perf: bump datavzrd wrapper to 2.6.0 and general bug fixes (#80)

Created a new and separate pull request previously was merged with
3-prime-rna branch

---------

Co-authored-by: David Laehnemann <david.laehnemann@hhu.de>

workflow/rules/datavzrd.smk

@@ -67,7 +67,7 @@ rule spia_datavzrd:
     log:
         "logs/datavzrd-report/spia-{model}/spia-{model}.log",
     wrapper:
-        "v1.29.0/utils/datavzrd"
+        "v2.6.0/utils/datavzrd"
 
 
 rule diffexp_datavzrd:
@@ -92,7 +92,7 @@ rule diffexp_datavzrd:
     log:
         "logs/datavzrd-report/diffexp.{model}/diffexp.{model}.log",
     wrapper:
-        "v1.29.0/utils/datavzrd"
+        "v2.6.0/utils/datavzrd"
 
 
 rule go_enrichment_datavzrd:
@@ -119,4 +119,4 @@ rule go_enrichment_datavzrd:
     log:
         "logs/datavzrd-report/go_enrichment-{model}/go_enrichment-{model}_{gene_fdr}.go_term_fdr_{go_term_fdr}.log",
     wrapper:
-        "v1.29.0/utils/datavzrd"
+        "v2.6.0/utils/datavzrd"

workflow/rules/trim_3prime.smk

@@ -1,5 +1,4 @@
 if is_3prime_experiment and three_prime_vendor == "lexogen":
-
     # Rule cutadapt1 checks and removes poly-A tails and sequence qualilty score <20.
     # reasoning behind parameters:
     #   * `-m 20`:

workflow/scripts/plot_diffexp_heatmap.R

@@ -53,7 +53,7 @@ if (all(selectedgenes == 0)) {
     # If number of transcripts is more than 100,
     # Since for RNA-seq multiple transcripts may present for a single gene.
 } else if (nrow(selectedgenes) > 100) {
-    pdf_height <- round(nrow(selectedgenes) / 7)
+    pdf_height <- round(nrow(selectedgenes) / 5)
     pdf(snakemake@output[["diffexp_heatmap"]],
         height = pdf_height, width = ncol(selectedgenes) * 2
     )
@@ -63,7 +63,7 @@ if (all(selectedgenes == 0)) {
     )
     dev.off()
 } else {
-    pdf_height <- round(nrow(selectedgenes) / 7)
+    pdf_height <- round(nrow(selectedgenes) / 5)
     pdf(
         file = snakemake@output[["diffexp_heatmap"]],
         height = pdf_height, width = ncol(selectedgenes) * 2

workflow/scripts/spia.R

@@ -21,7 +21,6 @@ diffexp <- read_tsv(snakemake@input[["diffexp"]]) %>%
     mutate(ens_gene = str_c("ENSEMBL:", ens_gene))
 universe <- diffexp %>% pull(var = ens_gene)
 sig_genes <- diffexp %>% filter(qval <= 0.05)
-
 if (nrow(sig_genes) == 0) {
     cols <- c(
         "Name", "Status", "Combined FDR",
@@ -30,7 +29,7 @@ if (nrow(sig_genes) == 0) {
         "Combined Bonferroni p-values",
         "p-value to observe a total accumulation", "Combined p-value", "Ids"
     )
-    res <- data.frame(matrix(ncol = 7, nrow = 0, dimnames = list(NULL, cols)))
+    res <- data.frame(matrix(ncol = 11, nrow = 0, dimnames = list(NULL, cols)))
     # create empty perturbation plots
     pdf(file = snakemake@output[["plots"]])
     write_tsv(res, snakemake@output[["table"]])