The future of text mining in genome-based clinical research

Efficient information retrieval and extraction is a major challenge in molecular biology and genome-based clinical research. In addition, there is an increasing demand to combine information from different resources and across different disciplines in life sciences. Unfortunately, a large proportion of this information is only available in scientific articles. Moreover, the volume of literature is growing almost exponentially. Text mining provides methods to retrieve and extract information contained in free-text automatically. Here, we discuss the challenges and limitations of text mining in biology and medicine, including unsolved problems and necessary developments.