SimText: A text mining framework for interactive analysis and visualization of similarities among biomedical entities

Abstract

<jats:title>Abstract</jats:title><jats:p>Literature exploration in PubMed on a large number of biomedical entities (e.g., genes, diseases, experiments) can be time consuming and challenging comparing many entities to one other. Here, we describe SimText, a user-friendly toolset that provides customizable and systematic workflows for the analysis of similarities among a set of entities based on words from abstracts and/or other text. SimText can be used for (i) data generation: text collection from PubMed and extraction of words with different text mining approaches, and (ii) interactive analysis of data using unsupervised learning techniques and visualization in a Shiny web application.</jats:p><jats:sec><jats:title>Availability and Implementation</jats:title><jats:p>We developed SimText as an open-source R software and integrated it into Galaxy, an online data analysis platform. A command line version of the toolset is available for download from GitHub at <jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://github.com/mgramm1/simtext">https://github.com/mgramm1/simtext</jats:ext-link>.</jats:p></jats:sec>