SMAC, a computational system to link literature, biomedical and expression data
Institution: Barts Cancer Institute, Queen Mary University of London
Corresponding Researcher: Claude Chelala
Keyword(s): data mining, literature mining
Summary
High-throughput technologies have produced a large amount of experimental and biomedical data creating an urgent need for comprehensive and automated mining approaches. To meet this need, we developed SMAC (SMart Automatic Classification method): a tool to extract, prioritise, integrate and analyse biomedical and molecular data according to user-defined terms. The robust ranking step performed on Medical Subject Headings (MeSH) ensures that papers are prioritised based on specific user requirements. SMAC then retrieves any related molecular data from the Gene Expression Omnibus and performs a wide range of bioinformatics analyses to extract biological insights. These features make SMAC a robust tool to explore the literature around any biomedical topic. SMAC can easily be customised/expanded and is distributed as a Docker container (https://hub.docker.com/r/hfx320/smac) ready-to-use on Windows, Mac and Linux OS. SMAC's functionalities have already been adapted and integrated into the Breast Cancer Now Tissue Bank bioinformatics platform and the Pancreatic Expression Database.
