Skip to content

Add ampliseq pipeline support #383

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.

Sign up for GitHub

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

Merged
maxulysse merged 7 commits into from
Aug 20, 2026
Merged

Add ampliseq pipeline support #383

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
e532045
Add ampliseq pipeline support
maxulysse Aug 13, 2026
dc9f88f
Update CHANGELOG for PR #383
maxulysse Aug 13, 2026
6986591
Merge branch 'dev' into feature/add-ampliseq-pipeline
maxulysse Aug 14, 2026
5d29374
Update multiqc_config.yml md5sum in ampliseq pipeline snapshot
maxulysse Aug 14, 2026
e68a719
Merge branch 'dev' into feature/add-ampliseq-pipeline
maxulysse Aug 14, 2026
69fd827
Update wget version to 1.25.0 in ampliseq snapshot
maxulysse Aug 14, 2026
2abb910
Merge branch 'dev' into feature/add-ampliseq-pipeline
maxulysse Aug 17, 2026
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
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,7 @@ Thank you to everyone else that has contributed by reporting bugs, enhancements
- [PR #380](https://github.com/nf-core/fetchngs/pull/380) - Use Seqera Wave container for wget to fix DNS resolution issues (#373)
- [PR #381](https://github.com/nf-core/fetchngs/pull/381) - Quote ena_metadata_fields and strip spaces to prevent word-splitting (#374)
- [PR #382](https://github.com/nf-core/fetchngs/pull/382) - Use csv.reader to fix stray quote and comma handling in multiqc_mappings_config (#375)
- [PR #383](https://github.com/nf-core/fetchngs/pull/383) - Add ampliseq pipeline support
- [PR #384](https://github.com/nf-core/fetchngs/pull/384) - Add mag pipeline support

### Software dependencies
Expand Down
2 changes: 1 addition & 1 deletion nextflow_schema.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@
"type": "string",
"fa_icon": "fab fa-apple",
"description": "Name of supported nf-core pipeline e.g. 'rnaseq'. A samplesheet for direct use with the pipeline will be created with the appropriate columns.",
"enum": ["atacseq", "mag", "rnaseq", "taxprofiler", "viralrecon"]
"enum": ["ampliseq", "atacseq", "mag", "rnaseq", "taxprofiler", "viralrecon"]
},
"nf_core_rnaseq_strandedness": {
"type": "string",
Expand Down
1 change: 1 addition & 0 deletions subworkflows/local/channel_sra_create_csv/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,7 @@ workflow CHANNEL_SRA_CREATE_CSV {

def buildPipelineMap(meta, pipeline, strandedness) {
def pipeline_extras = [
ampliseq: [run: ''],
atacseq: [replicate: 1],
mag: [group: '', short_reads_platform: 'ILLUMINA', long_reads_platform: ''],
rnaseq: [strandedness: strandedness],
Expand Down
59 changes: 59 additions & 0 deletions workflows/tests/sra_nf_core_pipeline_ampliseq.nf.test
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
nextflow_workflow {

name "Test workflow: workflows/fetchngs.nf"
script "../fetchngs.nf"
workflow "FETCHNGS"
tag "SRA_NF_CORE_PIPELINE_AMPLISEQ"

// Dependencies
tag "SRA_IDS_TO_RUNINFO"
tag "SRA_RUNINFO_TO_FTP"
tag "SRA_FASTQ_FTP"
tag "SRA_TO_SAMPLESHEET"
tag "MULTIQC_MAPPINGS_CONFIG"

test("Parameters: --nf_core_pipeline ampliseq") {

when {
workflow {
"""
input[0] = channel.of("DRX026011", "ERX1234253", "SRX6725035")
input[1] = "${outputDir}"
input[2] = []
input[3] = 'ftp'
input[4] = ''
input[5] = 'ampliseq'
input[6] = 'auto'
input[7] = 'experiment_accession,run_accession,sample_accession,experiment_alias,run_alias,sample_alias,experiment_title,sample_title,sample_description'
input[8] = false
"""
}
}

then {
// csv_file: Just the samplesheet
def csv_file = path(outputDir + '/samplesheet/samplesheet.csv').csv()

