Fix diversity subsampling comments and messages

template.qmd

@@ -140,7 +140,7 @@ samples is squared in red.](`r params$tree_ml`){#fig-tree_ml}
 ### Nucleotide diversity comparison
 
 Nucleotide diversity (π) has been calculated for $`r div_values[["boot.reps"]]`$ random
-sample subsets of size $`r div_values[["sample.size"]]`$, extracted with replacement
+sample subsets of size $`r div_values[["sample.size"]]`$, extracted
 from the context dataset. The distribution of the nuclotide diversity is assumed to
 `r div_values[["norm.text"]]` be normal after performing a Shapiro-Wilk test
 (p-value of $`r div_values[["normal.pvalue"]]`$).

workflow/scripts/download_context.R

@@ -94,7 +94,7 @@ dataframes <- lapply(
 # Join results
 metadata <- bind_rows(dataframes)
 
-log_info("Removeing overlapping sequences")
+log_info("Removing overlapping sequences")
 # Checkpoint: remove samples that overlap with target samples according to GISAID ID
 samples.accids <- sample.metadata %>%
     pull(snakemake@params[["samples_gisaid_accession_column"]])
@@ -103,10 +103,10 @@ metadata <- metadata %>% filter(!accession_id %in% samples.accids)
 print(glue("{nrow(metadata)} accession_ids remaining after GISAID ID filter"))
 
 # Checkpoint: enforce a minimum number of samples to have at least
-# as many possible combinations as bootstrap replicates.
+# as many possible combinations as random subsample replicates.
 # This is done by calculating the root of a function based on the
-# formula for calculating combinations with replacement
-# for n ≥ r ≥ 0: combinations with replacement = n! / (r! (n-r)!)
+# formula for calculating combinations for n ≥ r ≥ 0:
+# combinations = n! / (r! (n-r)!)
 r <- nrow(sample.metadata)
 min.comb <- snakemake@params[["min_theoretical_combinations"]]
 solution <- uniroot(

workflow/scripts/report/diversity_plot.R

@@ -60,7 +60,7 @@ diversity <- nuc.div(study_aln)
 
 
 # Perform bootstrap
-log_info("Performing bootstraped calculation for nucleotide diversity in oontext samples")
+log_info("Performing calculation for nucleotide diversity in context samples")
 plan(multisession, workers = snakemake@threads)
 divs <- boot.nd.parallel(gene_ex, length(study_aln), snakemake@params[["bootstrap_reps"]])
 plan(sequential)