Skip to content

Commit

Permalink
feat: add newer datasets, update pipelines, add yaml
Browse files Browse the repository at this point in the history
  • Loading branch information
ejseqera committed Nov 23, 2023
1 parent 4cc4737 commit 9a8c3f4
Show file tree
Hide file tree
Showing 11 changed files with 215 additions and 6 deletions.
6 changes: 6 additions & 0 deletions datasets/SRP459762-carcinoma-samplesheet.csv
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
sample,fastq_1,fastq_2,strandedness,run_accession,experiment_accession,sample_accession,secondary_sample_accession,study_accession,secondary_study_accession,submission_accession,run_alias,experiment_alias,sample_alias,study_alias,library_layout,library_selection,library_source,library_strategy,library_name,instrument_model,instrument_platform,base_count,read_count,tax_id,scientific_name,sample_title,experiment_title,study_title,sample_description,fastq_md5,fastq_bytes,fastq_ftp,fastq_galaxy,fastq_aspera
SRX21750941,s3://seqeralabs-showcase/nf-core-fetchngs/SRP459762/results/fastq/SRX21750941_SRR26033656_1.fastq.gz,s3://seqeralabs-showcase/nf-core-fetchngs/SRP459762/results/fastq/SRX21750941_SRR26033656_2.fastq.gz,auto,SRR26033656,SRX21750941,SAMN37353910,SRS18858468,PRJNA1014965,SRP459762,SRA1710039,MEC_T_07_1.fastq.gz,MEC_T_07,,PRJNA1014965,PAIRED,unspecified,TRANSCRIPTOMIC,RNA-Seq,MEC_T_07,Illumina HiSeq 2500,ILLUMINA,9105149798,45074999,9606,Homo sapiens,,Illumina HiSeq 2500 sequencing: RNA-Seq of mucoepidermoid carcinoma,Immunological subtyping of salivary gland cancer identifies histological origin-specific tumor immune microenvironment,,a4e3385ac9b33a12a2648687af5a9eda;1cba4d7de8569bc84216d0d6f5ba19a1,1734457262;1749369782,ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/056/SRR26033656/SRR26033656_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/056/SRR26033656/SRR26033656_2.fastq.gz,ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/056/SRR26033656/SRR26033656_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/056/SRR26033656/SRR26033656_2.fastq.gz,fasp.sra.ebi.ac.uk:/vol1/fastq/SRR260/056/SRR26033656/SRR26033656_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/SRR260/056/SRR26033656/SRR26033656_2.fastq.gz
SRX21750942,s3://seqeralabs-showcase/nf-core-fetchngs/SRP459762/results/fastq/SRX21750942_SRR26033655_1.fastq.gz,s3://seqeralabs-showcase/nf-core-fetchngs/SRP459762/results/fastq/SRX21750942_SRR26033655_2.fastq.gz,auto,SRR26033655,SRX21750942,SAMN37353911,SRS18858470,PRJNA1014965,SRP459762,SRA1710039,MEC_T_08_1.fastq.gz,MEC_T_08,,PRJNA1014965,PAIRED,unspecified,TRANSCRIPTOMIC,RNA-Seq,MEC_T_08,Illumina HiSeq 2500,ILLUMINA,7291499060,36096530,9606,Homo sapiens,,Illumina HiSeq 2500 sequencing: RNA-Seq of mucoepidermoid carcinoma,Immunological subtyping of salivary gland cancer identifies histological origin-specific tumor immune microenvironment,,37c4046ba9128693ff685fd1a8f867da;2aa0babe90e17ed58636909b11d0a4eb,1331451936;1345825378,ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/055/SRR26033655/SRR26033655_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/055/SRR26033655/SRR26033655_2.fastq.gz,ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/055/SRR26033655/SRR26033655_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/055/SRR26033655/SRR26033655_2.fastq.gz,fasp.sra.ebi.ac.uk:/vol1/fastq/SRR260/055/SRR26033655/SRR26033655_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/SRR260/055/SRR26033655/SRR26033655_2.fastq.gz
SRX21750943,s3://seqeralabs-showcase/nf-core-fetchngs/SRP459762/results/fastq/SRX21750943_SRR26033654_1.fastq.gz,s3://seqeralabs-showcase/nf-core-fetchngs/SRP459762/results/fastq/SRX21750943_SRR26033654_2.fastq.gz,auto,SRR26033654,SRX21750943,SAMN37353912,SRS18858471,PRJNA1014965,SRP459762,SRA1710039,MEC_T_09_1.fastq.gz,MEC_T_09,,PRJNA1014965,PAIRED,unspecified,TRANSCRIPTOMIC,RNA-Seq,MEC_T_09,Illumina HiSeq 2500,ILLUMINA,7761595884,38423742,9606,Homo sapiens,,Illumina HiSeq 2500 sequencing: RNA-Seq of mucoepidermoid carcinoma,Immunological subtyping of salivary gland cancer identifies histological origin-specific tumor immune microenvironment,,d7a91ce3b764c79722d4f36ec5713efa;e42d3c993a18108a5258af65141c580f,1170104300;1203799314,ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/054/SRR26033654/SRR26033654_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/054/SRR26033654/SRR26033654_2.fastq.gz,ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/054/SRR26033654/SRR26033654_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/054/SRR26033654/SRR26033654_2.fastq.gz,fasp.sra.ebi.ac.uk:/vol1/fastq/SRR260/054/SRR26033654/SRR26033654_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/SRR260/054/SRR26033654/SRR26033654_2.fastq.gz
SRX21750944,s3://seqeralabs-showcase/nf-core-fetchngs/SRP459762/results/fastq/SRX21750944_SRR26033653_1.fastq.gz,s3://seqeralabs-showcase/nf-core-fetchngs/SRP459762/results/fastq/SRX21750944_SRR26033653_2.fastq.gz,auto,SRR26033653,SRX21750944,SAMN37353913,SRS18858472,PRJNA1014965,SRP459762,SRA1710039,MEC_T_10_1.fastq.gz,MEC_T_10,,PRJNA1014965,PAIRED,unspecified,TRANSCRIPTOMIC,RNA-Seq,MEC_T_10,Illumina HiSeq 2500,ILLUMINA,9238355264,45734432,9606,Homo sapiens,,Illumina HiSeq 2500 sequencing: RNA-Seq of mucoepidermoid carcinoma,Immunological subtyping of salivary gland cancer identifies histological origin-specific tumor immune microenvironment,,1a63023afeca02cd10271a20385424b1;0939823df564a6d14b61eb45581994e8,1768219705;1783586223,ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/053/SRR26033653/SRR26033653_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/053/SRR26033653/SRR26033653_2.fastq.gz,ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/053/SRR26033653/SRR26033653_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/SRR260/053/SRR26033653/SRR26033653_2.fastq.gz,fasp.sra.ebi.ac.uk:/vol1/fastq/SRR260/053/SRR26033653/SRR26033653_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/SRR260/053/SRR26033653/SRR26033653_2.fastq.gz

4 changes: 4 additions & 0 deletions datasets/SRP459762-carcinoma-sra-ids.csv
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
SRR26033653
SRR26033654
SRR26033655
SRR26033656
5 changes: 3 additions & 2 deletions pipelines/hello.json
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
{
"description": "Hello World test pipeline.",
"launch": {
"pipeline": "https://github.com/nextflow-io/hello",
"revision": "master",
Expand All @@ -9,6 +8,8 @@
"preRunScript": "yum install jq -y\nexport NXF_VER=$(curl -s https://api.github.com/repos/nextflow-io/nextflow/tags | jq -r '.[].name' | head -n 1 | cut -c2-)",
"resume": false,
"pullLatest": false,
"stubRun": false
"stubRun": false,
"optimizationId": "erHSZqVJNxKlWbuL",
"optimizationTargets": ""
}
}
18 changes: 18 additions & 0 deletions pipelines/nf-core-fetchngs.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
{
"description": "Pipeline to fetch metadata and raw FastQ files from public and private databases\n\n",
"launch": {
"pipeline": "https://github.com/nf-core/fetchngs",
"revision": "1.10.1",
"configProfiles": [
"test"
],
"userSecrets": [],
"workspaceSecrets": [],
"configText": "",
"paramsText": "outdir: 's3://seqeralabs-showcase/nf-core-fetchngs/results'\nforce_sratools_download: true\nnf_core_pipeline: 'rnaseq'",
"preRunScript": "yum install jq -y\nexport NXF_VER=$(curl -s https://api.github.com/repos/nextflow-io/nextflow/tags | jq -r '.[].name' | head -n 1 | cut -c2-)",
"resume": false,
"pullLatest": false,
"stubRun": false
}
}
