DRAGEN Recipe - Germline WGS
This recipe is for processing whole genome sequencing data for germline workflows.
For most scenarios, simply creating the union of the command line options from the single caller scenarios will work.
The following are partial templates that can be used as starting points. Adjust them accordingly for your specific use case.
#!/bin/bash
set -euo pipefail
# Path to DRAGEN hashtable
DRAGEN_HASH_TABLE=<REF_DIR>
# Path to output directory for the DRAGEN run
OUTPUT=<OUT_DIR>
# File prefix for DRAGEN output files
PREFIX=<OUT_PREFIX>
# Define the input sources, select fastq list, fastq, bam, or cram.
INPUT_FASTQ_LIST="
--fastq-list $FASTQ_LIST \
--fastq-list-sample-id $FASTQ_LIST_SAMPLE_ID \
"
INPUT_FASTQ="
--fastq-file1 $FASTQ1 \
--fastq-file2 $FASTQ2 \
--RGSM $RGSM \
--RGID $RGID \
"
INPUT_BAM="
--bam-input $BAM \
"
INPUT_CRAM="
--cram-input $CRAM \
"
# Select input source, here in this example we use INPUT_FASTQ_LIST
INPUT_OPTIONS="
--ref-dir $DRAGEN_HASH_TABLE \
$INPUT_FASTQ_LIST \
"
OUTPUT_OPTIONS="
--output-directory $OUTPUT \
--output-file-prefix $PREFIX \
"
MA_OPTIONS="
--enable-map-align true \
--enable-sort true \
--enable-duplicate-marking true \
"
CNV_OPTIONS="
--enable-cnv true \
--cnv-enable-self-normalization true \
"
SNV_OPTIONS="
--enable-variant-caller true \
"
SV_OPTIONS="
--enable-sv true \
"
TARGETED_OPTIONS="
--enable-targeted true \
"
PGX_OPTIONS="
--enable-pgx true \
"
STR_OPTIONS="
--repeat-genotype-enable true \
"
# Automatic merging of VNTR calls into SV VCF disabled with the second option
# See the VNTR calling page for more details
VNTR_OPTIONS="
--enable-vntr true \
--sv-vntr-merge false \
"
HLA_OPTIONS="
--enable-hla=true \
--hla-enable-class-2=true \
"
# Construct final command line
CMD="
dragen \
$INPUT_OPTIONS \
$OUTPUT_OPTIONS \
$MA_OPTIONS \
$CNV_OPTIONS \
$SNV_OPTIONS \
$SV_OPTIONS \
$TARGETED_OPTIONS \
$PGX_OPTIONS \
$STR_OPTIONS \
$VNTR_OPTIONS \
$HLA_OPTIONS \
"
# Execute
echo $CMD
bash -c $CMD
Additional Notes and Options