XCR mapping QC

library(ithi.utils)
load_base_libs()

library(ithi.meta)
library(ithi.xcr)

Colour palettes

pal_patient <- select_palette("patient")

Parameters

db_path <- snakemake@params$db

xcr_table_path <- snakemake@input$xcr_table
library_size_path <- snakemake@input$library_size

Metadata

db <- src_sqlite(db_path, create = FALSE)
samples <- collect(tbl(db, "samples"))
duplicates <- collect(tbl(db, "duplicates"))
xcrseq <- collect(tbl(db, "xcrseq"))

id_type <- "voa_unique"

Analysis

xcr_table <- read_clonotypes(xcr_table_path, duplicates = FALSE, db_path, verbose = 0)

Read 45.9% of 304822 rows
Read 88.6% of 304822 rows
Read 304822 rows and 18 (of 18) columns from 0.070 GB file in 00:00:04

library_sizes <- fread(library_size_path)

Total reads

read_stats <- xcr_table %>% group_by(voa_unique, type) %>% summarise(mapped_reads = sum(count))

read_stats <- merge(read_stats, library_sizes, by.x = "voa_unique", by.y = "sample")
read_stats$voa <- map_id(read_stats$voa_unique, from = "voa_unique", to = "voa", 
    db_path, table = "xcrseq")
read_stats$patient_id <- map_id(read_stats$voa, from = "voa", to = "patient_id", 
    db_path, table = "samples")
read_stats$patient_id <- factor(read_stats$patient_id)
read_stats$project_id <- factor(map_id(read_stats$voa_unique, from = "voa_unique", 
    to = "project_id", db_path, table = "xcrseq"))

ggplot(read_stats, aes(x = patient_id, y = reads)) + geom_boxplot(aes(fill = project_id)) + 
    theme_bw() + theme_Publication() + xlab("Patient") + ylab("Total library size")

Mapped fraction

read_stats$mapped_fraction <- with(read_stats, mapped_reads/reads)

ggplot(read_stats, aes(x = patient_id, y = mapped_fraction)) + geom_boxplot(aes(fill = project_id)) + 
    theme_bw() + theme_Publication() + xlab("Patient") + ylab("Mapped fraction") + 
    facet_wrap(~type, scales = "free", nrow = 2)