Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

EB-140: Investigate if alias files can be used to recode more meaningful scaffold names #74

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft
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
85 changes: 85 additions & 0 deletions tests/config/recode_names/config.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,85 @@
{
"assemblies": [
{
"name": "Linum_tenue_thrum_v1",
"refNameAliases": {
"adapter": {
"type": "NcbiSequenceReportAliasAdapter",
"location": {
"uri": "sequence_report.tsv"
}
}
},
"displayName": "L. tenue genome assembly GCA_946122785.1"
}
],
"defaultSession": {
"id": "lten_default_session",
"name": "Linum tenue",
"widgets": {
"hierarchicalTrackSelector": {
"id": "hierarchicalTrackSelector",
"type": "HierarchicalTrackSelectorWidget",
"view": "lten_default_session_view",
"faceted": {
"showSparse": false,
"showFilters": true,
"showOptions": false,
"panelWidth": 400
}
}
},
"activeWidgets": {
"hierarchicalTrackSelector": "hierarchicalTrackSelector"
},
"views": [
{
"id": "lten_default_session_view",
"minimized": false,
"type": "LinearGenomeView",
"trackLabels": "offset",
"offsetPx": 0,
"bpPerPx": 100,
"displayedRegions": [
{
"refName": "LG1",
"start": 0,
"end": 72476498,
"reversed": false,
"assemblyName": "Linum_tenue_thrum_v1"
}
],
"tracks": [
{
"id": "lten_default_protein_coding_genes",
"type": "FeatureTrack",
"configuration": "ltenue_v1_genes.gff",
"minimized": false,
"displays": [
{
"id": "lten_default_protein_coding_genes_display",
"type": "LinearBasicDisplay",
"heightPreConfig": 180,
"configuration": "ltenue_v1_genes.gff-LinearBasicDisplay"
}
]
},
{
"id": "lten_default_repeats",
"type": "FeatureTrack",
"configuration": "L_tenue_v1_rep.bed",
"minimized": false,
"displays": [
{
"id": "lten_default_repeats_display",
"type": "LinearBasicDisplay",
"heightPreConfig": 200,
"configuration": "L_tenue_v1_rep.bed-LinearBasicDisplay"
}
]
}
]
}
]
}
}
16 changes: 16 additions & 0 deletions tests/config/recode_names/config.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
organism: "Linum tenue"
assembly:
name: Linum_tenue_thrum_v1
displayName: "L. tenue genome assembly GCA_946122785.1"
accession: GCA_946122785.1
# The following url points to the original ENA upload of the assembly. It will require an alias file to be able to load the protein coding genes track
url: "https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/946/122/785/GCA_946122785.1_Linum_tenue_thrum_v1/GCA_946122785.1_Linum_tenue_thrum_v1_genomic.fna.gz"
# Temp storage for alias file.
aliases: "sequence_report.tsv"
tracks:
- name: "Protein-coding genes"
url: "https://figshare.scilifelab.se/ndownloader/files/45076090"
fileName: "ltenue_v1_genes.gff.zip"
- name: "Repeats"
url: "https://figshare.scilifelab.se/ndownloader/files/48879751"
fileName: "L_tenue_v1_rep.bed.gz"
24 changes: 24 additions & 0 deletions tests/fixtures/recode_names/sequence_report.tsv
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
Assembly Accession Assembly Unplaced Count Assembly-unit accession Chromosome name GC Count GC Percent GenBank seq accession Molecule type Ordering RefSeq seq accession Role Seq length UCSC style name Unlocalized Count
GCA_946122785.1 Primary Assembly CAMGYJ010000002.1 Chromosome ABCDE assembled-molecule 123556469 LG1
GCA_946122785.1 Primary Assembly CAMGYJ010000004.1 Chromosome ABCDE assembled-molecule LG2
GCA_946122785.1 Primary Assembly CAMGYJ010000005.1 Chromosome ABCDE assembled-molecule LG3
GCA_946122785.1 Primary Assembly CAMGYJ010000006.1 Chromosome ABCDE assembled-molecule LG4
GCA_946122785.1 Primary Assembly CAMGYJ010000007.1 Chromosome ABCDE assembled-molecule LG5
GCA_946122785.1 Primary Assembly CAMGYJ010000008.1 Chromosome ABCDE assembled-molecule LG6
GCA_946122785.1 Primary Assembly CAMGYJ010000009.1 Chromosome ABCDE assembled-molecule LG7
GCA_946122785.1 Primary Assembly CAMGYJ010000010.1 Chromosome ABCDE assembled-molecule LG8
GCA_946122785.1 Primary Assembly CAMGYJ010000011.1 Chromosome ABCDE assembled-molecule LG9
GCA_946122785.1 Primary Assembly CAMGYJ010000003.1 Chromosome ABCDE assembled-molecule LG10
GCA_946122785.1 Primary Assembly CAMGYJ010000001.1 Chromosome ABCDE assembled-molecule CHL
GCA_946122785.1 Primary Assembly CAMGYJ010000012.1 Chromosome ABCDE assembled-molecule MIT1
GCA_946122785.1 Primary Assembly CAMGYJ010000013.1 Chromosome ABCDE assembled-molecule MIT10
GCA_946122785.1 Primary Assembly CAMGYJ010000014.1 Chromosome ABCDE assembled-molecule MIT11
GCA_946122785.1 Primary Assembly CAMGYJ010000015.1 Chromosome ABCDE assembled-molecule MIT12
GCA_946122785.1 Primary Assembly CAMGYJ010000016.1 Chromosome ABCDE assembled-molecule MIT2
GCA_946122785.1 Primary Assembly CAMGYJ010000017.1 Chromosome ABCDE assembled-molecule MIT3
GCA_946122785.1 Primary Assembly CAMGYJ010000018.1 Chromosome ABCDE assembled-molecule MIT4
GCA_946122785.1 Primary Assembly CAMGYJ010000019.1 Chromosome ABCDE assembled-molecule MIT5
GCA_946122785.1 Primary Assembly CAMGYJ010000020.1 Chromosome ABCDE assembled-molecule MIT6
GCA_946122785.1 Primary Assembly CAMGYJ010000021.1 Chromosome ABCDE assembled-molecule MIT7
GCA_946122785.1 Primary Assembly CAMGYJ010000022.1 Chromosome ABCDE assembled-molecule MIT8
GCA_946122785.1 Primary Assembly CAMGYJ010000023.1 Chromosome ABCDE assembled-molecule MIT9