This workflow will visualize the benchmarking of two sci-RNA-seqv3 data-set consisting of a large cohort of Four Core Genotypes (FCG) mice (FCG; 11.3 billion mate-pairs) and a smaller Danio Rerio cohort (490 million mate-pairs) in which additional nuclear oligo hashing barcodes were added.
library(dplyr)
library(patchwork)
source('misc_functions.R')
# Parallel options.
future::plan(strategy = future::multisession(workers = 10))
# Set seed.
base::set.seed(708813)
# Location of benchmarking logs.
files_benchmark <- list.files('~/DKFZ/odomLab/manuscript_scirocket/benchmarks/', full.names = T)cohorts <- readr::read_tsv('../config/testing_samplesheet.tsv', show_col_types = FALSE)
cohorts %>%
dplyr::group_by(experiment_name) %>%
dplyr::summarise(n = dplyr::n_distinct(sample_name), .groups = 'keep') %>%
dplyr::ungroup() %>%
dplyr::select(`Cohort` = experiment_name, `Total samples` = n) %>%
knitr::kable() %>%
kableExtra::kable_styling(bootstrap_options = "striped", full_width = FALSE)| Cohort | Total samples |
|---|---|
| sx42b | 48 |
| test_hashing | 1 |
Overview of cohorts
The runtime, IO and memory usage of experiments are logged using the Snakemake benchmarking suite. We now import the benchmarking logs of the two cohorts.
data_benchmark <- dplyr::bind_rows(future.apply::future_lapply(files_benchmark, function(x){
data <- readr::read_tsv(x, show_col_types = FALSE) %>%
dplyr::mutate(
step = gsub('_test_.*', '', basename(x)),
step = gsub('_zebra.*|_mouse.*', '', step),
step = gsub('_sx42b.*', '', step),
experiment = dplyr::if_else(grepl('sx42b|mouse', x), 'FCG', 'Zebrafish (Hashing)')
)
return(data)
}))
# Calc. mean + SE
data_benchmark <- data_benchmark %>%
dplyr::group_by(step, experiment) %>%
dplyr::summarise(
mean_m = mean(s / 60),
sd_m = sd(s / 60),
mean_io_in = mean(io_in / 1024),
sd_io_in = sd(io_in / 1024),
mean_io_out = mean(io_out / 1024),
sd_io_out = sd(io_out / 1024),
mean_max_rss = mean(max_rss / 1024),
sd_max_rss = sd(max_rss / 1024),
mean_mean_load = mean(mean_load / 100),
sd_mean_load = sd(mean_load / 100), .groups = 'keep'
) %>%
dplyr::mutate(
step = factor(step, levels = c('bcl2fastq', 'split_R1', 'split_R2', 'demultiplex_fastq_split', 'gather_demultiplexed_sequencing', 'gather_demultiplexed_samples', 'trim_fastp', 'generate_index_STAR', 'starSolo_align', 'sambamba_index', 'sci_dash')),
step = dplyr::recode_factor(
step,
bcl2fastq = 'Converting BCL (**bcl2fastq**)',
split_R1 = "Splitting R1 into chunks",
split_R2 = "Splitting R2 into chunks",
demultiplex_fastq_split = "Barcode demultiplexing (on chunks)",
gather_demultiplexed_sequencing = "Merging experiment-based files",
gather_demultiplexed_samples = "Merging sample-based files",
trim_fastp = "Trimming (**fastp**)",
generate_index_STAR = "Generating alignment index (**STAR**)",
starSolo_align = "Alignment and UMI counting (**STARSolo**)",
sambamba_index = "Generating BAM indexes (**sambamba**)",
sci_dash = "Generating interactive dashboard"
)
) %>%
dplyr::ungroup()generate_benchmarking_plot(data_benchmark %>% dplyr::filter(experiment == 'FCG'))
generate_benchmarking_plot(data_benchmark %>% dplyr::filter(experiment != 'FCG'), ylimits_runtime = c(0, 45), nudge_runtime = 2.5, nudge_io = 2.5, ylimits_maxio_read = c(0,100), ylimits_maxio_write = c(0, 100))
Using a single split chunk, we can determine the speed of de-multiplexing by checking the de-multiplexing time per 1M reads.
