Multiqc Qc Reports

pip install multiqc

# Verify
multiqc --version
# MultiQC v1.25.0

# With conda (recommended for bioinformatics)
conda install -c bioconda multiqc

decisions:
  - id: D1
    param: searchScope
    kind: required
    source: data
    ask: "Which directories should be scanned, and are there old or partial runs in them that must be excluded?"
    default: "the pipeline output root, with no exclusions"

  - id: D2
    param: sampleNameCleaning
    kind: required
    source: data
    ask: "Do the discovered sample names collapse correctly, or do suffixes from different tools split one sample into several rows?"
    default: "built-in extension stripping; verify the resulting sample list"

  - id: D3
    param: moduleFilter
    kind: optional
    source: user
    ask: "Report on every tool found, or only some?"
    default: "all modules detected"

  - id: D4
    param: exportData
    kind: optional_conditional
    source: upstream
    ask: "Should the parsed metrics be written as flat tables for a later programmatic QC gate?"
    default: "HTML report only"

# FastQC on all FASTQ files
mkdir -p qc/fastqc
fastqc data/*.fastq.gz -o qc/fastqc/ -t 8

# samtools flagstat on all BAM files
for bam in results/*.bam; do
    samtools flagstat $bam > qc/$(basename $bam .bam).flagstat
done
echo "QC files generated: $(ls qc/ | wc -l)"

# Basic run: scan current directory recursively
multiqc .

# Specify output directory and report name
multiqc . -o reports/ -n project_qc_report

# Scan specific subdirectories only
multiqc qc/fastqc/ results/star/ logs/trimming/ -o reports/

# Output: reports/project_qc_report.html
echo "Report: reports/project_qc_report.html"

# multiqc_config.yaml — place in working directory
title: "RNA-seq QC Report — Project X"
subtitle: "Analysis date: 2026-02"
intro_text: "Quality control summary for all 48 samples."

# Sample name cleaning: remove path prefixes and suffixes
fn_clean_exts:
  - ".fastq.gz"
  - "_R1"
  - ".sorted"

# Thresholds for pass/warn/fail coloring
general_stats_addcols:
  FastQC:
    pct_duplication:
      max: 40
      warn: 30

# Module run order
module_order:
  - fastqc
  - trimgalore
  - star
  - featurecounts
  - samtools

# Run with config file
multiqc . --config multiqc_config.yaml -o reports/

# Run only specific modules
multiqc . --module fastqc --module samtools

# Exclude specific modules
multiqc . --exclude fastqc

# Include only files matching a pattern
multiqc . --filename "*.flagstat" --filename "*_fastqc.zip"

# Ignore specific directories or files
multiqc . --ignore "tmp/" --ignore "*.bam"

# Add sample name regex substitution
multiqc . --replace-names "sample_" ""

# Export data tables (CSV, JSON, YAML, TSV)
multiqc . -o reports/ --data-format json
# Generates: reports/multiqc_data/multiqc_data.json

# Export flat CSV tables per tool
multiqc . -o reports/ --export
ls reports/multiqc_data/
# multiqc_fastqc.txt, multiqc_samtools_stats.txt, ...

# Extract general stats as pandas DataFrame
python3 - << 'EOF'
import json
import pandas as pd
with open("reports/multiqc_data/multiqc_general_stats.json") as f:
    data = json.load(f)
df = pd.DataFrame(data).T
print(df.head())
print(f"Shape: {df.shape}")
EOF

#!/bin/bash
# Complete RNA-seq QC pipeline → MultiQC summary
SAMPLES=(ctrl_rep1 ctrl_rep2 treat_rep1 treat_rep2)
OUTDIR="pipeline_output"
mkdir -p $OUTDIR/{fastqc,star,featurecounts,flagstat}

for sample in "${SAMPLES[@]}"; do
    # FastQC
    fastqc data/${sample}.fastq.gz -o $OUTDIR/fastqc/ -t 4
    # STAR alignment
    STAR --runThreadN 8 --genomeDir refs/star_index \
         --readFilesIn data/${sample}.fastq.gz \
         --outSAMtype BAM SortedByCoordinate \
         --outFileNamePrefix $OUTDIR/star/${sample}/
    # samtools flagstat
    samtools flagstat $OUTDIR/star/${sample}/Aligned.sortedByCoord.out.bam \
        > $OUTDIR/flagstat/${sample}.flagstat
done

# Final MultiQC report
multiqc $OUTDIR/ -o $OUTDIR/qc_report/ -n "full_pipeline_qc"
echo "Report ready: $OUTDIR/qc_report/full_pipeline_qc.html"