#!/bin/bash -Ceuo pipefail
INDEX=`find -L ./ -name "*.amb" | sed 's/\.amb$//'`

export bwt_max_mem=112G

sentieon bwa mem \
    -K 100000000 -Y -R '@RG\tID:20260529_LH00995_0049_B23YT2HLT4.SH032_HG514.L007\tPU:L007\tSM:SH032_HG514\tLB:SH032_HG514\tDS:s3://natera-platform-sandbox/pipeline-resources/ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.fasta\tPL:ILLUMINA' \
    -t 31 \
    $INDEX \
    0003.SH032_HG514_R1.fastq.gz 0003.SH032_HG514_R2.fastq.gz \
    | sentieon util sort \
        -r Homo_sapiens_assembly38.fasta \
        -t 31 \
        -o SH032_HG514.bam \
        --sam2bam \
        -

# When outputting CRAM, sentieon util sort may create a spurious .bai index.
# Remove it since CRAM uses .crai indices.
if [ "bam" = "cram" ] && [ -f "SH032_HG514.cram.bai" ]; then
    rm -f SH032_HG514.cram.bai
fi

cat <<-END_VERSIONS > versions.yml
"DAQ:SENTIEON_BWAMEM":
    sentieon: $(echo $(sentieon driver --version 2>&1) | sed -e "s/sentieon-genomics-//g")
END_VERSIONS