x <- readr::read_tsv('~/DKFZ/odomLab/manuscript_scirocket/logs/step2_demultiplexing_reads/demultiplex_fastq_split_sx42b_1-of-25.log', col_names = 'line', show_col_types = FALSE) %>%
dplyr::filter(grepl("INFO: Done:", line)) %>%
dplyr::mutate(
n_reads = as.integer(gsub(' read-pairs.*', '', gsub('.*INFO: Done: ', '', line))),
time = lubridate::as_datetime(gsub(' -.*', '', line))
)
x$time <- x$time - min(x$time)
ggplot2::ggplot(x, ggplot2::aes(x = n_reads, y = time)) +
ggplot2::geom_point(size = 1, shape = 21) +
ggplot2::scale_x_continuous(labels = scales::unit_format(suffix = ' million', scale = 0.000001), expand = c(0,0.01)) +
ggplot2::scale_y_continuous(limits = c(0, 12000), expand = c(0,0.01)) +
ggplot2::labs(x = 'No. read-pairs', y = 'Time (in seconds)') +
ggpubr::stat_cor(label.y = 11000, p.digits = 0, method = 'pearson', alternative = 'two.sided') +
theme_job
data_xl <- list('Demultiplexing' = cohorts, 'Benchmarking' = data_benchmark)
openxlsx::write.xlsx(data_xl, '~/DKFZ/odomLab/manuscript_scirocket/tables/SupplTable1.xlsx', asTable = TRUE)sessioninfo::session_info()─ Session info ───────────────────────────────────────────────────────────────
setting value
version R version 4.3.2 (2023-10-31)
os macOS Sonoma 14.3.1
system aarch64, darwin20
ui X11
language (EN)
collate en_US.UTF-8
ctype en_US.UTF-8
tz Europe/Berlin
date 2024-03-11
pandoc 3.1.12.2 @ /opt/homebrew/bin/ (via rmarkdown)
─ Packages ───────────────────────────────────────────────────────────────────
package * version date (UTC) lib source
abind 1.4-5 2016-07-21 [1] CRAN (R 4.3.0)
backports 1.4.1 2021-12-13 [1] CRAN (R 4.3.0)
bit 4.0.5 2022-11-15 [1] CRAN (R 4.3.0)
bit64 4.0.5 2020-08-30 [1] CRAN (R 4.3.0)
broom 1.0.5 2023-06-09 [1] CRAN (R 4.3.0)
car 3.1-2 2023-03-30 [1] CRAN (R 4.3.0)
carData 3.0-5 2022-01-06 [1] CRAN (R 4.3.0)
cli 3.6.2 2023-12-11 [1] CRAN (R 4.3.1)
codetools 0.2-19 2023-02-01 [1] CRAN (R 4.3.2)
colorspace 2.1-0 2023-01-23 [1] CRAN (R 4.3.0)
commonmark 1.9.1 2024-01-30 [1] CRAN (R 4.3.1)
crayon 1.5.2 2022-09-29 [1] CRAN (R 4.3.0)
digest 0.6.34 2024-01-11 [1] CRAN (R 4.3.1)
dplyr * 1.1.4 2023-11-17 [1] CRAN (R 4.3.1)
evaluate 0.23 2023-11-01 [1] CRAN (R 4.3.1)
fansi 1.0.6 2023-12-08 [1] CRAN (R 4.3.1)
farver 2.1.1 2022-07-06 [1] CRAN (R 4.3.0)
fastmap 1.1.1 2023-02-24 [1] CRAN (R 4.3.0)
future 1.33.1 2023-12-22 [1] CRAN (R 4.3.1)
future.apply 1.11.1 2023-12-21 [1] CRAN (R 4.3.1)
generics 0.1.3 2022-07-05 [1] CRAN (R 4.3.0)
ggplot2 3.5.0 2024-02-23 [1] CRAN (R 4.3.1)
ggpubr 0.6.0 2023-02-10 [1] CRAN (R 4.3.0)
