DRS_AAS_intersection_250718.R
s-mitsutomi
2025-07-18
suppressPackageStartupMessages(library(tidyverse))
devtools::load_all('~/Google Drive/My Drive/Scripts/R_packages/myUtilities/')## ℹ Loading myUtilitiesSettings
wd <- "/Users/s-mitsutomi/Google Drive/My Drive/Analysis/METTL2A/"
setwd(wd)
data_dir <- '/Volumes/Mitsu_NGS_3/METTL2A/'
tabledir_DRS_genome <- paste0(wd, 'Tables/DRS_m3C_sites/Genomic/')
tabledir_intersect <- paste0(wd, 'Tables/AlkAnilineSeq/Intersection/')
figdir <- paste0(wd, 'Figures/AAS_DRS_interaction/')
#figdir <- paste0(wd, 'Figures/DRS_m3C_sites/Metagene/')
#tabledir <- paste0(wd, 'Tables/DRS_m3C_sites/')
theme_set(
theme_classic(base_size = 7) +
theme(legend.position = 'bottom')
)Read data
total_cleaved_reads <-
read_tsv(
paste0(wd, 'Tables/AlkAnilineSeq/total_cleaved_reads_2024-04-02.tsv')
)## Rows: 617758 Columns: 8
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (6): transcript_id, transcript_name, transcript_type, chr, strand, base
## dbl (2): pos, total_cleaved_reads
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.total_cleaved_reads## # A tibble: 617,758 × 8
## transcript_id transcript_name transcript_type chr pos strand base
## <chr> <chr> <chr> <chr> <dbl> <chr> <chr>
## 1 nbis-gene-151 <NA> <NA> chr6 2.66e7 + G
## 2 nbis-gene-648 <NA> <NA> chr19 3.94e7 - G
## 3 nbis-gene-591 <NA> <NA> chr12 9.85e7 + G
## 4 nbis-gene-503 <NA> <NA> chr12 1.25e8 + G
## 5 nbis-gene-150 <NA> <NA> chr6 2.66e7 + G
## 6 ENST00000387441.1 MT-TH-201 Mt_tRNA chrM 1.22e4 + G
## 7 nbis-gene-92 <NA> <NA> chr17 8.12e6 + G
## 8 nbis-gene-640 <NA> <NA> chr1 2.05e8 + G
## 9 nbis-gene-450 <NA> <NA> chr14 2.06e7 - G
## 10 nbis-gene-555 <NA> <NA> chr5 1.81e8 + G
## # ℹ 617,748 more rows
## # ℹ 1 more variable: total_cleaved_reads <dbl>total_cleaved_reads |>
group_by(base) |>
reframe(n = n()) |>
mutate(percent = 100 * n / sum(n))## # A tibble: 5 × 3
## base n percent
## <chr> <int> <dbl>
## 1 A 216328 35.0
## 2 C 89172 14.4
## 3 G 172802 28.0
## 4 N 3 0.000486
## 5 T 139453 22.6reads_cleaved_at_C <-
total_cleaved_reads |>
filter(base == 'C')
reads_cleaved_at_C## # A tibble: 89,172 × 8
## transcript_id transcript_name transcript_type chr pos strand base
## <chr> <chr> <chr> <chr> <dbl> <chr> <chr>
## 1 ENST00000651540.1 ENST00000651540 lncRNA chr7 1.49e8 + C
## 2 ENST00000363286.1 RNU5B-1-201 snRNA chr15 6.53e7 + C
## 3 nbis-gene-416 <NA> <NA> chr17 3.16e7 + C
## 4 nbis-gene-24 <NA> <NA> chr6 2.75e7 + C
## 5 nbis-gene-367 <NA> <NA> chr16 1.43e7 + C
## 6 ENST00000387460.2 MT-TT-201 Mt_tRNA chrM 1.59e4 + C
## 7 . <NA> <NA> chr19 5.75e7 - C
## 8 ENST00000387377.1 MT-TM-201 Mt_tRNA chrM 4.43e3 + C
## 9 . <NA> <NA> chr3 4.86e7 + C
## 10 nbis-gene-106 <NA> <NA> chr17 8.14e6 - C
## # ℹ 89,162 more rows
## # ℹ 1 more variable: total_cleaved_reads <dbl>reads_cleaved_at_C |>
ggplot(aes(x = total_cleaved_reads)) +
geom_density() +
scale_x_log10()
Read m3C site in DRS
m3C_sites_gppy <-
read_bed12(paste0(wd, 'Tables/m3C_sites_gppy.bed')) |>
select(chrom, start, end, name, strand) |>
mutate(m3C_DRS = TRUE) |>
rename(
pos = start,
chr = chrom,
#transcript_id = name
)## Warning: One or more parsing issues, call `problems()` on your data frame for details,
