opencode-knowledge-work 0.0.0-stage → 0.1.0

package/content/bio-research/skills/bio-research-nextflow-development/scripts/config/pipelines/atacseq.yaml

@@ -0,0 +1,187 @@
+name: atacseq
+version: "2.1.2"
+description: "Chromatin accessibility analysis and peak calling"
+
+# Documentation and source - NOTE: Update version in URLs when upgrading pipeline
+urls:
+  documentation: "https://nf-co.re/atacseq/{version}/"
+  parameters: "https://nf-co.re/atacseq/{version}/parameters/"
+  output_docs: "https://nf-co.re/atacseq/{version}/docs/output/"
+  github: "https://github.com/nf-core/atacseq"
+  releases: "https://github.com/nf-core/atacseq/releases"
+
+data_types:
+  - ATAC-seq
+  - chromatin accessibility
+  - open chromatin
+
+detection_hints:
+  filename:
+    - atac
+    - atacseq
+    - chromatin
+    - accessibility
+  directory:
+    - atac
+    - atacseq
+    - chromatin
+    - epigenome
+    - epigenetics
+
+samplesheet:
+  input_types:
+    - fastq
+
+  columns:
+    - name: sample
+      required: true
+      type: string
+      inference: filename
+      description: "Condition/group identifier (replicates share same name)"
+
+    - name: fastq_1
+      required: true
+      type: path
+      inference: auto
+      description: "Absolute path to R1 FASTQ"
+
+    - name: fastq_2
+      required: true
+      type: path
+      inference: auto
+      description: "Absolute path to R2 FASTQ (paired-end required)"
+
+    - name: replicate
+      required: true
+      type: integer
+      default: 1
+      inference: filename
+      description: "Replicate number (integer)"
+
+decision_points:
+  - parameter: genome
+    prompt: "Which reference genome matches your organism?"
+    options:
+      - value: GRCh38
+        label: "Human GRCh38/hg38 (recommended)"
+        description: "Latest human reference"
+      - value: GRCh37
+        label: "Human GRCh37/hg19 (legacy)"
+        description: "Older human reference"
+      - value: mm10
+        label: "Mouse mm10"
+        description: "Mouse reference genome"
+    default: GRCh38
+    recommendation: "Default to GRCh38 for human samples"
+
+  - parameter: read_length
+    prompt: "What is the read length of your sequencing data?"
+    options:
+      - value: 50
+        label: "50 bp"
+        description: "Short reads"
+      - value: 75
+        label: "75 bp"
+        description: "Standard length"
+      - value: 100
+        label: "100 bp"
+        description: "Common for modern sequencers"
+      - value: 150
+        label: "150 bp"
+        description: "Long reads"
+    default: 50
+    recommendation: "Check FASTQ files or sequencing report for exact length"
+
+  - parameter: narrow_peak
+    prompt: "What type of peaks are you expecting?"
+    options:
+      - value: "true"
+        label: "Narrow peaks (default for ATAC-seq)"
+        description: "Standard ATAC-seq open chromatin regions"
+      - value: "false"
+        label: "Broad peaks"
+        description: "For histone marks or broader accessibility regions"
+    default: "true"
+    recommendation: "Use narrow peaks for standard ATAC-seq"
+
+test_profile:
+  command: "nextflow run nf-core/atacseq -r 2.1.2 -profile test,docker --outdir test_atacseq"
+  duration: "15 minutes"
+  success_indicators:
+    - "test_atacseq/multiqc/multiqc_report.html"
+  log_pattern: "Pipeline completed successfully"
+
+run_command:
+  template: |
+    nextflow run nf-core/atacseq \
+        -r 2.1.2 \
+        -profile docker \
+        --input {samplesheet} \
+        --outdir {outdir} \
+        --genome {genome} \
+        --read_length {read_length} \
+        -resume
+
+outputs:
+  primary:
+    - path: "bwa/mergedLibrary/*.mLb.mkD.sorted.bam"
+      description: "Filtered, deduplicated alignments"
+    - path: "bwa/mergedLibrary/bigwig/*.bigWig"
+      description: "Coverage tracks for genome browsers"
+    - path: "macs2/narrowPeak/*.narrowPeak"
+      description: "Peak calls (BED format)"
+    - path: "macs2/narrowPeak/consensus/consensus_peaks.bed"
+      description: "Consensus peaks across replicates"
+
+  validation:
+    - file: "multiqc/multiqc_report.html"
+      check: exists
+      description: "QC report must exist"
+    - file: "macs2/narrowPeak"
+      check: exists
+      description: "Peak calls directory"
+
+quality_metrics:
+  - name: mapped_reads
+    good: ">80%"
+    acceptable: "60-80%"
+    poor: "<60%"
+  - name: mitochondrial
+    good: "<20%"
+    acceptable: "20-40%"
+    poor: ">40%"
+  - name: duplicates
+    good: "<30%"
+    acceptable: "30-50%"
+    poor: ">50%"
+  - name: frip
+    good: ">30%"
+    acceptable: "15-30%"
+    poor: "<15%"
+  - name: tss_enrichment
+    good: ">6"
+    acceptable: "4-6"
+    poor: "<4"
+
+resources:
+  min_memory: "8.GB"
+  recommended_memory: "32.GB"
+  min_cpus: 4
+  recommended_cpus: 8
+  disk_space: "100.GB"
+
+troubleshooting:
+  - error: "Low FRiP score"
+    fix: "Check library complexity in plotFingerprint. May indicate over-transposition or low quality"
+  - error: "Few peaks called"
+    fix: "Lower threshold with --macs_qvalue 0.1 or use --narrow_peak false for broader peaks"
+  - error: "High duplicates"
+    fix: "Normal for low-input samples. Pipeline removes by default. Consider deeper sequencing"
+  - error: "High mitochondrial reads"
+    fix: "Sample quality issue. Pipeline filters mito by default (--keep_mito false)"
+
+replicate_patterns:
+  - "_rep(\\d+)"
+  - "_R(\\d+)_"
+  - "_(\\d+)$"
+  - "_replicate(\\d+)"

package/content/bio-research/skills/bio-research-nextflow-development/scripts/config/pipelines/rnaseq.yaml