ggsignif 0.6.4 2022-10-13 [1] CRAN (R 4.3.0)
ggtext 0.1.2 2022-09-16 [1] CRAN (R 4.3.0)
globals 0.16.2 2022-11-21 [1] CRAN (R 4.3.0)
glue 1.7.0 2024-01-09 [1] CRAN (R 4.3.1)
gridtext 0.1.5 2022-09-16 [1] CRAN (R 4.3.0)
gtable 0.3.4 2023-08-21 [1] CRAN (R 4.3.0)
highr 0.10 2022-12-22 [1] CRAN (R 4.3.0)
hms 1.1.3 2023-03-21 [1] CRAN (R 4.3.0)
htmltools 0.5.7 2023-11-03 [1] CRAN (R 4.3.1)
htmlwidgets 1.6.4 2023-12-06 [1] CRAN (R 4.3.1)
hues 0.2.0 2019-12-01 [1] CRAN (R 4.3.0)
jsonlite 1.8.8 2023-12-04 [1] CRAN (R 4.3.1)
kableExtra 1.4.0 2024-01-24 [1] CRAN (R 4.3.1)
knitr 1.45 2023-10-30 [1] CRAN (R 4.3.1)
labeling 0.4.3 2023-08-29 [1] CRAN (R 4.3.0)
lifecycle 1.0.4 2023-11-07 [1] CRAN (R 4.3.1)
listenv 0.9.1 2024-01-29 [1] CRAN (R 4.3.1)
lubridate 1.9.3 2023-09-27 [1] CRAN (R 4.3.1)
magrittr 2.0.3 2022-03-30 [1] CRAN (R 4.3.0)
markdown 1.12 2023-12-06 [1] CRAN (R 4.3.1)
munsell 0.5.0 2018-06-12 [1] CRAN (R 4.3.0)
openxlsx 4.2.5.2 2023-02-06 [1] CRAN (R 4.3.0)
parallelly 1.37.1 2024-02-29 [1] CRAN (R 4.3.1)
patchwork * 1.2.0 2024-01-08 [1] CRAN (R 4.3.1)
pillar 1.9.0 2023-03-22 [1] CRAN (R 4.3.0)
pkgconfig 2.0.3 2019-09-22 [1] CRAN (R 4.3.0)
purrr 1.0.2 2023-08-10 [1] CRAN (R 4.3.0)
R6 2.5.1 2021-08-19 [1] CRAN (R 4.3.0)
Rcpp 1.0.12 2024-01-09 [1] CRAN (R 4.3.1)
readr 2.1.5 2024-01-10 [1] CRAN (R 4.3.1)
rlang 1.1.3 2024-01-10 [1] CRAN (R 4.3.1)
rmarkdown 2.26 2024-03-05 [1] CRAN (R 4.3.1)
rstatix 0.7.2 2023-02-01 [1] CRAN (R 4.3.0)
rstudioapi 0.15.0 2023-07-07 [1] CRAN (R 4.3.0)
scales 1.3.0 2023-11-28 [1] CRAN (R 4.3.1)
sessioninfo 1.2.2 2021-12-06 [1] CRAN (R 4.3.0)
stringi 1.8.3 2023-12-11 [1] CRAN (R 4.3.1)
stringr 1.5.1 2023-11-14 [1] CRAN (R 4.3.1)
svglite 2.1.3 2023-12-08 [1] CRAN (R 4.3.1)
systemfonts 1.0.5 2023-10-09 [1] CRAN (R 4.3.1)
tibble 3.2.1 2023-03-20 [1] CRAN (R 4.3.0)
tidyr 1.3.1 2024-01-24 [1] CRAN (R 4.3.1)
tidyselect 1.2.0 2022-10-10 [1] CRAN (R 4.3.0)
timechange 0.3.0 2024-01-18 [1] CRAN (R 4.3.1)
tzdb 0.4.0 2023-05-12 [1] CRAN (R 4.3.0)
utf8 1.2.4 2023-10-22 [1] CRAN (R 4.3.1)
vctrs 0.6.5 2023-12-01 [1] CRAN (R 4.3.1)
viridisLite 0.4.2 2023-05-02 [1] CRAN (R 4.3.0)
vroom 1.6.5 2023-12-05 [1] CRAN (R 4.3.1)
withr 3.0.0 2024-01-16 [1] CRAN (R 4.3.1)
xfun 0.42 2024-02-08 [1] CRAN (R 4.3.1)
xml2 1.3.6 2023-12-04 [1] CRAN (R 4.3.1)
yaml 2.3.8 2023-12-11 [1] CRAN (R 4.3.1)
zip 2.3.1 2024-01-27 [1] CRAN (R 4.3.1)
[1] /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/library
──────────────────────────────────────────────────────────────────────────────