diff --git a/phylogenetic/defaults/config_zika.yaml b/phylogenetic/defaults/config_zika.yaml index 9b0ab9a..d25c2c6 100644 --- a/phylogenetic/defaults/config_zika.yaml +++ b/phylogenetic/defaults/config_zika.yaml @@ -1,3 +1,8 @@ +# Sequences must be FASTA and metadata must be TSV +# Both files must be zstd compressed +sequences_url: "https://data.nextstrain.org/files/workflows/zika/sequences.fasta.zst" +metadata_url: "https://data.nextstrain.org/files/workflows/zika/metadata.tsv.zst" + strain_id_field: "accession" display_strain_field: "strain" diff --git a/phylogenetic/rules/prepare_sequences.smk b/phylogenetic/rules/prepare_sequences.smk index fda49c3..39bd66f 100644 --- a/phylogenetic/rules/prepare_sequences.smk +++ b/phylogenetic/rules/prepare_sequences.smk @@ -27,8 +27,8 @@ rule download: sequences = "data/sequences.fasta.zst", metadata = "data/metadata.tsv.zst" params: - sequences_url = "https://data.nextstrain.org/files/workflows/zika/sequences.fasta.zst", - metadata_url = "https://data.nextstrain.org/files/workflows/zika/metadata.tsv.zst" + sequences_url = config["sequences_url"], + metadata_url = config["metadata_url"], shell: """ curl -fsSL --compressed {params.sequences_url:q} --output {output.sequences} @@ -101,4 +101,4 @@ rule align: --output {output.alignment} \ --fill-gaps \ --remove-reference - """ \ No newline at end of file + """