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 -nv -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 -nv -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 \
              --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"
              CI_FLAVOUR: "new"
              PYTEST_CONTAINER_NAME: "wf-common"
              PYTEST_CONTAINER_CONFIG_KEY: "common_sha"
              RTEST_CONTAINER_NAME: "wf-transcriptomes-core"
              RTEST_CONTAINER_CONFIG_KEY: "container_sha"

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


docker-run:
    tags:
        - linux
        - prod
        - amd64
        - eks
        - xlarge-highio
        - docker
    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: [
                "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_warn", "igv", "igv_fai_gz",
                "mismatch_seqid_error","mismatch_seqid_warn",
                "codex_discover", "codex_fixed_annotation", "codex_direct_rna",
                "codex_de_analysis", "codex_invalid_mode",
                "codex_conflicting_library_flags"
            ]
    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 -nv -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 -nv -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 \
                  --ref_genome ${CI_PROJECT_NAME}/data/chr20/hg38_chr20.fa --ref_annotation ${CI_PROJECT_NAME}/data/chr20/gencode.v22.annotation.chr20.gtf --cdna_preprocess --pychopper_backend phmm"
              NF_IGNORE_PROCESSES: preprocess_reads,filter_unstranded_annotation,validate_ref_annotation,faidx,gz_faidx,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 -nv -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 -nv -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 \
                  --ref_genome ${CI_PROJECT_NAME}/data/chr20/hg38_chr20.fa --ref_annotation ${CI_PROJECT_NAME}/data/chr20/gencode.v22.annotation.chr20.gtf --cdna_preprocess --pychopper_backend phmm \
                  -c ${CI_PROJECT_NAME}/data/demo.nextflow.config "
            NF_IGNORE_PROCESSES: preprocess_reads,filter_unstranded_annotation,validate_ref_annotation,faidx,gz_faidx,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 -nv -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 -nv -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 \
                  --ref_genome ${CI_PROJECT_NAME}/data/chr20/hg38_chr20.fa \
                  -c ${CI_PROJECT_NAME}/data/demo.nextflow.config "
              NF_IGNORE_PROCESSES: preprocess_reads
              ASSERT_NEXTFLOW_FAILURE: "1"
              ASSERT_NEXTFLOW_FAILURE_REXP: "Missing required parameter: --ref_annotation"
        - if: $MATRIX_NAME == "differential_expression"
          variables:
              NF_BEFORE_SCRIPT: "mkdir -p ${CI_PROJECT_NAME}/data/ && wget -nv -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 -nv -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 \
                --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,faidx,gz_faidx,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 -nv -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 -nv -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_mode fixed_annotation \
                  --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' \
                --sample_sheet test_data/sample_sheet.csv \
                -c ${CI_PROJECT_NAME}/data/demo.nextflow.config "
              NF_IGNORE_PROCESSES: >
                preprocess_reads,faidx,validate_ref_annotation,gz_faidx,merge_transcriptomes,merge_gff_bundles,assemble_transcripts,decompress_annotation,decompress_ref,
                build_minimap_index,get_transcriptome,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 -nv -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 -nv -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_mode fixed_annotation \
                  --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' \
                --sample_sheet test_data/sample_sheet.csv \
                -c  ${CI_PROJECT_NAME}/data/demo.nextflow.config "
              NF_IGNORE_PROCESSES: >
                preprocess_reads,validate_ref_annotation,faidx,gz_faidx,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 -nv -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 -nv -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_ncbi/differential_expression_fastq \
                  --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,faidx,gz_faidx,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 -nv -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 -nv -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_ncbi/differential_expression_fastq \
