GeNo is highly competitive system for gene name normalization, which obtains an F-measure performance of 86.4% (precision: 87.8%, recall: 85.0%) on the BIOCREATIVE-II test set. Our system tackles the complex gene normalization problem by employing a carefully crafted suite of symbolic and statistical methods, and by fully relying on publicly available software and data resources, including extensive background knowledge based on semantic profiling.
GeNo is available as a remotely employable UIMA Analysis Engine (AE). This AE is an Aggregate Analysis Engine that bundles the gene mapper with key components like our named entity recognition component JNET.
The appropriate XML-Component-Descriptor is ready for download following this link: GeNo Webservice Descriptor. This descriptor gives you access to our GeNo-Webservice over SOAP. Please note that for using GeNo as a web service, the Apache Axis libraries must be on your Java classpath. The remote use of GeNo was tested with Apache Axis 1.4. For further information on how to use remote Analysis Engines, please refer to the UIMA documentation.
If you encounter problems concerning the type system, feel free to download JULIE type system.
Please note that using GeNo will be subject to restrictions regarding the amount of documents that can be processed. This is necessary to spare our computing ressources. If you are in need to process a large volume of documents, please contact us.
Joachim Wermter, Katrin Tomanek , and Udo Hahn. High-Performance Gene Name Normalization with GENO. Bioinformatics, 2009.