#!/bin/bash -euo pipefail
gatk --java-options "-Xmx60620M -XX:-UsePerfData -XX:ParallelGCThreads=2" \
    MarkDuplicates \
    --INPUT dna_s760.Aligned.sortedByCoord.out.bam \
    --OUTPUT dna_s760.md.bam \
    --METRICS_FILE dna_s760.md.bam.metrics \
    --TMP_DIR . \
    --CREATE_INDEX true \
    --REFERENCE_SEQUENCE ref_genome.fa \
    -REMOVE_DUPLICATES false -VALIDATION_STRINGENCY LENIENT

# If cram files are wished as output, the run samtools for conversion
if [[ dna_s760.md.bam == *.cram ]]; then
    samtools view -Ch -T ref_genome.fa -o dna_s760.md.bam dna_s760.md.bam
    rm dna_s760.md.bam
    samtools index dna_s760.md.bam
fi

cat <<-END_VERSIONS > versions.yml
"NFCORE_RNAFUSION:RNAFUSION:QC_WORKFLOW:GATK4_MARKDUPLICATES":
    gatk4: $(echo $(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*$//')
    samtools: $(echo $(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*$//')
END_VERSIONS