Separate files into segment directories

* Capitalize L and S to match ingest
* Refactor and place intermediate files in segment directories
* Match segment capitalization in reference files and example files

phylogenetic/Snakefile

@@ -8,11 +8,14 @@ workdir: workflow.current_basedir
 # Use default configuration values. Override with Snakemake's --configfile/--config options.
 configfile: "defaults/config.yaml"
 
-SEGMENTS = ["l", "s"]
+segments = ["L", "S"]
+
+wildcard_constraints:
+    segment = "|".join(segments)
 
 rule all:
     input:
-        auspice_tree = expand("auspice/lassa_{segment}.json", segment=SEGMENTS)
+        auspice_tree = expand("auspice/lassa_{segment}.json", segment=segments)
 
 include: "rules/prepare_sequences.smk"
 include: "rules/construct_phylogeny.smk"

phylogenetic/build-configs/ci/copy_example_data.smk

@@ -3,8 +3,8 @@ rule copy_example_data:
         sequences="example_data/sequences_{segment}.fasta",
         metadata="example_data/metadata_{segment}.tsv",
     output:
-        sequences="data/sequences_{segment}.fasta",
-        metadata="data/metadata_{segment}.tsv",
+        sequences="data/{segment}/sequences.fasta",
+        metadata="data/{segment}/metadata.tsv",
     shell:
         """
         cp -f {input.sequences} {output.sequences}

phylogenetic/rules/annotate_phylogeny.smk

@@ -34,10 +34,10 @@ to the ones produced by Augur commands.
 rule ancestral:
     """Reconstructing ancestral sequences and mutations"""
     input:
-        tree = "results/tree_{segment}.nwk",
-        alignment = "results/aligned_{segment}.fasta",
+        tree = "results/{segment}/tree.nwk",
+        alignment = "results/{segment}/aligned.fasta",
     output:
-        node_data = "results/nt_muts_{segment}.json"
+        node_data = "results/{segment}/nt_muts.json"
     params:
         inference = "joint"
     shell:
@@ -52,11 +52,11 @@ rule ancestral:
 rule translate:
     """Translating amino acid sequences"""
     input:
-        tree = "results/tree_{segment}.nwk",
-        node_data = "results/nt_muts_{segment}.json",
+        tree = "results/{segment}/tree.nwk",
+        node_data = "results/{segment}/nt_muts.json",
         reference = "defaults/lassa_{segment}.gb"
     output:
-        node_data = "results/aa_muts_{segment}.json"
+        node_data = "results/{segment}/aa_muts.json"
     shell:
         """
         augur translate \
@@ -69,10 +69,10 @@ rule translate:
 rule traits:
     """Inferring ancestral traits for {params.columns!s}"""
     input:
-        tree = "results/tree_{segment}.nwk",
-        metadata = "data/metadata_{segment}.tsv",
+        tree = "results/{segment}/tree.nwk",
+        metadata = "data/{segment}/metadata.tsv",
     output:
-        node_data = "results/traits_{segment}.json",
+        node_data = "results/{segment}/traits.json",
     params:
         strain_id_field = config["strain_id_field"],
         columns = config['traits']['columns']

phylogenetic/rules/construct_phylogeny.smk

@@ -22,9 +22,9 @@ See Augur's usage docs for these commands for more details.
 rule tree:
     """Building tree"""
     input:
-        alignment = "results/aligned_{segment}.fasta"
+        alignment = "results/{segment}/aligned.fasta"
     output:
-        tree = "results/tree_raw_{segment}.nwk"
+        tree = "results/{segment}/tree_raw.nwk"
     params:
         method = "iqtree"
     shell:
@@ -44,12 +44,12 @@ rule refine:
       - fix clock rate at {params.clock_rate}
     """
     input:
-        tree = "results/tree_raw_{segment}.nwk",
-        alignment = "results/aligned_{segment}.fasta",
-        metadata = "data/metadata_{segment}.tsv",
+        tree = "results/{segment}/tree_raw.nwk",
+        alignment = "results/{segment}/aligned.fasta",
+        metadata = "data/{segment}/metadata.tsv",
     output:
-        tree = "results/tree_{segment}.nwk",
-        node_data = "results/branch_lengths_{segment}.json"
+        tree = "results/{segment}/tree.nwk",
+        node_data = "results/{segment}/branch_lengths.json"
     params:
         strain_id_field = config["strain_id_field"],
         coalescent = config['refine']['coalescent'],