                --transcriptome_mode fixed_annotation --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 \
                --sample_sheet test_data/sample_sheet.csv \
                -c ${CI_PROJECT_NAME}/data/demo.nextflow.config "
              NF_IGNORE_PROCESSES: >
                preprocess_reads,faidx,validate_ref_annotation,gz_faidx,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 -nv -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 -nv -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/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz \
                --ref_annotation  ${CI_PROJECT_NAME}/data/differential_expression/Homo_sapiens.GRCh38.109.gtf.gz \
                --direct_rna --transcriptome_mode fixed_annotation \
                --sample_sheet test_data/sample_sheet.csv \
                -c ${CI_PROJECT_NAME}/data/demo.nextflow.config "
              NF_IGNORE_PROCESSES: >
                preprocess_reads,validate_ref_annotation,faidx,gz_faidx,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 -nv -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 -nv -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_mouse/differential_expression_fastq \
                --transcriptome_mode fixed_annotation --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 \
                --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,validate_ref_annotation,faidx,gz_faidx,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_warn"
          variables:
              NF_BEFORE_SCRIPT: "mkdir -p ${CI_PROJECT_NAME}/data/ && wget -nv -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 -nv -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 \
                --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,faidx,gz_faidx,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
              AFTER_NEXTFLOW_CMD: "grep 'Unstranded entries found and excluded from differential expression analysis.' '.nextflow.log'"
        - if: $MATRIX_NAME == "igv"
          variables:
              NF_BEFORE_SCRIPT: "mkdir -p ${CI_PROJECT_NAME}/data/ && wget -nv -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 -nv -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 \
                --ref_annotation ${CI_PROJECT_NAME}/data/differential_expression/gencode.v22.annotation.chr20.gff \
                --direct_rna --transcriptome_mode fixed_annotation --minimap2_index_opts '-k 15' \
                --sample_sheet test_data/sample_sheet.csv \
                --igv \
                -c ${CI_PROJECT_NAME}/data/demo.nextflow.config "
              NF_IGNORE_PROCESSES: >
                preprocess_reads,gz_faidx,merge_transcriptomes,assemble_transcripts,decompress_annotation,decompress_ref,
                build_minimap_index,validate_ref_annotation,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome                
        - if: $MATRIX_NAME == "igv_fai_gz"
          variables:
              NF_BEFORE_SCRIPT: "mkdir -p ${CI_PROJECT_NAME}/data/ && wget -nv -O ${CI_PROJECT_NAME}/data/differential_expression_ncbi.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-transcriptomes/differential_expression_ncbi.tar.gz && tar -xzvf  ${CI_PROJECT_NAME}/data/differential_expression_ncbi.tar.gz -C  ${CI_PROJECT_NAME}/data/ &&  wget -nv -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_ncbi/differential_expression_fastq \
                --transcriptome_mode fixed_annotation --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 \
                --sample_sheet test_data/sample_sheet.csv \
                --igv \
                -c ${CI_PROJECT_NAME}/data/demo.nextflow.config "
              NF_IGNORE_PROCESSES: >
                preprocess_reads,validate_ref_annotation,merge_transcriptomes,assemble_transcripts,
                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome,faidx,gz_faidx                
        - if: $MATRIX_NAME == "mismatch_seqid_error"
          variables:
              NF_BEFORE_SCRIPT: "mkdir -p ${CI_PROJECT_NAME}/data/ && wget -nv -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 -nv -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_ncbi/differential_expression_fastq \
                  --de_analysis \
                  --ref_genome  ${CI_PROJECT_NAME}/data/differential_expression_ncbi/hg38_chr20.fa \
                  --ref_annotation  ${CI_PROJECT_NAME}/data/differential_expression_ncbi/GRCh38.p14_NCBI_test.gtf.gz \
                  --direct_rna \
                  --sample_sheet test_data/sample_sheet.csv \
                  -c  ${CI_PROJECT_NAME}/data/demo.nextflow.config "
              NF_IGNORE_PROCESSES: >
