Refactored rule all to build input list using python outside the rule…

… definition

config/config.yaml

@@ -17,7 +17,7 @@ db_path_blast: "/home/bio.aau.dk/mk20aj/databases/MIDAS"
 evalue: 1e-10 # E-value cutoff for blast
 
 # Parameters for filtering reads (filtering.smk)
-# Change based on amplicon length and desired quiality
+# Change based on amplicon length and desired quality
 length_lower_limit: 1200 # minimum length of reads to keep
 length_upper_limit: 1600 # maximum length of reads to keep
 quality_cut_off: 23 # minimum quality score to keep (phred-score)

workflow/Snakefile

@@ -25,17 +25,29 @@ include: "rules/09-fix_otu_table.smk"
 include: "rules/10-prep_for_ampvis2.smk" # <- shouldn't be necessary, amp_load() reads sintax files directly, see "taxonomy" here https://kasperskytte.github.io/ampvis2/reference/amp_load.html#arguments-1
 include: "rules/11-prep_for_phyloseq.smk"
 
-
+# Prepare inputs for rule all
 ## Rule all currently outputs all file formats. You can change this to only output the files you need.
 ## For example you can remove the blast files if you only need sintax annotation. By default, both sintax and blast files are output.
 ## You can also change the similarity level to any% by changing the id to the desired % in the expand function.
 ## You can comment out the files you don't need in the expand function.
+def prepare_inputs():
+    inputs = []
+    ids = ["97", "99"]
+    if config["include_sintax_output"]:
+        inputs.extend(expand(os.path.join(config['output_dir'], "final", "{id}", "OTUtable_tax_{id}_sintax.tsv"), id=ids))
+        inputs.extend(expand(os.path.join(config['output_dir'], "final", "{id}", "phyloseq_tax_{id}_sintax.tsv"), id=ids))
+        inputs.extend(expand(os.path.join(config['output_dir'], "final", "{id}", "phyloseq_abundance_{id}_sintax.tsv"), id=ids))
+
+    if config["include_blast_output"]:
+        inputs.extend(expand(os.path.join(config['output_dir'], "final", "{id}", "OTUtable_tax_{id}_blast.tsv"), id=ids))
+        inputs.extend(expand(os.path.join(config['output_dir'], "final", "{id}", "phyloseq_tax_{id}_blast.tsv"), id=ids))
+        inputs.extend(expand(os.path.join(config['output_dir'], "final", "{id}", "phyloseq_abundance_{id}_blast.tsv"), id=ids))
+
+    inputs.append(expand(os.path.join(config['output_dir'], "final", "report", "total_reads.tsv")))
+
+    return inputs
+
 rule all:
     input:
-        expand(os.path.join(config['output_dir'], "final", "{id}", "OTUtable_tax_{id}_sintax.tsv"), id=["97", "99"]) if config["include_sintax_output"] else None, #
-        expand(os.path.join(config['output_dir'], "final", "{id}", "phyloseq_tax_{id}_sintax.tsv"), id=["97", "99"]) if config["include_sintax_output"] else None, #
-        expand(os.path.join(config['output_dir'], "final", "{id}", "phyloseq_abundance_{id}_sintax.tsv"), id=["97", "99"]) if config["include_sintax_output"] else None, #
-        expand(os.path.join(config['output_dir'], "final", "report", "total_reads.tsv")), #
-        expand(os.path.join(config['output_dir'], "final", "{id}", "OTUtable_tax_{id}_blast.tsv"), id=["97", "99"]) if config["include_blast_output"] else None, #
-        expand(os.path.join(config['output_dir'], "final", "{id}", "phyloseq_tax_{id}_blast.tsv"), id=["97", "99"]) if config["include_blast_output"] else None, #
-        expand(os.path.join(config['output_dir'], "final", "{id}", "phyloseq_abundance_{id}_blast.tsv"), id=["97", "99"]) if config["include_blast_output"] else None #
+        prepare_inputs()
+