PanTools graph database structure
=================================

Please see :numref:`database-schema` for the PanTools graph database. Please use
it as a reference for writing Cypher queries and for understanding the structure
of the database.

.. graphviz::
   :name: database-schema
   :caption: PanTools graph database schema in neo4j.

   digraph G {
      rankdir=LR;
      node [shape=box];

      subgraph cluster_metadata {
         pangenome [label="pangenome"];
         genome [label="genome"];
         accession [label="accession"];
         phenotype [label="phenotype"];
         annotation [label="annotation"];
         sequence [label="sequence"];

         pangenome -> genome [label="has"];
         genome -> phenotype [label="has_phenotype"];
         genome -> accession [label="has"];
         annotation -> genome [label="annotates"];
         genome -> sequence [label="has"];
      }

      subgraph cluster_nucleotide {
         label="nucleotide layer";

         nucleotide [label="nucleotide"];

         nucleotide -> nucleotide [label="FF"];
         nucleotide -> nucleotide [label="FR"];
         nucleotide -> nucleotide [label="RF"];
         nucleotide -> nucleotide [label="RR"];
      }

      sequence -> nucleotide [label="FF"];
      nucleotide -> sequence [label="FF"];
      nucleotide -> sequence [label="RF"];
      nucleotide -> sequence [label="FR"];
      nucleotide -> sequence [label="RR"];

      subgraph cluster_annotation {
         label="annotation layer";
         gene [label="gene"];
         mRNA [label="mRNA"];
         CDS [label="CDS"];
         exon [label="exon"];

         gene -> mRNA [label="is_parent_of"];
         gene -> mRNA [label="codes_for"];
         mRNA -> CDS [label="is_parent_of"];
         CDS -> mRNA [label="contributes_to"];
         mRNA -> exon [label="is_parent_of"];
         mRNA -> mRNA [label="is_similar_to"];
      }

      homology_group [label="homology_group"];
      variant [label="variant"];
      repeat [label="repeat"];
      synteny [label="synteny"];

      homology_group -> mRNA [label="has_homolog"];
      mRNA -> variant [label="has_variant"];
      repeat -> nucleotide [label="start"];
      repeat -> nucleotide [label="stop"];
      mRNA -> synteny [label="part_of"];
      synteny -> synteny [label="is_syntenic_to"];
      gene -> nucleotide [label="starts"];
      gene -> nucleotide [label="stops"];
      mRNA -> nucleotide [label="starts"];
      mRNA -> nucleotide [label="stops"];
      CDS -> nucleotide [label="starts"];
      CDS -> nucleotide [label="stops"];
      exon -> nucleotide [label="starts"];
      exon -> nucleotide [label="stops"];

      subgraph cluster_functions {
         label="functions layer";

         GO [label="GO"];
         pfam [label="pfam"];
         interpro [label="interpro"];
         tigrfam [label="tigrfam"];

         GO -> GO [label="regulates"];
         GO -> GO [label="negatively_regulates"];
         GO -> GO [label="positively_regulates"];
         GO -> GO [label="is_a"];
         GO -> GO [label="part_of"];
         pfam -> GO [label="is_similar_to"];
         interpro -> GO [label="is_similar_to"];
         tigrfam -> GO [label="is_similar_to"];
         tigrfam -> GO [label="contributes_to"];
      }

      mRNA -> GO [label="has_GO"];
      mRNA -> pfam [label="has_pfam"];
      mRNA -> interpro [label="has_interpro"];
      mRNA -> tigrfam [label="has_tigrfam"];
   }