16 changes: 16 additions & 0 deletions pipelines/nf-core-proteinfold_full_db.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
{
"description": "",
"launch": {
"pipeline": "https://github.com/nf-core/proteinfold",
"revision": "1.0.0",
"configProfiles": [],
"userSecrets": [],
"workspaceSecrets": [],
"configText": "process {\n withName: 'RUN_ALPHAFOLD2|RUN_ALPHAFOLD2_PRED|COLABFOLD_BATCH' {\n accelerator = 1\n queue = 'TowerForge-5ZfzTbavbsB9Tx7YRr2ut0-work'\n }\n}",
"paramsText": "input: 'https://api.tower.nf/workspaces/138659136604200/datasets/5Ig3IWRgjlgVjpURNF6CSN/v/1/n/samplesheet.csv'\noutdir: 's3://seqeralabs-showcase/nf-core-proteinfold/db'\nuse_gpu: true",
"preRunScript": "yum install jq -y\nexport NXF_VER=$(curl -s https://api.github.com/repos/nextflow-io/nextflow/tags | jq -r '.[].name' | head -n 1 | cut -c2-)",
"resume": false,
"pullLatest": false,
"stubRun": false
}
}
15 changes: 15 additions & 0 deletions pipelines/nf-core-rnaseq-human.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
{
"launch": {
"pipeline": "https://github.com/nf-core/rnaseq",
"revision": "3.12.0",
"configProfiles": [],
"userSecrets": [],
"workspaceSecrets": [],
"configText": "",
"paramsText": "genome: 'GRCh37'\noutdir: 's3://seqeralabs-showcase/nf-core-rnaseq/results'\n\n",
"preRunScript": "yum install jq -y\nexport NXF_VER=$(curl -s https://api.github.com/repos/nextflow-io/nextflow/tags | jq -r '.[].name' | head -n 1 | cut -c2-)",
"resume": false,
"pullLatest": false,
"stubRun": false
}
}
1 change: 0 additions & 1 deletion pipelines/nf-core-rnaseq.json
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
{
"description": "RNA sequencing analysis pipeline using STAR, RSEM, HISAT2 or Salmon with gene/isoform counts and extensive quality control.",
"launch": {
"pipeline": "https://github.com/nf-core/rnaseq",
"revision": "3.12.0",
Expand Down
8 changes: 5 additions & 3 deletions pipelines/nf-core-viralrecon-illumina.json
Original file line number Diff line number Diff line change
@@ -1,16 +1,18 @@
{
"description": "Pipeline for assembly and intrahost/low-frequency variant calling for viral samples.",
"launch": {
"pipeline": "https://github.com/nf-core/viralrecon",
"revision": "2.6.0",
"configProfiles": [
"test"
],
"configText": "",
"paramsText": "input: 'https://api.tower.nf/workspaces/138659136604200/datasets/4GC5jTkiloEIYBscThIf7r/v/1/n/viralrecon-illumina-samples.csv'\noutdir: 'gs://seqeralabs-showcase-eu-north-1/nf-core-viralrecon/illumina/results'",
"towerConfig": "",
"paramsText": "input: 'https://api.tower.nf/workspaces/138659136604200/datasets/4GC5jTkiloEIYBscThIf7r/v/1/n/viralrecon-illumina-samples.csv'\noutdir: 'gs://seqeralabs-showcase-eu-north-1/nf-core-viralrecon/illumina/results'\nassemblers: 'spades,unicycler'",
"preRunScript": "yum install jq -y\nexport NXF_VER=$(curl -s https://api.github.com/repos/nextflow-io/nextflow/tags | jq -r '.[].name' | head -n 1 | cut -c2-)",
"resume": false,
"pullLatest": false,
"stubRun": false
"stubRun": false,
"optimizationId": "jnQkdRdVKPsdUuNC",
"optimizationTargets": "pcpu, peak_rss, realtime"
}
}
2 changes: 2 additions & 0 deletions pipelines/nf-core-viralrecon-nanopore.json
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,9 @@
"test_nanopore"
],
"configText": "",
"towerConfig": "",
"paramsText": "input: 'https://api.tower.nf/workspaces/138659136604200/datasets/443ChPTGqwQZwl7xrvvGpP/v/1/n/viralrecon-nanopore-samples.csv'\noutdir: 'gs://seqeralabs-showcase-eu-north-1/nf-core-viralrecon/nanopore/results'",
"preRunScript": "yum install jq -y\nexport NXF_VER=$(curl -s https://api.github.com/repos/nextflow-io/nextflow/tags | jq -r '.[].name' | head -n 1 | cut -c2-)",
"resume": false,
"pullLatest": false,
"stubRun": false
Expand Down
1 change: 1 addition & 0 deletions pipelines/nf-sentieon.json
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@
"SENTIEON_LICENSE_BASE64"
],
"configText": "",
"towerConfig": "reports:\n multiqc_report.html:\n display: \"MultiQC HTML report\"",
"paramsText": "input: 'https://api.tower.nf/workspaces/138659136604200/datasets/2K6cdA0sRDw7Bauc67CmIT/v/1/n/sentieon-samples.csv'\noutdir: 's3://seqeralabs-showcase/nf-sentieon/results'",
"preRunScript": "yum install jq -y\nexport NXF_VER=$(curl -s https://api.github.com/repos/nextflow-io/nextflow/tags | jq -r '.[].name' | head -n 1 | cut -c2-)",
"resume": false,
Expand Down
145 changes: 145 additions & 0 deletions setup_showcase.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,145 @@
compute-envs:
- name: 'seqera_aws_ireland_dragen'
workspace: 'seqeralabs/showcase'
credentials: 'seqera_aws_management_credentials'
wait: 'AVAILABLE'
file-path: './compute-envs/seqera_aws_ireland_dragen.json'
overwrite: True
- name: 'seqera_aws_ireland_fusionv2_nvme'
workspace: 'seqeralabs/showcase'
credentials: 'seqera_aws_development_credentials'
wait: 'AVAILABLE'
file-path: './compute-envs/seqera_aws_ireland_fusionv2_nvme.json'
overwrite: True
- name: 'seqera_aws_ireland_fusionv2_nvme_gpu'
workspace: 'seqeralabs/showcase'
credentials: 'seqera_aws_development_credentials'
wait: 'AVAILABLE'
file-path: './compute-envs/seqera_aws_ireland_fusionv2_nvme_gpu.json'
overwrite: True
- name: 'seqera_aws_ireland_s3'
workspace: 'seqeralabs/showcase'
wait: 'AVAILABLE'
file-path: './compute-envs/seqera_aws_ireland_s3.json'
overwrite: True
- name: 'seqera_azure_virginia'
workspace: 'seqeralabs/showcase'
wait: 'AVAILABLE'
file-path: './compute-envs/seqera_azure_virginia.json'
overwrite: True
- name: 'seqera_gcp_finland'
workspace: 'seqeralabs/showcase'
wait: 'AVAILABLE'
file-path: './compute-envs/seqera_gcp_finland.json'
overwrite: True
- name: 'seqera_slurm'
workspace: 'seqeralabs/showcase'
wait: 'AVAILABLE'
file-path: './compute-envs/seqera_slurm.json'
overwrite: True
datasets:
- name: 'dragen_samples'
description: 'Samplesheet containing links to minimal data required to test the seqeralabs/nf-dragen pipeline from end-to-end'
header: true
workspace: 'seqerakit-e2e/showcase'
file-path: './datasets/dragen_samples.csv'
overwrite: True
- name: 'rnaseq_samples'
description: 'Samplesheet containing links to minimal data required to test the nf-core/rnaseq pipeline (v3.10) from end-to-end.\nFurther information about how the dataset was created can be obtained via the link below:\nhttps://github.com/nf-core/test-datasets/tree/rnaseq#minimal-test-dataset-origin'
header: true
workspace: 'seqerakit-e2e/showcase'
file-path: './datasets/rnaseq_samples.csv'
overwrite: True
- name: 'sarek_samples'
description: 'Samplesheet containing links to minimal data required to test the nf-core/sarek pipeline (v3.1.2) from end-to-end.'
header: true
workspace: 'seqerakit-e2e/showcase'
file-path: './datasets/sarek_samples.csv'
overwrite: True
- name: 'sentieon_samples'
description: 'Samplesheet containing links to minimal data required to test the seqeralabs/nf-sentieon pipeline from end-to-end'
header: true
workspace: 'seqerakit-e2e/showcase'
file-path: './datasets/sentieon_samples.csv'
overwrite: True
- name: 'viralrecon_illumina_samples'
description: 'Samplesheet containing links to minimal Illumina data required to test the nf-core/viralrecon pipeline (v2.5) from end-to-end.\nFurther information about how the dataset was created can be obtained via the link below:\nhttps://github.com/nf-core/test-datasets/tree/viralrecon#content-of-this-repository'
header: true
workspace: 'seqerakit-e2e/showcase'
file-path: './datasets/viralrecon_illumina_samples.csv'
overwrite: True
- name: 'viralrecon_nanopore_samples'
description: 'Samplesheet containing links to minimal Nanopore metadata required to test the nf-core/viralrecon pipeline (v2.5) from end-to-end.'
header: true
workspace: 'seqerakit-e2e/showcase'
file-path: './datasets/viralrecon_nanopore_samples.csv'
overwrite: True
- name: 'proteinfold_sequences'
description: 'Samplesheet containing links to fasta files required to test the nf-core/proteinfold pipeline from end-to-end.'
header: true
workspace: 'seqerakit-e2e/showcase'
file-path: './datasets/proteinfold_sequences.csv'
overwrite: True
- name: 'SRP459762-carcinoma-sra-ids'
description: 'Immunological subtyping of salivary gland cancer identifies histological origin-specific tumor immune microenvironment SRA: SRP459762\nBioProject: PRJNA1014965'
header: true
workspace: 'seqerakit-e2e/showcase'
file-path: './datasets/SRP459762-carcinoma-sra-ids.csv'
overwrite: True
- name: 'SRP459762-carcinoma-samplesheet'
description: 'Samplesheet containing SRA IDs required to test the nf-core/rnaseq pipeline (v3.10) from end-to-end.\nFurther information about how the dataset was created can be obtained via the link below:\nhttps://github.com/nf-core/test-datasets/tree/rnaseq#minimal-test-dataset-origin'
header: true
workspace: 'seqerakit-e2e/showcase'
file-path: './datasets/SRP459762-carcinoma-samplesheet.csv'
overwrite: True
pipelines:
- name: 'hello'
workspace: 'seqerakit-e2e/showcase'
compute-envs: 'seqera_aws_ireland_fusionv2_nvme'
file-path: './pipelines/hello.json'
overwrite: True
- name: 'nf-core-proteinfold'
workspace: 'seqerakit-e2e/showcase'
compute-envs: 'seqera_aws_ireland_fusionv2_nvme_gpu'
file-path: './pipelines/nf-core-proteinfold.json'
overwrite: True
- name: 'nf-core-rnaseq'
workspace: 'seqerakit-e2e/showcase'
compute-envs: 'seqera_aws_ireland_fusionv2_nvme'
file-path: './pipelines/nf-core-rnaseq.json'
overwrite: True
- name: 'nf-core-sarek'
workspace: 'seqerakit-e2e/showcase'
compute-envs: 'seqera_aws_ireland_fusionv2_nvme'
file-path: './pipelines/nf-core-sarek.json'
overwrite: True
- name: 'nf-dragen'
workspace: 'seqerakit-e2e/showcase'
compute-envs: 'seqera_aws_ireland_dragen'
file-path: './pipelines/nf-dragen.json'
overwrite: True
- name: 'nf-sentieon'
workspace: 'seqerakit-e2e/showcase'
compute-envs: 'seqera_aws_ireland_fusionv2_nvme'
file-path: './pipelines/nf-sentieon.json'
overwrite: True
- name: 'nf-core-viralrecon-illumina'
workspace: 'seqerakit-e2e/showcase'
compute-envs: 'seqera_gcp_finland'
file-path: './pipelines/nf-core-viralrecon-illumina.json'
overwrite: True
- name: 'nf-core-viralrecon-nanopore'
workspace: 'seqerakit-e2e/showcase'
compute-envs: 'seqera_gcp_finland'
file-path: './pipelines/nf-core-viralrecon-nanopore.json'
overwrite: True
- name: 'nf-core-fetchngs'
workspace: 'seqerakit-e2e/showcase'
compute-envs: 'seqera_aws_ireland_fusionv2_nvme'
file-path: './pipelines/nf-core-fetchngs.json'
overwrite: True
- name: 'nf-core-rnaseq-human'
workspace: 'seqerakit-e2e/showcase'
compute-envs: 'seqera_aws_ireland_fusionv2_nvme'
file-path: './pipelines/nf-core-rnaseq-human.json'
overwrite: True

0 comments on commit 9a8c3f4

Please sign in to comment.