README.md

In ZBMEDLABS/epilepsyontologysimilarities: Epilepsy Ontology Similarities

epilepsyontologysimilarities

This is an R package that is developed for analyzing and visualizing statistical information of biomedical named entities that were automatically identified with a UIMA-based text mining workflow on the corpus of LIVIVO. The major scope of this R package is the comparison of drug names that co-occur with entities of epilepsy ontologies in documents of the LIVIVO corpus.

Basically, the UIMA-based workflow takes as input a dictionary containing biomedical entities with synonyms for identifying them in documents of the LIVIVO corpus. The epilepsy ontologies EpSO, ESSO, and EPILONT are used for creating three different dictionaries for epilepsy. The current version of DrugBank is taken for creating a dictionary for drug names. The results of the text mining workflow is written into a MongoDB databases. Finally, the information in the MongoDB is aggregated for creating lists of drug names that are sorted by their frequency of documents in which they co-occur with entities from each of the epilepsy dictionaries. These three frequency sorted lists are saved as R-objects in data/[rawDrugBankCoOcEpSO,rawDrugBankCoOcESSO,rawDrugBankCoOcEPILONT].rda

The ranked result lists of neurological drug terms co-occurring with named entities from the epilepsy ontologies EpSO, ESSO, and EPILONT are aggregated in order to generate two different results: an overview table of drugs that are relevant to epilepsy created with the method createNeuroTable, and a plot of tanimoto similarity coefficients between the aggregated list of drug terms against the list of drug terms from each of the ontologies created with the method createTanimotoBaseline(). The alignment of the Top-K Ranked Lists is conducted using the R-package TopKLists https://cran.r-project.org/package=TopKLists. The source data to create the ranked lists of drug names is produced using the text mining workflows described in Mueller, Bernd and Hagelstein, Alexandra (2016) and Mueller, Bernd et al. (2017) .

The UIMA-based text mining workflow is described in the following two publications:

Müller B, Hagelstein A (2016) Beyond Metadata – Enriching Life Science Publications in LIVIVO with Semantic Entities from the Linked Data Cloud (Joint Proceedings of the Posters and Demos Track of the 12th International Conference on Semantic Systems – SEMANTiCS2016 and the 1st International Workshop on Semantic Change & Evolving Semantics (SuCCESS’16), co-located with the 12th International Conference on Semantic Systems (SEMANTiCS 2016, Leipzig, Germany))

Müller B, Hagelstein A, Gübitz T (2016) Life Science Ontologies in Literature Retrieval: A Comparison of Linked Data Sets for Use on Semantic Search on a Heterogeneous Corpus. In: Proceedings of the 20th International Conference on Knowledge Engineering and Knowledge Management. Bologna, Italy

ZBMEDLABS/epilepsyontologysimilarities documentation built on Aug. 23, 2019, 1:18 p.m.