R/rd_binner.R

In DanielRivasMD/Rpack.chlSab: chlSab Vervet green monkey

#' @title Read Binner
#'
#' @description
#' Description
#'
#' @param f_tmp_dir Project enviorment option
#' @param f_tmp_file Project enviorment option
#' @param f_Chromosome Project enviorment option
#' @param ge_hit_df Project enviorment option
#' @param ge_bin_overlaps Project enviorment option
#' @param ge_bin_size Project enviorment option
#'
#' @return
#' Return
#'
#' @seealso \code{genomic_count}
#' @seealso \code{peak_linker}
#'
#' @importFrom data.table :=
#' @export

rd_binner <- function(

	f_tmp_dir,
	f_tmp_file,
	f_Chromosome,
	ge_hit_df,
	ge_bin_overlaps,
	ge_bin_size
) {

	depth_file <- data.table::fread(
		paste0(f_tmp_dir, f_tmp_file, "_cv_chr", f_Chromosome, ".txt"),
		col.names = c('Chr', 'bp', 'rd')
	)
	out_val <- tibble::as_tibble(ge_hit_df[ge_hit_df$Chr == f_Chromosome, "Chr"])
	tmp_ls <- list()
	for ( over in 1:ge_bin_overlaps ) {
		#
		step_size <- ge_bin_size * ( (over - 1) / ge_bin_overlaps )
		depth_file[, Positions := CopperGenomicFunctions::slid_win( (depth_file[, .(bp)] + step_size), ge_bin_size ) - step_size]
		tmp_ls[[over]] <- stats::aggregate(rd ~ Positions, data = depth_file, FUN = mean)
	}

	tmp_mean <- CopperGenomicFunctions::concat_ls(tmp_ls)
	out_val[, 2:3] <- tmp_mean[match(ge_hit_df[ge_hit_df$Chr == f_Chromosome, ]$Positions, tmp_mean$Positions), ]

	return(out_val)
}