rules/step1.smk → 00-rules/assembly.smk

@@ -8,11 +8,11 @@ rule illuminapairedend:
         R1=config['fastqFolderPath']+'{run}_R1.fastq.gz',
         R2=config['fastqFolderPath']+'{run}_R2.fastq.gz'
     output:
-        fq='assembled/{run}/{run}.fastq'
+        fq='01-assembly/{run}/{run}.fastq'
     singularity:
         config["container"]
     log:
-        'log/illuminapairedend/{run}.log'
+        '99-log/illuminapairedend/{run}.log'
     params:
         s_min=config["illuminapairedend"]["s_min"]
     shell:
@@ -21,42 +21,13 @@ rule illuminapairedend:
 ### Remove unaligned sequence records
 rule remove_unaligned:
     input:
-        fq='assembled/{run}/{run}.fastq'
+        fq='01-assembly/{run}/{run}.fastq'
     output:
-        ali='assembled/{run}/{run}.ali.fastq'
+        ali='01-assembly/{run}/{run}.ali.fastq'
     singularity:
         config["container"]
     log:
-        'log/remove_unaligned/{run}.log'
+        '99-log/remove_unaligned/{run}.log'
     shell:
         '''obigrep -p 'mode!=\"joined\"' {input.fq} > {output.ali} 2> {log}'''
 
-### Assign each sequence record to the corresponding sample/marker combination
-rule assign_sequences:
-    input:
-        'assembled/{run}/{run}.ali.fastq',
-    output:
-        assign='assembled/{run}/{run}.ali.assigned.fastq',
-        unid='assembled/{run}/{run}.unidentified.fastq'
-    singularity:
-        config["container"]
-    params:
-        barcodeFile=lambda wcs: config["barcodeFiles"][wcs.run]
-        barcodeFolder=config['fastqFolderPath']
-    log:
-        'log/assign_sequences/{run}.log'
-    shell:
-        '''ngsfilter -t {params.barcodeFolder}{params.barcodeFile} -u {output.unid} {input[0]} --fasta-output > {output.assign} 2> {log}'''
-
-### Split the input sequence file in a set of subfiles according to the values of attribute `sample`
-rule split_sequences:
-    input:
-        'assembled/{run}/{run}.ali.assigned.fastq'
-    params:
-        'samples/{run}_sample_'
-    singularity:
-        config["container"]
-    log:
-        'log/split_sequences/{run}.log'
-    shell:
-        '''obisplit -p "{params}" -t sample --fasta {input} 2> {log}'''

00-rules/demultiplex.smk

+### Assign each sequence record to the corresponding sample/marker combination
+rule assign_sequences:
+    input:
+        '01-assembly/{run}/{run}.ali.fastq',
+    output:
+        assign='01-assembly/{run}/{run}.ali.assigned.fastq',
+        unid='01-assembly/{run}/{run}.unidentified.fastq'
+    singularity:
+        config["container"]
+    params:
+        barcodeFile=lambda wcs: config["barcodeFiles"][wcs.run],
+        barcodeFolder=config['fastqFolderPath']
+    log:
+        '99-log/assign_sequences/{run}.log'
+    shell:
+        '''ngsfilter -t {params.barcodeFolder}{params.barcodeFile} -u {output.unid} {input} --fasta-output > {output.assign} 2> {log}'''
+
+
+### Split the input sequence file in a set of subfiles according to the values of attribute `sample`
+rule split_sequences:
+    input:
+        '01-assembly/{run}/{run}.ali.assigned.fastq'
+    params:
+        '02-demultiplex/{run}_sample_'
+    singularity:
+        config["container"]
+    log:
+        'log/split_sequences/{run}.log'
+    shell:
+        '''obisplit -p "{params}" -t sample --fasta {input} 2> {log}'''

00-rules/step2.smk

+### dereplicate reads into uniq sequences
+rule dereplicate_samples:
+    input:
+        'samples/{sample}.fasta'
+    output:
+        'samples/{sample}.uniq.fasta'
+    log:
+        'log/dereplicate_samples/{sample}.log'
+    shell:
+        '''obiuniq -m sample {input} > {output} 2> {log}'''
+
+### only sequence more than 20bp with no ambiguity IUAPC with total coverage greater than 10 reads
+rule goodlength_samples:
+    input:
+        'samples/{sample}.uniq.fasta'
+    output:
+        'samples/{sample}.l.u.fasta'
+    log:
+        'log/goodlength_samples/{sample}.log'
+    params:
+         count=config["good_length_samples"]["count"],
+         seq_length=config["good_length_samples"]["seq_length"]
+    shell:
+        '''obigrep  -p 'count>{params.count}' -s '^[ACGT]+$' -p 'seq_length>{params.seq_length}' {input} > {output} 2> {log}'''
+
+### Clean the sequences for PCR/sequencing errors (sequence variants)
+rule clean_pcrerr_samples:
+    input:
+        'samples/{sample}.l.u.fasta'
+    output:
+        'samples/{sample}.r.l.u.fasta'
+    log:
+        'log/clean_pcrerr/{sample}.log'
+    params:
+         r=config["clean_pcrerr_samples"]["r"]
+    shell:
+        '''obiclean -r {params.r} {input} > {output} 2> {log}'''
+
+### Remove sequence which are classified as 'internal' by obiclean
+rule rm_internal_samples:
+    input:
+        'samples/{sample}.r.l.u.fasta'
+    output:
+        'samples/{sample}.c.r.l.u.fasta'
+    log:
+        'log/rm_internal_samples/{sample}.log'
+    shell:
+        '''obigrep -p 'obiclean_internalcount == 0' {input} > {output} 2> {log}'''