderson Cancer Center, the news source reported. "The true value of our study is to serve as a starting point for building future prognostic and therapeutic strategies based on molecular profiling."

Liang previously conducted a study in which his team mined four cancers' molecular data. Using this information, his group developed an open-access platform enabling researchers to evaluate data-based cancer survival prediction models, Health Canal reported.

"By analyzing data from multiple cancer types, we were able to evaluate prognostic models and identify gene alterations that led to tumor formation," he said, according to the news source. "This would have not been obtained by looking at tumor data from just one cancer type."

Liang told the news source that the use of large data sets for measuring cancer survivability has yet to mature or reach its full potential. However, he believes his earlier study and The Cancer Genome Atlas represent powerful early steps.

New discoveries
The potential for data mining solutions to yield invaluable discoveries in the field of biology was further highlighted by Dr. Sarah Teichmann, a researcher with the Sanger Institute. Teichmann spoke at the Rotary Club in Cambridge to discuss her work and the key role played by data mining, Cambridge News reported.

Teichmann explained that her team analyzes tremendous amounts of genomic data in an effort to identify biological behaviors. Specifically, the group hopes to discover whether these behaviors can be turned off and on. If so, this could have significant implications for the treatment of countless diseases.

According to the news source, Teichmann's talk emphasized the important role played by engineering in the field of science research. Too often, the attention paid to scientists' work overlooks the contributions from computer engineers, without whose tools this advanced research would not be possible.

Proven tools
Data mining isn’t new but today’s tools and techniques allow unprecedented performance and accuracy with just a small amount of effort. Scientists and engineers don’t have to worry about developing algorithms over and over again, rather they can rely on commercially proven math and statistics algorithms to provide the underlying framework. By not having to worry about the code, organizations can focus on the trends, patterns and insights that drive their clinical research.

Related Posts

Leave a Reply

Your email address will not be published. Required fields are marked *

*

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>

Scroll to top