Skip to content

fix ribosome identification in alive module #103

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
myushen merged 1 commit into from
Jul 23, 2026
Merged

fix ribosome identification in alive module #103

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion DESCRIPTION
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
Package: HPCell
Title: Massively-Parallel R Native Pipeline for Single-Cell Analysis
Version: 0.5.1
Version: 0.5.2
Authors@R: c(person("Stefano", "Mangiola", email = "mangiolastefano@gmail.com",
role = c("aut", "cre")),
person("Jiayi", "Si", email = "si.j@wehi.edu.au",
Expand Down
32 changes: 22 additions & 10 deletions R/functions.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -666,12 +666,11 @@ alive_identification <- function(input_read_RNA_assay,
# Returns a named vector of IDs
# Matches the gene id's row by row and inserts NA when it can't find gene names
location <- mapIds(
EnsDb.Hsapiens.v86,
keys = rownames(input_read_RNA_assay),
column = "SEQNAME",
keytype = if (feature_nomenclature == "symbol") "SYMBOL" else "GENEID"
)

EnsDb.Hsapiens.v86,
keys = rownames(input_read_RNA_assay),
column = "SEQNAME",
keytype = if (feature_nomenclature == "symbol") "SYMBOL" else "GENEID"
)

which_mito = which(location == "MT")

Expand Down Expand Up @@ -728,8 +727,21 @@ alive_identification <- function(input_read_RNA_assay,
as_tibble(rownames = ".cell") %>%
dplyr::select(-sum, -detected)

# I HAVE TO DROP UNIQUE, AS SOON AS THE BUG IN SEURAT IS RESOLVED. UNIQUE IS BUG PRONE HERE.
percentage_output = PercentageFeatureSet(input_read_RNA_assay, pattern = "^RPS|^RPL", assay = assay)
if (feature_nomenclature == "symbol") {
percentage_output = PercentageFeatureSet(input_read_RNA_assay, pattern = "^RPS|^RPL", assay = assay)
} else {
# Ensembl IDs: resolve ribo gene IDs from biomart reference
data(ensembl_genes_biomart)
ribosome_ensembl_ids <- ensembl_genes_biomart[
grep("^(RPL|RPS)", ensembl_genes_biomart$external_gene_name), "ensembl_gene_id"
]
ribosome_features <- intersect(ribosome_ensembl_ids, rownames(input_read_RNA_assay))
percentage_output = PercentageFeatureSet(
input_read_RNA_assay,
features = if (length(ribosome_features) > 0) ribosome_features else character(0),
assay = assay
)
}
percentage_output = percentage_output[!duplicated(names(percentage_output))]
# Compute ribosome statistics
ribosome =
Expand Down Expand Up @@ -767,7 +779,7 @@ alive_identification <- function(input_read_RNA_assay,
ribosome |>
# Only retrieve metadata so nesting in the next step won't break
left_join(input_read_RNA_assay |> as_tibble() |> select(.cell, all_of(cell_type_column)), by = ".cell") |> as_tibble()

}


Expand Down Expand Up @@ -810,7 +822,7 @@ alive_identification <- function(input_read_RNA_assay,
mitochondrion |>
left_join(ribosome) |>
mutate(alive = !high_mitochondrion) |> # & !high_ribosome ) |>
# Select informative columns
# Select informative columns
select(.cell, {{cell_type_column}}, contains("subsets"), contains("observation"),
contains("high"), alive)
}
Expand Down
Loading