PubMed

Data from pubmed. entire file is downloaded, only taxon IDs set in project.xml will be loaded. if nothing configured, processes all entries.

Types of data loaded

genes, publications

How to load the data into your mine

project XML example

<source name="pubmed-gene" type="pubmed-gene">
  <property name="src.data.dir" location="DATA_DIR/pubmed/" />
  <property name="pubmed.organisms" value="7227"/>
  <property name="src.data.dir.includes" value="gene2pubmed"/>
</source>