The project.xml file

The following is an example of a project.xml suitable for a Plasmodium falciparum data mine. See below for a description of the parts of the file.

<project type="bio">
  <property name="target.model" value="genomic"/>
  <property name="common.os.prefix" value="common"/>
  <property name="intermine.properties.file" value="malariamine.properties"/>
  <property name="default.intermine.properties.file" location="../default.intermine.integrate.properties"/>

  <sources>
    <source name="malaria-gff" type="malaria-gff">
      <property name="gff3.taxonId" value="36329"/>
      <property name="src.data.dir" location="my_data_dir/malaria/malaria-genome/gff"/>
    </source>
    <source name="malaria-chromosome-fasta" type="fasta">
      <property name="source.name" value="fasta"/>
      <property name="fasta.className" value="org.flymine.model.genomic.Chromosome"/>
      <property name="fasta.includes" value="MAL*.fasta"/>
      <property name="fasta.taxonId" value="36329"/>
      <property name="src.data.dir" location="my_data_dir/malaria/malaria-genome/fasta"/>
    </source>
    <source name="uniprot-malaria" type="uniprot">
      <property name="uniprot.organisms" value="36329"/>
      <property name="src.data.dir" location="my_data_dir/malaria/uniprot/7.7/split"/>
    </source>
    <source name="go" type="go">
      <property name="src.data.file" location="my_data_dir/malaria/gene_ontology/gene_ontology.obo"/>
    </source>
    <source name="go-annotation" type="go-annotation" dump="true">
      <property name="ontologyfile" location="my_data_dir/malaria/gene_ontology/gene_ontology.obo"/>
      <property name="src.data.dir" location="my_data_dir/malaria/go-annotation"/>
    </source>
    <source name="inparanoid-orthologue" type="orthologue" dump="true">
      <property name="src.data.dir" location="my_data_dir/malaria/inparanoid/2006-04-16/"/>
    </source>
    <source name="psi-intact" type="psi">
      <property name="src.data.dir" location="my_data_dir/malaria/psi/intact/2006-05-26"/>
      <property name="organisms" value="36329"/>
    </source>
    <source name="update-publications" type="update-publications">
      <property name="src.data.file" location="build/publications.xml"/>
    </source>
    <source name="entrez-organism" type="entrez-organism" dump="true">
      <property name="src.data.file" location="build/organisms.xml"/>
    </source>
  </sources>

  <post-processing>
    <post-process name="create-references"/>
    <post-process name="make-spanning-locations"/>
    <post-process name="create-chromosome-locations-and-lengths"/>
    <post-process name="transfer-sequences" dump="true"/>

    <!-- this runs the postprocessing steps in all sources -->
    <post-process name="do-sources"/>

    <post-process name="set-collection-counts"/>
    <post-process name="summarise-objectstore"/>
  </post-processing>

</project>

The parts of the project.xml file

Properties

• target.model - the name of the model created and used by this project
• common.os.prefix - used by the integration system to choose which database properties to use
• intermine.properties.file - the name of the file in the home directory which contains properties such as database name, user names and passwords. These properties override the cotents of default.intermine.properties.file.
• default.intermine.properties.file - the location of the default properties for this mine

Sources

The sources element gives a list of sources to integrate along with any properties specific to those sources. Properties within the <source> tag are used only when processing the given source and will override any properties in the source's project.properties file.