This site is about text mining science. It is about text mining for science -- how we can use text mining to support scientific knowledge discovery. It is also about the science of text mining -- the techniques and algorithms that we develop to do text mining.

While there are many areas of science where text mining could be applied, this site is primarily about text mining for biomedicine. And even more specifically, it is mostly about text mining for supporting biological knowledge discovery at the molecular level (i.e. at the level of genes and proteins) or in pharmacogenomics (where genes and proteins interact with drug molecules). But, clinical text mining -- considering electronic health records or clinical reports like radiology or pathology reports -- is increasingly of interest to me, as is translational research (from bench to bedside).

Eventually, I believe that text mining can play a significant role in personalized medicine (aka precision medicine) by supporting the analysis of myriad text sources that provide evidence relating to individual patient variation, from text discussing genomic and proteomic variation to the clinical data.

I hope you enjoy looking around my site.

Karin Verspoor