Downloading: s3://natera-platform-sandbox/pipeline-resources/AIH/rna/GRCh38/starfusion/ctat_genome_lib_build_dir/ref_genome.fa
  Downloading: s3://natera-platform-sandbox/pipeline-resources/Homo_sapiens_assembly38.dbsnp138.vcf.gz
  Downloading: s3://natera-rnd-pltf-dev-nextflow-scratch-01/work/b3/fe0e6f0b46b136ba5ae57554247de3/.command.sh
  Downloading: s3://natera-rnd-pltf-dev-nextflow-scratch-01/work/ed/8d0d96a6ef1dae44f84274179cfa2d/rna_s1221_S42.md.bam
  Downloading: s3://natera-platform-sandbox/pipeline-resources/AIH/rna/GRCh38/starfusion/ctat_genome_lib_build_dir/ref_genome.dict
  Downloading: s3://natera-rnd-pltf-dev-nextflow-scratch-01/work/ed/8d0d96a6ef1dae44f84274179cfa2d/rna_s1221_S42.md.bai
  Downloading: s3://natera-platform-sandbox/pipeline-resources/AIH/rna/GRCh38/gatk4/dbsnp_hg38_contam_sites.bed
  Downloading: s3://natera-rnd-pltf-dev-nextflow-scratch-01/work/b3/fe0e6f0b46b136ba5ae57554247de3/.command.run
  Downloading: s3://natera-platform-sandbox/pipeline-resources/AIH/rna/GRCh38/starfusion/ctat_genome_lib_build_dir/ref_genome.fa.fai
  Downloading: s3://natera-platform-sandbox/pipeline-resources/beds/twist/Twist_rna_exome_AND_fusion_hg38.bed
  Downloading: s3://natera-platform-sandbox/pipeline-resources/Homo_sapiens_assembly38.dbsnp138.vcf.gz.tbi
==> STAGING COMPLETE (11 inputs)

+ mkdir rna_s1221_S42
+ all_qc -bam rna_s1221_S42.md.bam -beds Twist_rna_exome_AND_fusion_hg38.bed -dbsnp_vcf Homo_sapiens_assembly38.dbsnp138.vcf.gz -contamination_bed dbsnp_hg38_contam_sites.bed -output_folder rna_s1221_S42 -reference ref_genome.fa -region chr20
mkdir -p rna_s1221_S42/rna_s1221_S42.md/


cat Twist_rna_exome_AND_fusion_hg38.bed | cut -f 1-3 | bedtools sort -g ref_genome.fa.fai | bedtools merge > rna_s1221_S42/rna_s1221_S42.md/full_bed.bed


seqtool depth -bam rna_s1221_S42.md.bam -bed rna_s1221_S42/rna_s1221_S42.md/full_bed.bed -threads 4 -bam_threads 2 | bgzip -c > rna_s1221_S42/rna_s1221_S42.md/rna_s1221_S42.md.depth.gz
saturation_plot       -bams rna_s1221_S42.md.bam       -region chr20       -output rna_s1221_S42/rna_s1221_S42.md/saturation_plot.png       -threads 1 
seqtool saturation_metric       -at 1000000       -region chr20       -bam_threads 1       rna_s1221_S42.md.bam > rna_s1221_S42/rna_s1221_S42.md/saturation_qc.tsv 
fragment_size       -bams rna_s1221_S42.md.bam       -region chr20       -output_prefix rna_s1221_S42/rna_s1221_S42.md/fragsize       -threads 1 
samtools mpileup   -B --min-MQ 60 --min-BQ 30    -f ref_genome.fa   -l dbsnp_hg38_contam_sites.bed   rna_s1221_S42.md.bam > rna_s1221_S42.md.mpileup && contamination -input rna_s1221_S42.md.mpileup -dbsnp_vcf Homo_sapiens_assembly38.dbsnp138.vcf.gz > rna_s1221_S42/rna_s1221_S42.md/contamination.tsv 
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[mpileup] 1 samples in 1 input files
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
/opt/conda/lib/python3.9/site-packages/pyranges/__init__.py:8: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
  import pkg_resources
/opt/conda/lib/python3.9/site-packages/pyranges/__init__.py:8: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
  import pkg_resources


