Update Snakefile

snakemake/process_data/Snakefile

@@ -39,14 +39,13 @@ rule clip_reads:
 		flag = config["dir_created"],
 		reads = os.path.join(config["input_dir"], "{sample}" + config["input_reads_pattern"]),
 	output:
-		reads = os.path.join(config["output_dir"], "{sample}/pro.clipped.fastq"),
+		reads = os.path.join(config["output_dir"], "{sample}/pro.clipped.fastq.gz"),
 	params:
 		v = "-v",
 		n = "-n",
 		l = "20",
-		qual = "-Q33",
+		adapter = lambda wildcards: config[wildcards.sample]['adapter'],
 		z = "-z",
-		adapter = lambda wildcards: config[ wildcards.sample ]['adapter'],
 		cluster_log = os.path.join(config["cluster_log"], "clip_reads_{sample}.log")
 	log:
 		os.path.join(config["local_log"], "clip_reads_{sample}.log")
@@ -57,7 +56,7 @@ rule clip_reads:
 		{params.v} \
 		{params.n} \
 		-l {params.l} \
-		{params.qual} \
+		{params.z} \
 		-a {params.adapter} \
 		-i <(zcat {input.reads}) \
 		-o {output.reads}) &> {log}"
@@ -68,14 +67,14 @@ rule clip_reads:
 
 rule trim_reads:
 	input:
-		reads = os.path.join(config["output_dir"], "{sample}/pro.clipped.fastq")
+		reads = os.path.join(config["output_dir"], "{sample}/pro.clipped.fastq.gz")
 	output:
-		reads = os.path.join(config["output_dir"], "{sample}/pro.trimmed.fastq"),
+		reads = os.path.join(config["output_dir"], "{sample}/pro.trimmed.fastq.gz"),
 	params:
 		v = "-v",
 		l = "20",
-		t = "20",
-		qual = "-Q33",
+		t = lambda wildcards: config[wildcards.sample]['minimum_quality'],
+		Q = lambda wildcards: config[wildcards.sample]['quality_type'],
 		z = "-z",
 		cluster_log = os.path.join(config["cluster_log"], "trim_reads_{sample}.log")
 	log:
@@ -87,8 +86,9 @@ rule trim_reads:
 		{params.v} \
 		-l {params.l} \
 		-t {params.t} \
-		{params.qual} \
-		-i {input.reads} \
+		-Q {params.Q} \
+		{params.z} \
+		-i <(zcat {input.reads}) \
 		-o {output.reads}) &> {log}"
 
 #################################################################################
@@ -97,14 +97,15 @@ rule trim_reads:
 
 rule filter_reads:
 	input:
-		reads = os.path.join(config["output_dir"], "{sample}/pro.trimmed.fastq"),
+		reads = os.path.join(config["output_dir"], "{sample}/pro.trimmed.fastq.gz"),
 	output:
-		reads = os.path.join(config["output_dir"], "{sample}/pro.filtered.fastq"),
+		reads = os.path.join(config["output_dir"], "{sample}/pro.filtered.fastq.gz"),
 	params:
 		v = "-v",
-		q = "20",
+		q = lambda wildcards: config[wildcards.sample]['minimum_quality'],
 		p = "90",
-		qual = "-Q33",
+		z = "-z",
+		Q = lambda wildcards: config[wildcards.sample]['quality_type'],
 		cluster_log = os.path.join(config["cluster_log"], "filter_reads_{sample}.log")
 	log:
 		os.path.join(config["local_log"], "filter_reads_{sample}.log")
@@ -115,8 +116,9 @@ rule filter_reads:
 		{params.v} \
 		-q {params.q} \
 		-p {params.p} \
-		{params.qual} \
-		-i {input.reads} \
+		-Q {params.Q} \
+		{params.z} \
+		-i <(zcat {input.reads}) \
 		-o {output.reads}) &> {log}"
 
 #################################################################################
@@ -125,15 +127,13 @@ rule filter_reads:
 
 rule fastq_to_fasta:
 	input:
-		reads = os.path.join(config["output_dir"], "{sample}/pro.filtered.fastq"),
+		reads = os.path.join(config["output_dir"], "{sample}/pro.filtered.fastq.gz"),
 	output:
 		reads = os.path.join(config["output_dir"], "{sample}/pro.filtered.fasta"),
 	params:
 		v = "-v",
-		qual = "-Q33",
 		n = "-n",
 		r = "-r",
-		z = "-z",
 		cluster_log = os.path.join(config["cluster_log"], "fastq_to_fasta_{sample}.log")
 	log:
 		os.path.join(config["local_log"], "fastq_to_fasta_{sample}.log")
@@ -142,10 +142,9 @@ rule fastq_to_fasta:
 	shell:
 		"(fastq_to_fasta \
 		{params.v} \
-		{params.qual} \
 		{params.n} \
 		{params.r} \
-		-i {input.reads} \
+		-i <(zcat {input.reads}) \
 		-o {output.reads}) &> {log}"
 
 #################################################################################

snakemake/process_data/config.yaml

@@ -18,8 +18,7 @@
   ##############################################################################
   input_dir: "samples"
   input_reads_pattern: ".fastq.gz"
-  sample: ["example", "s_ribseq_r1"]
-  example: {adapter: GATCGGAAGAGCACA}
-  m_ribseq_r2: {adapter: CTGTAGGCACCATCA}
-  s_ribseq_r1: {adapter: CTGTAGGCACCATCA}
+  sample: ["example", "example2"]
+  example: {adapter: GATCGGAAGAGCACA, minimum_quality: 20, quality_type: 33}
+  example2: {adapter: CTGTAGGCACCATCA, minimum_quality: 20, quality_type: 64}
 ...