generated from nextstrain/pathogen-repo-guide
-
Notifications
You must be signed in to change notification settings - Fork 0
/
config.yaml
130 lines (126 loc) · 5 KB
/
config.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
# 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: "11292"
# 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
- host-tax-id
- 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_latin_name
host-tax-id: host_tax_id
isolate-lineage-source: sample_type
biosample-acc: biosample_accessions
submitter-names: authors
submitter-affiliation: institution
submitter-country: submitter_country
Group name: host_group
Curator common name: host_common_name
Family name: host_family
Genus name: host_genus
# 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: []
# 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",
"host_latin_name",
"host_family",
"host_genus",
"host_group",
"host_common_name",
"date_released",
"date_updated",
"sra_accessions",
"authors",
"abbr_authors",
"institution",
]