Difference between revisions of "Textpresso"

From GMOD
Jump to: navigation, search
(Added alere link)
(updated general description,and updated RBT and Brill information.)
Line 1: Line 1:
 
==Description==
 
==Description==
  
−
Textpresso is a text mining system for scientific 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.  [http://ilex.caltech.edu/trac/alere/ Alere] is a package of scripts that can be used wto retrieve articles for use with Textpresso .
+
'''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.  [http://ilex.caltech.edu/trac/alere/ Alere] is a package of scripts that can be used to construct a corpus (retrieve articles) for use with '''Textpresso''' .
 +
 
 +
'''Textpresso''' was initially developed by Hans-Michael Muller, Eimear Kenny and Paul W. Sternberg, with contributions from Juancarlos Chan and David Chen. The new version (officially known as Textpresso 2.0) was developed by Hans-Michael Muller with contributions from Arun Rangarajan and Tracy K. Teal. Textpresso is part of WormBase at the California Institute of Technology, California. Textpresso is supported by a grant from the National Human Genome Research Institute at the US National Institutes of Health # HG004090.  
  
  
Line 24: Line 26:
 
* If the model organism database is based on ACeDB then {{CPAN|AcePerl}} is required
 
* If the model organism database is based on ACeDB then {{CPAN|AcePerl}} is required
 
* XPDF  (http://www.foolabs.com/xpdf/), the pdftotext converter
 
* XPDF  (http://www.foolabs.com/xpdf/), the pdftotext converter
−
* [http://www.cs.jhu.edu/~brill/RBT1_14.tar.Z RBT], a part-of-speech tagger developed by Eric Brill  (http://research.microsoft.com/~brill/)
+
* RBT, a part-of-speech tagger developed by Eric Brill  ([http://research.microsoft.com/~brill/blog.htm blog], [http://research.microsoft.com/~brill/ homepage]''deprecated'').  RBT seems to be no longer available at JHU.  A copy appears to be available at [http://www.cst.dk/download/tagger/RBT1_14.tar.Z 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.
−
 
+
−
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.
+
  
 
This package has been tested with the Linux RedHat 9.0 distribution  (http://www.redhat.com) and Debian Linux 3.1 (http://www.debian.org) . Both  work with a 2.4.20 kernel or higher.
 
This package has been tested with the Linux RedHat 9.0 distribution  (http://www.redhat.com) and Debian Linux 3.1 (http://www.debian.org) . Both  work with a 2.4.20 kernel or higher.
Line 45: Line 45:
  
 
http://www.textpresso.org/textpresso/downloads.html
 
http://www.textpresso.org/textpresso/downloads.html
−
 
−
[[Category:GMOD Components]]
 
−
[[Category:Textpresso]]
 
  
 
[[Category:GMOD Components]]
 
[[Category:GMOD Components]]
 
[[Category:Textpresso]]
 
[[Category:Textpresso]]

Revision as of 16:02, 9 July 2008

Description

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 was initially developed by Hans-Michael Muller, Eimear Kenny and Paul W. Sternberg, with contributions from Juancarlos Chan and David Chen. The new version (officially known as Textpresso 2.0) was developed by Hans-Michael Muller with contributions from Arun Rangarajan and Tracy K. Teal. Textpresso is part of WormBase at the California Institute of Technology, California. Textpresso is supported by a grant from the National Human Genome Research Institute at the US National Institutes of Health # HG004090.


Demo & Screenshots

Please visit the live main site at www.textpresso.org for examples and screenshots.


Requirements

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
  • XML::Checker::Parser
  • XML::DOM::Parser
  • XML::XQL::DOM
  • XML::Checker::Parser,
  • 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.

This package has been tested with the Linux RedHat 9.0 distribution (http://www.redhat.com) and Debian Linux 3.1 (http://www.debian.org) . Both work with a 2.4.20 kernel or higher.

Documentation

Installation instruction can be found in the tarzipped package file and is called TextpressoManual.pdf.

A user guide is available online.


Contact

Hans-Michael Muller, mueller (at) caltech.edu


Downloads

http://www.textpresso.org/textpresso/downloads.html

Retrieved from "http://gmod.org/mediawiki/index.php?title=Textpresso&oldid=5760"