diff --git a/phylogenetic/Snakefile b/phylogenetic/Snakefile index 2318864..70fda3d 100644 --- a/phylogenetic/Snakefile +++ b/phylogenetic/Snakefile @@ -18,7 +18,6 @@ rule all: auspice_tree = expand("auspice/lassa_{segment}.json", segment=segments) include: "rules/prepare_sequences.smk" -include: "rules/prepare_sequences_segments.smk" include: "rules/construct_phylogeny.smk" include: "rules/annotate_phylogeny.smk" include: "rules/export.smk" diff --git a/phylogenetic/rules/prepare_sequences_segments.smk b/phylogenetic/rules/prepare_sequences_segments.smk deleted file mode 100644 index 72399d3..0000000 --- a/phylogenetic/rules/prepare_sequences_segments.smk +++ /dev/null @@ -1,47 +0,0 @@ -""" -This part of the workflow prepares sequences for constructing the segment phylogenetic tree. - -REQUIRED INPUTS: - - metadata = data/metadata.tsv - sequences = data/sequences.fasta - segment_reference = defaults/lassa_{segment}.fasta - -OUTPUTS: - - metadata = data/metadata_{segment}.tsv - sequences = data/sequences_{segment}.fasta - -This part of the workflow usually includes the following steps: - - - nextclade: Aligns sequences to the reference segment sequence and extracts the segment sequences to ensure the reference files are valid - - augur filter: Filters the sequences and metadata to include only the sequences that were successfully aligned -See Nextclade's usage docs for these commands for more details. -""" - -rule prepare_sequences_segments: - input: - metadata = "data/metadata.tsv", - sequences = "data/sequences.fasta", - segment_reference = "defaults/lassa_{segment}.fasta", - output: - metadata = "data/metadata_{segment}.tsv", - sequences = "data/sequences_{segment}.fasta", - params: - strain_id_field = config["strain_id_field"], - min_seed_cover = 0.01, - shell: - """ - nextclade run \ - --input-ref {input.segment_reference} \ - --output-fasta {output.sequences} \ - --min-seed-cover {params.min_seed_cover} \ - --silent \ - {input.sequences} - - augur filter \ - --sequences {output.sequences} \ - --metadata {input.metadata} \ - --metadata-id-columns {params.strain_id_field} \ - --output-metadata {output.metadata} - """ \ No newline at end of file