commenting and renaming

Snakefile

-singularity: "container.sif"
-
+# edit configuration here (see cluster.json for running on slurm scheduler)
 configfile: "config.yml"
 
-localrules: impute, clean, generate_samples_file
+localrules: impute, clean, download_container, generate_samples_file
+
+
 
+# this rule runs the entire pipeline and creates a R data set file (rds)
+# containing all imputed expression values
 rule impute:
     input:
         expand("{output_dir}/gene_expression/{region}.expression.txt", region = config['brain_regions'], output_dir = config['output_dir'])
     output:
         expand("{output_dir}/gene_expressions_combined.rds", output_dir = config['output_dir'])
+    singularity:
+        "container.sif"
     shell:
         """
         Rscript scripts/combine_expression_data.R
         """
 
+# delete output and logs (if run on slurm cluster)
+rule clean:
+    shell:
+        """
+        rm -rf {config[output_dir]}
+        rm -rf logs
+        rm -rf nohup.out
+        """
+
+# download the required singularity container from zenodo.org
+rule download_container:
+    shell:
+        """
+        echo 'not implemented'
+        """
+
+# extract dosages in custom PrediXcan format from vcf file
 rule vcf_to_dosages:
     input:
         config['input_vcf_gz_file']
     output:
         "{output_dir}/dosages/chr{i}.dosage.txt.gz"
+    singularity:
+        "container.sif"
     shell:
         """
         export prefix={wildcards.output_dir}/dosages
@@ -36,11 +60,14 @@ rule vcf_to_dosages:
         printf "done.\n\r\n\r"
         """
 
+# extract sample file for PrediXcan
 rule generate_samples_file:
     input:
         config['input_vcf_gz_file']
     output:
         "{output_dir}/dosages/samples.txt"
+    singularity:
+        "container.sif"
     params:
         format = "\'{ printf(\"%s %s\\n\", $1, $1); }\'"
     shell:
@@ -53,12 +80,15 @@ rule generate_samples_file:
         rm $prefix/samples_.txt
         """
 
+# run PrediXcan to impute gene expression for individual tissue type
 rule impute_gene_expression:
     input:
         samples_file = expand("{output_dir}/dosages/samples.txt", output_dir = config['output_dir']),
         dosage_files = expand("{output_dir}/dosages/chr{i}.dosage.txt.gz", i = range(1, 24), output_dir = config['output_dir'])
     output:
         "{output_dir}/gene_expression/{region}.expression.txt"
+    singularity:
+        "container.sif"
     shell:
         """
         mkdir -p {wildcards.output_dir}/gene_expression
@@ -72,11 +102,3 @@ rule impute_gene_expression:
         mv {wildcards.output_dir}/gene_expression/{wildcards.region}_predicted_expression.txt \
             {wildcards.output_dir}/gene_expression/{wildcards.region}.expression.txt
         """
-
-rule clean:
-    shell:
-        """
-        rm -rf {config[output_dir]}
-        rm -rf logs
-        rm -rf nohup.out
-        """