[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai

0it [00:00, ?it/s][W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai

153541it [00:00, 1534994.26it/s]
320738it [00:00, 1615528.43it/s][W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai

460613it [00:00, 1627554.34it/s]
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai




[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai


tabix -s 1 -b 2 -e 2 rna_s1221_S42/rna_s1221_S42.md/rna_s1221_S42.md.depth.gz


seqtool depth_hist     -nbins 500     rna_s1221_S42/rna_s1221_S42.md/rna_s1221_S42.md.depth.gz     > rna_s1221_S42/rna_s1221_S42.md/rna_s1221_S42.md.depth_hist.tsv


cat rna_s1221_S42/rna_s1221_S42.md/rna_s1221_S42.md.depth_hist.tsv | plot         -x 0         -xlabel Depth -ylabel "Number of Sites"         -xlim 0 2000         -title rna_s1221_S42.md         -output rna_s1221_S42/rna_s1221_S42.md/rna_s1221_S42.md.depth.png


[W::hts_idx_load3] The index file is older than the data file: Homo_sapiens_assembly38.dbsnp138.vcf.gz.tbi


seqtool read_qc    -bed Twist_rna_exome_AND_fusion_hg38.bed     -n_threads 1     -bam_threads 2     rna_s1221_S42.md.bam > rna_s1221_S42/rna_s1221_S42.md/read_qc.Twist_rna_exome_AND_fusion_hg38.bed.tsv
seqtool reads_per_target     -bed Twist_rna_exome_AND_fusion_hg38.bed     -threads 1     -bam_threads 2     rna_s1221_S42.md.bam > rna_s1221_S42/rna_s1221_S42.md/reads_per_target.Twist_rna_exome_AND_fusion_hg38.bed.tsv 
seqtool depth_stats  -bed Twist_rna_exome_AND_fusion_hg38.bed  rna_s1221_S42/rna_s1221_S42.md/rna_s1221_S42.md.depth.gz> rna_s1221_S42/rna_s1221_S42.md/depth_stats.Twist_rna_exome_AND_fusion_hg38.bed.tsv 
seqtool gc_bias  -reference ref_genome.fa  -bed Twist_rna_exome_AND_fusion_hg38.bed  -bin_size 0.05  -threads 1  -bam_threads 2  rna_s1221_S42.md.bam  > rna_s1221_S42/rna_s1221_S42.md/gc_bias_qc.Twist_rna_exome_AND_fusion_hg38.bed.tsv 
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai
[W::hts_idx_load3] The index file is older than the data file: rna_s1221_S42.md.bai




cat rna_s1221_S42/rna_s1221_S42.md/gc_bias_qc.Twist_rna_exome_AND_fusion_hg38.bed.tsv  | plot -x 0  -header infer  -ylim 0 2  -title "rna_s1221_S42.md" -suptitle "Twist_rna_exome_AND_fusion_hg38.bed" -output "rna_s1221_S42/rna_s1221_S42.md/gc_bias.Twist_rna_exome_AND_fusion_hg38.bed.png"  -ylabel "Fold enrichment / depletion"  -xlabel "GC Quantile" 






echo `date` > rna_s1221_S42/rna_s1221_S42.md/qc_complete.txt


+ merge_qc -folders rna_s1221_S42/rna_s1221_S42.md -output rna_s1221_S42/rna_s1221_S42_full_basic_stats.tsv
+ head -n1 rna_s1221_S42/rna_s1221_S42_full_basic_stats.tsv
++ basename Twist_rna_exome_AND_fusion_hg38.bed
+ grep -e Twist_rna_exome_AND_fusion_hg38.bed rna_s1221_S42/rna_s1221_S42_full_basic_stats.tsv