fixup: split nextclade

nextstrain · Dec 6, 2023 · 87d8c5d · 87d8c5d
1 parent 26e00f3
commit 87d8c5d
Showing 1 changed file with 17 additions and 60 deletions.
diff --git a/ingest/workflow/snakemake_rules/nextclade.smk b/ingest/workflow/snakemake_rules/nextclade.smk
@@ -1,4 +1,7 @@
 rule nextclade_all:
+    """
+    Classify sequences into DENV1, DENV2, DENV3, and DENV4
+    """
     input:
         sequences="results/sequences.fasta",
         dataset="../nextclade_data/all",
@@ -18,6 +21,9 @@ rule nextclade_all:
 
 # Might be able to parallelize this
 rule split_dengue_sequences:
+    """
+    Split sequences into DENV1, DENV2, DENV3, and DENV4
+    """
     input:
         sequences="results/sequences.fasta",
         metadata="results/metadata.tsv",
@@ -31,7 +37,7 @@ rule split_dengue_sequences:
     shell:
         """
         cp {input.sequences} {output.sequences_all}
-        
+
         augur filter \
           --sequences results/sequences.fasta \
           --metadata {input.nextclade_all_results} \
@@ -61,67 +67,15 @@ rule split_dengue_sequences:
           --output-sequences {output.sequences_denv4}
         """
 
-# The following rules should use wildcards
-rule nextclade_denv1:
-    input:
-        sequences="results/sequences_denv1.fasta",
-        dataset="../nextclade_data/denv1",
-    output:
-        "results/nextclade_results/nextclade_denv1.tsv",
-    threads: 4
-    shell:
-        """
-        nextclade run \
-          --input-dataset {input.dataset} \
-          -j {threads} \
-          --output-tsv {output} \
-          --min-match-rate 0.01 \
-          --silent \
-          {input.sequences}
-        """
-
-rule nextclade_denv2:
-    input:
-        sequences="results/sequences_denv2.fasta",
-        dataset="../nextclade_data/denv2",
-    output:
-        "results/nextclade_results/nextclade_denv2.tsv",
-    threads: 4
-    shell:
-        """
-        nextclade run \
-          --input-dataset {input.dataset} \
-          -j {threads} \
-          --output-tsv {output} \
-          --min-match-rate 0.01 \
-          --silent \
-          {input.sequences}
-        """
-
-rule nextclade_denv3:
-    input:
-        sequences="results/sequences_denv3.fasta",
-        dataset="../nextclade_data/denv3",
-    output:
-        "results/nextclade_results/nextclade_denv3.tsv",
-    threads: 4
-    shell:
-        """
-        nextclade run \
-          --input-dataset {input.dataset} \
-          -j {threads} \
-          --output-tsv {output} \
-          --min-match-rate 0.01 \
-          --silent \
-          {input.sequences}
-        """
-
-rule nextclade_denv4:
+rule nextclade_denvX:
+    """
+    For each type, classify into the appropriate subtype
+    """
     input:
-        sequences="results/sequences_denv4.fasta",
-        dataset="../nextclade_data/denv4",
+        sequences="results/sequences_denv{x}.fasta",
+        dataset="../nextclade_data/denv{x}",
     output:
-        "results/nextclade_results/nextclade_denv4.tsv",
+        "results/nextclade_results/nextclade_denv{x}.tsv",
     threads: 4
     shell:
         """
@@ -135,6 +89,9 @@ rule nextclade_denv4:
         """
 
 rule join_nextclade_clades:
+    """
+    Merge all the nextclade results into metadata and split metadata
+    """
     input:
         metadata="results/metadata.tsv",
         nextclade_denv1="results/nextclade_results/nextclade_denv1.tsv",