From d8a0e760c6f4d26fc30d79800214f359d41dcecb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Nicolas=20FERNANDEZ=20NU=C3=91EZ?=
<fernandez.nunez.nicolas@gmail.com>
Date: Tue, 12 Oct 2021 12:25:02 +0200
Subject: [PATCH] Add rule merging all reads passing filters
---
RQCP.sh | 2 +-
config/config.yaml | 1 +
resources/reads/.gitkeep | 0
.../rules/reads_quality_control_pipeline.smk | 27 ++++++++++++++++---
4 files changed, 26 insertions(+), 4 deletions(-)
delete mode 100644 resources/reads/.gitkeep
diff --git a/RQCP.sh b/RQCP.sh
index ff3d888..2beb9f0 100755
--- a/RQCP.sh
+++ b/RQCP.sh
@@ -56,7 +56,7 @@ echo "Quiet."
echo "________________________________________________________________________"
###### Create dir for QC tools #####
-mkdir ${WORKDIR}/results/reads/cutadapt/ ${WORKDIR}/results/reads/sickle-trim/ ${WORKDIR}/results/reads/fastq-join/ 2> /dev/null
+mkdir ${WORKDIR}/results/reads/cutadapt/ ${WORKDIR}/results/reads/sickle-trim/ ${WORKDIR}/results/reads/fastq-join/ ${WORKDIR}/results/reads/merged/ 2> /dev/null
###### Extract bwa indexes for small genomes #####
echo ""
diff --git a/config/config.yaml b/config/config.yaml
index cb2ec92..db1a547 100644
--- a/config/config.yaml
+++ b/config/config.yaml
@@ -35,6 +35,7 @@ datasets:
#- 'sickle-single'
- 'fastq-join'
#- 'fastq-join-unique'
+ - 'merged'
quality-tool:
- 'fastqc'
- 'fastq-screen'
diff --git a/resources/reads/.gitkeep b/resources/reads/.gitkeep
deleted file mode 100644
index e69de29..0000000
diff --git a/workflow/rules/reads_quality_control_pipeline.smk b/workflow/rules/reads_quality_control_pipeline.smk
index 559ff1a..77afcc4 100644
--- a/workflow/rules/reads_quality_control_pipeline.smk
+++ b/workflow/rules/reads_quality_control_pipeline.smk
@@ -52,7 +52,7 @@ SUBSET = config["fastq-screen"]["subset"] # Fastq-screen --subset
###############################################################################
rule all:
input:
- joined = expand("results/reads/fastq-join/{sample}_cutadapt_sickle-trim_fastq-join_Mate.fastq.gz",
+ merged = expand("results/reads/merged/{sample}_cutadapt_sickle-trim_fastq-join_merged.fastq.gz",
sample = SAMPLE),
multiqc = expand("results/quality/{qcdir}/multiqc/",
qcdir = QCDIR)
@@ -137,12 +137,33 @@ rule fastqc:
"--outdir {output.fastqc} " # -o: Create all output files in the specified output directory
"{input.fastq}/*.fastq.gz " # Input file.fastq
"&> {log}" # Add redirection for log
-
+
+###############################################################################
+rule merge:
+ # Aim: Merge all passing filters reads
+ # Use: cat {input} > {output}
+ priority: 1
+ message:
+ "Take all passing filter {wildcards.sample} reads"
+ input:
+ single = "results/reads/sickle-single/{sample}_cutadapt_sickle-trim_Single.fastq.gz",
+ forward= "results/reads/fastq-join-unique/{sample}_cutadapt_sickle-trim_fastq-join_Unique_R1.fastq.gz",
+ reverse = "results/reads/fastq-join-unique/{sample}_cutadapt_sickle-trim_fastq-join_Unique_R2.fastq.gz",
+ joined = "results/reads/fastq-join/{sample}_cutadapt_sickle-trim_fastq-join_Mate.fastq.gz",
+ output:
+ merged = "results/reads/merged/{sample}_cutadapt_sickle-trim_fastq-join_merged.fastq.gz"
+ shell:
+ "cat " # Cat, concatenate
+ "{input.single} " # Input trimmed singles fastq file from Sickle-trim
+ "{input.forward} " # Input unique forward files from Fastq-join
+ "{input.reverse} " # Input unique reverse files from Fastq-join
+ "{input.joined} " # Input join files from Fastq-join
+ "> {output.merged}" # Output merged
+
###############################################################################
rule fastqjoin:
# Aim: joins two paired-end reads on the overlapping ends
# Use: fastq-join [OPTIONS] <read1.fastq> <read2.fastq> [mate.fastq] -o <read.fastq> -o <read.fastq> -o <read.fastq>
- priority: 1
message:
"Fastq-join assemble R1 and R2 from {wildcards.sample} reads"
conda:
--
GitLab