text2term

text2term maps free-text descriptions of biomedical entities to controlled terms in ontologies to standardize metadata and facilitate data integration.

Key Features:

• Multiple access modes: The tool can be used programmatically as a Python package, via a command-line interface, or through a hosted web application.
• Highly configurable mapping: The tool supports both bulk and one-by-one standardization of discrete entity types such as disease names, cell types, or chemicals.
• Autocompletion support: The tool can support autocompletion of biomedical entities in forms.

Scientific Applications:

• Retrospective metadata standardization: The tool aids in retrospective standardization and cleaning of unstructured or imprecise metadata associated with biomedical data.
• Prospective metadata standardization: The tool supports prospective standardization of discrete entity types used in metadata to improve data findability and reusability.
• Data integration: The tool reduces the upfront curation effort required to make biomedical data usable and integrate datasets by mapping free-text descriptions to ontology terms.

Methodology:

The tool maps free-text descriptions of biomedical entities to controlled terms in ontologies using configurable algorithms; specific computational methods are not detailed in the sources.