From d9f48f73ce3e639d77cd5f5eff0c2ae63b5578f6 Mon Sep 17 00:00:00 2001
From: Jonathan Kitt <jonathan.kitt@inrae.fr>
Date: Mon, 3 Feb 2025 14:18:37 +0100
Subject: [PATCH 1/2] delete redundant functions()
---
R/add_snps.R | 38 ----------------------------
R/standardise_lr.R | 59 -------------------------------------------
R/standardize_lr.R | 62 ----------------------------------------------
3 files changed, 159 deletions(-)
delete mode 100644 R/add_snps.R
delete mode 100644 R/standardise_lr.R
delete mode 100644 R/standardize_lr.R
diff --git a/R/add_snps.R b/R/add_snps.R
deleted file mode 100644
index df0a2d9..0000000
--- a/R/add_snps.R
+++ /dev/null
@@ -1,38 +0,0 @@
-#' Add SNPs data
-#'
-#' @param lr lr values
-#' @param path_to_snps file containing the list of SNPs (three columns needed : 'probeset_id', 'chromosome', 'position')
-#' @param rm_unknown whether or not to remove rows when 'chromosome' or 'position' is missing (defaults to TRUE)
-#'
-#' @return a [tibble()]
-#' @export
-#'
-#' @examples
-#' \dontrun{
-#' add_snps(lr, path_to_snps, rm_unknown = TRUE)
-#' }
-
-add_snps <- function(lr, path_to_snps, rm_unknown = TRUE) {
-
- # Set NULL variables
-
- file_name <- probeset_id <- NULL
-
- snps <- readr::read_delim(path_to_snps) |>
- dplyr::select(probeset_id, chromosome, position)
-
- lr <- lr |>
- dplyr::left_join(snps) |>
- dplyr::select(file_name, chromosome, probeset_id, position,
- dplyr::everything()) |>
- dplyr::arrange(file_name, chromosome, position)
-
- if (rm_unknown == TRUE) {
- lr <- lr |>
- tidyr::drop_na(chromosome, position)
- }
-
- # Assign to Global Environment
- assign(x = "lr", value = lr, pos = ".GlobalEnv")
-
-}
diff --git a/R/standardise_lr.R b/R/standardise_lr.R
deleted file mode 100644
index 040110f..0000000
--- a/R/standardise_lr.R
+++ /dev/null
@@ -1,59 +0,0 @@
-#' Standardise lr values
-#'
-#' @param lr lr values
-#' @param method how to perform standardisation ("ref", "mean", or "both", defaults to "mean")
-#' @param ref name of the sample to use for standardisation (must be defined if method is "ref" or "both", defaults to NULL)
-#'
-#' @return a [tibble()]
-#' @export
-#'
-#' @examples
-#' \dontrun{
-#' standardise_lr(lr, method = "mean", ref = NULL)
-#' }
-
-standardise_lr <- function(lr, method = "mean", ref = NULL) {
-
- # Set NULL variables
-
- file_name <- probeset_id <- NULL
-
- # If method = "ref" or "both", check if ref is defined
- if(method %in% c("ref", "both")){
- print("Checking if reference sample is defined")
- if(is.null(ref)){
- stop("Reference sample is not defined")
- }
- if(!is.null(ref) & !ref %in% unique(lr$file_name)) {
- stop("Reference sample doesn't exist in the list of samples")
- }
- }
-
- # If method = "mean", calculate lr_st_mean
- if (method == "mean") {
- lr <- lr |>
- dplyr::mutate(lr_mean = mean(lr, na.rm = TRUE),
- .by = probeset_id) |>
- dplyr::mutate(lr_st_mean = lr - lr_mean) |>
- dplyr::select(-lr_mean)
- }
-
- # If method = "ref", calculate lr_st_ref
- if (method == "ref") {
- lr <- lr |>
- dplyr::mutate(lr_st_ref = lr - lr[file_name == ref],
- .by = probeset_id)
- }
-
- # If method = "both", calculate lr_st_ref & lr_st_mean
- if (method == "both") {
- lr <- lr |>
- dplyr::mutate(lr_st_ref = lr - lr[file_name == ref],
- lr_mean = mean(lr, na.rm = TRUE),
- .by = probeset_id) |>
- dplyr::mutate(lr_st_mean = lr - lr_mean,
- .before = lr_st_ref) |>
- dplyr::select(-lr_mean)
- }
-
-}
diff --git a/R/standardize_lr.R b/R/standardize_lr.R
deleted file mode 100644
index fa780b3..0000000
--- a/R/standardize_lr.R
+++ /dev/null
@@ -1,62 +0,0 @@
-#' Standardize lr values
-#'
-#' @param lr lr values
-#' @param method how to perform standardization ("ref", "mean", or "both", defaults to "mean")
-#' @param ref name of the sample to use for standardization (must be defined if method is "ref" or "both", defaults to NULL)
-#'
-#' @return a [tibble()]
-#' @export
-#'
-#' @examples
-#' \dontrun{
-#' standardize_lr(lr, method = "mean", ref = NULL)
-#' }
-
-standardize_lr <- function(lr, method = "mean", ref = NULL) {
-
- # Set NULL variables
-
- file_name <- probeset_id <- NULL
-
- # If method = "ref" or "both", check if ref is defined
- if(method %in% c("ref", "both")){
- print("Checking if reference sample is defined")
- if(is.null(ref)){
- stop("Reference sample is not defined")
- }
- if(!is.null(ref) & !ref %in% unique(lr$file_name)) {
- stop("Reference sample doesn't exist in the list of samples")
- }
- }
-
- # If method = "mean", calculate lr_st_mean
- if (method == "mean") {
- lr <- lr |>
- dplyr::mutate(lr_mean = mean(lr, na.rm = TRUE),
- .by = probeset_id) |>
- dplyr::mutate(lr_st_mean = lr - lr_mean) |>
- dplyr::select(-lr_mean)
- }
-
- # If method = "ref", calculate lr_st_ref
- if (method == "ref") {
- lr <- lr |>
- dplyr::mutate(lr_st_ref = lr - lr[file_name == ref],
- .by = probeset_id)
- }
-
- # If method = "both", calculate lr_st_ref & lr_st_mean
- if (method == "both") {
- lr <- lr |>
- dplyr::mutate(lr_st_ref = lr - lr[file_name == ref],
- lr_mean = mean(lr, na.rm = TRUE),
- .by = probeset_id) |>
- dplyr::mutate(lr_st_mean = lr - lr_mean,
- .before = lr_st_ref) |>
- dplyr::select(-lr_mean)
- }
-
- # Assign to Global Environment
- assign(x = "lr", value = lr, pos = ".GlobalEnv")
-
-}
--
GitLab
From ddda846a7943e83986fd22eb43fa25667c855422 Mon Sep 17 00:00:00 2001
From: Jonathan Kitt <jonathan.kitt@inrae.fr>
Date: Mon, 3 Feb 2025 14:54:58 +0100
Subject: [PATCH 2/2] delete redudant functions and add count_otv parameter to
detect_cpts()
---
NAMESPACE | 3 ---
R/detect_cpts.R | 38 +++++++++++++++++++++++++++++++++++---
man/add_snps.Rd | 26 --------------------------
man/detect_cpts.Rd | 7 ++++---
man/standardise_lr.Rd | 26 --------------------------
man/standardize_lr.Rd | 26 --------------------------
6 files changed, 39 insertions(+), 87 deletions(-)
delete mode 100644 man/add_snps.Rd
delete mode 100644 man/standardise_lr.Rd
delete mode 100644 man/standardize_lr.Rd
diff --git a/NAMESPACE b/NAMESPACE
index 86f2d28..337771f 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -1,11 +1,8 @@
# Generated by roxygen2: do not edit by hand
-export(add_snps)
export(calculate_lr)
export(detect_cpts)
export(read_axiom)
-export(standardise_lr)
-export(standardize_lr)
import(changepoint)
import(dplyr)
import(plyranges)
diff --git a/R/detect_cpts.R b/R/detect_cpts.R
index 12c86ad..f07a2c2 100644
--- a/R/detect_cpts.R
+++ b/R/detect_cpts.R
@@ -10,7 +10,7 @@
#' @param pen_value penalty value (defaults to 0)
#' @param max_cpts maximum number of changepoints (defaults to 1 for AMOC)
#' @param min_length minimum segment length, i.e. number of markers (defaults to 1)
-#' @param count_otvs whether or not to add number of OTVs in detected segments (defaults to TRUE)
+#' @param count_otv whether or not to add number of OTVs in detected segments (defaults to TRUE)
#'
#' @import dplyr
#' @import changepoint
@@ -22,13 +22,13 @@
#' @examples
#' \dontrun{
#' detect_cpts(lr, file_name = NULL, chromosome = NULL, var = "lr_st_mean", calc = "mean", method = "AMOC",
-#' penalty = "MBIC", pen_value = 0, max_cpts = 1, min_length = 1 count_otvs = TRUE)
+#' penalty = "MBIC", pen_value = 0, max_cpts = 1, min_length = 1 count_otv = TRUE)
#' }
detect_cpts <- function(lr, file_name = NULL, chromosome = NULL,
var = "lr_st_mean", calc = "mean",
penalty = "MBIC", pen_value = 0,
- method = "AMOC", max_cpts = 3, min_length = 1) {
+ method = "AMOC", max_cpts = 3, min_length = 1, count_otv = TRUE) {
# Set NULL variables
@@ -200,6 +200,38 @@ detect_cpts <- function(lr, file_name = NULL, chromosome = NULL,
}
+ if (count_otv == TRUE) {
+
+ ind <- unique(cpts$file_name)
+
+ olap_list <- list()
+
+ for (i in ind) {
+
+ seg <- cpts |>
+ dplyr::filter(file_name == i)
+
+ seg_gr <- seg |>
