NationalGenomicsInfrastructure/ngi_pipeline

# This file should be placed under $HOME/.ngiconfig/ngi_config.yaml
# or its path exported as the environment variable NGI_CONFIG

database:
    record_tracking_db_path: /data/ngi2016000/private/db/records_db.sql

environment:
    project_id: ngi2016000
    ngi_scripts_dir: /ngi_pipeline/scripts 
    conda_env: NGI
    flowcell_inbox:
            - /data/ngi2016000/incoming
 
piper:
    #sample:
    #    required_autosomal_coverage: 28.4
    load_modules:
        - bioinfo-tools piper/1.5.1
    threads: 16
    job_walltime:
        merge_process_variantcall: "10-00:00:00"
    shell_jobrunner: Shell
    #shell_jobrunner: ParallelShell --super_charge --ways_to_split 4
    #jobNative:
    #    - arg1
    #    - arg2
    #    - arg3
    # TODO: Piper module adds setupfilecreator to the path; unsure if this works or if complete path is required.  
    path_to_setupfilecreator: setupfilecreator
    gatk_key: "/path/to/gatk.key"

sarek:
    tag: 2.6.1
    tools:
      - haplotypecaller
      - snpeff
    genomes_base_paths:
        GRCh37: /sw/data/uppnex/ToolBox/ReferenceAssemblies/hg38make/bundle/2.8/b37/
        GRCh38: /sw/data/uppnex/ToolBox/hg38bundle/
    project: ngi2016000
    custom_config_base: /lupus/ngi/staging/latest/sw/sarek/configs/
    command: /lupus/ngi/staging/latest/sw/sarek/workflow/main.nf
    igenomes_ignore: " "
    no_gatk_spark: " "
    sequencing_center: "NGI-U"

nextflow:
    profile: uppmax
    config:
        - /lupus/ngi/staging/latest/conf/nextflow_irma_upps.config
        - /lupus/ngi/staging/latest/conf/sarek_irma.config
    resume: " "

supported_genomes:
    "GRCh37": "/sw/data/uppnex/piper_references/2016-04-07/gatk_bundle/2.8/b37//human_g1k_v37.fasta"
    # GRMc38 is currently not used.  
    #"GRCm38": "/sw/data/uppnex/reference/Mus_musculus/GRCm38/concat/Mus_musculus.GRCm38.69.dna.concat.fa"
    "rn4": None
    "saccer2": None
    "dm3": None
    "tair9": None
    "xentro2": None
    "ws210": None
    "canfam3": None

analysis:
    best_practice_analysis:
        whole_genome_reseq:
            analysis_engine: ngi_pipeline.engines.piper_ngi
        IGN:
            analysis_engine: ngi_pipeline.engines.piper_ngi
        qc:
            analysis_engine: ngi_pipeline.engines.qc_ngi
        RNA-seq:
            analysis_engine: ngi_pipeline.engines.rna_ngi
            ngi_nf_path: /sw//ngi-rnaseq/main.nf
            sthlm_ngi_conf: /conf//ngi-rnaseq_sthlm.config
            upps_ngi_conf: /conf//ngi-rnaseq_upps.config
        wgs_germline:
            analysis_engine: ngi_pipeline.engines.sarek
        wgs_somatic:
            analysis_engine: ngi_pipeline.engines.sarek
        exome_germline:
            analysis_engine: ngi_pipeline.engines.sarek
        exome_somatic:
            analysis_engine: ngi_pipeline.engines.sarek
    top_dir: nobackup/NGI
    sthlm_root: ngi2016000
    upps_root: ngi2016000
    base_root: /data

qc:
    load_modules:
        - bioinfo-tools
    fastqc:
        load_modules:
            - FastQC
        threads: 16
    fastq_screen:
        config_path: "/conf//fastq_screen.irma.conf"
        load_modules:
            - bowtie2
            - fastq_screen
        subsample_reads: 200000
        threads: 1

gt_concordance:
    XL_FILES_PATH: /genotype_data/incoming
    XL_FILES_ARCHIVED:  /genotype_data/archive
    GATK_PATH: /sw/apps/bioinfo/GATK/3.5.0//GenomeAnalysisTK.jar
    GATK_REF_FILE: /sw/data/uppnex/piper_references/2016-04-07/gatk_bundle/2.8/b37//human_g1k_v37.fasta
    GATK_VAR_FILE: /sw/data/uppnex/piper_references/2016-04-07/gatk_bundle/2.8/b37//dbsnp_138.b37.vcf
    INTERVAL_FILE: /ngi_pipeline/static/snps.interval_list
    SNPS_FILE: /ngi_pipeline/static/maf_snps.txt

logging: 
    log_file: "/data/ngi2016000/private/log/ngi_pipeline.log" 

mail:
    recipient: user@organization.org

paths: # Hard code paths here if you are that kind of a person
    binaries:
        #bowtie2:
        #fastqc:
        #fastq_screen:
    references: