Bwa Mem2 Dna Aligner

# Install with conda (recommended)
conda install -c bioconda bwa-mem2 samtools

# Or download pre-compiled binary
wget https://github.com/bwa-mem2/bwa-mem2/releases/download/v2.2.1/bwa-mem2-2.2.1_x64-linux.tar.bz2
tar -jxf bwa-mem2-2.2.1_x64-linux.tar.bz2
export PATH="$PWD/bwa-mem2-2.2.1_x64-linux:$PATH"

# Verify
bwa-mem2 version
# 2.2.1

decisions:
  - id: D1
    param: reference_bundle
    kind: required
    source: user
    ask: "Which species and genome assembly should reads be aligned against?"
    default: null

  - id: D2
    param: read_group
    kind: required
    source: user
    ask: "What sample name and library identity should be stamped into each alignment?"
    default: null

  - id: D3
    param: downstream_compatibility
    kind: derived
    source: upstream
    ask: "Will GATK or Picard consume this BAM, requiring supplementary alignments flagged and soft-clipped?"
    default: "-M -Y when a GATK/Picard step follows"

  - id: D4
    param: seedLength
    kind: optional
    source: user
    ask: "Do these reads need a shorter seed than the default to map sensitively?"
    default: 19

  - id: D5
    param: minAlignmentScore
    kind: optional
    source: user
    ask: "How weak an alignment is still worth reporting?"
    default: 30

  - id: D6
    param: interleavedInput
    kind: derived
    source: data
    ask: "Are both mates held in a single interleaved FASTQ?"
    default: false
    skip_if: "reads supplied as separate R1/R2 files"

  - id: D7
    param: threads
    kind: never_ask
    source: data
    reason: "Affects runtime only, not the alignments"
    default: "min(8, available_cores)"

# 1. Build genome index (~30 min, run once)
bwa-mem2 index GRCh38.fa

# 2. Align paired-end reads and sort
bwa-mem2 mem -t 16 -R "@RG\tID:sample1\tSM:sample1\tPL:ILLUMINA" \
    GRCh38.fa sample1_R1.fastq.gz sample1_R2.fastq.gz \
    | samtools sort -@ 8 -o sample1.sorted.bam

# 3. Index the BAM
samtools index sample1.sorted.bam
echo "Aligned reads: $(samtools view -c -F 4 sample1.sorted.bam)"

# Download GRCh38 primary assembly (human)
wget https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/001/405/GCA_000001405.15_GRCh38/seqs_for_alignment_pipelines.ucsc_ids/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.gz
gunzip GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.gz
mv GCA_000001405.15_GRCh38_no_alt_analysis_set.fna GRCh38.fa

# Or use ENSEMBL/GENCODE
wget https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_47/GRCh38.primary_assembly.genome.fa.gz
gunzip GRCh38.primary_assembly.genome.fa.gz

echo "Reference size: $(du -sh GRCh38.fa)"

# Build index (~28 GB RAM required for human genome)
bwa-mem2 index GRCh38.fa

# This creates: GRCh38.fa.0123, GRCh38.fa.amb, GRCh38.fa.ann,
#               GRCh38.fa.bwt.2bit.64, GRCh38.fa.pac
echo "Index files: $(ls GRCh38.fa.* | wc -l) created"
ls -lh GRCh38.fa.*

# Align with read group (required for GATK)
# @RG fields: ID (run ID), SM (sample name), PL (platform), LB (library), PU (flowcell)
bwa-mem2 mem \
    -t 16 \
    -R "@RG\tID:sample1_run1\tSM:sample1\tPL:ILLUMINA\tLB:lib1\tPU:flowcell1" \
    GRCh38.fa \
    sample1_R1.fastq.gz \
    sample1_R2.fastq.gz \
    | samtools sort -@ 8 -m 2G -o sample1.sorted.bam

samtools index sample1.sorted.bam
echo "Alignment complete."
echo "Total reads:   $(samtools view -c sample1.sorted.bam)"
echo "Mapped reads:  $(samtools view -c -F 4 sample1.sorted.bam)"

# Option A: samtools markdup (fast)
samtools fixmate -m sample1.sorted.bam sample1.fixmate.bam
samtools sort -@ 8 -o sample1.fixmate.sorted.bam sample1.fixmate.bam
samtools markdup -@ 8 sample1.fixmate.sorted.bam sample1.markdup.bam
samtools index sample1.markdup.bam

echo "Duplication rate:"
samtools flagstat sample1.markdup.bam | grep "duplicate"

# Option B: Picard MarkDuplicates (GATK best practices)
picard MarkDuplicates \
    INPUT=sample1.sorted.bam \
    OUTPUT=sample1.markdup.bam \
    METRICS_FILE=sample1.dupmetrics.txt \
    REMOVE_DUPLICATES=false \
    CREATE_INDEX=true
cat sample1.dupmetrics.txt | grep -A2 "ESTIMATED"

# Full alignment statistics
samtools flagstat sample1.markdup.bam > sample1.flagstat.txt
cat sample1.flagstat.txt

# Coverage statistics
samtools coverage sample1.markdup.bam | head -30

# Parse key metrics with Python
python3 - << 'EOF'
from pathlib import Path

flagstat = Path("sample1.flagstat.txt").read_text()
for line in flagstat.splitlines():
    if any(kw in line for kw in ["total", "mapped", "properly paired", "duplicate"]):
        print(line)
EOF

#!/bin/bash
# Complete WGS alignment → variant calling pipeline
GENOME="GRCh38.fa"
SAMPLE="sample1"
R1="data/${SAMPLE}_R1.fastq.gz"
R2="data/${SAMPLE}_R2.fastq.gz"
THREADS=16
OUTDIR="results/${SAMPLE}"
mkdir -p "$OUTDIR"

# Step 1: Align + sort
bwa-mem2 mem -t $THREADS \
    -R "@RG\tID:${SAMPLE}\tSM:${SAMPLE}\tPL:ILLUMINA\tLB:lib1\tPU:run1" \
    $GENOME $R1 $R2 \
    | samtools sort -@ 8 -o $OUTDIR/${SAMPLE}.sorted.bam
samtools index $OUTDIR/${SAMPLE}.sorted.bam

# Step 2: Mark duplicates
samtools fixmate -m $OUTDIR/${SAMPLE}.sorted.bam - \
    | samtools sort -@ 8 \
    | samtools markdup -@ 8 - $OUTDIR/${SAMPLE}.markdup.bam
samtools index $OUTDIR/${SAMPLE}.markdup.bam

# Step 3: GATK variant calling
gatk HaplotypeCaller \
    -R $GENOME \
    -I $OUTDIR/${SAMPLE}.markdup.bam \
    -O $OUTDIR/${SAMPLE}.g.vcf.gz \
    -ERC GVCF \
    --native-pair-hmm-threads 4

echo "Pipeline complete: $OUTDIR/${SAMPLE}.g.vcf.gz"