script/03_sequencing_effort.R

@@ -69,3 +69,31 @@ samples <- samples |>
   arrange(marker, run, sampling_event)
 
 write_tsv(samples, "finalresult/sequencing_effort/sample_seq_astan.tsv", na = "")
+
+
+######################################################
+# human (non bioinformaticien) friendly format
+######################################################
+
+sampling_effort <- read_tsv("finalresult/sampling_effort/sampling_events.tsv", col_select = c("sample_id", "dna_extracted")) |> 
+  rename("sampling_event" = "sample_id")
+
+samples_wide <- samples |>
+  select(marker, sampling_event) |> 
+  filter(!is.na(sampling_event)) |> 
+  group_by(marker, sampling_event) |> 
+  summarise(n = n()) |> 
+  pivot_wider(names_from = "marker", values_from = "n")
+
+samples_wide <- full_join(sampling_effort, samples_wide, by = "sampling_event") |> 
+  mutate(
+    across(`18s_v1v2`:ssu_v4v5, ~ replace_na(.x, 0)),
+    date = str_remove_all(sampling_event, "^RA|_\\d+") |> ymd(),
+    size_fraction = case_when(
+      str_detect(sampling_event, "_3") ~ ">3µm",
+      str_detect(sampling_event, "_02") ~ "0.2-3µm"
+    )
+  ) |> 
+  relocate(date,size_fraction,.after = sampling_event)
+
+write_tsv(samples_wide, "finalresult/sequencing_effort/sample_seq_astan_wide.tsv", na = "")