+ dplyr::select(seqnames = chromosome, start, end) |>
+ plyranges::as_granges()
+
+ snps_gr <- lr_sub |>
+ dplyr::filter(file_name == i) |>
+ dplyr::select(seqnames = chromosome, start = position, end = position, genotyping_call) |>
+ plyranges::as_granges()
+
+ otvs_gr <- snps_gr |>
+ plyranges::filter(genotyping_call == -2)
+
+ olap_list[[i]] <- seg |>
+ dplyr::mutate(count_snps = plyranges::count_overlaps(seg_gr, snps_gr),
+ count_otvs = plyranges::count_overlaps(seg_gr, otvs_gr))
+ }
+
+ cpts <- dplyr::bind_rows(olap_list)
+
+ }
+
return(cpts)
}
diff --git a/man/add_snps.Rd b/man/add_snps.Rd
deleted file mode 100644
index 4b10d75..0000000
--- a/man/add_snps.Rd
+++ /dev/null
@@ -1,26 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/add_snps.R
-\name{add_snps}
-\alias{add_snps}
-\title{Add SNPs data}
-\usage{
-add_snps(lr, path_to_snps, rm_unknown = TRUE)
-}
-\arguments{
-\item{lr}{lr values}
-
-\item{path_to_snps}{file containing the list of SNPs (three columns needed : 'probeset_id', 'chromosome', 'position')}
-
-\item{rm_unknown}{whether or not to remove rows when 'chromosome' or 'position' is missing (defaults to TRUE)}
-}
-\value{
-a \code{\link[=tibble]{tibble()}}
-}
-\description{
-Add SNPs data
-}
-\examples{
-\dontrun{
-add_snps(lr, path_to_snps, rm_unknown = TRUE)
-}
-}
diff --git a/man/detect_cpts.Rd b/man/detect_cpts.Rd
index 776d89e..c9e2434 100644
--- a/man/detect_cpts.Rd
+++ b/man/detect_cpts.Rd
@@ -14,7 +14,8 @@ detect_cpts(
pen_value = 0,
method = "AMOC",
max_cpts = 3,
- min_length = 1
+ min_length = 1,
+ count_otv = TRUE
)
}
\arguments{
@@ -38,7 +39,7 @@ detect_cpts(
\item{min_length}{minimum segment length, i.e. number of markers (defaults to 1)}
-\item{count_otvs}{whether or not to add number of OTVs in detected segments (defaults to TRUE)}
+\item{count_otv}{whether or not to add number of OTVs in detected segments (defaults to TRUE)}
}
\value{
a \code{\link[=tibble]{tibble()}}
@@ -49,6 +50,6 @@ Detect changepoints in signal intensity data
\examples{
\dontrun{
detect_cpts(lr, file_name = NULL, chromosome = NULL, var = "lr_st_mean", calc = "mean", method = "AMOC",
-penalty = "MBIC", pen_value = 0, max_cpts = 1, min_length = 1 count_otvs = TRUE)
+penalty = "MBIC", pen_value = 0, max_cpts = 1, min_length = 1 count_otv = TRUE)
}
}
diff --git a/man/standardise_lr.Rd b/man/standardise_lr.Rd
deleted file mode 100644
index 48f2038..0000000
--- a/man/standardise_lr.Rd
+++ /dev/null
@@ -1,26 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/standardise_lr.R
-\name{standardise_lr}
-\alias{standardise_lr}
-\title{Standardise lr values}
-\usage{
-standardise_lr(lr, method = "mean", ref = NULL)
-}
-\arguments{
-\item{lr}{lr values}
-
-\item{method}{how to perform standardisation ("ref", "mean", or "both", defaults to "mean")}
-
-\item{ref}{name of the sample to use for standardisation (must be defined if method is "ref" or "both", defaults to NULL)}
-}
-\value{
-a \code{\link[=tibble]{tibble()}}
-}
-\description{
-Standardise lr values
-}
-\examples{
-\dontrun{
-standardise_lr(lr, method = "mean", ref = NULL)
-}
-}
diff --git a/man/standardize_lr.Rd b/man/standardize_lr.Rd
deleted file mode 100644
index 8792558..0000000
--- a/man/standardize_lr.Rd
+++ /dev/null
@@ -1,26 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/standardize_lr.R
-\name{standardize_lr}
-\alias{standardize_lr}
-\title{Standardize lr values}
-\usage{
-standardize_lr(lr, method = "mean", ref = NULL)
-}
-\arguments{
-\item{lr}{lr values}
-
-\item{method}{how to perform standardization ("ref", "mean", or "both", defaults to "mean")}
-
-\item{ref}{name of the sample to use for standardization (must be defined if method is "ref" or "both", defaults to NULL)}
-}
-\value{
-a \code{\link[=tibble]{tibble()}}
-}
-\description{
-Standardize lr values
-}
-\examples{
-\dontrun{
-standardize_lr(lr, method = "mean", ref = NULL)
-}
-}
--
GitLab