Flexible Text Mining Strategies for Drug Discovery

The two text mining strategies: finding co-occurrences of biological entities within documents, and finding relation-ships using Natural Language Processing, are often seen as competitors. Here we adopt a flexible approach where the tech-niques are adapted and combined to suit the nature of the document corpus, and the specific task. The approach was tested on three tasks relevant to cancer treatment: finding kinases associated with cancer, finding gene mutations, and finding interactions between proteins as-sociated with cancer. The paper describes the use of entity disambiguation, co-occurrence and linguistic processing in these tasks, and provides an overview of the methodology and results.