Skip to content

Enhance retrieveMetadata() with genome list file input option #29

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

Open
AbhirupaGhosh wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Enhance retrieveMetadata() with genome list file input option #29

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f489be6
Enhance retrieveMetadata() with genome list file input option
AbhirupaGhosh Jun 24, 2026
05f0522
Style code (GHA)
AbhirupaGhosh Jun 24, 2026
aa2ace5
Fix genome_id_file parameter in prepareGenomes
AbhirupaGhosh Jun 24, 2026
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
35 changes: 31 additions & 4 deletions R/data_curation.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -912,6 +912,7 @@
#' - table_name: "metadata"
#' @export
retrieveMetadata <- function(user_bacs,
genome_id_file = NULL,
filter_type = "AMR",
base_dir = ".",
abx = "All",
Expand All @@ -921,10 +922,34 @@ retrieveMetadata <- function(user_bacs,
base_dir <- normalizePath(base_dir, mustWork = FALSE)

if (isTRUE(verbose)) message("Resolving genome IDs for user inputs.")
genome_ids <- .retrieveQueryIDs(
base_dir = base_dir, user_bacs = user_bacs,
overwrite = overwrite, verbose = verbose
)
# -------------------------------
# GENOME ID RESOLUTION (UPDATED)
# -------------------------------
if (!is.null(genome_id_file)) {
if (!file.exists(genome_id_file)) {
stop("Provided genome_id_file does not exist.")
}

if (isTRUE(verbose)) {
message("Using genome IDs from file: ", genome_id_file)
}

genome_ids <- readLines(genome_id_file, warn = FALSE)
genome_ids <- trimws(genome_ids)
genome_ids <- genome_ids[genome_ids != ""]
} else {
if (isTRUE(verbose)) message("Resolving genome IDs for user inputs.")

genome_ids <- .retrieveQueryIDs(
base_dir = base_dir,
user_bacs = user_bacs,
overwrite = overwrite,
verbose = verbose
)
}

genome_ids <- unique(as.character(genome_ids))

if (length(genome_ids) == 0) {
message("No genome IDs available for the specified inputs.")
return(NULL)
Expand Down Expand Up @@ -1751,6 +1776,7 @@ genomeList <- function(base_dir = ".",
#'
#' @export
prepareGenomes <- function(user_bacs,
genome_id_file = NULL,
base_dir = ".",
method = c("ftp", "cli"),
overwrite = FALSE,
Expand All @@ -1765,6 +1791,7 @@ prepareGenomes <- function(user_bacs,
if (isTRUE(verbose)) message("Step 0: Building AMR metadata (retrieveMetadata)")
invisible(retrieveMetadata(
user_bacs = user_bacs,
genome_id_file = NULL,
filter_type = "AMR",
base_dir = base_dir,
abx = "All",
Expand Down
Loading