                preprocess_reads,faidx,gz_faidx,merge_transcriptomes,assemble_transcripts,
                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome                
              ASSERT_NEXTFLOW_FAILURE: 1
              ASSERT_NEXTFLOW_FAILURE_REXP: No overlapping seqnames were found between the reference annotation and the reference genome
        - if: $MATRIX_NAME == "mismatch_seqid_warn"
          variables:
              NF_BEFORE_SCRIPT: "mkdir -p ${CI_PROJECT_NAME}/data/ && wget -nv -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 -nv -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_ncbi/differential_expression_fastq \
                  --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 \
                  --sample_sheet test_data/sample_sheet.csv --minimap2_index_opts '-w 25' \
                  -c  ${CI_PROJECT_NAME}/data/demo.nextflow.config "
              NF_IGNORE_PROCESSES: >
                preprocess_reads,faidx,gz_faidx,merge_transcriptomes,assemble_transcripts,
                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome                
              AFTER_NEXTFLOW_CMD: "grep 'Some seqnames are present in the genome but not the annotation' '.nextflow.log'"
        - if: $MATRIX_NAME == "codex_discover"
          variables:
              NF_BEFORE_SCRIPT: ":"
              NF_WORKFLOW_OPTS: "--fastq test_data/smoke/reads.fastq --sample sampleA --ref_genome test_data/smoke/reference.fa --ref_annotation test_data/smoke/annotation.gtf"
              NF_IGNORE_PROCESSES: preprocess_reads
              AFTER_NEXTFLOW_CMD: >
                  test -f ${CI_PROJECT_NAME}/cohort/transcripts.gtf &&
                  test -f ${CI_PROJECT_NAME}/cohort/cohort.transcriptome.fa &&
                  test -f ${CI_PROJECT_NAME}/samples/sampleA/transcripts.gtf                  
        - if: $MATRIX_NAME == "codex_fixed_annotation"
          variables:
              NF_BEFORE_SCRIPT: ":"
              NF_WORKFLOW_OPTS: "--fastq test_data/smoke/reads.fastq --sample sampleA --ref_genome test_data/smoke/reference.fa --ref_annotation test_data/smoke/annotation.gtf --transcriptome_mode fixed_annotation"
              NF_IGNORE_PROCESSES: preprocess_reads
              AFTER_NEXTFLOW_CMD: >
                  test -f ${CI_PROJECT_NAME}/cohort/transcripts.gtf &&
                  test -f ${CI_PROJECT_NAME}/cohort/transcript_counts.tsv                  
        - if: $MATRIX_NAME == "codex_direct_rna"
          variables:
              NF_BEFORE_SCRIPT: ":"
              NF_WORKFLOW_OPTS: "--fastq test_data/smoke/reads.fastq --sample sampleA --ref_genome test_data/smoke/reference.fa --ref_annotation test_data/smoke/annotation.gtf --direct_rna"
              NF_IGNORE_PROCESSES: preprocess_reads
              AFTER_NEXTFLOW_CMD: >
                  test -f ${CI_PROJECT_NAME}/cohort/alignments/sampleA.aligned.sorted.bam &&
                  test -f ${CI_PROJECT_NAME}/cohort/sqanti_cohort/classification_summary.tsv                  
        - if: $MATRIX_NAME == "codex_de_analysis"
          variables:
              NF_BEFORE_SCRIPT: ":"
              NF_WORKFLOW_OPTS: "--fastq test_data/smoke/de --sample_sheet test_data/smoke/sample_sheet_de.csv --ref_genome test_data/smoke/reference.fa --ref_annotation test_data/smoke/annotation.gtf --de_analysis --reference_level control --covariates batch"
              NF_IGNORE_PROCESSES: preprocess_reads
              AFTER_NEXTFLOW_CMD: >
                  test -f ${CI_PROJECT_NAME}/de_analysis/condition_treated_vs_control/results_dge.tsv &&
                  test -f ${CI_PROJECT_NAME}/de_analysis/condition_treated_vs_control/results_dtu_transcript.tsv                  
        - if: $MATRIX_NAME == "codex_invalid_mode"
          variables:
              NF_BEFORE_SCRIPT: ":"
              NF_WORKFLOW_OPTS: "--fastq test_data/smoke/reads.fastq --sample sampleA --ref_genome test_data/smoke/reference.fa --ref_annotation test_data/smoke/annotation.gtf --transcriptome_mode nonsense"
              NF_IGNORE_PROCESSES: preprocess_reads
              ASSERT_NEXTFLOW_FAILURE: "1"
              ASSERT_NEXTFLOW_FAILURE_REXP: "nonsense is not a valid choice"
        - if: $MATRIX_NAME == "codex_conflicting_library_flags"
          variables:
              NF_BEFORE_SCRIPT: ":"
              NF_WORKFLOW_OPTS: "--fastq test_data/smoke/reads.fastq --sample sampleA --ref_genome test_data/smoke/reference.fa --ref_annotation test_data/smoke/annotation.gtf --direct_rna --cdna_preprocess"
              ASSERT_NEXTFLOW_FAILURE: "1"
              ASSERT_NEXTFLOW_FAILURE_REXP: ".*--cdna_preprocess cannot be used together with --direct_rna"