Data mining for treasure

When I talk about the intelligent future, I’m referring to far more than just artificial intelligence and intelligence amplification. The application of existing knowledge and tools in new and innovative ways will play just as much a role. One excellent example can be found in a paper published yesterday in the Proceedings of the National Academy of Sciences. In “MiDReG: A method of mining developmentally regulated genes using Boolean implications”, Stanford University computer scientist,
Debashis Sahoo describes a computational method for bioinformatic data mining that may have a tremendous impact in biotech and the health sciences.

The method uses Boolean logic to identify genes having specific relationships and expressions in fractions of a second. Such identification can take years and cost hundreds of thousands of dollars using existing laboratory techniques. Still another benefit of this computational approach is that it can be used to mine existing databases.

This is a perfect example of how the convergence of informational technologies leads to accelerating progress. I would expect Sahoo’s method to radically increase our understanding of many genetic processes. I think this and other computational methods are likely to yield significant discoveries in cancer and aging research during the coming decade.