Skip to content

Remove Anaquin from RNA-seq processing #59

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jemma-nelson wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Remove Anaquin from RNA-seq processing #59

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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`
Expand Down
38 changes: 18 additions & 20 deletions processes/rna-star/aggregation/cufflinks_featurecounts.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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)
Expand Down Expand Up @@ -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
Expand All @@ -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"

Expand All @@ -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)
"""

}
Expand Down Expand Up @@ -359,52 +359,50 @@ 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)
path kallisto_index
path sequins_iso_mix

output:
path "anaquin_kallisto/*"
path "kallisto_output/*"
path "kallisto.log"

script:
"""
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)
path kallisto_index
path sequins_iso_mix

output:
path "anaquin_kallisto_adv/*"
path "kallisto_output_adv/*"
path "kallisto_adv.log"

script:
"""
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)
"""
}

Expand Down
2 changes: 1 addition & 1 deletion processes/rna-star/aggregation/cufflinks_featurecounts.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
VERSION=1.1
VERSION=1.2
OUT_DIR=output_$VERSION
mkdir -p "$OUT_DIR"

Expand Down
19 changes: 0 additions & 19 deletions scripts/rna-star/aggregate/concat_metrics.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
5 changes: 0 additions & 5 deletions scripts/rna-star/aggregate/reset.bash
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,12 +44,7 @@ files=( \
)

dirs=( \
"anaquin_cufflinks" \
"anaquin_kallisto" \
"anaquin_kallisto_adv" \
"anaquin_star" \
"kallisto_output" \
"anaquin_subsample" \
"kallisto_output_adv" \
)

Expand Down
7 changes: 1 addition & 6 deletions scripts/versions.bash
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
fi