Shift subtype query to config yaml

This reduces the conditional logic used to special-case the workflows
which wanted to filter on GenoFLU by shifting the entire query arg
into the config YAML. A (not unintentional) side effect is that future
builds which want to analyse different subtypes such as H7N6
<#108> are possible to
set-up using only a config overlay.

genome-focused-d1.1/config.yaml

@@ -34,6 +34,11 @@ dropped_strains: config/{subtype}/dropped_strains_{subtype}.txt
 clades_file: clade-labeling/h5n1-clades.tsv # use H5N1 clades
 description: config/{subtype}/description.md
 
+## Subtype query - this structure is different from all other config parameters, requiring
+#  a key for each of the subtypes defined above in 'builds'. The string will be supplied to
+#  augur filter's --query argument.
+subtype_query:
+    "h5n1-d1.1": "genoflu in 'D1.1'"
 
 #### Rule-specific parameters ####
 filter:

genome-focused/config.yaml

@@ -43,6 +43,11 @@ dropped_strains: config/{subtype}/dropped_strains_{subtype}.txt
 clades_file: clade-labeling/h5n1-clades.tsv # use H5N1 clades
 description: config/{subtype}/description_{subtype}.md
 
+## Subtype query - this structure is different from all other config parameters, requiring
+#  a key for each of the subtypes defined above in 'builds'. The string will be supplied to
+#  augur filter's --query argument.
+subtype_query:
+    "h5n1-cattle-outbreak": "genoflu in 'B3.13'"
 
 #### Rule-specific parameters ####
 # The formatting here represents the three-tiered nature of the avian-flu build which

rules/main.smk

@@ -32,27 +32,6 @@ rule test_target:
     """
     input: "auspice/avian-flu_h5n1_ha_all-time.json"
 
-def subtypes_by_subtype_wildcard(wildcards):
-
-    # TODO - this function does more than strictly subtype filtering as certain builds filter to
-    # GenoFLU constellation, and in the future this may be expanded. We should rename the function!
-    # TODO XXX - move to configs (started in https://github.com/nextstrain/avian-flu/pull/104 but
-    # We should make the entire query config-definable)
-    if wildcards.subtype == 'h5n1-d1.1':
-        return "genoflu in 'D1.1'"
-    elif wildcards.subtype == 'h5n1-cattle-outbreak':
-        return "genoflu in 'B3.13'"
-
-    db = {
-        'h5nx': ['h5n1', 'h5n2', 'h5n3', 'h5n4', 'h5n5', 'h5n6', 'h5n7', 'h5n8', 'h5n9'],
-        'h5n1': ['h5n1'],
-        'h7n9': ['h7n9'],
-        'h9n2': ['h9n2'],
-    }
-    assert wildcards.subtype in db, (f"Subtype {wildcards.subtype!r} is not defined in the snakemake function "
-        "`subtypes_by_subtype_wildcard` -- is there a typo in the subtype you are targetting?")
-    return(f"subtype in [{', '.join([repr(s) for s in db[wildcards.subtype]])}]")
-
 class InvalidConfigError(Exception):
     pass
 
@@ -206,7 +185,7 @@ rule filter_sequences_by_subtype:
     output:
         sequences = "results/{subtype}/{segment}/sequences.fasta",
     params:
-        subtypes=subtypes_by_subtype_wildcard,
+        subtypes=lambda w: config['subtype_query'][w.subtype],
     shell:
         """
         augur filter \
@@ -222,7 +201,7 @@ rule filter_metadata_by_subtype:
     output:
         metadata = "results/{subtype}/metadata.tsv",
     params:
-        subtypes=subtypes_by_subtype_wildcard,
+        subtypes= lambda w: config['subtype_query'][w.subtype],
     shell:
         """
         augur filter \

segment-focused/config.yaml

@@ -51,6 +51,14 @@ dropped_strains: config/{subtype}/dropped_strains_{subtype}.txt
 clades_file: clade-labeling/{subtype}-clades.tsv
 description: config/description_gisaid.md
 
+## Subtype query - this structure is different from all other config parameters, requiring
+#  a key for each of the subtypes defined above in 'builds'. The string will be supplied to
+#  augur filter's --query argument.
+subtype_query:
+    "h5nx": "subtype in ['h5n1', 'h5n2', 'h5n3', 'h5n4', 'h5n5', 'h5n6', 'h5n7', 'h5n8', 'h5n9']"
+    "h5n1": "subtype in ['h5n1']"
+    "h7n9": "subtype in ['h7n9']"
+    "h9n2": "subtype in ['h9n2']"
 
 #### Rule-specific parameters ####
 # The formatting here represents the three-tiered nature of the avian-flu build which