## e.g.:
## dat <- vroom(...)
## problems(dat)m3C_sites_gppy |>
export_tsv(outdir = tabledir_DRS_genome, compression = 'gz')##
## Exported to: /Users/s-mitsutomi/Google Drive/My Drive/Analysis/METTL2A/Tables/DRS_m3C_sites/Genomic/m3C_sites_gppy_2025-07-18.tsv.gz## # A tibble: 489 × 6
## chr pos end name strand m3C_DRS
## <chr> <dbl> <dbl> <chr> <chr> <lgl>
## 1 chr8 56073701 56073702 ENST00000009589.8 - TRUE
## 2 chr19 41771316 41771317 ENST00000199764.7 + TRUE
## 3 chr12 112408263 112408264 ENST00000202773.14 - TRUE
## 4 chr12 112406861 112406862 ENST00000202773.14 - TRUE
## 5 chr22 23894563 23894564 ENST00000215754.8 + TRUE
## 6 chr22 23894574 23894575 ENST00000215754.8 + TRUE
## 7 chr22 23895151 23895152 ENST00000215754.8 + TRUE
## 8 chr22 23894462 23894463 ENST00000215754.8 + TRUE
## 9 chr12 6536569 6536570 ENST00000229239.10 + TRUE
## 10 chr12 6537764 6537765 ENST00000229239.10 + TRUE
## # ℹ 479 more rowsexcluded_rnatype <- c(
NA, 'lncRNA', 'snRNA', 'snoRNA', 'nonsense_mediated_decay', 'miRNA',
'Mt_tRNA', 'rRNA_pseudogene', 'ribozyme', 'misc_RNA', 'rRNA',
"transcribed_unprocessed_pseudogene", "protein_coding_CDS_not_defined"
)
check_cleaved_reads_thresh <- function(cleave_thresh) {
cleaved_C_enough_reads <-
reads_cleaved_at_C |>
filter(total_cleaved_reads > cleave_thresh)
cleaved_C_enough_reads
merge_DRS_cleaved_C_enough_reads <-
cleaved_C_enough_reads |>
left_join(m3C_sites_gppy) |>
filter(
!(transcript_type %in% excluded_rnatype))
# merge_DRS_cleaved_C_enough_reads |>
# group_by(transcript_type) |>
# reframe(n = n())
merge_DRS_cleaved_C_enough_reads |>
group_by(m3C_DRS) |>
reframe(n = n()) |>
mutate(percent = 100 * n / sum(n)) |>
mutate(cleave_thresh = cleave_thresh)
}
overlap_AAS_DRS_threshold <-
seq(1, 100, 1) |>
map(check_cleaved_reads_thresh) |>
reduce(bind_rows) |>
filter(m3C_DRS == TRUE) |>
arrange(-percent) ## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`
## Joining with `by = join_by(chr, pos, strand)`overlap_AAS_DRS_threshold |>
export_tsv(outdir = tabledir_intersect)##
## Exported to: /Users/s-mitsutomi/Google Drive/My Drive/Analysis/METTL2A/Tables/AlkAnilineSeq/Intersection/overlap_AAS_DRS_threshold_2025-07-18.tsv## # A tibble: 100 × 4
## m3C_DRS n percent cleave_thresh
## <lgl> <int> <dbl> <dbl>
## 1 TRUE 9 5.56 68
## 2 TRUE 9 5.52 67
## 3 TRUE 9 5.42 66
## 4 TRUE 9 5.29 65
## 5 TRUE 9 5.17 64
## 6 TRUE 8 5.16 71
## 7 TRUE 9 5.11 62
## 8 TRUE 9 5.11 63
## 9 TRUE 7 5.11 79
## 10 TRUE 7 5.07 78
## # ℹ 90 more rowsoverlap_AAS_DRS_threshold |>
filter(cleave_thresh %% 10 == 0)## # A tibble: 10 × 4
## m3C_DRS n percent cleave_thresh
## <lgl> <int> <dbl> <dbl>
## 1 TRUE 8 5.06 70
## 2 TRUE 9 4.92 60
## 3 TRUE 10 4.48 50
## 4 TRUE 6 4.41 80
## 5 TRUE 5 4.27 90
## 6 TRUE 11 4.04 40
## 7 TRUE 4 3.85 100
## 8 TRUE 23 3.67 10
## 9 TRUE 16 3.66 20
## 10 TRUE 12 3.61 30Total cleaved reads > 50
Total 6146 sites
