README.md

Biotex

Biotex is a Automated Term Extractor (ATE) for Bio-medical terms (see here for more details).

This repository contains two ways of executing Biotex (Python and Java). A list of improvements made:

• Easy execution
• Python wrapper
• Parameters configuration without changing the source code
• ...

Installation

Requirements

• Python 3
• Java 7-8

Install

To make it works, clone this repository using :

git clone <repoAdress>

Then compile the project by using this command :

javac -cp .:JarBioTexExterne.jar:commons-io-2.5.jar Principal.java

Then create the necessary jar with this command :

jar cvfm Biotex.jar Manifest.txt Principal.class JarBioTexExterne.jar commons-io-2.5.jar

Running

Python

In Python, either you import the library and import the ’BiotexWrapper’ class or using this command :

python3 BiotexWrapper.py <input> [-d:debug] [-o:specify output filename] [-s:gramSize selected (ALL to get all gramSize)]

Java

Modify the configuration file 'configuration.txt' and change the value if needed (especially treetagger src). Then use :

java -jar Biotex.jar <input> <outputDir>