// Sanitize sra_metadata to remove unstable output directory paths
def sra_metadata = workflow.out.sra_metadata.collect { meta ->
assert meta instanceof Map
def fastq1 = meta.fastq_1 ? (meta.fastq_1 instanceof List ? path(meta.fastq_1[0]).fileName.toString() : path(meta.fastq_1).fileName.toString()) : ''
def fastq2 = meta.fastq_2 ? (meta.fastq_2 instanceof List ? path(meta.fastq_2[0]).fileName.toString() : path(meta.fastq_2).fileName.toString()) : ''
return [meta + [fastq_1: fastq1] + [fastq_2: fastq2]]
}

assert workflow.success
assertAll(
{ assert snapshot(
// Samplesheet
"samplesheet.csv:md5," + csv_file.sort().table.collect { row -> [row.getString("sample"), row.getString("fastq_1").replaceAll(outputDir, ""), row.getString("fastq_2").replaceAll(outputDir, "")].join(",") }.join("\n").md5(),
workflow.out.mappings,
workflow.out.sample_mappings,
sra_metadata,
// pipeline versions.yml file for multiqc from which Nextflow version is removed because we test pipelines on multiple Nextflow versions
removeFromYamlMap("${outputDir}/pipeline_info/nf_core_fetchngs_software_versions.yml", "Workflow"),
).match() }
)
}
}
}
157 changes: 157 additions & 0 deletions workflows/tests/sra_nf_core_pipeline_ampliseq.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,157 @@
{
"Parameters: --nf_core_pipeline ampliseq": {
"content": [
"samplesheet.csv:md5,e457eb1e61c4f04181127cea006de9ca",
[
"id_mappings.csv:md5,3e41ce6ab19feb76f2b20fa77a910ad3"
],
[
"multiqc_config.yml:md5,0f585277bfcae95ea182dcc9928f9243"
],
[
[
{
"base_count": "194930",
"experiment_accession": "DRX026011",
"experiment_alias": "DRX026011",
"experiment_title": "Illumina HiSeq 2500 paired end sequencing: Illumina HiSeq 2500 paired end sequencing of SAMD00024405",
"fastq_1": "DRX026011_DRR028935_1.fastq.gz",
"fastq_2": "DRX026011_DRR028935_2.fastq.gz",
"fastq_aspera": "fasp.sra.ebi.ac.uk:/vol1/fastq/DRR028/DRR028935/DRR028935_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/DRR028/DRR028935/DRR028935_2.fastq.gz",
"fastq_bytes": "60275;61610",
"fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/DRR028/DRR028935/DRR028935_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/DRR028/DRR028935/DRR028935_2.fastq.gz",
"fastq_galaxy": "ftp.sra.ebi.ac.uk/vol1/fastq/DRR028/DRR028935/DRR028935_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/DRR028/DRR028935/DRR028935_2.fastq.gz",
"fastq_md5": "cc01df82a9354bb6b3be93483b20c35a;941c9998d746416dad53c94c480ddf30",
"id": "DRX026011_DRR028935",
"instrument_model": "Illumina HiSeq 2500",
"instrument_platform": "ILLUMINA",
"library_layout": "PAIRED",
"library_name": "day0_BbSQE-I",
"library_selection": "cDNA",
"library_source": "TRANSCRIPTOMIC",
"library_strategy": "RNA-Seq",
"md5_1": "cc01df82a9354bb6b3be93483b20c35a",
"md5_2": "941c9998d746416dad53c94c480ddf30",
"read_count": "965",
"run_accession": "DRR028935",
"run_alias": "DRR028935",
"sample_accession": "SAMD00024405",
"sample_alias": "SAMD00024405",
"sample_description": "Liquid culture",
"sample_title": "Botryococcus braunii Showa at day 0 after inoculation into fresh culture medium",
"scientific_name": "Botryococcus braunii Showa",
"secondary_sample_accession": "DRS019431",
"secondary_study_accession": "DRP002616",
"single_end": false,
"study_accession": "PRJDB3420",
"study_alias": "DRP002616",
"study_title": "Liquid culture of Botryococcus braunii, race B, Showa",
"submission_accession": "DRA002949",
"tax_id": "1202541"
}
],
[
{
"base_count": "1996273",
"experiment_accession": "SRX6725035",
