config.yaml

# This configuration file should contain all required configuration parameters
# for the ingest workflow to run to completion.
#
# Define optional config parameters with their default values here so that users
# do not have to dig through the workflows to figure out the default values

# Required to fetch from NCBI Datasets
ncbi_taxon_id: "142786"

# The list of NCBI Datasets fields to include from NCBI Datasets output
# These need to be the "mnemonics" of the NCBI Datasets fields, see docs for full list of fields
# https://www.ncbi.nlm.nih.gov/datasets/docs/v2/reference-docs/command-line/dataformat/tsv/dataformat_tsv_virus-genome/#fields
# Note: the "accession" field MUST be provided to match with the sequences
ncbi_datasets_fields:
  - accession
  - sourcedb
  - sra-accs
  - isolate-lineage
  - geo-region
  - geo-location
  - isolate-collection-date
  - release-date
  - update-date
  - length
  - host-name
  - is-lab-host
  - isolate-lineage-source
  - biosample-acc
  - submitter-names
  - submitter-affiliation
  - submitter-country

# Config parameters related to the curate pipeline
curate:
  # URL pointed to public generalized geolocation rules
  # For the Nextstrain team, this is currently
  # "https://raw.githubusercontent.com/nextstrain/ncov-ingest/master/source-data/gisaid_geoLocationRules.tsv"
  geolocation_rules_url: "https://raw.githubusercontent.com/nextstrain/ncov-ingest/master/source-data/gisaid_geoLocationRules.tsv"
  # The path to the local geolocation rules within the pathogen repo
  # The path should be relative to the ingest directory.
  local_geolocation_rules: "defaults/geolocation_rules.tsv"
  # List of field names to change where the key is the original field name and the value is the new field name
  # The original field names should match the ncbi_datasets_fields provided above.
  # This is the first step in the pipeline, so any references to field names in the configs below should use the new field names
  field_map:
    accession: accession
    accession_version: accession_version
    sourcedb: database
    sra-accs: sra_accessions
    isolate-lineage: strain
    geo-region: region
    geo-location: location
    isolate-collection-date: date
    release-date: date_released
    update-date: date_updated
    length: length
    host-name: host
    is-lab-host: is_lab_host
    isolate-lineage-source: sample_type
    biosample-acc: biosample_accessions
    submitter-names: authors
    submitter-affiliation: institution
    submitter-country: submitter_country
  # Standardized strain name regex
  # Currently accepts any characters because we do not have a clear standard for strain names across pathogens
  strain_regex: "^.+$"
  # Back up strain name field to use if "strain" doesn"t match regex above
  strain_backup_fields: ["accession"]
  # List of date fields to standardize to ISO format YYYY-MM-DD
  date_fields: ["date", "date_released", "date_updated"]
  # List of expected date formats that are present in the date fields provided above
  # These date formats should use directives expected by datetime
  # See https://docs.python.org/3.9/library/datetime.html#strftime-and-strptime-format-codes
  expected_date_formats: ["%Y", "%Y-%m", "%Y-%m-%d", "%Y-%m-%dT%H:%M:%SZ"]
  # The expected field that contains the GenBank geo_loc_name
  genbank_location_field: location
  titlecase:
    # List of string fields to titlecase
    fields: ["region", "country", "division", "location"]
    # List of abbreviations not cast to titlecase, keeps uppercase
    abbreviations: ["USA"]
    # Articles that should not be cast to titlecase
    articles: [
      "and", "d", "de", "del", "des", "di", "do", "en", "l", "la", "las", "le",
      "los", "nad", "of", "op", "sur", "the", "y"
    ]
  # Metadata field that contains the list of authors associated with the sequence
  authors_field: "authors"
  # Default value to use if the authors field is empty
  authors_default_value: "?"
  # Name to use for the generated abbreviated authors field
  abbr_authors_field: "abbr_authors"
  # Path to the manual annotations file
  # The path should be relative to the ingest directory
  annotations: "defaults/annotations.tsv"
  # The ID field in the metadata to use to merge the manual annotations
  annotations_id: "accession"
  # The ID field in the metadata to use as the sequence id in the output FASTA file
  output_id_field: "accession"
  # The field in the NDJSON record that contains the actual genomic sequence
  output_sequence_field: "sequence"
  # The list of metadata columns to keep in the final output of the curation pipeline.
  metadata_columns: [
    "accession",
    "accession_version",
    "strain",
    "date",
    "region",
    "country",
    "division",
    "location",
    "length",
    "host",
    "is_lab_host",
    "date_released",
    "date_updated",
    "sra_accessions",
    "authors",
    "abbr_authors",
    "institution",
  ]