Even in the age of the database in biology, scientific literature still holds the newest information and the intelligence surrounding that data. Unfortunately, researchers cannot hope to read all the articles relevant to their field of study if they also want to contribute.

I will describe LitMiner, our effort to develop a unified collection of text and language processing tools to solve the real information needs of genomic and proteomic scientists. Besides being useful, we are developing LitMiner as a foundation for advances in text mining.

To close the talk, I will summarize three of our interesting advances in text retrieval and predicting the future (better than chance anyway).