"experiment_alias": "Emb289P1_bin131",
"experiment_title": "Illumina HiSeq 2500 sequencing: Binning of metagenomic reads from the P1 gut compartment of Embiratermes neotenicus",
"fastq_1": "SRX6725035_SRR9984183.fastq.gz",
"fastq_2": "",
"fastq_aspera": "fasp.sra.ebi.ac.uk:/vol1/fastq/SRR998/003/SRR9984183/SRR9984183.fastq.gz",
"fastq_bytes": "605358",
"fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/SRR998/003/SRR9984183/SRR9984183.fastq.gz",
"fastq_galaxy": "ftp.sra.ebi.ac.uk/vol1/fastq/SRR998/003/SRR9984183/SRR9984183.fastq.gz",
"fastq_md5": "0b512d2dc31685983456bd56fd836544",
"id": "SRX6725035_SRR9984183",
"instrument_model": "Illumina HiSeq 2500",
"instrument_platform": "ILLUMINA",
"library_layout": "SINGLE",
"library_name": "Emb289P1_bin131",
"library_selection": "RANDOM",
"library_source": "METAGENOMIC",
"library_strategy": "WGS",
"md5_1": "0b512d2dc31685983456bd56fd836544",
"md5_2": "",
"read_count": "58",
"run_accession": "SRR9984183",
"run_alias": "Emb289P1_bin131.fastq",
"sample_accession": "SAMN12581720",
"sample_alias": "Emb289P1_bin131",
"sample_description": "Keywords: GSC:MIxS MIMAG:5.0",
"sample_title": "MIMAG Metagenome-assembled Genome sample from Defluviitaleaceae bacterium",
"scientific_name": "Defluviitaleaceae bacterium",
"secondary_sample_accession": "SRS5277011",
"secondary_study_accession": "SRP218535",
"single_end": true,
"study_accession": "PRJNA560329",
"study_alias": "PRJNA560329",
"study_title": "Phylogenomic analysis of 589 metagenome-assembled genomes encompassing all major prokaryotic lineages from the gut of higher termites",
"submission_accession": "SRA942061",
"tax_id": "2660712"
}
],
[
{
"base_count": "35658",
"experiment_accession": "ERX1234253",
"experiment_alias": "qiita_ptid_1263:10317.BLANK.93.3E.r22",
"experiment_title": "Illumina HiSeq 2500 sequencing: qiita_ptid_1263:10317.BLANK.93.3E.r22",
"fastq_1": "ERX1234253_ERR1160846.fastq.gz",
"fastq_2": "",
"fastq_aspera": "fasp.sra.ebi.ac.uk:/vol1/fastq/ERR116/006/ERR1160846/ERR1160846.fastq.gz",
"fastq_bytes": "18077",
"fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/ERR116/006/ERR1160846/ERR1160846.fastq.gz",
"fastq_galaxy": "ftp.sra.ebi.ac.uk/vol1/fastq/ERR116/006/ERR1160846/ERR1160846.fastq.gz",
"fastq_md5": "5924f20ef547ebdfed7cad795bbab6e6",
"id": "ERX1234253_ERR1160846",
"instrument_model": "Illumina HiSeq 2500",
"instrument_platform": "ILLUMINA",
"library_layout": "SINGLE",
"library_name": "10317.BLANK.93.3E.r22",
"library_selection": "PCR",
"library_source": "METAGENOMIC",
"library_strategy": "AMPLICON",
"md5_1": "5924f20ef547ebdfed7cad795bbab6e6",
"md5_2": "",
"read_count": "283",
"run_accession": "ERR1160846",
"run_alias": "qiita_ppdid_706:10317.BLANK.93.3E.r22",
"sample_accession": "SAMEA3687214",
"sample_alias": "qiita_sid_10317:10317.BLANK.93.3E.r22",
"sample_description": "American Gut control",
"sample_title": "10317.BLANK.93.3E.r22",
"scientific_name": "metagenome",
"secondary_sample_accession": "ERS994363",
"secondary_study_accession": "ERP012803",
"single_end": true,
"study_accession": "PRJEB11419",
"study_alias": "qiita_sid_10317",
"study_title": "American Gut Project",
"submission_accession": "ERA541392",
"tax_id": "256318"
}
]
],
{
"MULTIQC_MAPPINGS_CONFIG": {
"python": "3.9.5"
},
"SRA_FASTQ_FTP": {
"wget": "1.25.0"
},
"SRA_IDS_TO_RUNINFO": {
"python": "3.9.5"
},
"SRA_RUNINFO_TO_FTP": {
"python": "3.9.5"
}
}
],
"timestamp": "2026-08-13T14:53:37.03746842",
"meta": {
"nf-test": "0.9.5",
"nextflow": "26.04.4"
}
}
}
Loading