benchmark_ndf_rt: Benchmarking NDF RT task
In beamandrew/cui2vec: cui2vec Word Embeddings for Multimodal Data

The benchmarking strategy leverages previously published ‘known’ relationships between medicalconcepts. We compare how similar the embeddings for a pair of concepts are by computing the cosine similarity of their corresponding vectors, and use this similarity to assess whether or not thetwo concepts are related. benchmark_ndf_rt assesses an embedding's ability to power to detect "may treat" and "may prevent" relationships using bootstrap scores of random drug-disease pairs.

1	benchmark_ndf_rt(embedding_df, sig_level = 0.05, bootstraps = 10000)

`embedding_df`	The embedding data frame with bound semantic type
`sig_level`	The significance level threshold
`bootstraps`	The number of bootstraps to perform