JULIELab/gene-name-mapping: v1.0.0

This is a UIMA-enabled gene mapping software used to deliver NCBI Gene IDs for gene mentions found in the scientific literature.

The code base and the resource creation scripts are based on the GeNo project [1]. However, the gene name repository can be updated using the resource creation scripts.

Note that this component only normalizes gene names and does not find the names itself. The current main features are the integration of symbols, names and synonyms from the NCBI Gene database and gene name disambiguation via GeneRif. By default, this project uses human genes. The resources required for gene name normalization can be built with the scripts contained in this repository. See the README in the GitHub repository for more details.

[1] Wermter, J., Tomanek, K., & Hahn, U. (2009). High-performance gene name normalization with GeNo. Bioinformatics (Oxford, England), 25(6), 815–821. https://doi.org/10.1093/bioinformatics/btp071