Deeptools Ngs Analysis

pip install deeptools
# Verify installation
bamCoverage --version

decisions:
  - id: D1
    param: normalizationMethod
    kind: required
    source: user
    ask: "How should coverage be scaled so tracks from different samples can be compared - by read depth, by genome coverage, or not at all?"
    default: "none - raw coverage, comparable only within one sample"

  - id: D2
    param: effectiveGenomeSize
    kind: derived
    source: upstream
    depends_on: [D1]
    ask: "Which assembly's mappable size should the coverage normalization use?"
    default: "looked up for the alignment reference"
    skip_if: "normalization does not require a genome size"

  - id: D3
    param: readExtension
    kind: required
    source: user
    ask: "Should reads be extended to the sequenced fragment length? Correct for ChIP and ATAC, wrong for spliced RNA."
    default: "not extended"

  - id: D4
    param: duplicateHandling
    kind: required
    source: user
    ask: "Should reads flagged as duplicates be ignored when building coverage?"
    default: "included"

  - id: D5
    param: mappingQualityFloor
    kind: required
    source: user
    ask: "Below what mapping confidence should reads be excluded from the signal?"
    default: "no filter"

  - id: D6
    param: binSize
    kind: optional
    source: user
    ask: "At what resolution should signal be summarized?"
    default: "50 bp"

  - id: D7
    param: comparisonOperation
    kind: optional
    source: user
    ask: "When comparing two samples, should the track hold a log ratio, a plain ratio, or a difference?"
    default: "log2 ratio"

  - id: D8
    param: profileAnchor
    kind: optional
    source: user
    ask: "Should profiles be anchored on feature starts, ends, centres, or scaled across whole features?"
    default: "feature start, 500 bp either side"

  - id: D9
    param: processors
    kind: never_ask
    source: data
    reason: "Affects runtime only, not the signal"
    default: "min(8, available_cores)"

# Convert BAM to normalized bigWig
bamCoverage --bam sample.bam --outFileName sample.bw \
    --normalizeUsing RPGC --effectiveGenomeSize 2913022398 \
    --binSize 10 --numberOfProcessors 8

# Create heatmap around TSS
computeMatrix reference-point -S sample.bw -R genes.bed \
    -b 3000 -a 3000 --referencePoint TSS -o matrix.gz
plotHeatmap -m matrix.gz -o heatmap.png --colorMap RdBu

# Basic conversion with RPGC normalization
bamCoverage --bam input.bam --outFileName output.bw \
    --normalizeUsing RPGC --effectiveGenomeSize 2913022398 \
    --binSize 10 --numberOfProcessors 8 \
    --extendReads 200 --ignoreDuplicates

# CPM normalization (simpler, no genome size needed)
bamCoverage --bam input.bam --outFileName output.bw \
    --normalizeUsing CPM --binSize 10 -p 8

# RNA-seq: strand-specific coverage
bamCoverage --bam rnaseq.bam --outFileName forward.bw \
    --filterRNAstrand forward --normalizeUsing CPM -p 8
# IMPORTANT: Never use --extendReads for RNA-seq (spans splice junctions)

# Log2 ratio: treatment / control
bamCompare -b1 treatment.bam -b2 control.bam -o log2ratio.bw \
    --operation log2 --scaleFactorsMethod readCount \
    --extendReads 200 -p 8

# Subtract control from treatment
bamCompare -b1 treatment.bam -b2 control.bam -o subtract.bw \
    --operation subtract --scaleFactorsMethod readCount

# Sample correlation heatmap
multiBamSummary bins --bamfiles rep1.bam rep2.bam rep3.bam \
    -o counts.npz --binSize 10000 -p 8
plotCorrelation -in counts.npz --corMethod pearson \
    --whatToShow heatmap -o correlation.png
# Good: replicates cluster with r > 0.9

# PCA of samples
plotPCA -in counts.npz -o pca.png --plotTitle "Sample PCA"

# ChIP enrichment fingerprint
plotFingerprint -b input.bam chip.bam -o fingerprint.png \
    --extendReads 200 --ignoreDuplicates
# Good ChIP: steep rise curve; flat diagonal = poor enrichment

# Coverage depth assessment
plotCoverage -b sample.bam -o coverage.png --ignoreDuplicates -p 8

# Fragment size distribution (paired-end)
bamPEFragmentSize -b sample.bam -o fragsize.png

# Reference-point mode: signal around TSS
computeMatrix reference-point -S chip.bw -R genes.bed \
    -b 3000 -a 3000 --referencePoint TSS -o matrix.gz -p 8

