Text-mining solutions for biomedical research: enabling integrative biology

Key Points Text mining is a means to process the scientific literature at a large scale. It is the means to make documents and their content more accessible. Literature repositories, such as PubMed Central and UK PubMed Central, are data collections just like the scientific biomedical databases. They require special techniques to parse the text and to deliver the facts for further analysis. Data integration, such as the normalization of named entities in the text to database entries, is an essential step towards integrative biology using semantic Web technology. Knowledge discovery is the ultimate goal of any researcher when exploiting integrated biomedical resources. The scientific literature contributes novel hypotheses and facts. The use of formal knowledge representations — such as ontologies and fact data repositories — is paramount to make efficient use of our hypothesis generation and validation. Solutions are emerging that provide intelligent but automated systems to assist biomedical researchers, particularly those dealing with high-throughput data. Text mining — retrieving information from papers and databases — is increasingly used in data-rich fields such as genomics, systems biology and biomedical research. This Review discusses recent tools that can aid researchers and sets out the potential of enhancing integrative research using text mining. In response to the unbridled growth of information in literature and biomedical databases, researchers require efficient means of handling and extracting information. As well as providing background information for research, scientific publications can be processed to transform textual information into database content or complex networks and can be integrated with existing knowledge resources to suggest novel hypotheses. Information extraction and text data analysis can be particularly relevant and helpful in genetics and biomedical research, in which up-to-date information about complex processes involving genes, proteins and phenotypes is crucial. Here we explore the latest advancements in automated literature analysis and its contribution to innovative research approaches.