updated annotation (not tested)

workflow/rules/annotation.smk

@@ -143,7 +143,45 @@ rule annotation_rgi:
         #       need to run the CMD twice
         "rgi main --input_sequence {input.faa} --output_file {params.obname} --input_type protein --local -a {params.alignment_tool} --clean -n {threads} || "
         "rgi main --input_sequence {input.faa} --output_file {params.obname} --input_type protein --local -a {params.alignment_tool} --clean -n {threads} && "
-        ") 2> {log.err} > {log.out}"
+        "date) 2> {log.err} > {log.out}"
+
+##################################################
+# CRISPR
+
+rule casc:
+    input:
+        os.path.join(RESULTS_DIR, "assembly/{rtype}/{tool}/ASSEMBLY.fasta")
+    output:
+        os.path.join(RESULTS_DIR, "annotation/casc/{rtype}/{tool}/ASSEMBLY.results.txt")
+    log:
+        out="logs/annotation_casc_{rtype}.{tool}.out.log",
+        err="logs/annotation_casc_{rtype}.{tool}.err.log"
+    threads:
+        config["casc"]["threads"]
+    conda:
+        os.path.join(ENV_DIR, "analysis.yaml")
+    shell:
+        "(date && "
+        "export PATH={config[casc][path]} && "
+        "export PERL5LIB={config[casc][perl5lib]} && "
+        "casc -i {input} -o $(dirname {output}) -n {threads} --conservative && "
+        "date) 2> {log.err} > {log.out}"
+
+rule minced:
+    input:
+        os.path.join(RESULTS_DIR, "assembly/{rtype}/{tool}/ASSEMBLY.fasta")
+    output:
+        txt=os.path.join(RESULTS_DIR, "annotation/minced/{rtype}/{tool}/ASSEMBLY.results.txt"),
+        gff=os.path.join(RESULTS_DIR, "annotation/minced/{rtype}/{tool}/ASSEMBLY.results.gff")
+    log:
+        out="logs/annotation_minced_{rtype}.{tool}.out.log",
+        err="logs/annotation_minced_{rtype}.{tool}.err.log"
+    conda: "../envs/analysis.yaml"
+    shell:
+        "(date && "
+        "export PATH={config[minced][path]} && "
+        "minced {input} {output.txt} {output.gff} && "
+        "date) 2> {log.err} > {log.out}"
 
 ##################################################
 # PlasFlow
@@ -169,7 +207,8 @@ rule annotation_plasflow:
     input:
         os.path.join(RESULTS_DIR, "annotation/plasflow/{rtype}/{tool}/input.fasta")
     output:
-        os.path.join(RESULTS_DIR, "annotation/plasflow/{rtype}/{tool}/plasflow.tsv")
+        tmp=os.path.join(RESULTS_DIR, "annotation/plasflow/{rtype}/{tool}/plasflow.tsv.tmp"),
+        tsv=os.path.join(RESULTS_DIR, "annotation/plasflow/{rtype}/{tool}/plasflow.tsv")
     log:
         out="logs/annotation_plasflow_{rtype}.{tool}.out.log",
         err="logs/annotation_plasflow_{rtype}.{tool}.err.log"
@@ -185,7 +224,6 @@ rule annotation_plasflow:
         "PlasFlow: predict: {input}"
     shell:
         "(date && "
-        "PlasFlow.py --input {input} --output {output}.tmp --threshold {params.threshold} &> {log} && "
-        "date) 2> {log.err} > {log.out} && "
-        "cut -f3,4,6- {output}.tmp > {output} && "
-        "rm {output}.tmp*"
\ No newline at end of file
+        "PlasFlow.py --input {input} --output {output.tmp} --threshold {params.threshold} &> {log} && "
+        "cut -f3,4,6- {output.tmp} > {output.tsv} && "
+        "date) 2> {log.err} > {log.out}"

workflow/steps/annotation.smk

@@ -24,6 +24,15 @@ rule PROTEINS:
             os.path.join(RESULTS_DIR, "annotation/rgi/{rtype_tool}/rgi.txt"),
             rtype_tool=["%s/%s" % (rtype, tool) for rtype, tool in READ_ASSEMBLERS]
         )
+        # crispr
+        expand(
+            os.path.join(RESULTS_DIR, "annotation/casc/{rtype_tool}/ASSEMBLY.results.txt"),
+            rtype_tool=["%s/%s" % (rtype, tool) for rtype, tool in READ_ASSEMBLERS]
+        )
+        expand(
+            os.path.join(RESULTS_DIR, "annotation/minced/{rtype_tool}/ASSEMBLY.results.txt"),
+            rtype_tool=["%s/%s" % (rtype, tool) for rtype, tool in READ_ASSEMBLERS]
+        )
         # plasflow
         expand(
             os.path.join(RESULTS_DIR, "annotation/plasflow/{rtype_tool}/plasflow.tsv"),