@@ -0,0 +1,147 @@
+name: rnaseq
+version: "3.22.2"
+description: "Gene expression quantification and differential expression analysis"
+
+# Documentation and source - NOTE: Update version in URLs when upgrading pipeline
+urls:
+  documentation: "https://nf-co.re/rnaseq/{version}/"
+  parameters: "https://nf-co.re/rnaseq/{version}/parameters/"
+  output_docs: "https://nf-co.re/rnaseq/{version}/docs/output/"
+  github: "https://github.com/nf-core/rnaseq"
+  releases: "https://github.com/nf-core/rnaseq/releases"
+
+data_types:
+  - RNA-seq
+  - mRNA-seq
+  - bulk RNA-seq
+
+detection_hints:
+  filename:
+    - rna
+    - rnaseq
+    - mrna
+    - expression
+  directory:
+    - rnaseq
+    - rna
+    - expression
+    - transcriptome
+
+samplesheet:
+  input_types:
+    - fastq
+
+  columns:
+    - name: sample
+      required: true
+      type: string
+      inference: filename
+      description: "Sample identifier"
+
+    - name: fastq_1
+      required: true
+      type: path
+      inference: auto
+      description: "Absolute path to R1 FASTQ"
+
+    - name: fastq_2
+      required: false
+      type: path
+      inference: auto
+      description: "Absolute path to R2 FASTQ (empty for single-end)"
+
+    - name: strandedness
+      required: true
+      type: enum
+      allowed:
+        - auto
+        - forward
+        - reverse
+        - unstranded
+      default: "auto"
+      inference: default
+      description: "Library strandedness (auto recommended)"
+
+decision_points:
+  - parameter: genome
+    prompt: "Which reference genome matches your organism?"
+    options:
+      - value: GRCh38
+        label: "Human GRCh38/hg38 (recommended for human)"
+        description: "Latest human reference assembly"
+      - value: GRCh37
+        label: "Human GRCh37/hg19 (legacy)"
+        description: "Older human reference for compatibility"
+      - value: mm10
+        label: "Mouse mm10/GRCm38"
+        description: "Mouse reference genome"
+      - value: BDGP6
+        label: "Drosophila BDGP6"
+        description: "Fruit fly reference"
+    default: GRCh38
+    recommendation: "Default to GRCh38 for human samples"
+
+  - parameter: aligner
+    prompt: "Which alignment strategy would you prefer?"
+    options:
+      - value: star_salmon
+        label: "STAR + Salmon (recommended)"
+        description: "Most accurate, standard for differential expression"
+      - value: star_rsem
+        label: "STAR + RSEM"
+        description: "Better for isoform-level quantification"
+      - value: hisat2
+        label: "HISAT2"
+        description: "Lower memory requirements, faster"
+    default: star_salmon
+    recommendation: "Use star_salmon unless memory-constrained or need isoforms"
+
+test_profile:
+  command: "nextflow run nf-core/rnaseq -r 3.22.2 -profile test,docker --outdir test_rnaseq"
+  duration: "15 minutes"
+  success_indicators:
+    - "test_rnaseq/multiqc/multiqc_report.html"
+  log_pattern: "Pipeline completed successfully"
+
+run_command:
+  template: |
+    nextflow run nf-core/rnaseq \
+        -r 3.22.2 \
+        -profile docker \
+        --input {samplesheet} \
+        --outdir {outdir} \
+        --genome {genome} \
+        --aligner {aligner} \
+        -resume
+
+outputs:
+  primary:
+    - path: "star_salmon/salmon.merged.gene_counts.tsv"
+      description: "Raw gene counts for DESeq2/edgeR"
+    - path: "star_salmon/salmon.merged.gene_tpm.tsv"
+      description: "TPM normalized expression values"
+    - path: "star_salmon/*.bam"
+      description: "Aligned reads"
+
+  validation:
+    - file: "multiqc/multiqc_report.html"
+      check: exists
+      description: "QC report must exist"
+    - file: "star_salmon/salmon.merged.gene_counts.tsv"
+      check: non_empty
+      description: "Count matrix must have data"
+
+resources:
+  min_memory: "8.GB"
+  recommended_memory: "32.GB"
+  min_cpus: 4
+  recommended_cpus: 8
+  disk_space: "100.GB"
+
+troubleshooting:
+  - error: "STAR index fails"
+    fix: "Increase memory with --max_memory '64.GB' or provide pre-built --star_index"
+  - error: "Low alignment rate"
+    fix: "Verify genome matches species; check FastQC for adapter contamination"
+  - error: "Strandedness detection fails"
+    fix: "Specify explicitly with --strandedness reverse (or forward/unstranded)"

package/content/bio-research/skills/bio-research-nextflow-development/scripts/config/pipelines/sarek.yaml

@@ -0,0 +1,233 @@
+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