modifications

dada2.R

@@ -4,7 +4,7 @@ derepF <- derepFastq(snakemake@input[[1]], verbose = TRUE)
 derepR <- derepFastq(snakemake@input[[2]], verbose = TRUE)
 errF <- learnErrors(snakemake@input[[1]], multithread = snakemake@threads, verbose = TRUE)
 errR <- learnErrors(snakemake@input[[2]], multithread = snakemake@threads, verbose = TRUE)
-dadaFs <- dada(derep, err = errF, multithread = snakemake@threads, verbose = TRUE)
-dadaRs <- dada(derep, err = errR, multithread = snakemake@threads, verbose = TRUE)
-mergers <- mergePairs(dadaFs, dadaRs, verbose=TRUE)
-saveRDS(dada, snakemake@output[[1]])
+dadaFs <- dada(derepF, err = errF, multithread = snakemake@threads, verbose = TRUE)
+dadaRs <- dada(derepR, err = errR, multithread = snakemake@threads, verbose = TRUE)
+mergers <- mergePairs(dadaFs, derepF, dadaRs, derepR, verbose=TRUE)
+saveRDS(mergers, snakemake@output[[1]])

dada2.smk

 rule dada2:
 	input:
-		filt = "work/filter/{sample}.sra_1.fastq.gz",
-		filtrev = "work/filter/{sample}.sra_2.fastq.gz"
+		filt = "work/filter/{sample}_1.fastq.gz",
+		filtrev = "work/filter/{sample}_2.fastq.gz"
 	output:
 		"work/dada/{sample}.rds"
 	threads:
@@ -25,7 +25,7 @@ rule makeSequenceTable:
 rule metrics:
   input:
     rds = "work/dada/seqtab.rds",
-    fastqc = expand("work/fastqc/{sample}_fastqc.zip", sample=SAMPLES)
+    fastqc = expand("work/fastqc/{sample}_{unit}_fastqc.zip", sample=SAMPLES, unit=unit)
   output:
     tsv = "work/dada/metrics.tsv"
   script:

filterAndTrim.R

 library(dada2)
 
-filterAndTrim(snakemake@input[[1]],snakemake@input[[2]] snakemake@output[[1]], maxN=0, rm.phix=TRUE, compress=TRUE, verbose = TRUE)
+filterAndTrim(snakemake@input[[1]],snakemake@output[[1]], snakemake@input[[2]], snakemake@output[[2]], maxN=0, rm.phix=TRUE, compress=TRUE, verbose = TRUE)
\ No newline at end of file

global.smk

@@ -4,23 +4,26 @@ shell.prefix("source /usr/local/genome/Anaconda2-5.1.0/etc/profile.d/conda.sh;")
 configfile: "./config.json"
 
 SAMPLES=config["SAMPLES"]
+unit=config["unit"]
 
 rule all:
-	input:expand("DATA/{sample}.sra.fastq.gz", sample=SAMPLES),
+	input:#expand("DATA/{sample}.fastq.gz", sample=SAMPLES),
 		"report/multiqc_report.html",
+		expand("work/filter/{sample}_1.fastq.gz", sample=SAMPLES),
+		expand("work/filter/{sample}_2.fastq.gz", sample=SAMPLES),
 		expand("work/dada/{sample}.rds", sample=SAMPLES),
 		"work/dada/seqtab.fasta",
 		"work/dada/seqtab.tsv",
 		"work/dada/metrics.tsv",
-		"work/frogs/affiliation.biom",
-		"report/clusters_metrics.html",
-		"report/affiliations_metrics.html",
-		"report/abundance.biom",
-		"report/abundance.tsv",
-		"report/tree.nwk"
+		#"work/frogs/affiliation.biom",
+		#"report/clusters_metrics.html",
+		#"report/affiliations_metrics.html",
+		#"report/abundance.biom",
+		#"report/abundance.tsv",
+		#"report/tree.nwk"
 
-include: "prefetech.smk"
+#include: "prefetech.smk"
 include: "quality.smk"
 include: "preprocess.smk"
 include: "dada2.smk"
-include: "affiliation.smk"
+#include: "affiliation.smk"

preprocess.smk

 rule cutadapt:
 	input:
-		fwd = "DATA/{sample}.sra_1.fastq.gz",
-		rev = "DATA/{sample}.sra_2.fastq.gz"
+		fwd = "DATA/{sample}_1.fastq.gz",
+		rev = "DATA/{sample}_2.fastq.gz"
 	output:
-		cut = "work/cutadapt/{sample}.sra_1.fastq.gz",
-		cutrev = "work/cutadapt/{sample}.sra_2.fastq.gz"
+		cut = "work/cutadapt/{sample}_1.fastq.gz",
+		cutrev = "work/cutadapt/{sample}_2.fastq.gz"
 	params:
 		five = lambda wildcards: config["FIVE_PRIMER"][wildcards.sample],
 		three = lambda wildcards: config["THREE_PRIMER"][wildcards.sample]
@@ -14,20 +14,23 @@ rule cutadapt:
 		"cutadapt "
 		"-g {params.five} "
 		"-a {params.three} "
+		"-G {params.five} "
+		"-A {params.three} "
 		"--error-rate 0.1 "
 		"--discard-untrimmed "
 		"--match-read-wildcards "
-		"-o {output} "
+		"-o {output.cut} "
+		"-p {output.cutrev} "
 		"{input} "
 		"&& "
 		"conda deactivate"
 
 rule filter:
 	input:
-		cut = "work/cutadapt/{sample}.sra_1.fastq.gz",
-		cutrev = "work/cutadapt/{sample}.sra_2.fastq.gz"
+		cut = "work/cutadapt/{sample}_1.fastq.gz",
+		cutrev = "work/cutadapt/{sample}_2.fastq.gz"
 	output:
-		filt = "work/filter/{sample}.sra_1.fastq.gz",
-		filtrev = "work/filter/{sample}.sra_2.fastq.gz"
+		filt = "work/filter/{sample}_1.fastq.gz",
+		filtrev = "work/filter/{sample}_2.fastq.gz"
 	script:
 		"filterAndTrim.R"

quality.smk

 rule fastqc:
     input:
-        fwd = "DATA/{sample}.sra_1.fastq.gz",
-        rev = "DATA/{sample}.sra_2.fastq.gz"
+        fwd = "DATA/{sample}_1.fastq.gz",
+        rev = "DATA/{sample}_2.fastq.gz"
     output:
-        zip = "work/fastqc/{sample}_fastqc.zip",
-        html = "work/fastqc/{sample}_fastqc.html"
+        zip = "work/fastqc/{sample}_{unit}_fastqc.zip",
+        html = "work/fastqc/{sample}_{unit}_fastqc.html"
     params:
         output = "work/fastqc/"
     shell:
@@ -19,7 +19,7 @@ rule fastqc:
 
 rule multiqc:
     input:
-        expand("work/fastqc/{sample}_fastqc.zip", sample=SAMPLES)
+        expand("work/fastqc/{sample}_{unit}_fastqc.zip", sample=SAMPLES, unit=unit)
     output:
         html = "report/multiqc_report.html",
     params: