wf-transcriptomes-v202/.gitlab-ci.yml

# Include shared CI
include:
    - project: "epi2melabs/ci-templates"
      file: "wf-containers.yaml"

variables:
              NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/differential_expression.tar.gz -C ${CI_PROJECT_NAME}/data/  &&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
              NF_WORKFLOW_OPTS: "--fastq  ${CI_PROJECT_NAME}/data/differential_expression/differential_expression_fastq \
              --de_analysis --ref_genome ${CI_PROJECT_NAME}/data/differential_expression/hg38_chr20.fa \
              --transcriptome-source ${CI_PROJECT_NAME}/data/reference-guided \
              --ref_annotation ${CI_PROJECT_NAME}/data/differential_expression/gencode.v22.annotation.chr20.gtf \
              --direct_rna --minimap2_index_opts '-k 15' --sample_sheet ${CI_PROJECT_NAME}/data/differential_expression/sample_sheet.csv \
              --jaffal_refBase ${CI_PROJECT_NAME}/data/differential_expression/chr20/ --jaffal_genome hg38_chr20 --jaffal_annotation genCode22 \
              -c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
              CI_FLAVOUR: "new"

macos-run:
  # Let's avoid those ARM64 runners for now
  tags:
    - macos
    - x86

aws-run:
  artifacts:
        when: always

docker-run:
    artifacts:
        when: always
        paths:
            - ${CI_PROJECT_NAME}
            - .nextflow.log
        exclude:
            - ${CI_PROJECT_NAME}/**/*.gtf
            - ${CI_PROJECT_NAME}/**/*.gtf.gz
            - ${CI_PROJECT_NAME}/**/*.gff3
            - ${CI_PROJECT_NAME}/**/*.gff3.gz
            - ${CI_PROJECT_NAME}/**/*.gff
            - ${CI_PROJECT_NAME}/**/*.gff.gz
            - ${CI_PROJECT_NAME}/**/*.fna
            - ${CI_PROJECT_NAME}/**/*.fasta
            - ${CI_PROJECT_NAME}/**/*.mmi
    

    # Define a 1D job matrix to inject a variable named MATRIX_NAME into
    #   the CI environment, we can use the value of MATRIX_NAME to determine
    #   which options to apply as part of the rules block below
    # NOTE There is a slightly cleaner way to define this matrix to include
    #   the variables, but it is broken when using long strings! See CW-756
    parallel:
        matrix:
            - MATRIX_NAME: [
                "fusions", "differential_expression", "isoforms", "isoforms_bam",
                "only_differential_expression", "differential_expression_gff3",
                "ncbi_gzip", "ncbi_no_gene_id", "ensembl_with_versions",
                "differential_expression_mouse", "no_ref_annotation",
                "unstranded_annotation_error"
            ]
    rules:
        # NOTE As we're overriding the rules block for the included docker-run
        #   we must redefine this CI_COMMIT_BRANCH rule to prevent docker-run
        #   being incorrectly scheduled for "detached merge request pipelines" etc.
        - if: ($CI_COMMIT_BRANCH == null || $CI_COMMIT_BRANCH == "dev-template")
          when: never
        - if: $MATRIX_NAME == "isoforms"
          variables:
              NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/wf-isoforms_test_data.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz -C ${CI_PROJECT_NAME}/data/ &&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
              NF_WORKFLOW_OPTS: "--fastq  ${CI_PROJECT_NAME}/data/ERR6053095_chr20.fastq --transcriptome-source reference-guided \
                  --ref_genome ${CI_PROJECT_NAME}/data/chr20/hg38_chr20.fa --ref_annotation ${CI_PROJECT_NAME}/data/chr20/gencode.v22.annotation.chr20.gtf --pychopper_backend phmm \
                  -c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
              NF_IGNORE_PROCESSES: preprocess_reads,check_annotation_strand,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
        - if: $MATRIX_NAME == "isoforms_bam"
          variables:
            NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/wf-isoforms_test_data.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz -C ${CI_PROJECT_NAME}/data/ &&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
            NF_WORKFLOW_OPTS: "--bam  ${CI_PROJECT_NAME}/data/ERR6053095_chr20.bam --transcriptome-source reference-guided \
                  --ref_genome ${CI_PROJECT_NAME}/data/chr20/hg38_chr20.fa --ref_annotation ${CI_PROJECT_NAME}/data/chr20/gencode.v22.annotation.chr20.gtf --pychopper_backend phmm \
                  -c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
            NF_IGNORE_PROCESSES: preprocess_reads,check_annotation_strand,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
        - if: $MATRIX_NAME == "no_ref_annotation"
          variables:
              NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/wf-isoforms_test_data.tar.gz && tar -xzvf  ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz -C ${CI_PROJECT_NAME}/data/ &&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
              NF_WORKFLOW_OPTS: "--fastq  ${CI_PROJECT_NAME}/data/ERR6053095_chr20.fastq --transcriptome-source reference-guided \
                  --ref_genome ${CI_PROJECT_NAME}/data/chr20/hg38_chr20.fa \
                  -c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
              NF_IGNORE_PROCESSES: run_gffcompare,check_annotation_strand,preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
        - if: $MATRIX_NAME == "fusions"
          variables:
              NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/wf-isoforms_test_data.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz -C ${CI_PROJECT_NAME}/data/ &&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
              NF_WORKFLOW_OPTS: "-executor.\\$$local.memory 16GB --fastq  ${CI_PROJECT_NAME}/data/ERR6053095_chr20.fastq --transcriptome-source reference-guided \
                  --ref_genome ${CI_PROJECT_NAME}/data/chr20/hg38_chr20.fa --ref_annotation ${CI_PROJECT_NAME}/data/chr20/gencode.v22.annotation.chr20.gtf \
                  --jaffal_refBase ${CI_PROJECT_NAME}/data/chr20/ --jaffal_genome hg38_chr20 --jaffal_annotation genCode22 \
                  -c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
              NF_IGNORE_PROCESSES: preprocess_reads,check_annotation_strand,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
        - if: $MATRIX_NAME == "differential_expression"
          variables:
              NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/differential_expression.tar.gz -C ${CI_PROJECT_NAME}/data/ &&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
              NF_WORKFLOW_OPTS: "--fastq  ${CI_PROJECT_NAME}/data/differential_expression/differential_expression_fastq \
                  --de_analysis \
                  --ref_genome ${CI_PROJECT_NAME}/data/differential_expression/hg38_chr20.fa --transcriptome-source reference-guided \
                --ref_annotation ${CI_PROJECT_NAME}/data/differential_expression/gencode.v22.annotation.chr20.gtf \
                --direct_rna --minimap2_index_opts '-k 15'  --sample_sheet ${CI_PROJECT_NAME}/data/differential_expression/sample_sheet.csv \
                -c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
              NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
        - if: $MATRIX_NAME == "only_differential_expression"
          variables:
              NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/differential_expression.tar.gz -C ${CI_PROJECT_NAME}/data/  &&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
              NF_WORKFLOW_OPTS: "--fastq  ${CI_PROJECT_NAME}/data/differential_expression/differential_expression_fastq \
                  --transcriptome-source precomputed \
                  --de_analysis \
                  --ref_genome ${CI_PROJECT_NAME}/data/differential_expression/hg38_chr20.fa \
                --ref_annotation ${CI_PROJECT_NAME}/data/differential_expression/gencode.v22.annotation.chr20.gff \
                --direct_rna --minimap2_index_opts '-k 15' \
                --ref_transcriptome ${CI_PROJECT_NAME}/data/differential_expression/ref_transcriptome.fasta \
                --sample_sheet test_data/sample_sheet.csv \
                -c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
              NF_IGNORE_PROCESSES: >
                preprocess_reads,merge_transcriptomes,assemble_transcripts,decompress_annotation,decompress_ref,
                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome                
        - if: $MATRIX_NAME == "differential_expression_gff3"
          variables:
              NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/differential_expression.tar.gz -C ${CI_PROJECT_NAME}/data/ &&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
              NF_WORKFLOW_OPTS: "--fastq   ${CI_PROJECT_NAME}/data/differential_expression/differential_expression_fastq \
                  --transcriptome-source precomputed \
                  --de_analysis \
                  --ref_genome  ${CI_PROJECT_NAME}/data/differential_expression/hg38_chr20.fa \
                --ref_annotation  ${CI_PROJECT_NAME}/data/differential_expression/gencode.v22.annotation.chr20.gff3 \
                --direct_rna --minimap2_index_opts '-k 15' \
                --ref_transcriptome  ${CI_PROJECT_NAME}/data/differential_expression/ref_transcriptome.fasta \
                --sample_sheet test_data/sample_sheet.csv \
                -c  ${CI_PROJECT_NAME}/data/demo.nextflow.config"
              NF_IGNORE_PROCESSES: >
                preprocess_reads,merge_transcriptomes,assemble_transcripts,decompress_annotation,decompress_ref,
                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome                
        - if: $MATRIX_NAME == "ncbi_gzip"
          variables:
              NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O  ${CI_PROJECT_NAME}/data/differential_expression_ncbi.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression_ncbi.tar.gz && tar -xzvf  ${CI_PROJECT_NAME}/data/differential_expression_ncbi.tar.gz -C  ${CI_PROJECT_NAME}/data/ &&  wget -O  ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
              NF_WORKFLOW_OPTS: "-executor.\\$$local.memory 16GB \
                  --fastq   ${CI_PROJECT_NAME}/data/differential_expression_ncbi/differential_expression_fastq \
                  --transcriptome-source precomputed \
                  --de_analysis \
                  --ref_genome  ${CI_PROJECT_NAME}/data/differential_expression_ncbi/GRCh38.p14.NCBI_test.fna.gz \
                --ref_annotation  ${CI_PROJECT_NAME}/data/differential_expression_ncbi/GRCh38.p14_NCBI_test.gtf.gz \
                --direct_rna --minimap2_index_opts '-w 25' \
               --sample_sheet test_data/sample_sheet.csv \
               -c  ${CI_PROJECT_NAME}/data/demo.nextflow.config"
              NF_IGNORE_PROCESSES: >
                preprocess_reads,merge_transcriptomes,assemble_transcripts,
                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome                           
        - if: $MATRIX_NAME == "ncbi_no_gene_id"
          variables:
              NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/differential_expression_ncbi.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression_ncbi.tar.gz && tar -xzvf  ${CI_PROJECT_NAME}/data/differential_expression_ncbi.tar.gz -C  ${CI_PROJECT_NAME}/data/ &&  wget -O  ${CI_PROJECT_NAME}/data/demo.nextflow.config  https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
              NF_WORKFLOW_OPTS: "-executor.\\$$local.memory 16GB \
                --fastq ${CI_PROJECT_NAME}/data/differential_expression_ncbi/differential_expression_fastq \
                --transcriptome-source precomputed --de_analysis \
                --ref_genome ${CI_PROJECT_NAME}/data/differential_expression_ncbi/GCF_000001405.40_GRCh38.p14_genomic.fna.gz \
                --ref_annotation ${CI_PROJECT_NAME}/data/differential_expression_ncbi/GCF_000001405.40_GRCh38.p14_genomic.gff.gz \
                --direct_rna --ref_transcriptome ${CI_PROJECT_NAME}/data/differential_expression_ncbi/GCF_000001405.40_GRCh38.p14_rna.fna.gz \
                --transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv \
                -c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
              NF_IGNORE_PROCESSES: >
                preprocess_reads,merge_transcriptomes,assemble_transcripts,
                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome                      
        - if: $MATRIX_NAME == "ensembl_with_versions"
          variables:
              NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/differential_expression.tar.gz -C  ${CI_PROJECT_NAME}/data/ &&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
              NF_WORKFLOW_OPTS: "-executor.\\$$local.memory 16GB \
                --fastq  ${CI_PROJECT_NAME}/data/differential_expression/differential_expression_fastq \
                --de_analysis \
                --ref_genome ${CI_PROJECT_NAME}/data/differential_expression/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz \
                --ref_annotation  ${CI_PROJECT_NAME}/data/differential_expression/Homo_sapiens.GRCh38.109.gtf.gz \
                --direct_rna --ref_transcriptome  ${CI_PROJECT_NAME}/data/differential_expression/Homo_sapiens.GRCh38.cdna.all.fa.gz \
                --transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv \
                -c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
              NF_IGNORE_PROCESSES: >
                preprocess_reads,merge_transcriptomes,assemble_transcripts,
                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome                
        - if: $MATRIX_NAME == "differential_expression_mouse"
          variables:
              NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/differential_expression_mouse.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression_mouse.tar.gz && tar -xzvf  ${CI_PROJECT_NAME}/data/differential_expression_mouse.tar.gz -C ${CI_PROJECT_NAME}/data/&&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
              NF_WORKFLOW_OPTS: "-executor.\\$$local.memory 16GB \
                --fastq  ${CI_PROJECT_NAME}/data/differential_expression_mouse/differential_expression_fastq \
                --transcriptome-source precomputed --de_analysis \
                --ref_genome  ${CI_PROJECT_NAME}/data/differential_expression_mouse/GRCm39.genome.fa.gz \
                --ref_annotation  ${CI_PROJECT_NAME}/data/differential_expression_mouse/gencode.vM33.annotation.gtf \
                --direct_rna --ref_transcriptome  ${CI_PROJECT_NAME}/data/differential_expression_mouse/gencode.vM33.transcripts.fa.gz \
                --transcriptome_assembly false --sample_sheet  ${CI_PROJECT_NAME}/data/differential_expression_mouse/sample_sheet.csv \
                -c  ${CI_PROJECT_NAME}/data/demo.nextflow.config"
              NF_IGNORE_PROCESSES: >
                preprocess_reads,merge_transcriptomes,assemble_transcripts,decompress_annotation,
                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam                    
        - if: $MATRIX_NAME == "unstranded_annotation_error"
          variables:
              NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-transcriptomes/differential_expression.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/differential_expression.tar.gz -C ${CI_PROJECT_NAME}/data/  &&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
              NF_WORKFLOW_OPTS: "--fastq  ${CI_PROJECT_NAME}/data/differential_expression/differential_expression_fastq \
                  --de_analysis \
                  --ref_genome ${CI_PROJECT_NAME}/data/differential_expression/hg38_chr20.fa --transcriptome-source reference-guided \
                --ref_annotation ${CI_PROJECT_NAME}/data/differential_expression/unstranded_annotation.gtf \
                --direct_rna --minimap2_index_opts '-k 15'  --sample_sheet ${CI_PROJECT_NAME}/data/differential_expression/sample_sheet.csv \
                -c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
              NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
              ASSERT_NEXTFLOW_FAILURE: "test_fail" # set to any non-zero length str to allow the nextflow CMD to fail
              ASSERT_NEXTFLOW_FAILURE_REXP: "In ref_annotation, transcript features must have a strand of either '+' or '-'"