institute for computational biomedicine: textractor

CRT home > Textractor

[ description ]

Textractor is a software framework. The framework is designed to facilitate the development of software tools that process text to extract information. The focus of this framework is on applications that need to process large quantities of text, for instance large collections of full text articles (>10,000 articles). The development of textractor started at the Institute for Computational Biomedicine, Weill Cornell Medical College. Since we distribute the source code under the GPL, you are welcome to reuse or extend the framework in any way you like.

[ about the method ]

Software architecture of the framework is unpublished and should be cited as Textractor http://icb.med.cornell.edu/crt/textractor/ (L. Shi and F. Campagne 2004).

[ documentation ]

Supplementary material for the gene/gene product extraction article:

Precision measurements on JBC2000 (Excel)

NCB14 Evaluation results (Excel)

PMC15 Evaluation results (Excel)

The catalog of protein name references

The protein dictionary

The names collected from the last quarter of JBC1999 by regular expressions for SVM training are below:

Protein names

Cell names

Interaction names

Biological process names

You can download the protein name lookup program here:

The lookup program (JAR file, version 1.1)

To use the lookup program, you will need Java 1.4+. Download the JAR file (tlookup.jar) and type java -jar tlookup.jar for usage information.

You can also download the source code, but will need a full fledged software development environment (JDK1.4+, Ant 1.6+) and will need a suitable JDO implementation (we developed with FastObjects and have not tested porting on another JDO implementation). By downloading this distribution, you agree to the terms of the Gnu General Public License.

The Textractor source code v1.1(GPL)

The latest development snapshot of the source code archived on August 2nd 2006 is also available for download. This version requires JDK 1.5+ and a suitable JDO implementation.

The Textractor source code v20060802144806 (GPL)

A precompiled version archived on August 2nd, 2006 is also available for download. This version requires apache ant version 1.6.5 and acess to an oracle database to use.

Textractor v20060802144806 precompiled for use with Oracle.

Textractor API Documentation

Textractor API

Textractor is used in the following projects:

Twease

If you find this software useful, please let us know in a quick email.

News

Mar, 2008; A free bioinformatics walk-in clinic will be available every Monday, 1-3pm at the Weill Cornell Medical Library, in the Computer Room on the lower level. [More]
Feb, 2007; In a recent national ranking of graduate programs, carried out by the Chronicle of Higher Education, Weill Cornell's PBSB program was ranked #3 in Physiology and #10 in Biophysics. [More]

[News Archives] [Mailing List]

Events

May 14-15, 2008 Cornell University Life Sciences Research Resources Expo. An intercampus exhibition of Cornell core facilities. [More]
Jul 19-23, 2008 16th Annual International Conference on Intelligent Systems for Molecular Biology (ISMB) A forum for disseminating the latest developments in bioinformatics. [ISMB 2008]