Skip to content
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

Allow bigwig creation for RNA-seq; Fixed cluster memory allocation #7

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Allow bigwig creation for RNA-seq; Fixed cluster memory allocation #7

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
83 changes: 46 additions & 37 deletions Snakefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,13 +30,13 @@ def choose_rule_all(config):
if config["to_multiqc"] == "TRUE":
myout.append("output/multiqc_report.html")
# myout.append(expand("output/bam/{sample}.unique.sorted.rmdup.chr.bam", sample=SAMPLES))
if config["to_bw"] == "TRUE" and config["experiment"] != "rnaseq":
if config["to_bw"] == "TRUE" :
myout.append(
expand('output/bw/{sample}.unique.sorted.rmdup.chr.bw',
expand('output/bw/{sample}.rmdup.chr.bw',
sample=SAMPLES))
if config["to_bed"] == "TRUE" and config["experiment"] != "rnaseq":
myout.append(
expand('output/bed/{sample}.unique.sorted.rmdup.chr.bed',
expand('output/bed/{sample}.rmdup.chr.bed',
sample=SAMPLES))
if config["to_tdf"] == "TRUE" and config["experiment"] != "rnaseq":
myout.append(
Expand Down Expand Up @@ -154,8 +154,10 @@ rule trim_fastq_fastqc:
if config['trim_polyA'] == "TRUE":
if config["type"] == "paired":
if config["use_UMI"] == "TRUE":
shell("umi_tools extract -I {input.pair1} --bc-pattern={params.umi_1} --bc-pattern2={params.umi_2} \
--read2-in={params.pair2} --stdout=output/temp_dir/{wildcards.sample}_R1.fq{suffix} \
shell("umi_tools extract -I {input.pair1} \
--bc-pattern={params.umi_1} --bc-pattern2={params.umi_2} \
--read2-in={params.pair2} \
--stdout=output/temp_dir/{wildcards.sample}_R1.fq{suffix} \
--read2-out=output/temp_dir/{wildcards.sample}_R2.fq{suffix}")
else:
# mv files to R1 and R2 ending in temporary directory
Expand Down Expand Up @@ -205,8 +207,10 @@ rule trim_fastq_fastqc:
else:
if config["type"] == "paired":
if config["use_UMI"] == "TRUE":
shell("umi_tools extract -I {input.pair1} --bc-pattern={params.umi_1} --bc-pattern2={params.umi_2} \
--read2-in={params.pair2} --stdout=output/temp_dir/{wildcards.sample}_R1.fq{suffix} \
shell("umi_tools extract -I {input.pair1} \
--bc-pattern={params.umi_1} --bc-pattern2={params.umi_2} \
--read2-in={params.pair2} \
--stdout=output/temp_dir/{wildcards.sample}_R1.fq{suffix} \
--read2-out=output/temp_dir/{wildcards.sample}_R2.fq{suffix}")
else:
# mv files to R1 and R2 ending in temporary directory
Expand All @@ -233,7 +237,8 @@ rule trim_fastq_fastqc:
output/trim_fastq/{wildcards.sample}_R2_trimmed.fq.gz")
if config["type"] == "single":
if config["use_UMI"] == "TRUE":
shell("umi_tools extract --stdin={input.pair1} --bc-pattern={params.umi_1} \
shell("umi_tools extract --stdin={input.pair1} \
--bc-pattern={params.umi_1} \
--log={log} --stdout output/temp_dir/{wildcards.sample}_R1.fq{suffix}")
else:
# mv files to R1 and R2 ending in temporary directory
Expand Down Expand Up @@ -332,10 +337,10 @@ rule fastq_to_bam_HISAT:
shell("samtools sort -@ 8 -O BAM -o {output.bam} output/bam/{wildcards.sample}.sam")
shell("rm output/bam/{wildcards.sample}.sam")
shell("samtools index {output.bam}")
if config["experiment"] != "cutrun" :
shell("rm output/temp_dir/{wildcards.sample}_R1.fq{suffix}")
if config["type"] == "paired":
shell("rm output/temp_dir/{wildcards.sample}_R2.fq{suffix}")
## Remove temporary files
shell("rm output/temp_dir/{wildcards.sample}_R1.fq{suffix}")
if config["type"] == "paired":
shell("rm output/temp_dir/{wildcards.sample}_R2.fq{suffix}")
if config["keep_fastq"] == "FALSE":
shell("rm output/trim_fastq/{wildcards.sample}_R1_trimmed.fq.gz \
output/trim_fastq/{wildcards.sample}_R2_trimmed.fq.gz")
Expand Down Expand Up @@ -397,11 +402,13 @@ if config["experiment"] != "rnaseq" :
"output/logs/{sample}.rmdup.log"
run:
if config["experiment"] == "cutrun" :
shell("picard MarkDuplicates --REMOVE_DUPLICATES true -I {input.sorted_bam} -O {output.dup_removed} \
-M output/logs/{wildcards.sample}_marked_dup_metrics.txt -VALIDATION_STRINGENCY SILENT 2> {log}")
shell("picard MarkDuplicates --REMOVE_DUPLICATES true \
-I {input.sorted_bam} -O {output.dup_removed} \
-M output/logs/{wildcards.sample}_marked_dup_metrics.txt \
-VALIDATION_STRINGENCY SILENT 2> {log}")
if config["experiment"] == "chipseq" :
shell("picard MarkDuplicates --REMOVE_DUPLICATES true -I {input.sorted_bam} -O {output.dup_removed} \
-M output/logs/{wildcards.sample}_marked_dup_metrics.txt 2> {log}")
shell("picard MarkDuplicates --REMOVE_DUPLICATES true -I {input.sorted_bam} \
-O {output.dup_removed} -M output/logs/{wildcards.sample}_marked_dup_metrics.txt 2> {log}")
if config["keep_unfiltered_bam"] == "FALSE":
shell("rm -f {input.sorted_bam} {input.sorted_bam}.bai")
## Rule for calculating insert size for PE sequencing
Expand Down Expand Up @@ -461,6 +468,22 @@ if config["experiment"] == "rnaseq":
REF_FLAT={params.refflat} \
STRAND=FIRST_READ_TRANSCRIPTION_STRAND")


# Eliminate extraneous chromosomes from bam file
rule rmdup_to_chrbam:
input:
rules.sortedbam_to_rmdup.output if config["experiment"] == "rnaseq" else "output/bam/{sample}.unique.sorted.rmdup.bam"
output:
chrbam = "output/bam/{sample}.rmdup.chr.bam",
chrbambai = "output/bam/{sample}.rmdup.chr.bam.bai"
log:
"output/logs/{sample}.chrbam.log"
run:
shell("samtools view -H {input} | \
sed -e \"s/SN:\([0-9XY]\)/SN:chr\\1/\" -e \"s/SN:MT/SN:chrM/\" | \
samtools reheader - {input} > {output.chrbam}")
shell("samtools index {output.chrbam}")

# Additional rules for ChIP-seq
# Create TDF files
rule rmdup_to_tdf:
Expand All @@ -476,28 +499,13 @@ rule rmdup_to_tdf:
"igvtools count {input} {output.tdf} {params.chr_sizes} "
"2> {log}"

# Eliminate extraneous chromosomes from bam file
rule rmdup_to_chrbam:
input:
"output/bam/{sample}.unique.sorted.rmdup.bam"
output:
chrbam = "output/bam/{sample}.unique.sorted.rmdup.chr.bam",
chrbambai = "output/bam/{sample}.unique.sorted.rmdup.chr.bam.bai"
log:
"output/logs/{sample}.chrbam.log"
run:
shell("samtools view -H {input} | \
sed -e \"s/SN:\([0-9XY]\)/SN:chr\\1/\" -e \"s/SN:MT/SN:chrM/\" | \
samtools reheader - {input} > {output.chrbam}")
shell("samtools index {output.chrbam}")