total_cleaved_reads_morethan50 <-
total_cleaved_reads |>
filter(total_cleaved_reads >= 50) |>
mutate(
transcript_type2 = ifelse(
grepl('nbis-gene-', transcript_id),
'tRNA', transcript_type)
) |>
select(transcript_type2, everything()) |>
arrange(-total_cleaved_reads)
total_cleaved_reads_morethan50 ## # A tibble: 6,237 × 9
## transcript_type2 transcript_id transcript_name transcript_type chr pos
## <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 tRNA nbis-gene-151 <NA> <NA> chr6 2.66e7
## 2 tRNA nbis-gene-648 <NA> <NA> chr19 3.94e7
## 3 tRNA nbis-gene-591 <NA> <NA> chr12 9.85e7
## 4 tRNA nbis-gene-503 <NA> <NA> chr12 1.25e8
## 5 tRNA nbis-gene-150 <NA> <NA> chr6 2.66e7
## 6 Mt_tRNA ENST0000038744… MT-TH-201 Mt_tRNA chrM 1.22e4
## 7 tRNA nbis-gene-92 <NA> <NA> chr17 8.12e6
## 8 tRNA nbis-gene-640 <NA> <NA> chr1 2.05e8
## 9 tRNA nbis-gene-450 <NA> <NA> chr14 2.06e7
## 10 tRNA nbis-gene-555 <NA> <NA> chr5 1.81e8
## # ℹ 6,227 more rows
## # ℹ 3 more variables: strand <chr>, base <chr>, total_cleaved_reads <dbl>total_cleaved_reads_morethan50_annotated <-
total_cleaved_reads_morethan50 |>
filter(!is.na(transcript_type2))
total_cleaved_reads_morethan50_annotated## # A tibble: 4,566 × 9
## transcript_type2 transcript_id transcript_name transcript_type chr pos
## <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 tRNA nbis-gene-151 <NA> <NA> chr6 2.66e7
## 2 tRNA nbis-gene-648 <NA> <NA> chr19 3.94e7
## 3 tRNA nbis-gene-591 <NA> <NA> chr12 9.85e7
## 4 tRNA nbis-gene-503 <NA> <NA> chr12 1.25e8
## 5 tRNA nbis-gene-150 <NA> <NA> chr6 2.66e7
## 6 Mt_tRNA ENST0000038744… MT-TH-201 Mt_tRNA chrM 1.22e4
## 7 tRNA nbis-gene-92 <NA> <NA> chr17 8.12e6
## 8 tRNA nbis-gene-640 <NA> <NA> chr1 2.05e8
## 9 tRNA nbis-gene-450 <NA> <NA> chr14 2.06e7
## 10 tRNA nbis-gene-555 <NA> <NA> chr5 1.81e8
## # ℹ 4,556 more rows
## # ℹ 3 more variables: strand <chr>, base <chr>, total_cleaved_reads <dbl>Base composition
All
total_cleaved_reads_morethan50_basecomposition <-
total_cleaved_reads_morethan50 |>
group_by(base) |>
reframe(n = n()) |>
mutate(percent = 100 * n / sum(n))
total_cleaved_reads_morethan50_basecomposition## # A tibble: 5 × 3
## base n percent
## <chr> <int> <dbl>
## 1 A 1797 28.8
## 2 C 1108 17.8
## 3 G 1855 29.7
## 4 N 1 0.0160
## 5 T 1476 23.7total_cleaved_reads_morethan50_basecomposition_barplot <-
total_cleaved_reads_morethan50_basecomposition |>
ggplot(aes(x = '', y = percent, fill = base |> reorder(-n))) +
geom_bar(stat = 'identity', position = 'stack') +
scale_fill_manual(
values = c('#01C001', '#5051FF','#E6E602', '#E00800', 'gray')
) +
coord_flip()
total_cleaved_reads_morethan50_basecomposition_barplot |>
ggsave_pdf(
width = 4, height = 2.5, outdir = figdir
)
Annotated sites (without inter gene regions)
