Fix the kraken anchor and add the missing log files

sequana_pipelines/laa/laa.rules

@@ -91,8 +91,10 @@ if do_snpeff:
     rule copy_genbank:
         input: config["annotation_file"]
         output: __copy_genbank__output
+        log:
+            "logs/copy_genbank.log"
         shell:
-            """cp {input} {output}"""
+            """cp {input} {output} >{log} 2>&1"""
     expected_output.append(__copy_genbank__output)
 
 
@@ -113,10 +115,12 @@ if laa is True:
         threads: 2
         container:
             config["apptainers"]["laa"]
+        log:
+            "logs/bc{sample}/laa.log"
         shell:
             """
-            cd {params.directory}
-            laa --noPhasing --minLength 1000 --maxReads 2400  --numThreads={threads} {input}
+            (cd {params.directory} && \
+             laa --noPhasing --minLength 1000 --maxReads 2400 --numThreads={threads} {input}) >{log} 2>&1
             """
 
 
@@ -130,9 +134,11 @@ if bam2ccs:
         threads: 4
         container:
             config['apptainers']['ccs']
+        log:
+            "logs/bc{sample}/bam2ccs.log"
         shell:
             """
-            ccs {input} {output} --numThreads {threads}
+            ccs {input} {output} --numThreads {threads} >{log} 2>&1
             """
 
 
@@ -142,9 +148,11 @@ if ccs2fastq:
         output: "fastq/{sample}/data.fastq"
         container:
             config['apptainers']['samtools']
+        log:
+            "logs/{sample}/ccs2fastq.log"
         shell:
             """
-            samtools fastq {input} > {output}
+            samtools fastq {input} > {output} 2>{log}
             """
 
 
@@ -216,9 +224,11 @@ else:
             src=reference_file
         output:
             src=new_reference
+        log:
+            "logs/copy_reference.log"
         shell:
             """
-            cp {input.src} {output.src}
+            cp {input.src} {output.src} >{log} 2>&1
             """
 
 
@@ -269,30 +279,36 @@ rule mapping:
 rule samtools_stats:
     input: "{sample}/mapping/mapping.sorted.bam"
     output: "{sample}/mapping/samtools_{sample}.txt"
+    log:
+        "logs/{sample}/samtools_stats.log"
     container:
         config['apptainers']['samtools']
     shell:
-        "samtools stats -in {input} > {output}"
+        "samtools stats -in {input} > {output} 2>{log}"
 
 
 rule bamtools_stats:
     input: "{sample}/mapping/mapping.sorted.bam"
     output: "{sample}/mapping/sequana_bamtools_stats_{sample}.txt"
+    log:
+        "logs/{sample}/bamtools_stats.log"
     container:
         config['apptainers']['sequana_tools']
     shell:
-        "bamtools stats -in {input} > {output}"
+        "bamtools stats -in {input} > {output} 2>{log}"
 
 
 rule mapping_index:
         input: "{sample}/mapping/mapping.sorted.bam"
         output: "{sample}/mapping/mapping.sorted.bam.bai"
         threads:
             1
+        log:
+            "logs/{sample}/mapping_index.log"
         container:
             config['apptainers']['sequana_tools']
         shell:
-            "bamtools index -in {input}"
+            "bamtools index -in {input} >{log} 2>&1"
 
 
 if do_freebayes:
@@ -322,11 +338,13 @@ if do_split_multiallelic:
             "{sample}/freebayes/variants.raw.vcf"
         output:
             "{sample}/freebayes/variants.raw.split.vcf"
+        log:
+            "logs/{sample}/split_multiallelic.log"
         container:
             config['apptainers']['sequana_tools']
         shell:
             """
-            bcftools norm -m -both {input} | vt decompose_blocksub - > {output}
+            (bcftools norm -m -both {input} | vt decompose_blocksub -) > {output} 2>{log}
             """
     __freebayes__output = __split_multiallelic__output
 
@@ -464,6 +482,9 @@ rule rulegraph:
         manager.get_run("rulegraph/run", "v1")(input, output, params)
 
 
+localrules: rulegraph, dot2svg
+
+
 rule dot2svg:
     input:
         "rulegraph/rulegraph.dot"
@@ -613,12 +634,14 @@ rule mafft:
         aln="outputs/mafft/mafft.aln.fa"
     threads:
         2
+    log:
+        "logs/mafft.log"
     container:
         config['apptainers']['sequana_tools']
     shell:
         """
         mafft --thread {threads} --retree 1 --maxiterate 0 --add {input.fasta} \
-        --keeplength {input.reference} > {output.aln}
+        --keeplength {input.reference} > {output.aln} 2>{log}
         """
 
 
@@ -649,14 +672,16 @@ rule raxml_mltree:
         N=config['raxml_mltree']['N'],
         options=config['raxml_mltree']['options'],
         wkdir=os.path.abspath("outputs/raxml")
+    log:
+        "logs/raxml_mltree.log"
     container:
         config['apptainers']['raxml']
     shell:
         """
         # First, let us get a best likelihood tree from 20 ML trees
         mkdir -p outputs/raxml && \
         rm -f outputs/raxml/*T1111* &&\
-        raxmlHPC-PTHREADS -m GTRGAMMA -s {input.aln}  -p 12345  -T {threads} -w {params.wkdir} -N {params.N} -n T1111 1>{output.log}
+        raxmlHPC-PTHREADS -m GTRGAMMA -s {input.aln}  -p 12345  -T {threads} -w {params.wkdir} -N {params.N} -n T1111 1>{output.log} 2>{log}
         """
 
 
@@ -712,6 +737,8 @@ rule raxml_bipartitions:
     params:
         wkdir=os.path.abspath("outputs/raxml")
     threads: 1
+    log:
+        "logs/raxml_bipartitions.log"
     container:
         config['apptainers']['raxml']
     shell:
@@ -720,7 +747,7 @@ rule raxml_bipartitions:
         mkdir -p outputs/raxml
         rm -f outputs/raxml/*T3333*
 
-        raxmlHPC -m GTRCAT -f b -p 12345 -w {params.wkdir} -t {input.best} -z {input.boot} -n T3333
+        raxmlHPC -m GTRCAT -f b -p 12345 -w {params.wkdir} -t {input.best} -z {input.boot} -n T3333 >{log} 2>&1
 
         """
 
@@ -809,7 +836,8 @@ rule remapping:
 rule build_fasta:
     input: expand("{sample}/consensus/consensus.fa", sample=sorted(manager.samples))
     output: "outputs/allfasta.fa"
-    shell: "cat {input} > {output}"
+    log: "logs/build_fasta.log"
+    shell: "cat {input} > {output} 2>{log}"
 
 
 if do_kraken:
@@ -1076,7 +1104,7 @@ this <a href="multiqc_report.html">multiqc report.</a></p>
             sample_summary['kraken_json'] = json.loads(k._get_stats().to_json())
             conf.summary_sections.append({
                 "name": "Kraken ",
-                "anchor'": "kraken",
+                "anchor": "kraken",
                 "content": k._get_summary_section()
             })