Class GeneDocumentFactory


  • public class GeneDocumentFactory
    extends Object
    • Constructor Summary

      Constructors 
      Constructor Description
      GeneDocumentFactory​(de.julielab.geneexpbase.configuration.Configuration configuration, de.julielab.speciesassignment.GeneSpeciesAssigner speciesAssigner, de.julielab.geneexpbase.TermNormalizer normalizer)  
    • Constructor Detail

      • GeneDocumentFactory

        @Inject
        public GeneDocumentFactory​(de.julielab.geneexpbase.configuration.Configuration configuration,
                                   de.julielab.speciesassignment.GeneSpeciesAssigner speciesAssigner,
                                   de.julielab.geneexpbase.TermNormalizer normalizer)
                            throws de.julielab.geneexpbase.GeneExpException
        Throws:
        de.julielab.geneexpbase.GeneExpException
    • Method Detail

      • createGeneDocument

        public de.julielab.geneexpbase.genemodel.GeneDocument createGeneDocument​(org.apache.uima.jcas.JCas jCas,
                                                                                 Map<String,​Matcher> entityMappingTypes,
                                                                                 Function<de.julielab.jcore.types.EntityMention,​org.apache.commons.lang3.tuple.Pair<String,​org.apache.lucene.search.BooleanQuery>> contextFun,
                                                                                 de.julielab.geneexpbase.configuration.Parameters parameters)
                                                                          throws org.apache.uima.analysis_engine.AnalysisEngineProcessException

        Creates a document by setting all required information from the jCas.

        Items added are:

        • Title text
        • Text body
        • Sentences
        • PoS tags
        • Chunks
        • Acronyms
        • MeSH Headings (from which species headings will be recognized)
        • Species text mentions
        • The genes, according to the entityMappingTypes. This is a mapping from qualified UIMA types to matchers that need to match the EntityMentions' specificType feature in order for the EntityMention to be used as a gene mention.

        Parameters:
        jCas - The JCas to create the GeneDocument form.
        entityMappingTypes - This is a mapping from qualified UIMA types to matchers that need to match the EntityMentions' specificType feature in order for the EntityMention to be used as a gene mention.
        contextFun - A function that delivers the context information for each gene mention.
        parameters -
        Throws:
        org.apache.uima.analysis_engine.AnalysisEngineProcessException