TDC Tools: streamlining information retrieval applications thanks to a tabular Document-Concept representation of the biomedical literature

Motivation: Several methods can be used to obtain the content of the biomedical literature articles annotated with standardized concepts. Various information retrieval (IR) applications exploit these resources, e.g. Literature-Based Discovery (LBD). Such applications often require a complex processing pipeline to transform the raw literature into an appropriate structured representation.

Results: TDC Tools offer an intermediate level of representation aimed to facilitate the design and implementation of IR systems exploiting a concept-based view of the literature. Conceptually this intermediate representation decouples the data extraction part from the task-specific exploitation part, thus improving the modularity, interoperability and ultimately the reusability of such systems.

Availability: The software and its dependencies are published under open-source license and provided with detailed instructions: https://github.com/erwanm/tdc-tools.