Define params and envs to follow lint format guidelines

PathoGenOmics-Lab · Aug 8, 2023 · ff018be · ff018be
1 parent 0c0c18d
commit ff018be
Show file tree

Hide file tree

Showing 6 changed files with 25 additions and 12 deletions.
diff --git a/workflow/envs/fetch.yaml b/workflow/envs/fetch.yaml
@@ -4,3 +4,4 @@ channels:
   - anaconda
 dependencies:
   - entrez-direct==16.2
+  - curl==8.2.1
diff --git a/workflow/rules/asr.smk b/workflow/rules/asr.smk
@@ -4,7 +4,9 @@ rule reconstruct_ancestral_sequence:
     params:
         seqtype = "DNA",
         name = OUTPUT_NAME,
-        etc = ETC_TREE_PARAMS
+        etc = ETC_TREE_PARAMS,
+        outgroup = config["ALIGNMENT_REFERENCE"],
+        model = config["TREE_MODEL"]
     input:
         fasta = OUTDIR/"nextalign"/f"{OUTPUT_NAME}.aligned.masked.fasta"
     output:
@@ -17,8 +19,8 @@ rule reconstruct_ancestral_sequence:
         mkdir -p {output.folder}
         iqtree2 \
             {params.etc} -asr \
-            -o {config[ALIGNMENT_REFERENCE]} -T AUTO --threads-max {threads} -s {input.fasta} \
-            --seqtype {params.seqtype} -m {config[TREE_MODEL]} --prefix {output.folder}/{params.name} >{log} 2>&1
+            -o {params.outgroup} -T AUTO --threads-max {threads} -s {input.fasta} \
+            --seqtype {params.seqtype} -m {params.model} --prefix {output.folder}/{params.name} >{log} 2>&1
         """
 
 

diff --git a/workflow/rules/context.smk b/workflow/rules/context.smk
@@ -75,7 +75,9 @@ rule ml_context_tree:
         seqtype = "DNA",
         name = OUTPUT_NAME,
         etc = ETC_TREE_PARAMS,
-        bootstrap = 1000
+        bootstrap = 1000,
+        outgroup = config["ALIGNMENT_REFERENCE"],
+        model = config["TREE_MODEL"]
     input:
         fasta = OUTDIR/"nextalign"/f"{OUTPUT_NAME}.aligned.masked.fasta",
         outgroup_aln = OUTDIR/"context"/"nextalign"/"context_sequences.aligned.masked.fasta"
@@ -93,6 +95,6 @@ rule ml_context_tree:
         mkdir -p {output.folder}
         iqtree2 \
             {params.etc} -B {params.bootstrap} \
-            -o {config[ALIGNMENT_REFERENCE]} -T AUTO --threads-max {threads} -s aln.fasta \
-            --seqtype {params.seqtype} -m {config[TREE_MODEL]} --prefix {output.folder}/{params.name}
+            -o {params.outgroup} -T AUTO --threads-max {threads} -s aln.fasta \
+            --seqtype {params.seqtype} -m {params.model} --prefix {output.folder}/{params.name}
         """
diff --git a/workflow/rules/fasta.smk b/workflow/rules/fasta.smk
@@ -7,8 +7,7 @@ rule rename_fastas:
         LOGDIR / "rename_fastas" / "{sample}.log.txt"
     shell:
         "sed 's/>.*/>'{wildcards.sample}'/g' {input.fasta} > {output.renamed} 2> {log}"
-
-
+
 
 rule concat_fasta:
     threads: 1

diff --git a/workflow/rules/fetch.smk b/workflow/rules/fetch.smk
@@ -1,17 +1,21 @@
 rule fetch_alignment_reference:
     threads: 1
     conda: "../envs/fetch.yaml"
+    params:
+        ref = config["ALIGNMENT_REFERENCE"]
     output:
         fasta = OUTDIR/"reference.fasta"
     log:
         LOGDIR / "fetch_alignment_reference" / "log.txt"
     shell:
-        "esearch -db nucleotide -query {config[ALIGNMENT_REFERENCE]} | efetch -format fasta > {output.fasta} 2> {log}"
+        "esearch -db nucleotide -query {params.ref} | efetch -format fasta > {output.fasta} 2> {log}"
 
 
 rule fetch_mapping_references:
     threads: 1
     conda: "../envs/fetch.yaml"
+    params:
+        refs = config["MAPPING_REFERENCES"]
     output:
         fasta = OUTDIR/"mapping_references.fasta"
     log:
@@ -21,17 +25,20 @@ rule fetch_mapping_references:
         # Create empty file
         echo -n > {output.fasta}
         # Download and concatenate each reference
-        echo {config[MAPPING_REFERENCES]} | while read -r ref_id; do
+        echo {params.refs} | while read -r ref_id; do
             esearch -db nucleotide -query "$ref_id" | efetch -format fasta >> {output.fasta} 2>> {log}
         done
         """
 
 
 rule fetch_alignment_annotation:
     threads: 1
+    conda: "../envs/fetch.yaml"
+    params:
+        ref = config["ALIGNMENT_REFERENCE"]
     output:
         OUTDIR/"reference.gff3"
     log:
         LOGDIR / "fetch_alignment_annotation" / "log.txt"
     shell:
-        "curl 'https://www.ncbi.nlm.nih.gov/sviewer/viewer.cgi?db=nuccore&report=gff3&id={config[ALIGNMENT_REFERENCE]}' -o {output} -s 2>{log}"
+        "curl 'https://www.ncbi.nlm.nih.gov/sviewer/viewer.cgi?db=nuccore&report=gff3&id={params.ref}' -o {output} -s 2>{log}"
diff --git a/workflow/rules/report.smk b/workflow/rules/report.smk
@@ -154,6 +154,8 @@ rule report:
         stats_lm  = rules.phylo_plots.output.stats_lm,
         table     = rules.summary_table.output.table,
         sum_nv    = rules.general_NV_description.output.summary_nv
+    params:
+        workflow_version = __version__
     output:
         html = report(OUTDIR/f"{OUTPUT_NAME}.report.html")
     log:
@@ -163,7 +165,7 @@ rule report:
         set +o pipefail
         Rscript -e 'library(quarto)' -e \"quarto_render(input = '{input.qmd}',\
                                            execute_params=list( \
-                                                       workflow_version='{__version__}',\
+                                                       workflow_version='{params.workflow_version}',\
                                                        div='{input.diversity}',\
                                                        freyja ='{input.freyja}',\
                                                        tree = '{input.tree}',\