Currently, all MEDLINE documents are indexed by medical subject headings (MeSH). Computing semantic similarity between two MeSH headings as well as two documents has become very important for many biomedical text mining applications. We develop an R package, MeSHSim, which can compute nine similarity measures between MeSH nodes, by which similarity between MeSH headings as well as MEDLINE documents can be easily computed. Also, MeSHSim supports querying hierarchy information of a MeSH heading and retrieving MeSH headings of a query document, and can be easily integrated into pipelines for any biomedical text analysis tasks. MeSHSim is released under general public license (GPL), and available through Bioconductor and from Github at https://github.com/JingZhou2015/MeSHSim.
Currently all MEDLINE documents are indexed by Medical Subject Headings (MeSH). Computing semantic similarity between two MeSH headings as well as two documents has become very important for many biomedical text mining applications. We develop an R package, MeSHSim, which can compute nine similarity measures between MeSH nodes, by which similarity between MeSH Headings as well as MEDLINE documents can be easily computed. Also MeSHSim supports querying hierarchy information of a MeSH heading and retrieving MeSH headings of a query document, and can be easily integrated into pipelines for any biomedical text analysis tasks. MeSHSim is released under GPL
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.