Skip to content

Commit

Permalink
chore: delete commented-out code
Browse files Browse the repository at this point in the history
  • Loading branch information
@kelly-sovacool
kelly-sovacool committed Apr 12, 2024
1 parent 5664d0a commit dbd895b
Show file tree
Hide file tree
Showing 3 changed files with 0 additions and 489 deletions.
179 changes: 0 additions & 179 deletions workflow/rules/findcircrna.smk
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1354,185 +1354,6 @@ bash {output.merge_bash_script}
"""


# if RUN_DCC and RUN_MAPSPLICE and RUN_NCLSCAN:
# rule merge_per_sample:
# input:
# unpack(get_per_sample_files_to_merge)
# output:
# merged_counts=join(WORKDIR,"results","{sample}","{sample}.circRNA_counts.txt.gz"),
# params:
# script=join(SCRIPTS_DIR,"_merge_per_sample_counts_table.py"),
# samplename="{sample}",
# peorse=get_peorse,
# reffa=REF_FA,
# minreadcount=config['minreadcount'] # this filter is redundant as inputs are already pre-filtered.
# envmodules:
# TOOLS["python37"]["version"]
# shell:"""
# set -exo pipefail
# outdir=$(dirname {output.merged_counts})

# parameters=" --circExplorer {input.circExplorer}"
# parameters="$parameters --ciri {input.CIRI}"
# parameters="$parameters --dcc {input.DCC}"
# parameters="$parameters --mapsplice {input.MapSplice}"
# if [[ "{params.peorse}" == "PE" ]]; then # NCLscan is run only if the sample is PE
# parameters="$parameters --nclscan {input.NCLscan}"
# fi
# parameters="$parameters --min_read_count_reqd {params.minreadcount}"
# parameters="$parameters --reffa {params.reffa}"
# parameters="$parameters --samplename {params.samplename} -o {output.merged_counts}"

# echo "python {params.script} $parameters"
# python {params.script} $parameters
# """
# elif RUN_DCC and not RUN_MAPSPLICE and not RUN_NCLSCAN:
# rule merge_per_sample:
# input:
# unpack(get_per_sample_files_to_merge)
# output:
# merged_counts=join(WORKDIR,"results","{sample}","{sample}.circRNA_counts.txt.gz"),
# params:
# script=join(SCRIPTS_DIR,"_merge_per_sample_counts_table.py"),
# samplename="{sample}",
# peorse=get_peorse,
# reffa=REF_FA,
# minreadcount=config['minreadcount'] # this filter is redundant as inputs are already pre-filtered.
# envmodules:
# TOOLS["python37"]["version"]
# shell:"""
# set -exo pipefail
# outdir=$(dirname {output.merged_counts})

# parameters=" --circExplorer {input.circExplorer}"
# parameters="$parameters --ciri {input.CIRI}"
# parameters="$parameters --dcc {input.DCC}"
# parameters="$parameters --min_read_count_reqd {params.minreadcount}"
# parameters="$parameters --reffa {params.reffa}"
# parameters="$parameters --samplename {params.samplename} -o {output.merged_counts}"

# echo "python {params.script} $parameters"
# python {params.script} $parameters
# """
# elif RUN_DCC and RUN_MAPSPLICE and not RUN_NCLSCAN:
# rule merge_per_sample:
# input:
# unpack(get_per_sample_files_to_merge)
# output:
# merged_counts=join(WORKDIR,"results","{sample}","{sample}.circRNA_counts.txt.gz"),
# params:
# script=join(SCRIPTS_DIR,"_merge_per_sample_counts_table.py"),
# samplename="{sample}",
# peorse=get_peorse,
# reffa=REF_FA,
# minreadcount=config['minreadcount'] # this filter is redundant as inputs are already pre-filtered.
# envmodules:
# TOOLS["python37"]["version"]
# shell:"""
# set -exo pipefail
# outdir=$(dirname {output.merged_counts})

# parameters=" --circExplorer {input.circExplorer}"
# parameters="$parameters --ciri {input.CIRI}"
# parameters="$parameters --dcc {input.DCC}"
# parameters="$parameters --mapsplice {input.MapSplice}"
# parameters="$parameters --min_read_count_reqd {params.minreadcount}"
# parameters="$parameters --reffa {params.reffa}"
# parameters="$parameters --samplename {params.samplename} -o {output.merged_counts}"

