We report on the original implementation of named entity recognition (NER) modules based on an automatic text categorization pipeline, so-called ToxiCat (Toxicogenomic Categorizer), developed to perform biomedical documents classification and prioritization for the previous Biocreative campaign in order to speed up the curation of the Comparative Toxicogenomics Database (CTD). ToxiCat NER modules are a group of components that analyse text for enclosed information. These modules are based on an information retrieval engine for MEDLINE (EAGLi), a gene normalization (GN) service (NormaGene) developed for a previous BioCreative campaign, gene ontology categorizer (GOCat) and finally an entity recognizer for diseases and chemicals. The NER services are publically available as RESTful web services at http://pingu.unige.ch:8080/Toxicat.