new rules with new path wildcards

04_filter_samples/rules/clean_pcrerr_samples.smk

+### Clean the sequences for PCR/sequencing errors (sequence variants)
+rule clean_pcrerr_samples:
+    input:
+        '../results/04_filter_samples/02_goodlength/{demultiplexs}.l.u.fasta'
+    output:
+        '../results/04_filter_samples/03_clean_pcrerr/{demultiplexs}.r.l.u.fasta'
+    singularity:
+        config["singularity"]["obitools"]
+    log:
+        '../logs/04_filter_samples/03_clean_pcrerr/{demultiplexs}.log'
+    params:
+         r=config["clean_pcrerr_samples"]["r"]         
+    shell:
+        '''if [[ -s {input} ]]; then obiclean -r {params.r} {input} > {output} 2> {log} ; else touch {output} 2> {log} ; fi'''
\ No newline at end of file

04_filter_samples/rules/dereplicate_samples.smk

+### dereplicate reads into uniq sequences
+rule dereplicate_samples:
+    input:
+        '../results/03_demultiplex/02_raw/{demultiplexs}.fasta'
+    output:
+        '../results/04_filter_samples/01_dereplicated/{demultiplexs}.uniq.fasta'
+    singularity:
+        config["singularity"]["obitools"]
+    log:
+        '../logs/04_filter_samples/01_dereplicated/{demultiplexs}.log'
+    params:
+        dmulti= lambda wildcards: dfMultiChecked[dfMultiChecked.demultiplex == wildcards.demultiplexs].to_dict('records')[0],        
+    shell:
+        '''mkdir -p 01_dereplicated/{params.dmulti[projmarkrun]}; obiuniq -m sample {input} > {output} 2> {log}'''
\ No newline at end of file

04_filter_samples/rules/goodlength_samples.smk

+### only sequence more than 20bp with no ambiguity IUAPC with total coverage greater than 10 reads
+rule goodlength_samples:
+    input:
+        '../results/04_filter_samples/01_dereplicated/{demultiplexs}.uniq.fasta'
+    output:
+        '../results/04_filter_samples/02_goodlength/{demultiplexs}.l.u.fasta'
+    singularity:
+        config["singularity"]["obitools"]
+    log:
+        '../logs/04_filter_samples/02_goodlength/{demultiplexs}.log'
+    params:
+        seq_count=config["good_length_samples"]["seq_count"],
+        seq_length=config["good_length_samples"]["seq_length"]        
+    shell:
+        '''obigrep  -p 'count>{params.seq_count}' -s '^[ACGT]+$' -p 'seq_length>{params.seq_length}' {input} > {output} 2> {log}'''
\ No newline at end of file

04_filter_samples/rules/rm_internal_samples.smk

+### Remove sequence which are classified as 'internal' by obiclean
+rule rm_internal_samples:
+    input:
+        '../results/04_filter_samples/03_clean_pcrerr/{demultiplexs}.r.l.u.fasta'
+    output:
+        '../results/04_filter_samples/04_filtered/{demultiplexs}.c.r.l.u.fasta'
+    params:
+        dmulti= lambda wildcards: dfMultiChecked[dfMultiChecked.demultiplex == wildcards.demultiplexs].to_dict('records')[0],
+    singularity:
+        config["singularity"]["obitools"]
+    log:
+        '../logs/04_filter_samples/04_filtered/{demultiplexs}.log'
+    shell:
+        '''if [[ -s {input} ]]; then mkdir -p 04_filtered/{params.dmulti[projmarkrun]}; obigrep -p "obiclean_internalcount == 0" {input} > {output} 2> {log} ; else touch {output} 2> {log} ; fi'''