Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion ingest/config/defaults.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -54,12 +54,12 @@ shared_fields:
- author_affiliations
- authors
- ncbi_release_date #TODO (#2171): Allow segments to have different dates
- ncbi_update_date
# Fields that that are not shared at sample level
# But specific to each segment
segment_specific_fields:
- sra_run_accession # Usually the same for each segment?
- ncbi_protein_count
- ncbi_virus_tax_id
- insdc_accession_base
- insdc_version
- insdc_accession_full
Expand Down
190 changes: 101 additions & 89 deletions kubernetes/loculus/values.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -933,6 +933,8 @@ defaultOrganismConfig: &defaultOrganismConfig
header: "INSDC"
- name: ncbi_virus_tax_id
type: int
perSegment: true
oneHeader: true
autocomplete: true
customDisplay:
type: link
Expand Down Expand Up @@ -1209,84 +1211,66 @@ defaultOrganisms:
genes:
- name: OPG001
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/mpox/OPG001.fasta]]"
west-nile:
cchf:
<<: *defaultOrganismConfig
schema:
<<: *schema
organismName: "West Nile Virus"
image: "https://upload.wikimedia.org/wikipedia/commons/thumb/1/1e/West_Nile_Virus_Image.jpg/256px-West_Nile_Virus_Image.jpg?20200815184100"
metadataAdd:
- name: lineage
header: "Lineage"
noInput: true
generateIndex: true
autocomplete: true
initiallyVisible: true
preprocessing:
inputs: {input: nextclade.clade}
- name: total_stop_codons
type: int
header: "Alignment states and QC metrics"
noInput: true
preprocessing:
inputs: {input: nextclade.qc.stopCodons.totalStopCodons}
- name: stop_codons
header: "Alignment states and QC metrics"
noInput: true
preprocessing:
inputs: {input: nextclade.qc.stopCodons.stopCodons}
organismName: "Crimean-Congo Hemorrhagic Fever Virus"
nucleotideSequences: [L, M, S]
image: "https://upload.wikimedia.org/wikipedia/commons/thumb/5/5e/Crimean-Congo_Hemorrhagic_Fever_%28CCHF%29_Virus_%2840689899455%29.jpg/1920px-Crimean-Congo_Hemorrhagic_Fever_%28CCHF%29_Virus_%2840689899455%29.jpg"
website:
<<: *website
tableColumns:
- sample_collection_date
- ncbi_release_date
- authors
- author_affiliations
- geo_loc_country
- geo_loc_admin_1
- length
- lineage
- authors
- author_affiliations
- ncbi_release_date
- host_name_scientific
- length_M
- length_S
- length_L
defaultOrderBy: sample_collection_date
defaultOrder: descending
preprocessing:
- <<: *preprocessing
configFile:
<<: *preprocessingConfigFile
nextclade_dataset_name: nextstrain/wnv/all-lineages
nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/wnv/data_output
genes: [capsid, prM, env, NS1, NS2A, NS2B, NS3, NS4A, 2K, NS4B, NS5]
log_level: DEBUG
nextclade_dataset_name: nextstrain/cchfv/linked
nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/cornelius-cchfv/data_output
nucleotideSequences: [L, M, S]
genes: [RdRp, GPC, NP]
ingest:
<<: *ingest
configFile:
taxon_id: 3048448
<<: *ingestConfigFile
taxon_id: 3052518
nucleotide_sequences:
- L
- M
- S
nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/cornelius-cchfv/data_output
nextclade_dataset_name: nextstrain/cchfv/linked
referenceGenomes:
nucleotideSequences:
- name: main
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/west-nile/reference.fasta]]"
insdc_accession_full: NC_009942.1
- name: L
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/cchf/reference_L.fasta]]"
insdc_accession_full: NC_005301.3
- name: M
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/cchf/reference_M.fasta]]"
insdc_accession_full: NC_005300.2
- name: S
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/cchf/reference_S.fasta]]"
insdc_accession_full: NC_005302.1
genes:
- name: 2K
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/west-nile/2K.fasta]]"
- name: NS1
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/west-nile/NS1.fasta]]"
- name: NS2A
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/west-nile/NS2A.fasta]]"
- name: NS2B
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/west-nile/NS2B.fasta]]"
- name: NS3
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/west-nile/NS3.fasta]]"
- name: NS4A
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/west-nile/NS4A.fasta]]"
- name: NS4B
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/west-nile/NS4B.fasta]]"
- name: NS5
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/west-nile/NS5.fasta]]"
- name: capsid
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/west-nile/capsid.fasta]]"
- name: env
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/west-nile/env.fasta]]"
- name: prM
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/west-nile/prM.fasta]]"
- name: RdRp
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/cchf/RdRp.fasta]]"
- name: GPC
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/cchf/GPC.fasta]]"
- name: NP
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/cchf/NP.fasta]]"
dummy-organism:
schema:
image: "https://www.un.org/sites/un2.un.org/files/field/image/1583952355.1997.jpg"
Expand Down Expand Up @@ -1372,13 +1356,13 @@ defaultOrganisms:
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/sars-cov-2/ORF9b.fasta]]"
- name: "S"
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/sars-cov-2/S.fasta]]"
cchf:
h5n1:
<<: *defaultOrganismConfig
schema:
<<: *schema
organismName: "Crimean-Congo Hemorrhagic Fever Virus"
nucleotideSequences: [L, M, S]
image: "https://upload.wikimedia.org/wikipedia/commons/thumb/5/5e/Crimean-Congo_Hemorrhagic_Fever_%28CCHF%29_Virus_%2840689899455%29.jpg/1920px-Crimean-Congo_Hemorrhagic_Fever_%28CCHF%29_Virus_%2840689899455%29.jpg"
organismName: "Influenza A/H5N1"
nucleotideSequences: [seg1, seg2, seg3, seg4, seg5, seg6, seg7, seg8]
image: "https://www.cdc.gov/flu/images/virus/Flu19_trans_RNPs2-medium.png"
website:
<<: *website
tableColumns:
Expand All @@ -1389,49 +1373,77 @@ defaultOrganisms:
- author_affiliations
- ncbi_release_date
- host_name_scientific
- length_M
- length_S
- length_L
- length_seg4
- length_seg6
defaultOrderBy: sample_collection_date
defaultOrder: descending
preprocessing:
- <<: *preprocessing
configFile:
<<: *preprocessingConfigFile
log_level: DEBUG
nextclade_dataset_name: nextstrain/cchfv/linked
nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/cornelius-cchfv/data_output
nucleotideSequences: [L, M, S]
genes: [RdRp, GPC, NP]
nextclade_dataset_name: community/genspectrum/flu/h5n1
nextclade_dataset_server: https://raw.githubusercontent.com/anna-parker/nextclade_data/h5n1/data_output
nucleotideSequences: [seg1, seg2, seg3, seg4, seg5, seg6, seg7, seg8]
genes: [PB2, PB1, PA, PAX, HA, NA, NP, M1, M2, NS1, NS2]
ingest:
<<: *ingest
configFile:
<<: *ingestConfigFile
taxon_id: 3052518
nucleotide_sequences:
- L
- M
- S
nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/cornelius-cchfv/data_output
nextclade_dataset_name: nextstrain/cchfv/linked
taxon_id: 197911
filter_fasta_headers: "(H5N1)"
nucleotide_sequences: [seg1, seg2, seg3, seg4, seg5, seg6, seg7, seg8]
nextclade_dataset_server: https://raw.githubusercontent.com/anna-parker/nextclade_data/h5n1/data_output
nextclade_dataset_name: community/genspectrum/flu/h5n1
referenceGenomes:
nucleotideSequences:
- name: L
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/cchf/reference_L.fasta]]"
insdc_accession_full: NC_005301.3
- name: M
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/cchf/reference_M.fasta]]"
insdc_accession_full: NC_005300.2
- name: S
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/cchf/reference_S.fasta]]"
insdc_accession_full: NC_005302.1
- name: seg1
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/segments/seg1.fasta]]"
insdc_accession_full: NC_007357.1
- name: seg2
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/segments/seg2.fasta]]"
insdc_accession_full: NC_007358.1
- name: seg3
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/segments/seg3.fasta]]"
insdc_accession_full: NC_007359.1
- name: seg4
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/segments/seg4.fasta]]"
insdc_accession_full: NC_007362.1
- name: seg5
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/segments/seg5.fasta]]"
insdc_accession_full: NC_007360.1
- name: seg6
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/segments/seg6.fasta]]"
insdc_accession_full: NC_007361.1
- name: seg7
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/segments/seg7.fasta]]"
insdc_accession_full: NC_007363.1
- name: seg8
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/segments/seg8.fasta]]"
insdc_accession_full: NC_007364.1
genes:
- name: RdRp
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/cchf/RdRp.fasta]]"
- name: GPC
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/cchf/GPC.fasta]]"
- name: PB2
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/genes/PB2.fasta]]"
- name: PB1
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/genes/PB1.fasta]]"
- name: PA
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/genes/PA.fasta]]"
- name: PAX
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/genes/PAX.fasta]]"
- name: HA
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/genes/HA.fasta]]"
- name: NA
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/genes/NA.fasta]]"
- name: NP
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/cchf/NP.fasta]]"
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/genes/NP.fasta]]"
- name: M1
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/genes/M1.fasta]]"
- name: M2
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/genes/M2.fasta]]"
- name: NS1
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/genes/NS1.fasta]]"
- name: NS2
sequence: "[[URL:https://raw.githubusercontent.com/corneliusroemer/seqs/main/artefacts/influenza/h5n1/genes/NS2.fasta]]"
auth:
smtp:
host: "in-v3.mailjet.com"
Expand Down