Input data and outputs for the OCALM project

This repository contain a zip file with input and output data for an experiment with OCALM (https://github.com/fanavarro/ocalm):

• input
  • ontologies: ontologies used as input (FoodOn, LKIF, GeneOntology), together with their normalized form.
  • text
    • food_text: natural language text corpus about food, including the original and the processed text.
    • gene_text: natural language text corpus about genetics, including the original and the processed text.
    • legal_text: natural language text corpus about legal topics, including the original and the processed text.
• results: the results derived from comparing each ontology with each natural language text corpus by using OCALM.
• NCBO_Recommender_results: the results of the NCBO Recommender with the same experiment performed by OCALM.
• analysis.R: R script to get figures summarizing the results.

The SNOMED ontology and the medical text corpus used for input were not included due to licensing issues; however, the results are included in this repository.