From c95864b2a30c5c5eac12dab5d54bfc52721dc274 Mon Sep 17 00:00:00 2001
From: burri0000 <dominik.burri@unibas.ch>
Date: Mon, 19 Oct 2020 10:53:10 +0200
Subject: [PATCH] use temp() and shadow rules for removing unnecessary files
---
Snakefile | 76 ++++++++++++++-----------
workflow/rules/paired_end.snakefile.smk | 26 +++++----
workflow/rules/single_end.snakefile.smk | 18 ++++--
3 files changed, 72 insertions(+), 48 deletions(-)
diff --git a/Snakefile b/Snakefile
index 2753972..1648e97 100644
--- a/Snakefile
+++ b/Snakefile
@@ -170,16 +170,16 @@ rule create_index_star:
"""
input:
genome = lambda wildcards:
- get_sample(
+ os.path.abspath(get_sample(
'genome',
search_id='organism',
- search_value=wildcards.organism),
+ search_value=wildcards.organism)),
gtf = lambda wildcards:
- get_sample(
+ os.path.abspath(get_sample(
'gtf',
search_id='organism',
- search_value=wildcards.organism)
+ search_value=wildcards.organism))
output:
chromosome_info = os.path.join(
@@ -195,6 +195,8 @@ rule create_index_star:
"STAR_index",
"chrName.txt")
+ shadow: "full"
+
params:
output_dir = os.path.join(
config['star_indexes'],
@@ -251,11 +253,11 @@ rule extract_transcriptome:
search_id='organism',
search_value=wildcards.organism)
output:
- transcriptome = os.path.join(
+ transcriptome = temp(os.path.join(
config['output_dir'],
"transcriptome",
"{organism}",
- "transcriptome.fa")
+ "transcriptome.fa"))
log:
stderr = os.path.join(
@@ -293,11 +295,11 @@ rule concatenate_transcriptome_and_genome:
search_value=wildcards.organism)
output:
- genome_transcriptome = os.path.join(
+ genome_transcriptome = temp(os.path.join(
config['output_dir'],
"transcriptome",
"{organism}",
- "genome_transcriptome.fa")
+ "genome_transcriptome.fa"))
singularity:
"docker://bash:5.0.16"
@@ -339,6 +341,8 @@ rule create_index_salmon:
"{kmer}",
"salmon.idx"))
+ shadow: "full"
+
params:
kmerLen = "{kmer}"
@@ -382,6 +386,8 @@ rule create_index_kallisto:
"{organism}",
"kallisto.idx")
+ shadow: "full"
+
params:
output_dir = os.path.join(
config['kallisto_indexes'],
@@ -414,9 +420,9 @@ rule extract_transcripts_as_bed12:
get_sample('gtf')
output:
- bed12 = os.path.join(
+ bed12 = temp(os.path.join(
config['output_dir'],
- "full_transcripts_protein_coding.bed")
+ "full_transcripts_protein_coding.bed"))
singularity:
"docker://zavolab/zgtf:0.1"
@@ -516,12 +522,14 @@ rule calculate_TIN_scores:
"full_transcripts_protein_coding.bed")
output:
- TIN_score = os.path.join(
+ TIN_score = temp(os.path.join(
config['output_dir'],
"samples",
"{sample}",
"TIN",
- "TIN_score.tsv")
+ "TIN_score.tsv"))
+
+ shadow: "full"
params:
sample = "{sample}"
@@ -944,30 +952,32 @@ rule star_rpm:
search_value=wildcards.sample))
output:
- str1 = os.path.join(
+ str1 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"STAR_coverage",
- "{sample}_Signal.Unique.str1.out.bg"),
- str2 = os.path.join(
+ "{sample}_Signal.Unique.str1.out.bg")),
+ str2 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"STAR_coverage",
- "{sample}_Signal.UniqueMultiple.str1.out.bg"),
- str3 = os.path.join(
+ "{sample}_Signal.UniqueMultiple.str1.out.bg")),
+ str3 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"STAR_coverage",
- "{sample}_Signal.Unique.str2.out.bg"),
- str4 = os.path.join(
+ "{sample}_Signal.Unique.str2.out.bg")),
+ str4 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"STAR_coverage",
- "{sample}_Signal.UniqueMultiple.str2.out.bg")
+ "{sample}_Signal.UniqueMultiple.str2.out.bg"))
+
+ shadow: "full"
params:
out_dir = lambda wildcards, output:
@@ -1041,20 +1051,20 @@ rule rename_star_rpm_for_alfa:
search_value=wildcards.sample))
output:
- plus = os.path.join(
+ plus = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"ALFA",
"{unique}",
- "{sample}.{unique}.plus.bg"),
- minus = os.path.join(
+ "{sample}.{unique}.plus.bg")),
+ minus = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"ALFA",
"{unique}",
- "{sample}.{unique}.minus.bg")
+ "{sample}.{unique}.minus.bg"))
params:
orientation = lambda wildcards:
@@ -1088,10 +1098,10 @@ rule generate_alfa_index:
''' Generate ALFA index files from sorted GTF file '''
input:
gtf = lambda wildcards:
- get_sample(
+ os.path.abspath(get_sample(
'gtf',
search_id='organism',
- search_value=wildcards.organism),
+ search_value=wildcards.organism)),
chr_len = os.path.join(
config["star_indexes"],
@@ -1114,6 +1124,8 @@ rule generate_alfa_index:
"ALFA",
"sorted_genes.unstranded.ALFA_index")
+ shadow: "full"
+
params:
genome_index = "sorted_genes",
out_dir = lambda wildcards, output:
@@ -1171,20 +1183,20 @@ rule alfa_qc:
"sorted_genes.stranded.ALFA_index")
output:
- biotypes = os.path.join(
+ biotypes = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"ALFA",
"{unique}",
- "ALFA_plots.Biotypes.pdf"),
- categories = os.path.join(
+ "ALFA_plots.Biotypes.pdf")),
+ categories = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"ALFA",
"{unique}",
- "ALFA_plots.Categories.pdf"),
+ "ALFA_plots.Categories.pdf")),
table = os.path.join(
config["output_dir"],
"samples",
@@ -1446,13 +1458,13 @@ rule sort_bed_4_big:
"{sample}.{unique}.{strand}.bg")
output:
- sorted_bg = os.path.join(
+ sorted_bg = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"bigWig",
"{unique}",
- "{sample}_{unique}_{strand}.sorted.bg")
+ "{sample}_{unique}_{strand}.sorted.bg"))
singularity:
"docker://cjh4zavolab/bedtools:2.27"
diff --git a/workflow/rules/paired_end.snakefile.smk b/workflow/rules/paired_end.snakefile.smk
index 25046d0..f06d4dc 100644
--- a/workflow/rules/paired_end.snakefile.smk
+++ b/workflow/rules/paired_end.snakefile.smk
@@ -18,16 +18,16 @@ rule pe_remove_adapters_cutadapt:
"{sample}.fq2.fastq.gz"),
output:
- reads1 = os.path.join(
+ reads1 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
- "{sample}.pe.remove_adapters_mate1.fastq.gz"),
- reads2 = os.path.join(
+ "{sample}.pe.remove_adapters_mate1.fastq.gz")),
+ reads2 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
- "{sample}.pe.remove_adapters_mate2.fastq.gz")
+ "{sample}.pe.remove_adapters_mate2.fastq.gz"))
params:
adapter_3_mate1 = lambda wildcards:
@@ -91,16 +91,16 @@ rule pe_remove_polya_cutadapt:
"{sample}.pe.remove_adapters_mate2.fastq.gz")
output:
- reads1 = os.path.join(
+ reads1 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
- "{sample}.pe.remove_polya_mate1.fastq.gz"),
- reads2 = os.path.join(
+ "{sample}.pe.remove_polya_mate1.fastq.gz")),
+ reads2 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
- "{sample}.pe.remove_polya_mate2.fastq.gz")
+ "{sample}.pe.remove_polya_mate2.fastq.gz"))
params:
polya_3_mate1 = lambda wildcards:
@@ -203,6 +203,8 @@ rule pe_map_genome_star:
"map_genome",
"{sample}.pe.Log.final.out")
+ shadow: "full"
+
params:
sample_id = "{sample}",
index = lambda wildcards:
@@ -292,10 +294,10 @@ rule pe_quantification_salmon:
"{sample}",
"{sample}.pe.remove_polya_mate2.fastq.gz"),
gtf = lambda wildcards:
- get_sample(
+ os.path.abspath(get_sample(
'gtf',
search_id='index',
- search_value=wildcards.sample),
+ search_value=wildcards.sample)),
index = lambda wildcards:
os.path.join(
config["salmon_indexes"],
@@ -323,6 +325,8 @@ rule pe_quantification_salmon:
"{sample}.salmon.pe",
"quant.sf")
+ shadow: "full"
+
params:
output_dir = os.path.join(
config["output_dir"],
@@ -399,6 +403,8 @@ rule pe_genome_quantification_kallisto:
"quant_kallisto",
"{sample}.pe.kallisto.pseudo.sam")
+ shadow: "full"
+
params:
output_dir = os.path.join(
config["output_dir"],
diff --git a/workflow/rules/single_end.snakefile.smk b/workflow/rules/single_end.snakefile.smk
index 071b9e5..565bc01 100644
--- a/workflow/rules/single_end.snakefile.smk
+++ b/workflow/rules/single_end.snakefile.smk
@@ -11,11 +11,11 @@ rule remove_adapters_cutadapt:
"{sample}.fq1.fastq.gz")
output:
- reads = os.path.join(
+ reads = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
- "{sample}.se.remove_adapters_mate1.fastq.gz")
+ "{sample}.se.remove_adapters_mate1.fastq.gz"))
params:
adapters_3 = lambda wildcards:
@@ -70,11 +70,11 @@ rule remove_polya_cutadapt:
"{sample}.se.remove_adapters_mate1.fastq.gz")
output:
- reads = os.path.join(
+ reads = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
- "{sample}.se.remove_polya_mate1.fastq.gz")
+ "{sample}.se.remove_polya_mate1.fastq.gz"))
params:
polya_3 = lambda wildcards:
@@ -151,6 +151,8 @@ rule map_genome_star:
"map_genome",
"{sample}.se.Log.final.out")
+ shadow: "full"
+
params:
sample_id = "{sample}",
index = lambda wildcards:
@@ -241,10 +243,10 @@ rule quantification_salmon:
search_value=wildcards.sample),
"salmon.idx"),
gtf = lambda wildcards:
- get_sample(
+ os.path.abspath(get_sample(
'gtf',
search_id='index',
- search_value=wildcards.sample)
+ search_value=wildcards.sample))
output:
gn_estimates = os.path.join(
@@ -260,6 +262,8 @@ rule quantification_salmon:
"{sample}.salmon.se",
"quant.sf")
+ shadow: "full"
+
params:
output_dir = os.path.join(
config["output_dir"],
@@ -341,6 +345,8 @@ rule genome_quantification_kallisto:
"quant_kallisto",
"{sample}.se.kallisto.pseudo.sam")
+ shadow: "full"
+
params:
output_dir = os.path.join(
config["output_dir"],
--
GitLab