application.conf

spark-uri = ""
log-level = "WARN"
output-dir = ${HOME}/data/ot/results
input-dir = ${HOME}/data/ot/extract
execution-mode = production
data-resources {
    local-dir = ${HOME}/repos/platform-pipe/src/main/resources/data
    evidence-json-schema = "https://raw.githubusercontent.com/opentargets/json_schema/1.6.2/opentargets.json"
    eco-scores = "https://storage.googleapis.com/open-targets-data-releases/19.11/input/annotation-files/eco_scores-2019-10-31.tsv"
}
data-sources: [
    { name = cancer_gene_census, type = somatic_mutation }
    { name = chembl, type = known_drug }
    { name = crispr, type = affected_pathway }
    { name = europepmc, type = literature }
    { name = eva, type = genetic_association }
    { name = eva_somatic, type = somatic_mutation }
    { name = expression_atlas, type = rna_expression }
    { name = gene2phenotype, type = genetic_association }
    { name = genomics_england, type = genetic_association }
    { name = gwas_catalog, type = genetic_association }
    { name = intogen, type = somatic_mutation }
    { name = phenodigm, type = animal_model }
    { name = phewas_catalog, type = genetic_association }
    { name = postgap, type = genetic_association }
    { name = progeny, type = affected_pathway }
    { name = reactome, type = affected_pathway }
    { name = slapenrich, type = affected_pathway }
    { name = sysbio, type = affected_pathway }
    { name = uniprot, type = genetic_association }
    { name = uniprot_literature, type = genetic_association }
    { name = uniprot_somatic, type = somatic_mutation }
]
pipeline {
    enable-assertions = false
    enable-summaries = false
    scoring {
        allow-unknown-data-type = true
        allow-missing-score = false
        save-evidence-scores = false
        evidence-extract-dir-name = "evidence.json"
        source-weights {
            crisp = 1
            europepmc = 0.2
            expression_atlas = 0.2
            phenodigm = 0.2
            progeny = 0.5
            slapenrich = 0.5
            sysbio = 0.5
        }
    }
    evidence {
        raw-evidence-dir-name = "evidence_raw.json"
        gene-extract-dir-name = "gene.json"
        efo-extract-dir-name = "efo.json"
        excluded-biotypes {
          expression_atlas  = [
              IG_C_pseudogene
              IG_J_pseudogene
              IG_pseudogene
              IG_V_pseudogene
              polymorphic_pseudogene
              processed_pseudogene
              pseudogene
              rRNA
              rRNA_pseudogene
              snoRNA
              snRNA
              transcribed_processed_pseudogene
              transcribed_unitary_pseudogene
              transcribed_unprocessed_pseudogene
              TR_J_pseudogene
              TR_V_pseudogene
              unitary_pseudogene
              unprocessed_pseudogene
          ]
        }
    }
    decorators {
        log = {enabled = true}
        time = {enabled = true}
        reference = {enabled = true}
        dataset-summary = {enabled = false}
    }
}
external-config {
    # From 19.11.4 data_pipeline release
    mrtarget-data: "https://storage.googleapis.com/open-targets-data-releases/19.11/input/mrtarget.data.19.11.yml"
    mrtarget-es: "https://github.com/opentargets/data_pipeline/blob/329ff219f9510d137c7609478b05d358c9195579/mrtarget.es.yml"
}