parameters.yaml

# This file contains defaults for the "config" object used in the Snakefile.
# To temporarily override or provide a value, you can use snakemake's --config
# or --configfile options.
---
# conda environment file to use by default
# This must be a relative path to the top-level Snakefile directory (e.g., `ncov/`).
conda_environment: "workflow/envs/nextstrain.yaml"

strip_strain_prefixes:
  - hCoV-19/
  - SARS-CoV-2/

sanitize_metadata:
  metadata_id_columns:
    - strain
    - name
    - Virus name
  database_id_columns:
    - "Accession ID"
    - gisaid_epi_isl
    - genbank_accession
  error_on_duplicate_strains: false
  parse_location_field: Location
  rename_fields:
    - "Virus name=strain"
    - "Type=type"
    - "Accession ID=gisaid_epi_isl"
    - "Collection date=date"
    - "Additional location information=additional_location_information"
    - "Sequence length=length"
    - "Host=host"
    - "Patient age=patient_age"
    - "Gender=sex"
    - "Clade=GISAID_clade"
    - "Pango lineage=pango_lineage"
    - "pangolin_lineage=pango_lineage"
    - "Lineage=pango_lineage"
    - "Pangolin version=pangolin_version"
    - "Variant=variant"
    - "AA Substitutions=aaSubstitutions"
    - "Submission date=date_submitted"
    - "Is reference?=is_reference"
    - "Is complete?=is_complete"
    - "Is high coverage?=is_high_coverage"
    - "Is low coverage?=is_low_coverage"
    - "N-Content=n_content"
    - "GC-Content=gc_content"

reference_node_name: "USA/WA1/2020"
nextclade_dataset: sars-cov-2

# Define files used for external configuration. Common examples consist of a
# list of strains to include and exclude from analyses, a reference sequence to
# align sequences to, colors for strain attributes in auspice, and auspice
# configuration files.
files:
  include: "defaults/include.txt"
  exclude: "defaults/exclude.txt"
  reference: "defaults/reference_seq.gb"
  alignment_reference: "defaults/reference_seq.fasta"
  annotation: "defaults/annotation.gff"
  outgroup: "defaults/outgroup.fasta" # is this arg still used? file doesn't exist in gh repo
  ordering: "defaults/color_ordering.tsv"
  color_schemes: "defaults/color_schemes.tsv"
  auspice_config: "defaults/auspice_config.json"
  lat_longs: "defaults/lat_longs.tsv"
  description: "defaults/description.md"
  clades: "defaults/clades.tsv"
  clade_name_mapping: "defaults/clade_display_names.yml"
  emerging_lineages: "defaults/emerging_lineages.tsv"
  mutational_fitness_distance_map: "defaults/mutational_fitness_distance_map.json"
  sites_to_mask: "defaults/sites_ignored_for_tree_topology.txt"

# Define genes to translate during alignment by nextclade.
genes: ["ORF1a", "ORF1b", "S", "ORF3a", "E", "M", "ORF6", "ORF7a", "ORF7b", "ORF8", "N", "ORF9b"]

# Filter settings
filter:
  # Require nearly full-length genomes.
  min_length: 27000

  # Omit sequences with incomplete date annotations, and USA seqs without a state.
  exclude_where: "division='USA'"
  exclude_ambiguous_dates_by: "any"

  # Exclude sequences which are from before Dec 2019 (likely date mix-ups)
  min_date: "2019-12-01"

# When choosing contextual samples for a focal set, applying crowding penalty
# will help reduce the number of genetically identical strains that get chosen,
# and allows for more diversity represented on the tree.
priorities:
  crowding_penalty: 0.1

# Alignment settings
# Alignments are partitioned into smaller groups to speed up the overall alignment process.
# The number of sequences per group determines the run time of a single alignment job.
partition_sequences:
  sequences_per_group: 150

# Mask settings determine how the multiple sequence alignment is masked prior to phylogenetic inference.
mask:
  # Number of bases to mask from the beginning and end of the alignment. These regions of the genome
  # are difficult to sequence accurately.
  mask_from_beginning: 100
  mask_from_end: 200

  # Specific sites to mask in the reference genome's coordinates.
  # These are 1-indexed coordinates of sites that have been identified as prone to sequencing errors.
  mask_sites: "21987 21846"
  # 21987 (S:142) is a problematic ARTIC V3 primer site. Impacts Delta & some 21L (Omicron) descendants
  # 21846 (S:T95I) was/is often artifacually reverted in Delta

# Depending on how you define focal and contextual inputs, the same strains may
# appear in both inputs. This option tells the workflow not to throw an error
# when duplicates occur but to accept the first instance of a given strain's
# sequences (e.g., the focal set).
combine_sequences_for_subsampling:
  warn_about_duplicates: true

tree:
  tree-builder-args: "'-ninit 10 -n 4'"

# TreeTime settings
refine:
  root: "Wuhan/Hu-1/2019"
  clock_rate: 0.0008
  clock_std_dev: 0.0004
  coalescent: "opt"
  date_inference: "marginal"
  divergence_unit: "mutations"
  clock_filter_iqd: 8

ancestral:
  inference: "joint"

colors:
  default:
    # Amount of time back to color clades, if "all" then all clades are colored
    # Can be specified per build in builds.yaml
    clade_recency: "all"

# Frequencies settings
frequencies:

  # default settings that can be over-ridden for specific builds
  default:

    # min_date is set by default to 1 year before present
    min_date: "1Y"

    # max_date is set by default to present date - recent_days_to_censor

    # KDE bandwidths in proportion of a year to use per strain.
    # using 1M bandwidth by default
    narrow_bandwidth: 0.0833


