LigerCat: using "MeSH Clouds" from journal, article, or gene citations to facilitate the identification of relevant biomedical literature

Abstract

The identification of relevant literature from within large collections is often a challenging endeavor. In the context of indexed resources, such as MEDLINE, it has been shown that keywords from a controlled vocabulary (e.g., MeSH) can be used in combination to retrieve relevant search results. One effective strategy for identifying potential search terms is to examine a collection of documents for frequently occurring terms. In this way, "Tag clouds" are a popular mechanism for ascertaining terms associated with a collection of documents. Here, we present the Literature and Genomic Electronic Resource Catalogue (LigerCat) system for exploring biomedical literature through the selection of terms within a "MeSH cloud" that is generated based on an initial query using journal, article, or gene data. The resultant interface is encapsulated within a Web interface: http://ligercat.ubio.org. The system is also available for installation under an MIT license.

Figure 1:

Overview of LigerCat process. (1) MEDLINE results are examined based on an initial text query (to the NLM Journals or MEDLINE database) or molecular sequence query (to a local GENBANK database that we have linked to MEDLINE results); (2) the results are generated and then (3) used to query MEDLINE via a multi-selection enabled MeSH Cloud.

Figure 2:

MeSH cloud based on Genes search using Amyloid Beta Precursor Protein (gi: 41406053).