name: sarek version: "3.7.1" description: "Variant calling for WGS/WES data (germline and somatic)" # Documentation and source - NOTE: Update version in URLs when upgrading pipeline urls: documentation: "https://nf-co.re/sarek/{version}/" parameters: "https://nf-co.re/sarek/{version}/parameters/" output_docs: "https://nf-co.re/sarek/{version}/docs/output/" github: "https://github.com/nf-core/sarek" releases: "https://github.com/nf-core/sarek/releases" data_types: - WGS - WES - whole genome sequencing - whole exome sequencing - tumor-normal - germline - somatic detection_hints: filename: - tumor - normal - germline - wgs - wes - exome - dna - variant directory: - variant - wgs - wes - exome - germline - somatic samplesheet: input_types: - fastq - bam - cram columns: - name: patient required: true type: string inference: filename description: "Patient/subject identifier for grouping samples" - name: sample required: true type: string inference: filename description: "Sample identifier (e.g., tumor, normal)" - name: lane required: false type: string default: "L001" inference: filename description: "Sequencing lane" - name: fastq_1 required: true type: path inference: auto condition: "input_type == 'fastq'" description: "Absolute path to R1 FASTQ" - name: fastq_2 required: false type: path inference: auto condition: "input_type == 'fastq'" description: "Absolute path to R2 FASTQ" - name: bam required: true type: path inference: auto condition: "input_type in ['bam', 'cram']" description: "Absolute path to BAM/CRAM file" - name: bai required: true type: path inference: auto condition: "input_type in ['bam', 'cram']" description: "Absolute path to BAM/CRAM index" - name: status required: false type: integer allowed: - 0 - 1 default: 0 inference: filename description: "0=normal, 1=tumor (critical for somatic calling)" decision_points: - parameter: genome prompt: "Which reference genome should be used?" options: - value: GRCh38 label: "Human GRCh38/hg38 (recommended)" description: "Latest human reference with most annotation support" - value: GRCh37 label: "Human GRCh37/hg19 (legacy)" description: "For compatibility with older datasets" - value: mm10 label: "Mouse mm10" description: "Mouse reference genome" default: GRCh38 recommendation: "Default to GRCh38 for human data" - parameter: tools prompt: "What type of variant calling do you need?" options: - value: "haplotypecaller,snpeff" label: "Germline variants (single samples)" description: "For finding inherited variants in normal samples" condition: "no tumor samples detected" - value: "mutect2,strelka,snpeff" label: "Somatic variants (tumor-normal pairs)" description: "For finding cancer mutations with matched normal" condition: "tumor-normal pairs detected" - value: "haplotypecaller,deepvariant,snpeff" label: "Germline with DeepVariant" description: "Higher accuracy germline calling (requires GPU)" - value: "mutect2,manta,snpeff" label: "Somatic with structural variants" description: "Comprehensive tumor analysis including SVs" default: "haplotypecaller,snpeff" recommendation: "Use somatic tools if tumor/normal pairs detected, otherwise germline" - parameter: wes prompt: "Is this whole exome sequencing (WES) data?" options: - value: "false" label: "No - Whole Genome Sequencing (WGS)" description: "Full genome coverage" - value: "true" label: "Yes - Whole Exome Sequencing (WES)" description: "Requires --intervals BED file" default: "false" recommendation: "If WES, user must provide intervals BED file" test_profile: command: "nextflow run nf-core/sarek -r 3.7.1 -profile test,docker --outdir test_sarek" duration: "20 minutes" success_indicators: - "test_sarek/multiqc/multiqc_report.html" log_pattern: "Pipeline completed successfully" run_command: template: | nextflow run nf-core/sarek \ -r 3.7.1 \ -profile docker \ --input {samplesheet} \ --outdir {outdir} \ --genome {genome} \ --tools {tools} \ -resume wes_template: | nextflow run nf-core/sarek \ -r 3.7.1 \ -profile docker \ --input {samplesheet} \ --outdir {outdir} \ --genome {genome} \ --tools {tools} \ --wes \ --intervals {intervals} \ -resume outputs: primary: - path: "preprocessing/recalibrated/*.recal.bam" description: "Analysis-ready BAM files" - path: "variant_calling/*/*.vcf.gz" description: "Variant call files" - path: "annotation/snpeff/*.ann.vcf.gz" description: "Annotated variants" validation: - file: "multiqc/multiqc_report.html" check: exists description: "QC report must exist" - file: "preprocessing/recalibrated" check: exists description: "Recalibrated BAMs directory" resources: min_memory: "16.GB" recommended_memory: "64.GB" wgs_memory: "128.GB" min_cpus: 4 recommended_cpus: 16 disk_space: "500.GB" troubleshooting: - error: "BQSR fails" fix: "Check known sites available for genome. Skip with --skip_bqsr for non-standard references" - error: "Mutect2 no variants" fix: "Verify tumor/normal pairing in samplesheet (check status column: 0=normal, 1=tumor)" - error: "Out of memory" fix: "--max_memory '128.GB' for WGS data" - error: "DeepVariant GPU issues" fix: "Ensure NVIDIA Docker runtime configured, or use CPU mode" tumor_normal_keywords: tumor: - tumor - tumour - met - metastasis - primary - cancer - malignant normal: - normal - germline - blood - pbmc - control - healthy - matched