Set threads for augur subsample

Take advantage of built-in parallelism.

Author: victorlin

phylogenetic/rules/prepare_sequences.smk

@@ -3,7 +3,7 @@ This part of the workflow prepares sequences for constructing the phylogenetic t
 
 See Augur's usage docs for these commands for more details.
 """
-from augur.subsample import get_referenced_files
+from augur.subsample import get_referenced_files, get_parallelism
 
 rule filter:
     """
@@ -22,13 +22,15 @@ rule filter:
         sequences = "results/genome/filtered.fasta"
     params:
         strain_id = config["strain_id_field"]
+    threads: lambda w, input: get_parallelism(input.config, limit=workflow.cores)
     shell:
         """
         augur subsample \
             --config {input.config} \
             --sequences {input.sequences} \
             --metadata {input.metadata} \
             --metadata-id-columns {params.strain_id} \
+            --nthreads {threads} \
             --output-sequences {output.sequences} \
         """
 

phylogenetic/rules/prepare_sequences_N450.smk

@@ -3,7 +3,7 @@ This part of the workflow prepares sequences for constructing the phylogenetic t
 
 See Augur's usage docs for these commands for more details.
 """
-from augur.subsample import get_referenced_files
+from augur.subsample import get_referenced_files, get_parallelism
 
 rule align_and_extract_N450:
     input:
@@ -42,12 +42,14 @@ rule filter_N450:
         sequences = "results/N450/aligned.fasta"
     params:
         strain_id = config["strain_id_field"]
+    threads: lambda w, input: get_parallelism(input.config, limit=workflow.cores)
     shell:
         """
         augur subsample \
             --config {input.config} \
             --sequences {input.sequences} \
             --metadata {input.metadata} \
             --metadata-id-columns {params.strain_id} \
+            --nthreads {threads} \
             --output-sequences {output.sequences} \
         """