refactor: rename REGION field to CHROM (#34)

* refactor: rename REGION field to CHROM

* refactor: update renaming logic

* refactor: rename REGION field to CHROM

Author: ahmig

workflow/rules/sites.smk

@@ -31,8 +31,6 @@ rule filter_mpileup_all_sites:
     output:
         sites_pass = temp(OUTDIR / "all_sites" / "{sample}.filtered_sites.tsv"),
         sites_fail = temp(OUTDIR / "all_sites" / "{sample}.fail_sites.tsv"),
-    log:
-        LOGDIR / "filter_mpileup_all_sites" / "{sample}.txt"
     run:
         import pandas as pd
         df = pd.read_csv(input[0], sep="\t")

workflow/scripts/calculate_dnds.R

@@ -19,7 +19,7 @@ variants <- read_delim(
   col_select = c(
     "SAMPLE",
     "VARIANT_NAME",
-    "REGION",
+    "CHROM",
     "ALT_FREQ",
     "SYNONYMOUS",
     "POS"

workflow/scripts/fill_all_sites.R

@@ -17,26 +17,25 @@ variants <- read_tsv(snakemake@input[["variants"]])
 
 # Create a mapping of variant names to their genomic position
 variant_coords <- variants %>%
-  select(VARIANT_NAME, REGION, POS) %>%
+  select(VARIANT_NAME, CHROM, POS) %>%
   distinct()
 
 log_info("Reading filtered sites")
 sites <- read_tsv(snakemake@input[["sites"]]) %>%
-  select(SAMPLE, POS) %>%  # TODO: consider region/chrom
-  distinct() %>%
+  distinct(SAMPLE, POS) %>%  # TODO: consider region/chrom
   mutate(FILTER_PASS = TRUE)
 
 log_info("Processing variants")
 all_variants <- variants %>%
   # Select minimal columns
-  select(VARIANT_NAME, REGION, SAMPLE, ALT_FREQ) %>%
+  distinct(VARIANT_NAME, CHROM, SAMPLE, ALT_FREQ) %>%
   # Handle duplicates
-  group_by(SAMPLE, VARIANT_NAME, REGION) %>%
+  group_by(SAMPLE, VARIANT_NAME, CHROM) %>%
   summarise(ALT_FREQ = sum(ALT_FREQ, na.rm = TRUE), .groups = "drop") %>%
   # Complete with NA
-  complete(SAMPLE, VARIANT_NAME, REGION) %>%
+  complete(SAMPLE, VARIANT_NAME, CHROM) %>%
   # Assign genomic positions for all combinations
-  left_join(variant_coords, by = c("REGION", "VARIANT_NAME")) %>%
+  left_join(variant_coords, by = c("CHROM", "VARIANT_NAME")) %>%
   # Merge filtered sites
   # TODO: consider region/chrom
   left_join(sites, by = c("SAMPLE", "POS")) %>%

workflow/scripts/merge_annotation.R

@@ -75,7 +75,8 @@ merged <- left_join(
 ) %>%
   mutate(
     SAMPLE = snakemake@params$sample
-  )
+  ) %>%
+  rename(CHROM = REGION)
 
 log_info("Saving results")
 write_tsv(

workflow/scripts/report/af_time_correlation_data.R

@@ -19,14 +19,14 @@ variants <- read_delim(
   col_select = c(
     "VARIANT_NAME",
     "SAMPLE",
-    "REGION",
+    "CHROM",
     "ALT_FREQ",
     "POS"
   )
 ) %>%
   # Fill positions without alt frequency with NA
   complete(
-    nesting(REGION, VARIANT_NAME, POS),
+    nesting(CHROM, VARIANT_NAME, POS),
     SAMPLE,
     fill = list(ALT_FREQ = NA)
   )

workflow/scripts/report/nv_panel_data.R

@@ -19,7 +19,7 @@ variants <- read_delim(
   snakemake@input$variants,
   col_select = c(
     "SAMPLE",
-    "REGION",
+    "CHROM",
     "POS",
     "ALT",
     "VARIANT_NAME",
@@ -77,7 +77,7 @@ if (nrow(variants) == 0) {
   log_warning("No variants found, using an empty table")
   variants <- tibble(
     SAMPLE = date_order,
-    REGION = as.character(NA),
+    CHROM = as.character(NA),
     VARIANT_NAME = as.character(NA),
     ALT_FREQ = as.numeric(NA),
     EFFECT = as.character(NA),

workflow/scripts/report/polymorphic_sites_over_time_data.R

@@ -42,7 +42,7 @@ if (nrow(sites) == 0) {
   log_warn("There are none, using an empty table and no linear regression")
   sites <- tibble(
     SAMPLE = date_order,
-    REGION = as.character(NA),
+    CHROM = as.character(NA),
     VARIANT_NAME = as.character(NA),
     ALT_FREQ = as.numeric(NA),
     EFFECT = as.character(NA),