update rules step 05

05_assignment/rules/assign_taxon.smk

+### Assign each sequence to a taxon
+rule assign_taxon:
+    input:
+        '../results/05_assignment/02_dereplicated/{run}.uniq.fasta'
+    output:
+        '../results/05_assignment/03_assigned/{run}.tag.u.fasta'
+    singularity:
+        config["singularity"]["obitools"]
+    params:
+        drun= lambda wildcards: dfpmr[dfpmr.projmarkrun == wildcards.run].to_dict('records')[0],
+    log:
+        '../logs/05_assignment/03_assign_taxon/{run}.log'
+    shell:
+        '''ecotag -d {params.drun[bdr]} -R {params.drun[fasta]} {input} > {output} 2> {log}'''
\ No newline at end of file

05_assignment/rules/dereplicate_runs.smk

+### Dereplicate and merge samples together
+rule dereplicate_runs:
+    input:
+        '../results/05_assignment/01_runs/{run}.fasta'
+    output:
+        '../results/05_assignment/02_dereplicated/{run}.uniq.fasta'
+    singularity:
+        config["singularity"]["obitools"]
+    log:
+        '../logs/05_assignment/02_dereplicated/{run}.log'
+    shell:
+        '''obiuniq -m sample {input} > {output} 2> {log}'''
\ No newline at end of file

05_assignment/rules/rm_attributes.smk

+### Some unuseful attributes can be removed at this stage
+rule rm_attributes:
+    input:
+        '../results/05_assignment/03_assigned/{run}.tag.u.fasta'
+    output:
+        '../results/05_assignment/04_formated/{run}.a.t.u.fasta'
+    singularity:
+        config["singularity"]["obitools"]
+    log:
+        '../logs/05_assignment/04_rm_attributes/{run}.log'
+    shell:
+        '''obiannotate --delete-tag=scientific_name_by_db --delete-tag=obiclean_samplecount \
+ --delete-tag=obiclean_count --delete-tag=obiclean_singletoncount \
+ --delete-tag=obiclean_cluster --delete-tag=obiclean_internalcount \
+ --delete-tag=obiclean_head  --delete-tag=obiclean_headcount \
+ --delete-tag=id_status --delete-tag=rank_by_db --delete-tag=obiclean_status \
+ --delete-tag=seq_length_ori --delete-tag=sminL --delete-tag=sminR \
+ --delete-tag=reverse_score --delete-tag=reverse_primer --delete-tag=reverse_match --delete-tag=reverse_tag \
+ --delete-tag=forward_tag --delete-tag=forward_score --delete-tag=forward_primer --delete-tag=forward_match \
+ --delete-tag=tail_quality {input} > {output} 2> {log}'''
\ No newline at end of file

05_assignment/rules/sort_runs.smk

+### The sequences can be sorted by decreasing order of count
+rule sort_runs:
+    input:
+        '../results/05_assignment/04_formated/{run}.a.t.u.fasta'
+    output:
+        '../results/05_assignment/04_formated/{run}.s.a.t.u.fasta'
+    singularity:
+        config["singularity"]["obitools"]
+    log:
+        '../logs/05_assignment/05_sort_runs/{run}.log'
+    shell:
+        '''obisort -k count -r {input} > {output} 2> {log}'''
\ No newline at end of file

05_assignment/rules/table_runs.smk

+### Generate a table final results
+rule table_runs:
+    input:
+        '../results/05_assignment/04_formated/{run}.s.a.t.u.fasta'
+    output:
+        '../results/06_final_tables/{run}.csv'
+    singularity:
+        config["singularity"]["obitools"]
+    params:
+        drun= lambda wildcards: dfpmr[dfpmr.projmarkrun == wildcards.run].to_dict('records')[0],
+    log:
+        '../logs/05_assignment/06_table_runs/{run}.log'
+    shell:
+        '''mkdir -p ../results/06_final_tables/{params.drun[projet]}/{params.drun[marker]}; obitab -o {input} > {output} 2> {log}'''
\ No newline at end of file