# Create bigwig from bam file (main chromosomes only)
rule chrbam_to_bw:
input:
chrbam = rules.rmdup_to_chrbam.output.chrbam,
chrbambai = rules.rmdup_to_chrbam.output.chrbambai
chrbam = "output/bam/{sample}.rmdup.chr.bam",
chrbambai = "output/bam/{sample}.rmdup.chr.bam.bai"
output:
bw_file = "output/bw/{sample}.unique.sorted.rmdup.chr.bw"
bw_file = "output/bw/{sample}.rmdup.chr.bw"
log:
"output/logs/{sample}.bw.log"
run:
Expand All @@ -507,9 +515,10 @@ rule chrbam_to_bw:
# Create bed file from bam file (main chromosomes only)
rule chrbam_to_bed:
input:
chrbam = "output/bam/{sample}.unique.sorted.rmdup.chr.bam"
chrbam = "output/bam/{sample}.rmdup.chr.bam",
chrbambai = "output/bam/{sample}.rmdup.chr.bam.bai"
output:
bed = "output/bed/{sample}.unique.sorted.rmdup.chr.bed"
bed = "output/bed/{sample}.rmdup.chr.bed"
log:
"output/logs/{sample}.bed.log"
shell:
Expand Down Expand Up @@ -671,7 +680,7 @@ rule fpkm_matrix:
rule run_multiqc:
input:
"output/fpkm_genic_matrix.txt" if config["experiment"] == "rnaseq" else \
expand("output/bam/{sample}.unique.sorted.rmdup.chr.bam", sample=SAMPLES)
expand("output/bam/{sample}.rmdup.chr.bam", sample=SAMPLES)
output:
multiqc_report = "output/multiqc_report.html"
params:
Expand Down
9 changes: 5 additions & 4 deletions cluster.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,6 @@
"queue" : "premium",
"allocation": "acc_yourlab",
"tasks" : 1,
"memory" : 12000,
"resources" : "\"rusage[mem=12000] span[hosts=1]\"",
"jobname" : "{rule}.{wildcards}",
"output" : "output/logs/{rule}.{wildcards}.o",
Expand All @@ -14,23 +13,25 @@

"trim_fastq_fastqc" :
{
"resources" : "\"rusage[mem=24000] span[hosts=1]\"",
"walltime" : "10:00"
},

"fastq_to_bam_HISAT" :
{
"memory" : 24000,
"resources" : "\"rusage[mem=24000] span[hosts=1]\"",
"walltime" : "10:00"
},

"bam_to_unique_mapped":
{
"memory" : 24000,
"resources" : "\"rusage[mem=24000] span[hosts=1]\"",
"walltime" : "06:00"
},

"sortedbam_to_rmdup":
{
"resources" : "\"rusage[mem=24000] span[hosts=1]\"",
"walltime" : "04:00"
},

Expand All @@ -46,7 +47,7 @@

"chrbam_to_bw":
{
"memory" : 24000,
"resources" : "\"rusage[mem=24000] span[hosts=1]\"",
"walltime" : "02:00"
},

Expand Down
2 changes: 1 addition & 1 deletion config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ UMI_read1_pattern: "X"
UMI_read2_pattern: "NNNNNNNN"
## See https://umi-tools.readthedocs.io/en/latest/ for informaton on "umi_tools extract" parameters

# FOR CUT&RUN AND CHIPSEQ -
# FOR CUT&RUN, CHIPSEQ, and RNASEQ (if you wish to generate bigwigs for RNASEQ)
chr_sizes: "/path/to/mm10/mm10.chrom.sizes" # path to chrom.sizes file (only for chipseq)
# This file must named as follows "<genomeid>.chrom.sizes", any other filename format (e.g. "mm10_chr_len") will
# cause the TDF step to produce an empty TDF. Please see the Broad website for more information:
Expand Down