config.yml

default:
  spark_master: yarn
  enrichments:
    all: gs://ot-team/irene/stop_reasons/predictions_aggregations_all/
    non_oncology: gs://ot-team/irene/stop_reasons/predictions_aggregations_non_oncology
    oncology: gs://ot-team/irene/stop_reasons/predictions_aggregations_oncology
  permuted_enrichments_template: gs://ot-team/irene/stop_reasons/baseline_predictions_aggregations_08092023
  stop_vs_phase_enrichments_template: gs://ot-team/irene/stop_reasons/reason_vs_phase_aggregations
  input:
    # gcp
    disease_path: gs://open-targets-data-releases/22.04/output/etl/parquet/diseases/
    evidence_path: gs://open-targets-data-releases/22.04/output/etl/parquet/evidence/
    target_path: gs://open-targets-data-releases/22.04/output/etl/parquet/targets/
    interactions_path: gs://open-targets-data-releases/22.04/output/etl/parquet/interaction
    hpa_path: gs://ot-team/dochoa/proteinatlas.json.gz
    # static
    predictions_freeze_path: gs://ot-team/dochoa/stop_reasons/stopped_predictions_formatted_30_09_22.csv
    pak_wvectors: data/wvectors.csv
    pak_class_frequencies: data/frequencies.csv
    classes_lut: data/classes.csv