Alignment Statistics

Code 
library(readr)
library(dplyr)
library(ggplot2)
library(gt)
library(tidyr)

data_dir <- "../results/hotair/summary/website"
aln <- read_tsv(file.path(data_dir, "alignment_stats.tsv"), show_col_types = FALSE)

Reads per Sample

Code 
aln |>
  select(sample, Total = total_reads, Mapped = mapped_reads) |>
  pivot_longer(-sample, names_to = "type", values_to = "reads") |>
  ggplot(aes(x = sample, y = reads, fill = type)) +
  geom_col(position = "dodge") +
  scale_y_continuous(labels = scales::comma) +
  labs(x = NULL, y = "Reads", fill = NULL, title = "Total vs Mapped Reads") +
  theme_minimal(base_size = 14) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Mapping Rate

Code 
aln |>
  ggplot(aes(x = reorder(sample, -mapping_rate), y = mapping_rate, fill = sample)) +
  geom_col(show.legend = FALSE) +
  geom_text(aes(label = paste0(round(mapping_rate, 1), "%")), vjust = -0.5) +
  ylim(0, 100) +
  labs(x = NULL, y = "Mapping Rate (%)", title = "Mapping Rate by Sample") +
  theme_minimal(base_size = 14) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Detailed Statistics

Code 
aln |>
  gt() |>
  fmt_number(c(total_reads, mapped_reads, primary_mapped), decimals = 0) |>
  fmt_number(mapping_rate, decimals = 1, pattern = "{x}%") |>
  cols_label(
    sample = "Sample",
    total_reads = "Total Reads",
    mapped_reads = "Mapped Reads",
    mapping_rate = "Mapping Rate",
    primary_mapped = "Primary Mapped"
  ) |>
  tab_header(title = "Alignment Statistics")
Alignment Statistics
Sample Total Reads Mapped Reads Mapping Rate Primary Mapped
HOTAIR_WT 167,480 139,101 83.1% 139,101
HOTAIR_A783U 179,822 144,559 80.4% 144,559
HOTAIR_bc06 144 72 50.0% 72
HOTAIR_AL 144,275 117,174 81.2% 117,174