feat: separate entities into seqerakit yamls

seqerakit/compute-envs/seqera_aws_dragen.yml

@@ -0,0 +1,7 @@
+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: False

seqerakit/compute-envs/seqera_aws_ireland_fusionv2_nvme.yml

@@ -0,0 +1,22 @@
+compute-envs:
+  - type: aws-batch forge
+    name: "seqera_aws_ireland_fusionv2_nvme"
+    workspace: "seqeralabs/showcase"
+    credentials: "seqera_aws_development_credentials"
+    region: "eu-west-1"
+    work-dir: "s3://seqeralabs-showcase"
+    wave: True
+    fusion-v2: True
+    fast-storage: true
+    provisioning-model: "SPOT"
+    instance-type: "c6id,m6id,r6id"
+    max-cpus: 500
+    allow-buckets:
+      [
+        "s3://ngi-igenomes",
+        "s3://nf-core-awsmegatests",
+        "s3://seqeralabs-showcase",
+      ]
+    head-job-role: "$HEAD_JOB_IAM_ROLE"
+    wait: "AVAILABLE"
+    overwrite: False

seqerakit/compute-envs/seqera_aws_ireland_fusionv2_nvme_gpu.yml

@@ -0,0 +1,21 @@
+compute-envs:
+  - type: aws-batch forge
+    name: "seqera_aws_ireland_fusionv2_nvme_gpu"
+    workspace: "seqeralabs/showcase"
+    credentials: "seqera_aws_development_credentials"
+    region: "eu-west-1"
+    work-dir: "s3://seqeralabs-showcase"
+    wave: True
+    fusion-v2: True
+    fast-storage: true
+    provisioning-model: "SPOT"
+    instance-type: "g4dn"
+    max-cpus: 500
+    allow-buckets:
+      [
+        "s3://ngi-igenomes",
+        "s3://nf-core-awsmegatests",
+        "s3://seqeralabs-showcase",
+      ]
+    wait: "AVAILABLE"
+    overwrite: False

seqerakit/compute-envs/seqera_aws_ireland_s3.yml

@@ -0,0 +1,18 @@
+compute-envs:
+  - type: aws-batch forge
+    name: "seqera_aws_ireland_s3"
+    workspace: "seqeralabs/showcase"
+    credentials: "seqera_aws_development_credentials"
+    region: "eu-west-1"
+    work-dir: "s3://seqeralabs-showcase"
+    provisioning-model: "SPOT"
+    max-cpus: 500
+    allow-buckets:
+      [
+        "s3://ngi-igenomes",
+        "s3://nf-core-awsmegatests",
+        "s3://seqeralabs-showcase",
+      ]
+    cli-path: "/home/ec2-user/miniconda/bin/aws"
+    wait: "AVAILABLE"
+    overwrite: False

seqerakit/compute-envs/seqera_azure_virginia_fusion.yml

@@ -0,0 +1,12 @@
+compute-envs:
+  - type: azure-batch forge
+    name: "seqera_azure_virginia_fusion"
+    workspace: "seqeralabs/showcase"
+    credentials: "seqera_azure_development_credentials"
+    location: "eastus"
+    work-dir: "az://azure-benchmarking"
+    fusion-v2: True
+    wave: True
+    vm-count: 1
+    vm-type: "Standard_E16d_v5"
+    registry-credentials: seqera_dockerhub_credentials

seqerakit/compute-envs/seqera_gcp_finland.yml

@@ -0,0 +1,13 @@
+compute-envs:
+  - type: google-batch
+    name: "seqera_gcp_finland_fusion"
+    workspace: "seqeralabs/showcase"
+    credentials: "seqera_gcp_credentials"
+    location: "europe-north1"
+    work-dir: "gs://seqeralabs-showcase-eu-north-1"
+    fusion-v2: True
+    wave: True
+    spot: True
+    boot-disk-dize: 200
+    wait: "AVAILABLE"
+    overwrite: False

seqerakit/compute-envs/seqera_slurm.yml

@@ -0,0 +1,13 @@
+compute-envs:
+  - type: slurm
+    name: "seqera_slurm"
+    workspace: "seqeralabs/showcase"
+    credentials: "seqera_slurm_credentials"
+    work-dir: "/home/ubuntu/work"
+    launch-dir: "/home/ubuntu/showcase-launchdir"
+    user-name: "ubuntu"
+    host-name: "slurm.seqera.io"
+    head-queue: "long"
+    compute-queue: "long"
+    wait: "AVAILABLE"
+    overwrite: False

seqerakit/datasets/nf-core-fetchngs_human_samples.yml

@@ -0,0 +1,7 @@
+datasets:
+  - 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: False

seqerakit/datasets/nf-core-proteinfold_samples.yml

@@ -0,0 +1,7 @@
+datasets:
+  - 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: False

seqerakit/datasets/nf-core-rnaseq_human_samples.yml

@@ -0,0 +1,7 @@
+datasets:
+  - 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: False

seqerakit/datasets/nf-core-rnaseq_samples.yml

@@ -0,0 +1,7 @@
+datasets:
+  - 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: False

