From 8793fa4ac786a2542eb49ff02c5e86b99a3fd8e3 Mon Sep 17 00:00:00 2001
From: mariabernard <maria.bernard@jouy.inra.fr>
Date: Fri, 7 Jun 2019 09:17:09 +0200
Subject: [PATCH] 1000RNASeq_chicken ASE : perform rmdup for single end read
---
Snakemake/1000RNASeq_chicken/ASE/Snakefile | 4 ++--
.../1000RNASeq_chicken/ASE/rules/ASE_counter.smk | 2 +-
Snakemake/1000RNASeq_chicken/ASE/rules/STAR.smk | 16 ++++++++--------
3 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/Snakemake/1000RNASeq_chicken/ASE/Snakefile b/Snakemake/1000RNASeq_chicken/ASE/Snakefile
index 78851bb..b10780e 100644
--- a/Snakemake/1000RNASeq_chicken/ASE/Snakefile
+++ b/Snakemake/1000RNASeq_chicken/ASE/Snakefile
@@ -130,7 +130,7 @@ for sample in table["sample_name"].unique():
final_outputs.append("Results/STAR_Aln_2/" + sample + "_rg_genomic_pp_rmdup_uniq_split.bam")
# single end, no filter on properly paired
elif len(sample_table["reverse_read"].dropna() ) == 0:
- final_outputs.append("Results/STAR_Aln_2/" + sample + "_rg_genomic_uniq_split.bam")
+ final_outputs.append("Results/STAR_Aln_2/" + sample + "_rg_genomic_rmdup_uniq_split.bam")
# # counter
for sample in table["sample_name"].unique():
@@ -146,4 +146,4 @@ for sample in table["sample_name"].unique():
rule all:
input:
- final_outputs
\ No newline at end of file
+ final_outputs
diff --git a/Snakemake/1000RNASeq_chicken/ASE/rules/ASE_counter.smk b/Snakemake/1000RNASeq_chicken/ASE/rules/ASE_counter.smk
index d91340a..b239bb5 100644
--- a/Snakemake/1000RNASeq_chicken/ASE/rules/ASE_counter.smk
+++ b/Snakemake/1000RNASeq_chicken/ASE/rules/ASE_counter.smk
@@ -18,7 +18,7 @@ def get_splitNCigar_bam(wildcards):
return "Results/STAR_Aln_2/" + wildcards.sample + "_rg_genomic_pp_rmdup_uniq_split.bam"
# single end, no filter
elif len(sample_table["reverse_read"].dropna() ) == 0:
- return "Results/STAR_Aln_2/" + wildcards.sample + "_rg_genomic_uniq_split.bam"
+ return "Results/STAR_Aln_2/" + wildcards.sample + "_rg_genomic_rmdup_uniq_split.bam"
else :
raise Exception(wildcards.sample + " is sequenced in pair end & single end mode\n This workflow do not accept this case!\n")
diff --git a/Snakemake/1000RNASeq_chicken/ASE/rules/STAR.smk b/Snakemake/1000RNASeq_chicken/ASE/rules/STAR.smk
index cc55d4b..8df1b00 100644
--- a/Snakemake/1000RNASeq_chicken/ASE/rules/STAR.smk
+++ b/Snakemake/1000RNASeq_chicken/ASE/rules/STAR.smk
@@ -8,7 +8,7 @@ Align RNASeq reads on masked genome
'''
wildcard_constraints:
- properlyPaired_rmDup = '_pp_rmdup_|_'
+ properlyPaired_rmDup = '_pp_|_'
STAR_INDEX_FILE=['genomeParameters.txt', 'chrName.txt', 'chrLength.txt', 'chrStart.txt', 'chrNameLength.txt', 'exonGeTrInfo.tab', 'geneInfo.tab', 'transcriptInfo.tab', 'exonInfo.tab', 'sjdbList.fromGTF.out.tab', 'sjdbInfo.txt', 'sjdbList.out.tab', 'Genome', 'SA', 'SAindex']
@@ -161,8 +161,8 @@ rule rmdup:
input:
bam = get_properly_paired_bam
output:
- bam = "Results/STAR_Aln_2/{sample}_rg_genomic{properlyPaired_rmDup}.bam",
- metrics = "Results/STAR_Aln_2/{sample}_rg_genomic{properlyPaired_rmDup}.metrics.txt",
+ bam = "Results/STAR_Aln_2/{sample}_rg_genomic{properlyPaired}.bam",
+ metrics = "Results/STAR_Aln_2/{sample}_rg_genomic{properlyPaired}.metrics.txt",
params:
mem=str(int(config["rmdup"]["mem"].replace("G","")) -4 )+"G" if int(config["rmdup"]["mem"].replace("G","")) -4 > 1 else config["rmdup"]["mem"] ,
jar=find_jar("picard.jar")
@@ -173,9 +173,9 @@ rule rmdup:
rule remove_multimap:
input:
- bam = "Results/STAR_Aln_2/{sample}_rg_genomic{properlyPaired_rmDup}.bam"
+ bam = "Results/STAR_Aln_2/{sample}_rg_genomic{properlyPaired}rmdup.bam"
output:
- bam = "Results/STAR_Aln_2/{sample}_rg_genomic{properlyPaired_rmDup}uniq.bam"
+ bam = "Results/STAR_Aln_2/{sample}_rg_genomic{properlyPaired}rmdup_uniq.bam"
shell:
"""
samtools view -h -q 255 {input.bam} -bo {output.bam}
@@ -184,9 +184,9 @@ rule remove_multimap:
rule SplitNCigarReads:
input:
fasta = 'Results/genomeMasked/' + os.path.splitext(os.path.basename(config['fasta_ref']))[0] + '_masked.fa',
- bam = "Results/STAR_Aln_2/{sample}_rg_genomic{properlyPaired_rmDup}uniq.bam"
+ bam = "Results/STAR_Aln_2/{sample}_rg_genomic{properlyPaired}rmdup_uniq.bam"
output:
- bam = "Results/STAR_Aln_2/{sample}_rg_genomic{properlyPaired_rmDup}uniq_split.bam"
+ bam = "Results/STAR_Aln_2/{sample}_rg_genomic{properlyPairedrmdup_uniq_split.bam"
params:
mem=config["SplitNCigarReads"]["mem"],
jar=find_jar("GenomeAnalysisTK.jar")
@@ -194,4 +194,4 @@ rule SplitNCigarReads:
"""
java -Xmx{params.mem} -jar {params.jar} -T SplitNCigarReads -R {input.fasta} -I {input.bam} -o {output.bam} -rf ReassignOneMappingQuality -RMQF 255 -RMQT 60 -U ALLOW_N_CIGAR_READS
"""
-
\ No newline at end of file
+
--
GitLab