pipeline.yaml

CovidGraphPipeline:
  - name: CREATE_FULL_TEXT_INDEXES
    image_repo: covidgraph/graph-processing-fulltext-indexes
  - name: JHU
    image_repo: covidgraph/data_jhu_population
    dependencies:
      - CREATE_FULL_TEXT_INDEXES
  - name: BIOBASE
    info_link: https://git.connect.dzd-ev.de/dzdconnectpipeline/dataloading_biobase
    desc: Load different bio science repos into neo4j
    image_repo: registry-gl.connect.dzd-ev.de:443/dzdconnectpipeline/dataloading_biobase
    tag: prod
    env_vars:
      RUN_MODE: NotTest
  - name: ONTOLOGIES
    info_link: https://git.connect.dzd-ev.de/dzdconnectpipeline/dataloading_ontologies
    desc: Load biomedical ontologies and mappings from biomedical entities to ontologies.
    image_repo: registry-gl.connect.dzd-ev.de:443/dzdconnectpipeline/dataloading_ontologies
    tag: prod
    env_vars:
      OBO_ONTOLOGIES: go,doid,mp,pato,hp
    dependencies:
      - BIOBASE
  - name: LENS_PATENT_DATA
    image_repo: covidgraph/data-lens-org-covid19-patents
  - name: CORD19
    image_repo: covidgraph/data-cord19
    env_vars:
      CONFIGS_PAPER_BATCH_SIZE: 300
      CONFIGS_NO_OF_PROCESSES: 12
    volumes: { "/tmp/data/cord19": { "bind": "/app/dataset", "mode": "rw" } }
  - name: TEXT_FRAGGER
    image_repo: covidgraph/graph-processing_fragmentize_text
    dependencies:
      - CORD19
      - LENS_PATENT_DATA
  - name: TEXT_GENE_MATCH
    image_repo: covidgraph/graph-processing_text_gene_match
    dependencies:
      - CORD19
      - LENS_PATENT_DATA
      - BIOBASE
      - TEXT_FRAGGER
  - name: CLINICAL_TRIALS_GOV
    image_repo: covidgraph/data-clinical_trials_gov
  - name: HELOMICS_HETIONET
    image_repo: helomics/data_hetionet
  - name: BIOBERT
    image_repo: covidgraph/data-biobert
    dependencies:
      - CORD19
  - name: MASYMOS
    image_repo: covidgraph/data_masymos
    env_vars:
      SOURCE: ${MASYMOS_SOURCE_FILE}
    dependencies:
      - CORD19