total_cleaved_reads_morethan50_annotated_basecomposition <-
total_cleaved_reads_morethan50_annotated |>
group_by(base) |>
reframe(n = n()) |>
mutate(percent = 100 * n / sum(n))
total_cleaved_reads_morethan50_annotated_basecomposition## # A tibble: 5 × 3
## base n percent
## <chr> <int> <dbl>
## 1 A 1363 29.9
## 2 C 790 17.3
## 3 G 1363 29.9
## 4 N 1 0.0219
## 5 T 1049 23.0total_cleaved_reads_morethan50_annotated_basecomposition_barplot <-
total_cleaved_reads_morethan50_annotated_basecomposition |>
ggplot(aes(x = '', y = percent, fill = base |> reorder(-n))) +
geom_bar(stat = 'identity', position = 'stack') +
scale_fill_manual(
values = c('#01C001', '#5051FF','#E6E602', '#E00800', 'gray')
) +
coord_flip()
total_cleaved_reads_morethan50_annotated_basecomposition_barplot |>
ggsave_pdf(
width = 4, height = 2.5, outdir = figdir
)
cleaved_C_enough_reads_50 <-
total_cleaved_reads_morethan50_annotated |>
filter(base == 'C')
cleaved_C_enough_reads_50 |>
export_tsv(outdir = tabledir_intersect, compression = 'gz')##
## Exported to: /Users/s-mitsutomi/Google Drive/My Drive/Analysis/METTL2A/Tables/AlkAnilineSeq/Intersection/cleaved_C_enough_reads_50_2025-07-18.tsv.gz## # A tibble: 790 × 9
## transcript_type2 transcript_id transcript_name transcript_type chr pos
## <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 lncRNA ENST0000065154… ENST00000651540 lncRNA chr7 1.49e8
## 2 snRNA ENST0000036328… RNU5B-1-201 snRNA chr15 6.53e7
## 3 tRNA nbis-gene-416 <NA> <NA> chr17 3.16e7
## 4 tRNA nbis-gene-24 <NA> <NA> chr6 2.75e7
## 5 tRNA nbis-gene-367 <NA> <NA> chr16 1.43e7
## 6 Mt_tRNA ENST0000038746… MT-TT-201 Mt_tRNA chrM 1.59e4
## 7 Mt_tRNA ENST0000038737… MT-TM-201 Mt_tRNA chrM 4.43e3
## 8 tRNA nbis-gene-106 <NA> <NA> chr17 8.14e6
## 9 tRNA nbis-gene-150 <NA> <NA> chr6 2.66e7
## 10 tRNA nbis-gene-290 <NA> <NA> chr12 5.62e7
## # ℹ 780 more rows
## # ℹ 3 more variables: strand <chr>, base <chr>, total_cleaved_reads <dbl>cleaved_C_enough_reads_50 |>
group_by(transcript_type2) |>
reframe(n = n()) |>
mutate(percent = 100 * n / sum(n)) |>
arrange(-percent)## # A tibble: 15 × 3
## transcript_type2 n percent
## <chr> <int> <dbl>
## 1 Mt_rRNA 202 25.6
## 2 rRNA_pseudogene 185 23.4
## 3 tRNA 184 23.3
## 4 snRNA 55 6.96
## 5 lncRNA 28 3.54
## 6 misc_RNA 28 3.54
## 7 Mt_tRNA 26 3.29
## 8 rRNA 24 3.04
## 9 protein_coding 23 2.91
## 10 snoRNA 17 2.15
## 11 ribozyme 10 1.27
## 12 miRNA 3 0.380
## 13 nonsense_mediated_decay 3 0.380
## 14 protein_coding_CDS_not_defined 1 0.127
## 15 transcribed_unprocessed_pseudogene 1 0.127cleaved_C_enough_reads_50 |>
ggplot(aes(
x = transcript_type2 |> reorder(total_cleaved_reads, sum),
y = total_cleaved_reads
)) +
geom_violin() +
scale_y_log10() +
coord_flip()## Warning: Groups with fewer than two datapoints have been dropped.
## ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.
## Groups with fewer than two datapoints have been dropped.
## ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.
merge_DRS_cleaved_C_enough_reads_50 <-
cleaved_C_enough_reads_50 |>
filter(
!(transcript_type %in% excluded_rnatype)
) |>
full_join(m3C_sites_gppy) ## Joining with `by = join_by(chr, pos, strand)`merge_DRS_cleaved_C_enough_reads_50 |>
export_tsv(outdir = tabledir_intersect, compression = 'gz')##
## Exported to: /Users/s-mitsutomi/Google Drive/My Drive/Analysis/METTL2A/Tables/AlkAnilineSeq/Intersection/merge_DRS_cleaved_C_enough_reads_50_2025-07-18.tsv.gz## # A tibble: 704 × 12
## transcript_type2 transcript_id transcript_name transcript_type chr pos
## <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 Mt_rRNA ENST00000387347… MT-RNR2-201 Mt_rRNA chrM 2240
## 2 Mt_rRNA ENST00000389680… MT-RNR1-201 Mt_rRNA chrM 1011
## 3 Mt_rRNA ENST00000389680… MT-RNR1-201 Mt_rRNA chrM 1009
## 4 Mt_rRNA ENST00000387347… MT-RNR2-201 Mt_rRNA chrM 1827
## 5 Mt_rRNA ENST00000387347… MT-RNR2-201 Mt_rRNA chrM 2347
## 6 Mt_rRNA ENST00000389680… MT-RNR1-201 Mt_rRNA chrM 1508
## 7 Mt_rRNA ENST00000387347… MT-RNR2-201 Mt_rRNA chrM 2340
## 8 Mt_rRNA ENST00000389680… MT-RNR1-201 Mt_rRNA chrM 1511
## 9 Mt_rRNA ENST00000387347… MT-RNR2-201 Mt_rRNA chrM 1817
## 10 Mt_rRNA ENST00000389680… MT-RNR1-201 Mt_rRNA chrM 1001
## # ℹ 694 more rows
## # ℹ 6 more variables: strand <chr>, base <chr>, total_cleaved_reads <dbl>,
## # end <dbl>, name <chr>, m3C_DRS <lgl>unique(merge_DRS_cleaved_C_enough_reads_50$transcript_type2)## [1] "Mt_rRNA" "protein_coding" NAmerge_DRS_cleaved_C_enough_reads_50 |>
group_by(m3C_DRS, transcript_type) |>
reframe(n = n())## # A tibble: 4 × 3
## m3C_DRS transcript_type n
## <lgl> <chr> <int>
## 1 TRUE Mt_rRNA 10
## 2 TRUE <NA> 479
## 3 NA Mt_rRNA 192
## 4 NA protein_coding 23merge_DRS_cleaved_C_enough_reads_50 |>
filter(chr == 'chrM') |>
group_by(m3C_DRS, transcript_type) |>
reframe(n = n())## # A tibble: 4 × 3
## m3C_DRS transcript_type n
## <lgl> <chr> <int>
## 1 TRUE Mt_rRNA 10
## 2 TRUE <NA> 219
## 3 NA Mt_rRNA 192
## 4 NA protein_coding 2