# Scale-regions mode: signal across gene bodies
computeMatrix scale-regions -S chip.bw -R genes.bed \
    -b 1000 -a 1000 --regionBodyLength 5000 -o matrix.gz -p 8

# Generate heatmap
plotHeatmap -m matrix.gz -o heatmap.png \
    --colorMap RdBu --kmeans 3 --sortUsing mean

# Generate profile plot
plotProfile -m matrix.gz -o profile.png \
    --plotType lines --colors blue red

# Multiple signal files: compare marks
computeMatrix reference-point -S h3k4me3.bw h3k27me3.bw -R genes.bed \
    -b 3000 -a 3000 --referencePoint TSS -o multi_matrix.gz
plotHeatmap -m multi_matrix.gz -o multi_heatmap.png

# Filter by mapping quality and fragment size
alignmentSieve --bam input.bam --outFile filtered.bam \
    --minMappingQuality 10 --minFragmentLength 150 \
    --maxFragmentLength 700

# ATAC-seq: apply Tn5 offset correction (+4/-5 bp shift)
alignmentSieve --bam atac.bam --outFile shifted.bam --ATACshift
# Then index: samtools index shifted.bam

# GC bias correction (only if significant bias detected)
computeGCBias -b input.bam --effectiveGenomeSize 2913022398 \
    -g genome.2bit --GCbiasFrequenciesFile gc_freq.txt -p 8
correctGCBias -b input.bam --effectiveGenomeSize 2913022398 \
    --GCbiasFrequenciesFile gc_freq.txt -o corrected.bam

# Signal enrichment at peak regions
plotEnrichment -b chip.bam input.bam --BED peaks.bed \
    -o enrichment.png --ignoreDuplicates -p 8

#!/bin/bash
# Complete ChIP-seq QC + visualization pipeline
CHIP="chip.bam"
INPUT="input.bam"
GENES="genes.bed"
PEAKS="peaks.bed"
GSIZE=2913022398
THREADS=8

# 1. QC: sample correlation
multiBamSummary bins --bamfiles $INPUT $CHIP -o summary.npz -p $THREADS
plotCorrelation -in summary.npz --corMethod pearson --whatToShow heatmap -o correlation.png

# 2. QC: enrichment fingerprint
plotFingerprint -b $INPUT $CHIP -o fingerprint.png --extendReads 200 --ignoreDuplicates

# 3. Convert to normalized bigWig
bamCoverage --bam $CHIP --outFileName chip.bw --normalizeUsing RPGC \
    --effectiveGenomeSize $GSIZE --extendReads 200 --ignoreDuplicates -p $THREADS

# 4. Log2 ratio track
bamCompare -b1 $CHIP -b2 $INPUT -o log2ratio.bw --operation log2 \
    --scaleFactorsMethod readCount --extendReads 200 -p $THREADS

# 5. Heatmap at TSS
computeMatrix reference-point -S chip.bw log2ratio.bw -R $GENES \
    -b 3000 -a 3000 --referencePoint TSS -o tss_matrix.gz -p $THREADS
plotHeatmap -m tss_matrix.gz -o tss_heatmap.png --colorMap RdBu --kmeans 3

# 6. Profile at peaks
computeMatrix reference-point -S chip.bw -R $PEAKS \
    -b 2000 -a 2000 -o peak_matrix.gz -p $THREADS
plotProfile -m peak_matrix.gz -o peak_profile.png

#!/bin/bash
ATAC="atac.bam"
PEAKS="atac_peaks.bed"
GSIZE=2913022398
THREADS=8

# 1. Apply Tn5 offset correction (+4/-5 bp)
alignmentSieve --bam $ATAC --outFile shifted.bam --ATACshift -p $THREADS
samtools index shifted.bam

# 2. Generate RPGC-normalized coverage
bamCoverage --bam shifted.bam --outFileName atac.bw \
    --normalizeUsing RPGC --effectiveGenomeSize $GSIZE \
    --binSize 5 --extendReads -p $THREADS

# 3. Check nucleosome periodicity (expect 200bp/400bp peaks)
bamPEFragmentSize -b shifted.bam -o fragsize.png \
    --maxFragmentLength 1000 --binSize 1

# 4. Heatmap at ATAC peaks
computeMatrix reference-point -S atac.bw -R $PEAKS \
    -b 2000 -a 2000 -o atac_matrix.gz -p $THREADS
plotHeatmap -m atac_matrix.gz -o atac_heatmap.png --colorMap Blues --kmeans 2