seqerakit/datasets/nf-core-sarek_samples.yml

@@ -0,0 +1,7 @@
+datasets:
+  - 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: False

seqerakit/datasets/nf-core-viralrecon_samples.yml

@@ -0,0 +1,13 @@
+datasets:
+  - 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: False
+  - 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: False

seqerakit/datasets/nf-dragen_samples.yml

@@ -0,0 +1,7 @@
+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: False

seqerakit/datasets/nf-sentieon_samples.yml

@@ -0,0 +1,7 @@
+datasets:
+  - 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: False

seqerakit/pipelines/hello.yml

@@ -0,0 +1,9 @@
+pipelines:
+  - name: "hello"
+    description: "Classic hello world script in Nextflow language"
+    url: "https://github.com/nextflow-io/hello"
+    compute-env: "seqera_aws_ireland_fusionv2_nvme"
+    revision: "master"
+    labels: "hello-world"
+    pre-run: "./pre-run.sh"
+    overwrite: False

seqerakit/pipelines/nf-core-fetchngs.yml

@@ -0,0 +1,15 @@
+pipelines:
+  - name: "nf-core-fetchngs"
+    description: "Pipeline to fetch metadata and raw FastQ files from public and private databases"
+    url: "https://github.com/nf-core/fetchngs"
+    workspace: "seqeralabs/showcase"
+    compute-envs: "seqera_aws_ireland_fusionv2_nvme"
+    revision: "1.10.1"
+    profile: "test"
+    labels: ["download", "ena", "sra"]
+    pre-run: "./pre-run.sh"
+    params:
+      outdir: "s3://seqeralabs-showcase/nf-core-fetchngs/results"
+      force_sratools_download: True
+      nf_core_pipeline: "rnaseq"
+    overwrite: False

seqerakit/pipelines/nf-core-proteinfold-params.yml

@@ -0,0 +1,13 @@
+outdir: "s3://seqeralabs-showcase/nf-core-proteinfold/results"
+use_gpu: true
+alphafold2_db: "s3://ngi-igenomes/test-data/proteinfold/db/alphafold_mini"
+bfd_path: "s3://ngi-igenomes/test-data/proteinfold/db/alphafold_mini/bfd/*"
+small_bfd_path: "s3://ngi-igenomes/test-data/proteinfold/db/alphafold_mini/small_bfd/*"
+alphafold2_params_path: "s3://ngi-igenomes/test-data/proteinfold/db/alphafold_mini/alphafold_params_*/*"
+mgnify_path: "s3://ngi-igenomes/test-data/proteinfold/db/alphafold_mini/mgnify/*"
+pdb70_path: "s3://ngi-igenomes/test-data/proteinfold/db/alphafold_mini/pdb70/**"
+pdb_mmcif_path: "s3://ngi-igenomes/test-data/proteinfold/db/alphafold_mini/pdb_mmcif/**"
+uniclust30_path: "s3://ngi-igenomes/test-data/proteinfold/db/alphafold_mini/uniclust30/**"
+uniref90_path: "s3://ngi-igenomes/test-data/proteinfold/db/alphafold_mini/uniref90/*"
+pdb_seqres_path: "s3://ngi-igenomes/test-data/proteinfold/db/alphafold_mini/pdb_seqres/*"
+uniprot_path: "s3://ngi-igenomes/test-data/proteinfold/db/alphafold_mini/uniprot/*"

seqerakit/pipelines/nf-core-proteinfold.config

@@ -0,0 +1,6 @@
+process {
+    withName: 'RUN_ALPHAFOLD2|RUN_ALPHAFOLD2_PRED|COLABFOLD_BATCH' {
+        accelerator = 1
+        queue = <COMPUTE_QUEUE>
+    }
+}

seqerakit/pipelines/nf-core-rnaseq.yml

@@ -0,0 +1,25 @@
+pipelines:
+  - name: "nf-core-rnaseq"
+    url: "https://github.com/nf-core/rnaseq"
+    description: "RNA sequencing analysis pipeline using STAR, RSEM, HISAT2 or Salmon with gene/isoform counts and extensive quality control."
+    workspace: "seqeralabs/showcase"
+    compute-envs: "seqera_aws_ireland_fusionv2_nvme"
+    revision: "3.12.0"
+    profile: "test"
+    labels: ["star_salmon", "yeast"]
+    pre-run: "./pre-run.sh"
+    params:
+      outdir: "s3://seqeralabs-showcase/nf-core-rnaseq/results"
+    overwrite: False
+  - name: "nf-core-rnaseq-human"
+    url: "https://github.com/nf-core/rnaseq"
+    description: "RNA sequencing analysis pipeline using STAR, RSEM, HISAT2 or Salmon with gene/isoform counts and extensive quality control."
+    workspace: "seqeralabs/showcase"
+    compute-envs: "seqera_aws_ireland_fusionv2_nvme"
+    revision: "3.12.0"
+    labels: ["GRCh37", "star_salmon", "human"]
+    pre-run: "./pre-run.sh"
+    params:
+      outdir: "s3://seqeralabs-showcase/nf-core-rnaseq-human/results"
+      genome: "GRCh37"
+    overwrite: False

seqerakit/pipelines/nf-core-sarek.yml

@@ -0,0 +1,12 @@
+pipelines:
+  - name: "nf-core-sarek"
+    url: "https://github.com/nf-core/sarek"
+    description: "Analysis pipeline to detect germline or somatic variants (pre-processing, variant calling and annotation) from WGS / targeted sequencing."
+    workspace: "seqeralabs/showcase"
+    compute-envs: "seqera_azure_virginia_fusion"
+    revision: "3.1.2"
+    profile: "test"
+    labels: ["germline", "variant-calling"]
+    pre-run: "./pre-run.sh"
+    params:
+      outdir: "az://seqeralabs-showcase/nf-core-sarek/results"

seqerakit/pipelines/nf-core-viralrecon.yml

@@ -0,0 +1,25 @@
+pipelines:
+  - name: "nf-core-viralrecon-illumina"
+    url: "https://github.com/nf-core/viralrecon"
+    description: "Assembly and intrahost/low-frequency variant calling for viral samples."
+    workspace: "seqeralabs/showcase"
+    compute-envs: "seqera_gcp_finland_fusion"
+    revision: "2.6.0"
+    profile: "test"
+    labels: ["illumina", "sars-cov-2"]
+    params:
+      outdir: "gs://seqeralabs-showcase-eu-north-1/nf-core-viralrecon/illumina/results"
+      assemblers: "spades,unicycler"
+    overwrite: False
+  - name: "nf-core-viralrecon-nanopore"
+    url: "https://github.com/nf-core/viralrecon"
+    description: "Assembly and intrahost/low-frequency variant calling for viral samples."
+    workspace: "seqeralabs/showcase"
+    compute-envs: "seqera_gcp_finland_fusion"
+    revision: "2.6.0"
+    profile: "test_nanopore"
+    labels: ["nanopore", "sars-cov-2"]
+    pre-run: "./pre-run.sh"
+    params:
+      outdir: "gs://seqeralabs-showcase-eu-north-1/nf-core-viralrecon/nanopore/results"
+    overwrite: False

seqerakit/pipelines/nf-dragen.yml

@@ -0,0 +1,14 @@
+pipelines:
+  - name: "nf-dragen"
+    description: "Proof-of-concept Nextflow pipeline to run Illumina DRAGEN software."
+    url: "https://github.com/seqera-labs/nf-dragen"
+    workspace: "seqeralabs/showcase"
+    compute-envs: "seqera_aws_ireland_dragen"
+    revision: "master"
+    profile: "test"
+    labels: ["fpga", "variant-calling"]
+    pre-run: "./pre-run.sh"
+    params:
+      outdir: "s3://nf-tower-bucket/nf-dragen/results"
+    workspace-secrets: ["DRAGEN_PASSWORD", "DRAGEN_USERNAME"]
+    overwrite: False

seqerakit/pipelines/nf-proteinfold.yml

@@ -0,0 +1,26 @@
+pipelines:
+  - name: "nf-core-proteinfold"
+    url: "https://github.com/nf-core/proteinfold"
+    description: "Protein 3D structure prediction pipeline."
+    workspace: "seqeralabs/showcase"
+    compute-envs: "seqera_aws_ireland_fusionv2_nvme_gpu"
+    revision: "1.0.0"
+    profile: "test_full"
+    labels: ["gpu", "structure-prediction"]
+    pre-run: "./pre-run.sh"
+    params-file: "./nf-core-proteinfold-params.yml"
+    config: "./nf-core-proteinfold.config"
+    overwrite: False
+  - name: "nf-core-proteinfold_full_db"
+    url: "https://github.com/nf-core/proteinfold"
+    description: "Protein 3D structure prediction pipeline."
+    workspace: "seqeralabs/showcase"
+    compute-envs: "seqera_aws_ireland_fusionv2_nvme_gpu"
+    revision: "1.0.0"
+    labels: ["gpu", "structure-prediction"]
+    pre-run: "./pre-run.sh"
+    config: "./nf-core-proteinfold.config"
+    params:
+      outdir: "s3://seqeralabs-showcase/nf-core-proteinfold/db"
+      use_gpu: true
+    overwrite: False

seqerakit/pipelines/nf-sentieon.yml

@@ -0,0 +1,13 @@
+pipelines:
+  - name: "nf-sentieon"
+    url: "https://github.com/seqeralabs/nf-sentieon"
+    description: 'Proof-of-concept Nextflow pipeline to run Sentieon software.\nhttps://www.sentieon.com/'
+    workspace: "seqeralabs/showcase"
+    compute-envs: "seqera_aws_ireland_fusionv2_nvme"
+    revision: "master"
+    profile: "test"
+    labels: ["variant-calling", "wgs"]
+    pre-run: "./pre-run.sh"
+    params:
+      outdir: "s3://seqeralabs-showcase/nf-sentieon/results"
+    overwrite: False

seqerakit/pipelines/pre-run.sh

@@ -0,0 +1,2 @@
+yum install jq -y
+export NXF_VER=$(curl -s https://api.github.com/repos/nextflow-io/nextflow/tags | jq -r '.[].name' | head -n 1 | cut -c2-)