From 5ca32e136a350cb860132a0026516fd09eceeff8 Mon Sep 17 00:00:00 2001 From: Jemma Nelson Date: Tue, 21 Mar 2023 10:47:26 -0700 Subject: [PATCH] STAR v1.2: Remove anaquin from pipeline --- README.md | 1 - .../aggregation/cufflinks_featurecounts.nf | 38 +++++++++---------- .../aggregation/cufflinks_featurecounts.sh | 2 +- scripts/rna-star/aggregate/concat_metrics.sh | 19 ---------- scripts/rna-star/aggregate/reset.bash | 5 --- scripts/versions.bash | 7 +--- 6 files changed, 20 insertions(+), 52 deletions(-) diff --git a/README.md b/README.md index e60ee441..ea517519 100644 --- a/README.md +++ b/README.md @@ -19,7 +19,6 @@ Modules The current modules to load for working the pipeline are: -* `anaquin/2.0.1` * `bcl2fastq/1.8.4` * `bcl2fastq2/2.15.0.4` * `bedops/2.4.35-typical` diff --git a/processes/rna-star/aggregation/cufflinks_featurecounts.nf b/processes/rna-star/aggregation/cufflinks_featurecounts.nf index a7506ae5..0f82e94a 100644 --- a/processes/rna-star/aggregation/cufflinks_featurecounts.nf +++ b/processes/rna-star/aggregation/cufflinks_featurecounts.nf @@ -67,7 +67,7 @@ workflow RNA_AGG { kallisto(fastq, kallisto_index, sequins_iso_mix) kallisto_advanced(fastq, kallisto_index, sequins_iso_mix) - anaquin(bam_to_use, sequins_ref, kallisto_index, neat_mix_A, sequins_iso_mix) + // anaquin(bam_to_use, sequins_ref, kallisto_index, neat_mix_A, sequins_iso_mix) // QC Metrics insert_sizes(bam_to_use) @@ -276,7 +276,7 @@ process density { process cufflinks { publishDir params.outdir, mode: params.publishmode - module "cufflinks/2.2.1", "R/3.2.5", "anaquin/2.0.1" + module "cufflinks/2.2.1", "R/3.2.5" input: path input_bam @@ -285,7 +285,7 @@ process cufflinks { output: - tuple path("genes.fpkm_tracking"), path("isoforms.fpkm_tracking"), path("anaquin_cufflinks/*") + tuple path("genes.fpkm_tracking"), path("isoforms.fpkm_tracking") path "skipped.gtf" path "transcripts.gtf" @@ -304,11 +304,11 @@ process cufflinks { mv genes.fpkm_tracking.sort genes.fpkm_tracking mv isoforms.fpkm_tracking.sort isoforms.fpkm_tracking - # quantification with anaquin Rna Expression - anaquin RnaExpression -o anaquin_cufflinks -rmix "$sequins_iso_mix" -usequin transcripts.gtf -mix A \ - || (echo "NA" > anaquin_cufflinks/RnaExpression_genes.tsv \ - && echo "NA" > anaquin_cufflinks/RnaExpression_isoforms.tsv \ - && echo "NA" > anaquin_cufflinks/RnaExpression_summary.stats) + # # quantification with anaquin Rna Expression + # anaquin RnaExpression -o anaquin_cufflinks -rmix "$sequins_iso_mix" -usequin transcripts.gtf -mix A \ + # || (echo "NA" > anaquin_cufflinks/RnaExpression_genes.tsv \ + # && echo "NA" > anaquin_cufflinks/RnaExpression_isoforms.tsv \ + # && echo "NA" > anaquin_cufflinks/RnaExpression_summary.stats) """ } @@ -359,7 +359,7 @@ process feature_counts { process kallisto { publishDir params.outdir, mode: params.publishmode - module "kallisto/0.43.1", "anaquin/2.0.1" + module "kallisto/0.43.1" input: tuple path(r1_fq), path(r2_fq) @@ -367,7 +367,6 @@ process kallisto { path sequins_iso_mix output: - path "anaquin_kallisto/*" path "kallisto_output/*" path "kallisto.log" @@ -375,17 +374,17 @@ process kallisto { """ kallisto quant -i "${kallisto_index}" -o kallisto_output "${r1_fq}" "${r2_fq}" 2> kallisto.log - anaquin RnaExpression -o anaquin_kallisto -rmix "${sequins_iso_mix}" -usequin kallisto_output/abundance.tsv -mix A \ - || (echo "NA" > anaquin_kallisto/RnaExpression_genes.tsv \ - && echo "NA" > anaquin_kallisto/RnaExpression_isoforms.tsv \ - && echo "NA" > anaquin_kallisto/RnaExpression_summary.stats) + #anaquin RnaExpression -o anaquin_kallisto -rmix "${sequins_iso_mix}" -usequin kallisto_output/abundance.tsv -mix A \ + #|| (echo "NA" > anaquin_kallisto/RnaExpression_genes.tsv \ + # && echo "NA" > anaquin_kallisto/RnaExpression_isoforms.tsv \ + # && echo "NA" > anaquin_kallisto/RnaExpression_summary.stats) """ } process kallisto_advanced { publishDir params.outdir, mode: params.publishmode - module "kallisto/0.43.1", "anaquin/2.0.1" + module "kallisto/0.43.1" input: tuple path(r1_fq), path(r2_fq) @@ -393,7 +392,6 @@ process kallisto_advanced { path sequins_iso_mix output: - path "anaquin_kallisto_adv/*" path "kallisto_output_adv/*" path "kallisto_adv.log" @@ -401,10 +399,10 @@ process kallisto_advanced { """ kallisto quant --bias -b 100 --rf-stranded -i "${kallisto_index}" -o kallisto_output_adv "${r1_fq}" "${r2_fq}" 2> kallisto_adv.log - anaquin RnaExpression -o anaquin_kallisto_adv -rmix "${sequins_iso_mix}" -usequin kallisto_output_adv/abundance.tsv -mix A \ - || (echo "NA" > anaquin_kallisto_adv/RnaExpression_genes.tsv \ - && echo "NA" > anaquin_kallisto_adv/RnaExpression_isoforms.tsv \ - && echo "NA" > anaquin_kallisto_adv/RnaExpression_summary.stats) + # anaquin RnaExpression -o anaquin_kallisto_adv -rmix "${sequins_iso_mix}" -usequin kallisto_output_adv/abundance.tsv -mix A \ + # || (echo "NA" > anaquin_kallisto_adv/RnaExpression_genes.tsv \ + # && echo "NA" > anaquin_kallisto_adv/RnaExpression_isoforms.tsv \ + # && echo "NA" > anaquin_kallisto_adv/RnaExpression_summary.stats) """ } diff --git a/processes/rna-star/aggregation/cufflinks_featurecounts.sh b/processes/rna-star/aggregation/cufflinks_featurecounts.sh index d5fcb22d..d104dd16 100644 --- a/processes/rna-star/aggregation/cufflinks_featurecounts.sh +++ b/processes/rna-star/aggregation/cufflinks_featurecounts.sh @@ -1,4 +1,4 @@ -VERSION=1.1 +VERSION=1.2 OUT_DIR=output_$VERSION mkdir -p "$OUT_DIR" diff --git a/scripts/rna-star/aggregate/concat_metrics.sh b/scripts/rna-star/aggregate/concat_metrics.sh index f6ce9d90..97c74a33 100644 --- a/scripts/rna-star/aggregate/concat_metrics.sh +++ b/scripts/rna-star/aggregate/concat_metrics.sh @@ -18,23 +18,4 @@ rm -f metrics.info cat ribosomal_counts.info | grep 'ribosomal' cat adapter_counts.info | grep 'adapter' - if [ -s anaquin_star/RnaAlign_summary.stats.info ]; then - cat anaquin_star/RnaAlign_summary.stats.info | grep 'sequins-dilution' - cat anaquin_star/RnaAlign_summary.stats.info | grep 'sequins-base-level-sensitivity' - cat anaquin_star/RnaAlign_summary.stats.info | grep 'sequins-base-level-precision' - fi - - if [ -s anaquin_subsample/anaquin_kallisto/RnaExpression_isoforms.neatmix.tsv.info ]; then - cat anaquin_subsample/anaquin_kallisto/RnaExpression_isoforms.neatmix.tsv.info | grep 'neat-mixA-mean-spearman' - fi - - if [ -s anaquin_subsample/anaquin_kallisto/RnaExpression_summary.stats.info ]; then - cat anaquin_subsample/anaquin_kallisto/RnaExpression_summary.stats.info | grep 'sequins-isoforms-log2-pearson-cor' - cat anaquin_subsample/anaquin_kallisto/RnaExpression_summary.stats.info | grep 'sequins-genes-slope' - cat anaquin_subsample/anaquin_kallisto/RnaExpression_summary.stats.info | grep 'sequins-genes-log2-pearson-cor' - cat anaquin_subsample/anaquin_kallisto/RnaExpression_summary.stats.info | grep 'sequins-percent-isoforms-found' - cat anaquin_subsample/anaquin_kallisto/RnaExpression_summary.stats.info | grep 'sequins-percent-genes-found' - cat anaquin_subsample/anaquin_kallisto/RnaExpression_summary.stats.info | grep 'sequins-detection-sensitivity-isoforms' - cat anaquin_subsample/anaquin_kallisto/RnaExpression_summary.stats.info | grep 'sequins-detection-sensitivity-genes' - fi } > metrics.info diff --git a/scripts/rna-star/aggregate/reset.bash b/scripts/rna-star/aggregate/reset.bash index 94e2d6bb..43393614 100644 --- a/scripts/rna-star/aggregate/reset.bash +++ b/scripts/rna-star/aggregate/reset.bash @@ -44,12 +44,7 @@ files=( \ ) dirs=( \ - "anaquin_cufflinks" \ - "anaquin_kallisto" \ - "anaquin_kallisto_adv" \ - "anaquin_star" \ "kallisto_output" \ - "anaquin_subsample" \ "kallisto_output_adv" \ ) diff --git a/scripts/versions.bash b/scripts/versions.bash index 8de23c6e..1c70a2e4 100644 --- a/scripts/versions.bash +++ b/scripts/versions.bash @@ -88,12 +88,7 @@ echo "R:" R --version | grep "R version" fi -if [[ `command -v anaquin` ]]; then -echo "Anaquin:" -anaquin | grep 'Version' -fi - if [[ `command -v tabix` ]]; then echo "Tabix/BGZIP:" which tabix | sed -e 's/.*htslib\///g' | sed -e 's/\/bin\/tabix//g' -fi \ No newline at end of file +fi