task pathseq { String sample_id File fastq1 File fastq2 File host_image File host_kmer File microbe_dict File microbe_bwa_image File microbe_taxonomy String disk_size String docker String cluster command <<< set -o pipefail set -e mkdir ubam mkdir filter_log mkdir clean_pair_bam mkdir clean_unpaired_bam mkdir pathseq_result mkdir bwa_pair_bam mkdir bwa_pair_unpair_bam gatk FastqToSam \ -F1 ${fastq1} \ -F2 ${fastq2} \ -O ./ubam/${sample_id}.bam \ -SM ${sample_id} time gatk --java-options "-Xmx58g" PathSeqFilterSpark \ --input ./ubam/${sample_id}.bam \ --paired-output ./clean_pair_bam/${sample_id}_paired.bam \ --unpaired-output ./clean_unpaired_bam/${sample_id}_unpaired.bam \ --min-clipped-read-length 70 \ --kmer-file ${host_kmer} \ --filter-bwa-image ${host_image} \ --filter-metrics filter_log/${sample_id}.log time gatk --java-options "-Xmx58g" PathSeqBwaSpark \ --paired-input ./clean_pair_bam/${sample_id}_paired.bam \ --unpaired-input ./clean_unpaired_bam/${sample_id}_unpaired.bam \ --paired-output bwa_pair_bam/${sample_id}_bwa_paired.bam \ --unpaired-output bwa_unpair_bam/${sample_id}_bwa_unpaired.bam \ --microbe-bwa-image ${microbe_bwa_image} \ --microbe-dict ${microbe_dict} time gatk --java-options "-Xmx58g" PathSeqScoreSpark \ --paired-input bwa_pair_bam/${sample_id}_bwa_paired.bam \ --unpaired-input bwa_unpair_bam/${sample_id}_bwa_unpaired.bam \ --taxonomy-file ${microbe_taxonomy} \ --scores-output pathseq_result/${sample_id}.pathseq.txt \ --output pathseq_result/${sample_id}.pathseq_reads.bam \ --min-score-identity 0.90 \ --identity-margin 0.02 >>> runtime { docker: docker cluster: cluster systemDisk: "cloud_ssd 40" dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/" } output { File pathseq_txt = "pathseq_result/${sample_id}.pathseq.txt" File pathseq_bam = "pathseq_result/${sample_id}.pathseq_reads.bam" File pathseq_sbi = "pathseq_result/${sample_id}.pathseq_reads.bam.sbi" } }