From ab5dff414e809a719e0b5ba1b6e23530a0f53551 Mon Sep 17 00:00:00 2001 From: Jennifer Chang Date: Wed, 17 Jan 2024 11:23:51 -0800 Subject: [PATCH] Consistent naming of reference genome files * Dropped "_dengue" from names, since it's redundant in the context of the project * Added "_genome" to the end of the reference genome files, to parallel the "_E" at the end of the reference E sequence files. --- .../{reference_dengue_all.gb => reference_all_genome.gb} | 0 ...eference_dengue_denv1.gb => reference_denv1_genome.gb} | 0 ...eference_dengue_denv2.gb => reference_denv2_genome.gb} | 0 ...eference_dengue_denv3.gb => reference_denv3_genome.gb} | 0 ...eference_dengue_denv4.gb => reference_denv4_genome.gb} | 0 phylogenetic/rules/annotate_phylogeny.smk | 2 +- phylogenetic/rules/prepare_sequences.smk | 2 +- phylogenetic/rules/prepare_sequences_E.smk | 8 ++++---- 8 files changed, 6 insertions(+), 6 deletions(-) rename phylogenetic/config/{reference_dengue_all.gb => reference_all_genome.gb} (100%) rename phylogenetic/config/{reference_dengue_denv1.gb => reference_denv1_genome.gb} (100%) rename phylogenetic/config/{reference_dengue_denv2.gb => reference_denv2_genome.gb} (100%) rename phylogenetic/config/{reference_dengue_denv3.gb => reference_denv3_genome.gb} (100%) rename phylogenetic/config/{reference_dengue_denv4.gb => reference_denv4_genome.gb} (100%) diff --git a/phylogenetic/config/reference_dengue_all.gb b/phylogenetic/config/reference_all_genome.gb similarity index 100% rename from phylogenetic/config/reference_dengue_all.gb rename to phylogenetic/config/reference_all_genome.gb diff --git a/phylogenetic/config/reference_dengue_denv1.gb b/phylogenetic/config/reference_denv1_genome.gb similarity index 100% rename from phylogenetic/config/reference_dengue_denv1.gb rename to phylogenetic/config/reference_denv1_genome.gb diff --git a/phylogenetic/config/reference_dengue_denv2.gb b/phylogenetic/config/reference_denv2_genome.gb similarity index 100% rename from phylogenetic/config/reference_dengue_denv2.gb rename to phylogenetic/config/reference_denv2_genome.gb diff --git a/phylogenetic/config/reference_dengue_denv3.gb b/phylogenetic/config/reference_denv3_genome.gb similarity index 100% rename from phylogenetic/config/reference_dengue_denv3.gb rename to phylogenetic/config/reference_denv3_genome.gb diff --git a/phylogenetic/config/reference_dengue_denv4.gb b/phylogenetic/config/reference_denv4_genome.gb similarity index 100% rename from phylogenetic/config/reference_dengue_denv4.gb rename to phylogenetic/config/reference_denv4_genome.gb diff --git a/phylogenetic/rules/annotate_phylogeny.smk b/phylogenetic/rules/annotate_phylogeny.smk index d58b4a9d..9f5b17de 100644 --- a/phylogenetic/rules/annotate_phylogeny.smk +++ b/phylogenetic/rules/annotate_phylogeny.smk @@ -45,7 +45,7 @@ rule translate: tree = "results/tree_{serotype}_{gene}.nwk", node_data = "results/nt-muts_{serotype}_{gene}.json", # The genbank references for the E gene are dynamically generated files located within the results folder. - reference = lambda wildcard: "config/reference_dengue_{serotype}.gb" if wildcard.gene in ["genome"] else "results/config/reference_dengue_{serotype}_{gene}.gb" + reference = lambda wildcard: "config/reference_{serotype}_{gene}.gb" if wildcard.gene in ["genome"] else "results/config/reference_{serotype}_{gene}.gb" output: node_data = "results/aa-muts_{serotype}_{gene}.json" shell: diff --git a/phylogenetic/rules/prepare_sequences.smk b/phylogenetic/rules/prepare_sequences.smk index b906f2ec..211c78ab 100644 --- a/phylogenetic/rules/prepare_sequences.smk +++ b/phylogenetic/rules/prepare_sequences.smk @@ -82,7 +82,7 @@ rule align: """ input: sequences = "results/filtered_{serotype}.fasta", - reference = "config/reference_dengue_{serotype}.gb" + reference = "config/reference_{serotype}_genome.gb" output: alignment = "results/aligned_{serotype}_genome.fasta" shell: diff --git a/phylogenetic/rules/prepare_sequences_E.smk b/phylogenetic/rules/prepare_sequences_E.smk index d33e1ad6..b85f2b54 100644 --- a/phylogenetic/rules/prepare_sequences_E.smk +++ b/phylogenetic/rules/prepare_sequences_E.smk @@ -22,10 +22,10 @@ rule generate_E_reference_files: Generating reference files for the E gene """ input: - reference = "config/reference_dengue_{serotype}.gb", + reference = "config/reference_{serotype}_genome.gb", output: - fasta = "results/config/reference_dengue_{serotype}_E.fasta", - genbank = "results/config/reference_dengue_{serotype}_E.gb", + fasta = "results/config/reference_{serotype}_E.fasta", + genbank = "results/config/reference_{serotype}_E.gb", params: gene = "E", shell: @@ -43,7 +43,7 @@ rule nextclade3_cut_E: """ input: sequences = "data/sequences_{serotype}.fasta", - reference = "results/config/reference_dengue_{serotype}_E.fasta" + reference = "results/config/reference_{serotype}_E.fasta" output: sequences = "results/sequences_{serotype}_E.fasta" params: