Textpresso is an information extracting and processing (text mining) package for biological literature whose capabilities go far beyond that of a simple keyword search engine. The two key elements are the collection of the full text of scientific articles split into individual sentences, and the implementation of semantic categories, for which a database of articles and individual sentences can be searched. The source of the full text articles are PDFs, and additional bibliographical information that is obtained from other citation databases can be processed as well. Alere is a package of scripts that can be used to construct a corpus (retrieve articles) for use with Textpresso. Textpresso is supported by a grant from the National Human Genome Research Institute at the US National Institutes of Health # HG004090.
Textpresso 1 & 2
Textpresso was initially developed by Hans-Michael Müller, Eimear Kenny and Paul W. Sternberg, with contributions from Juancarlos Chan and David Chen. Textpresso 2.0 was developed by Hans-Michael Müller with contributions from Arun Rangarajan and Tracy K. Teal. Textpresso is part of WormBase at the California Institute of Technology, California.
Textpresso 2 Extensions
A fork of Textpresso has been created that contains a number of extensions to Textpresso 2. These include
- Interface overhaul, including AJAX and heavy integration of jQuery DatatTables, user authentication, and a GUI for managing the literature corpus.
- Modularization and customization for better database support
- Addition of a plug-in API
- Speed increase
These extensions were written by Nathan Liles of the Hu Lab at Texas A&M University. Nathan presented this work at the January 2010 GMOD Meeting. The Textpresso team plans to fold these extensions back into the main Textpresso code base in the future.
Demo & Screenshots
Please visit the live main site at www.textpresso.org for examples and screenshots.
The package is designed for Linux operating systems and is tested to run on an Intel x86 based hardware. The required minimal disk space is around 6GB per 1000 full text papers, half of it is used by the publically (via WWW) accessible database, while the other half is needed for database preparation and maintenance. If necessary, the latter can be reduced.
- Software for a world wide web server such as Apache needs to be installed, and an Internet connection should exist
- Perl 5.6.1 or higher should be present, and the most common Perl packages.
- The installation script requires bash
- Mailer::Mail (in MailTools-1.58)
- PDF::Create (in PDF-Create).
- If the model organism database is based on ACeDB then AcePerl is required
- XPDF (http://www.foolabs.com/xpdf/), the pdftotext converter
- RBT, a part-of-speech tagger developed by Eric Brill (blog, homepagedeprecated). RBT seems to be no longer available at JHU. A copy appears to be available at Københavns Universitet (I didn't download and check it). RBT is distributed free of charge under a license of the Massachusetts Institute of Technology and the University of Pennsylvania. If you want to recompile either of the packages, you additionally need a C compiler.
Hans-Michael Müller, mueller (at) caltech.edu