  # settings that can be over-ridden across all builds, but not for specific builds
  recent_days_to_censor: 0

  # Number of weeks between pivots
  pivot_interval: 1

  # Measure pivots in weeks
  pivot_interval_units: "weeks"

  # Weight of KDE that uses wide bandwidth
  proportion_wide: 0.0

  # Diffusion frequency settings
  minimal_frequency: 0.01
  stiffness: 20
  inertia: 0.2

# Logistic growth settings
logistic_growth:
  # Calculate logistic growth over the last N pivots which corresponds to N
  # times the amount of time represented by the `pivot_interval_units` in the
  # frequencies configuration.
  delta_pivots: 6

  # Set the minimum number of tips a clade must have before its logistic growth
  # is calculated.
  min_tips: 50

  # Set the minimum and maximum current frequency a clade must for its logistic
  # growth to be calculated.
  min_frequency: 0.000001
  max_frequency: 0.95

# Cluster-specific settings
cluster:
  # Require a minimum number of tips to be annotated as a cluster.
  min_tips: 3
  # Find clusters with the same values in the given column (e.g., division, country, etc.).
  group_by: division

#
# Region-specific settings
#
traits:
  default:
    sampling_bias_correction: 2.5
    columns: ["country"]

# Default subsampling schemes designed for different geographic scales. With the
# exception of the "global" region, most subsampling schemes define a large
# focal set of sequences related to a specific geographic entity (e.g., Africa,
# Switzerland, etc.) and a smaller set of contextual sequences from the rest of
# the world.
#
# Users can control the specificity of subsampling by defining as many
# subsampling sets as they require. For example, one may wish to include all
# sequences from California, many contextual sequences from the USA, and a few
# contextual sequences from the rest of the world.
#
# Each build defines its subsampling scheme by specifying a `subsampling_scheme`
# attribute whose value is the name of an entry in the subsampling configuration
# below or defined elsewhere in another configuration file.
subsampling:
  # Default subsampling logic to select all strains from all inputs (i.e., no subsampling).
  all:
    all:
      no_subsampling: true

  # Default subsampling logic for regions
  region:
    # Focal samples for region
    region:
      group_by: "division year month"
      seq_per_group: 48
      exclude: "--exclude-where 'region!={region}'"
    # Contextual samples for region from the rest of the world
    global:
      group_by: "country year month"
      seq_per_group: 4
      exclude: "--exclude-where 'region={region}'"
      priorities:
        type: "proximity"
        focus: "region"

  # Custom subsampling logic for global region.
  region_global:
    global:
      group_by: "country year month"
      seq_per_group: 20

  # Custom subsampling logic for regions like Europe where grouping by country
  # is the smallest resolution required.
  region_grouped_by_country:
    # Focal samples for region
    region:
      group_by: "country year month"
      seq_per_group: 64
      exclude: "--exclude-where 'region!={region}'"
    # Contextual samples for region from the rest of the world
    global:
      group_by: "country year month"
      seq_per_group: 6
      exclude: "--exclude-where 'region={region}'"
      priorities:
        type: "proximity"
        focus: "region"

  # Default subsampling logic for countries
  country:
    # Focal samples for country
    country:
      group_by: "division year month"
      seq_per_group: 200
      exclude: "--exclude-where 'country!={country}'"
    # Contextual samples from country's region
    region:
      group_by: "country year month"
      seq_per_group: 20
      exclude: "--exclude-where 'country={country}' 'region!={region}'"
      priorities:
        type: "proximity"
        focus: "country"
    # Contextual samples from the rest of the world,
    # excluding the current region to avoid resampling.
    global:
      group_by: "country year month"
      seq_per_group: 10
      exclude: "--exclude-where 'region={region}'"
      priorities:
        type: "proximity"
        focus: "country"

  # Default subsampling logic for divisions
  division:
    # Focal samples for division
    division:
      group_by: "year month"
      seq_per_group: 300
      exclude: "--exclude-where 'region!={region}' 'country!={country}' 'division!={division}'"
    # Contextual samples from division's country
    country:
      group_by: "division year month"
      seq_per_group: 20
      exclude: "--exclude-where 'region!={region}' 'country!={country}' 'division={division}'"
      priorities:
        type: "proximity"
        focus: "division"
    # Contextual samples from division's region
    region:
      group_by: "country year month"
      seq_per_group: 10
      exclude: "--exclude-where 'region!={region}' 'country={country}'"
      priorities:
        type: "proximity"
        focus: "division"
    # Contextual samples from the rest of the world, excluding the current
    # division to avoid resampling.
    global:
      group_by: "country year month"
      seq_per_group: 5
      exclude: "--exclude-where 'region={region}'"
      priorities:
        type: "proximity"
        focus: "division"

  # Default subsampling logic for locations
  location:
    # Focal samples for location
    focal:
      group_by: "year month"
      seq_per_group: 300
      exclude: "--exclude-where 'region!={region}' 'country!={country}' 'division!={division}' 'location!={location}'"
    # Samples that are genetically related to the focal samples
    related:
      group_by: "country year month"
      seq_per_group: 20
      exclude: "--exclude-where 'location={location}'"
      priorities:
        type: "proximity"
        focus: "focal"
    # Contextual samples from the rest of the world
    contextual:
      group_by: "country year month"
      seq_per_group: 10
      exclude: "--exclude-where 'location={location}'"

# Configure the prefix to use for Auspice JSONs.
auspice_json_prefix: ncov