phylogenetic/rules/export.smk

@@ -29,9 +29,9 @@ rule colors:
     input:
         color_schemes = "defaults/color_schemes.tsv",
         color_orderings = "defaults/color_orderings.tsv",
-        metadata = "data/metadata_{segment}.tsv",
+        metadata = "data/{segment}/metadata.tsv",
     output:
-        colors = "results/colors_{segment}.tsv"
+        colors = "results/{segment}/colors.tsv"
     shell:
         """
         python3 scripts/assign-colors.py \
@@ -44,17 +44,17 @@ rule colors:
 rule export:
     """Exporting data files for for auspice"""
     input:
-        tree = "results/tree_{segment}.nwk",
-        metadata = "data/metadata_{segment}.tsv",
-        branch_lengths = "results/branch_lengths_{segment}.json",
-        traits = "results/traits_{segment}.json",
-        nt_muts = "results/nt_muts_{segment}.json",
-        aa_muts = "results/aa_muts_{segment}.json",
-        colors = "results/colors_{segment}.tsv",
+        tree = "results/{segment}/tree.nwk",
+        metadata = "data/{segment}/metadata.tsv",
+        branch_lengths = "results/{segment}/branch_lengths.json",
+        traits = "results/{segment}/traits.json",
+        nt_muts = "results/{segment}/nt_muts.json",
+        aa_muts = "results/{segment}/aa_muts.json",
+        colors = "results/{segment}/colors.tsv",
         description = config['export']['description'],
         auspice_config = config['export']['auspice_config'],
     output:
-        auspice = "results/lassa_{segment}.json",
+        auspice = "results/{segment}/lassa.json",
     params:
         strain_id_field = config["strain_id_field"],
     shell:
@@ -73,8 +73,8 @@ rule export:
 
 rule final_strain_name:
     input:
-        auspice_json="results/lassa_{segment}.json",
-        metadata="data/metadata_{segment}.tsv",
+        auspice_json="results/{segment}/lassa.json",
+        metadata="data/{segment}/metadata.tsv",
     output:
         auspice_json="auspice/lassa_{segment}.json",
     params:

phylogenetic/rules/prepare_sequences.smk

@@ -24,8 +24,8 @@ See Augur's usage docs for these commands for more details.
 rule download:
     """Downloading sequences and metadata from data.nextstrain.org"""
     output:
-        sequences = "data/sequences_{segment}.fasta.zst",
-        metadata = "data/metadata_{segment}.tsv.zst"
+        sequences = "data/{segment}/sequences.fasta.zst",
+        metadata = "data/{segment}/metadata.tsv.zst"
     params:
         sequences_url = config["sequences_url"],
         metadata_url = config["metadata_url"],
@@ -38,11 +38,11 @@ rule download:
 rule decompress:
     """Decompressing sequences and metadata"""
     input:
-        sequences = "data/sequences_{segment}.fasta.zst",
-        metadata = "data/metadata_{segment}.tsv.zst"
+        sequences = "data/{segment}/sequences.fasta.zst",
+        metadata = "data/{segment}/metadata.tsv.zst"
     output:
-        sequences = "data/sequences_{segment}.fasta",
-        metadata = "data/metadata_{segment}.tsv"
+        sequences = "data/{segment}/sequences.fasta",
+        metadata = "data/{segment}/metadata.tsv"
     shell:
         """
         zstd -d -c {input.sequences} > {output.sequences}
@@ -56,11 +56,11 @@ rule filter:
       - excluding strains in {input.exclude}
     """
     input:
-        sequences = "data/sequences_{segment}.fasta",
-        metadata = "data/metadata_{segment}.tsv",
+        sequences = "data/{segment}/sequences.fasta",
+        metadata = "data/{segment}/metadata.tsv",
         exclude = config['filter']['exclude']
     output:
-        sequences = "results/filtered_{segment}.fasta"
+        sequences = "results/{segment}/filtered.fasta"
     params:
         strain_id_field = config["strain_id_field"],
         group_by = config['filter']['group_by'],
@@ -83,10 +83,10 @@ rule align:
       - filling gaps with N
     """
     input:
-        sequences = "results/filtered_{segment}.fasta",
+        sequences = "results/{segment}/filtered.fasta",
         reference = "defaults/lassa_{segment}.gb"
     output:
-        alignment = "results/aligned_{segment}.fasta"
+        alignment = "results/{segment}/aligned.fasta"
     shell:
         """
         augur align \