diff --git a/RQCP.sh b/RQCP.sh index ff3d8889620a1f01dc4010aa9444d55ca6c5e460..2beb9f03c488950c82ef483a5babc8a3874f7c1d 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 cb2ec9286e17c01bcc0a24015abd3b4573107b48..db1a5479c2900bfd7e6bd6d6422d46a48ef0d912 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 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/workflow/rules/reads_quality_control_pipeline.smk b/workflow/rules/reads_quality_control_pipeline.smk index 559ff1a42d1f86f0e1f62b1fce9182816c1a9ac5..77afcc46e9f4ae3f02e380cec828c7404dcc6703 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: