Overview

Moara is a project developed by BioComputing unit at Centro Nacional de Biotecnologia (CNB) for the development of biological text mining tools. It consists of a Java library and some auxiliary MySQL databases for carrying out the below functionalities:

• CBR-Tagger: gene/protein training and extraction of mentions;
• Wrapper of the ABNER for the gene/protein extraction of mentions;
• ML-Normalization: flexible and machine-learning gene/protein normalization and disambiguation for the yeast, mouse, fly and human; and trainable for additional organisms.

Referencing Moara

• Neves M L, Carazo J M and Pascual-Montano A. Moara: a Java library for extracting and normalizing gene and protein mentions, BMC Bioinformatics, 2010, 11:157. [PubMed] [full text] [BibTex]

The available classes are presented in the figure below:

Coming soon

• Java API.