# echo "python {params.script} $parameters"
# python {params.script} $parameters
# """
# elif not RUN_DCC and RUN_MAPSPLICE and not RUN_NCLSCAN:
# rule merge_per_sample:
# input:
# unpack(get_per_sample_files_to_merge)
# output:
# merged_counts=join(WORKDIR,"results","{sample}","{sample}.circRNA_counts.txt.gz"),
# params:
# script=join(SCRIPTS_DIR,"_merge_per_sample_counts_table.py"),
# samplename="{sample}",
# peorse=get_peorse,
# reffa=REF_FA,
# minreadcount=config['minreadcount'] # this filter is redundant as inputs are already pre-filtered.
# envmodules:
# TOOLS["python37"]["version"]
# shell:"""
# set -exo pipefail
# outdir=$(dirname {output.merged_counts})

# parameters=" --circExplorer {input.circExplorer}"
# parameters="$parameters --ciri {input.CIRI}"
# parameters="$parameters --mapsplice {input.MapSplice}"
# parameters="$parameters --min_read_count_reqd {params.minreadcount}"
# parameters="$parameters --reffa {params.reffa}"
# parameters="$parameters --samplename {params.samplename} -o {output.merged_counts}"

# echo "python {params.script} $parameters"
# python {params.script} $parameters
# """
# elif not RUN_DCC and not RUN_MAPSPLICE and RUN_NCLSCAN:
# rule merge_per_sample:
# input:
# unpack(get_per_sample_files_to_merge)
# output:
# merged_counts=join(WORKDIR,"results","{sample}","{sample}.circRNA_counts.txt.gz"),
# params:
# script=join(SCRIPTS_DIR,"_merge_per_sample_counts_table.py"),
# samplename="{sample}",
# peorse=get_peorse,
# reffa=REF_FA,
# minreadcount=config['minreadcount'] # this filter is redundant as inputs are already pre-filtered.
# envmodules:
# TOOLS["python37"]["version"]
# shell:"""
# set -exo pipefail
# outdir=$(dirname {output.merged_counts})

# parameters=" --circExplorer {input.circExplorer}"
# parameters="$parameters --ciri {input.CIRI}"
# if [[ "{params.peorse}" == "PE" ]]; then # NCLscan is run only if the sample is PE
# parameters="$parameters --nclscan {input.NCLscan}"
# fi
# parameters="$parameters --min_read_count_reqd {params.minreadcount}"
# parameters="$parameters --reffa {params.reffa}"
# parameters="$parameters --samplename {params.samplename} -o {output.merged_counts}"

# echo "python {params.script} $parameters"
# python {params.script} $parameters
# """
# else: # DCC, MapSplice and NCLScan are all off!
# rule merge_per_sample:
# input:
# unpack(get_per_sample_files_to_merge)
# output:
# merged_counts=join(WORKDIR,"results","{sample}","{sample}.circRNA_counts.txt.gz"),
# params:
# script=join(SCRIPTS_DIR,"_merge_per_sample_counts_table.py"),
# samplename="{sample}",
# peorse=get_peorse,
# reffa=REF_FA,
# minreadcount=config['minreadcount'] # this filter is redundant as inputs are already pre-filtered.
# envmodules:
# TOOLS["python37"]["version"]
# shell:"""
# set -exo pipefail
# outdir=$(dirname {output.merged_counts})

# parameters=" --circExplorer {input.circExplorer}"
# parameters="$parameters --ciri {input.CIRI}"
# parameters="$parameters --min_read_count_reqd {params.minreadcount}"
# parameters="$parameters --reffa {params.reffa}"
# parameters="$parameters --samplename {params.samplename} -o {output.merged_counts}"

# echo "python {params.script} $parameters"
# python {params.script} $parameters
# """


# localrules:
# create_master_counts_file,


# rule create_master_counts_file:
# merge all per-sample counts tables into a single giant counts matrix and annotate it with known circRNA databases
Expand Down
89 changes: 0 additions & 89 deletions workflow/rules/post_align_processing.smk
View file
Original file line number Diff line number Diff line change
@@ -1,92 +1,3 @@
# rule split_splice_reads_BAM_create_BW:
# input:
# bam=rules.create_spliced_reads_bam.output.bam
# output:
# bam=join(WORKDIR,"results","{sample}","STAR2p","{sample}.spliced_reads."+HOST+".bam"),
# bw=join(WORKDIR,"results","{sample}","STAR2p","{sample}.spliced_reads."+HOST+".bw")
# params:
# sample="{sample}",
# workdir=WORKDIR,
# memG=getmemG("split_splice_reads_BAM_create_BW"),
# outdir=join(WORKDIR,"results","{sample}","STAR2p"),
# regions=REF_REGIONS,
# randomstr=str(uuid.uuid4())
# threads: getthreads("split_splice_reads_BAM_create_BW")
# envmodules: TOOLS["samtools"]["version"],TOOLS["bedtools"]["version"],TOOLS["ucsc"]["version"],TOOLS["sambamba"]["version"]
# shell:"""
# if [ -d /lscratch/${{SLURM_JOB_ID}} ];then
# TMPDIR="/lscratch/${{SLURM_JOB_ID}}"
# else
# TMPDIR="/dev/shm/{params.randomstr}"
# mkdir -p $TMPDIR
# fi
# cd {params.outdir}
# bam_basename="$(basename {input.bam})"
# while read a b;do
# bam="${{bam_basename%.*}}.${{a}}.bam"
# samtools view {input.bam} $b -b > ${{TMPDIR}}/${{bam%.*}}.tmp.bam
# sambamba sort --memory-limit={params.memG} --tmpdir=${{TMPDIR}} --nthreads={threads} --out=$bam ${{TMPDIR}}/${{bam%.*}}.tmp.bam
# bw="${{bam%.*}}.bw"
# bdg="${{bam%.*}}.bdg"
# sizes="${{bam%.*}}.sizes"
# bedtools genomecov -bga -split -ibam $bam > $bdg
# bedSort $bdg $bdg
# if [ "$(wc -l $bdg|awk '{{print $1}}')" != "0" ];then
# samtools view -H $bam|grep ^@SQ|cut -f2,3|sed "s/SN://g"|sed "s/LN://g" > $sizes
# bedGraphToBigWig $bdg $sizes $bw
# else
# touch $bw
# fi
# rm -f $bdg $sizes
# done < {params.regions}
# cd $TMPDIR && rm -f *
# """

# rule split_linear_reads_BAM_create_BW:
# # This rule is identical to split_splice_reads_BAM_create_BW, "spliced_reads" is replaced by "linear_reads"
# input:
# bam=rules.create_linear_reads_bam.output.bam
# output:
# bam=join(WORKDIR,"results","{sample}","STAR2p","{sample}.linear_reads."+HOST+".bam"),
# bw=join(WORKDIR,"results","{sample}","STAR2p","{sample}.linear_reads."+HOST+".bw")
# params:
# sample="{sample}",
# workdir=WORKDIR,
# memG=getmemG("split_linear_reads_BAM_create_BW"),
# outdir=join(WORKDIR,"results","{sample}","STAR2p"),
# regions=REF_REGIONS,
# randomstr=str(uuid.uuid4())
# threads: getthreads("split_linear_reads_BAM_create_BW")
# envmodules: TOOLS["samtools"]["version"],TOOLS["bedtools"]["version"],TOOLS["ucsc"]["version"],TOOLS["sambamba"]["version"]
# shell:"""
# if [ -d /lscratch/${{SLURM_JOB_ID}} ];then
# TMPDIR="/lscratch/${{SLURM_JOB_ID}}"
# else
# TMPDIR="/dev/shm/{params.randomstr}"
# mkdir -p $TMPDIR
# fi
# cd {params.outdir}
# bam_basename="$(basename {input.bam})"
# while read a b;do
# bam="${{bam_basename%.*}}.${{a}}.bam"
# samtools view {input.bam} $b -b > ${{TMPDIR}}/${{bam%.*}}.tmp.bam
# sambamba sort --memory-limit={params.memG} --tmpdir=${{TMPDIR}} --nthreads={threads} --out=$bam ${{TMPDIR}}/${{bam%.*}}.tmp.bam
# bw="${{bam%.*}}.bw"
# bdg="${{bam%.*}}.bdg"
# sizes="${{bam%.*}}.sizes"
# bedtools genomecov -bga -split -ibam $bam > $bdg
# bedSort $bdg $bdg
# if [ "$(wc -l $bdg|awk '{{print $1}}')" != "0" ];then
# samtools view -H $bam|grep ^@SQ|cut -f2,3|sed "s/SN://g"|sed "s/LN://g" > $sizes
# bedGraphToBigWig $bdg $sizes $bw
# else
# touch $bw
# fi
# rm -f $bdg $sizes
# done < {params.regions}
# cd $TMPDIR && rm -f *
# """


localrules:
merge_genecounts,
Expand Down
Loading

0 comments on commit dbd895b

Please sign in to comment.