New unit tests and minor improvements

.gitignore

@@ -1,2 +1,3 @@
 .Rproj.user
 .DS_Store
+my_bed.bed

R/bin_splitter.R

@@ -4,7 +4,7 @@
 #' specified size.
 #' 
 #' @details This function internally calls the purify_regions function to 
-#' properly format the incoming regions.Thus, thuis function can accept either a 
+#' properly format the incoming regions.Thus, this function can accept either a 
 #' data frame of regions or individual region coordinates.
 #'
 #' @param these_regions The region(s) to be queried. Can be a data frame with
@@ -39,7 +39,7 @@ bin_splitter = function(these_regions = NULL,
                         qend = NULL,
                         bin_size = 1000){
 
-  #call helperto format regions
+  #call helper to format regions
   my_regions = purify_regions(these_regions = these_regions,
                               qchrom = qchrom,
                               qstart = qstart,

README.md

@@ -1,6 +1,6 @@
-# BioMaesteR
-A package with convenience functions for generic genomic analysis within R. 
-Standardized, generic functions as well as bundled data objects that can be 
-called in various settings in the scope of biological analysis in R. 
-This package is specialized to provide bioinformatics infrastructure that can be 
-used in a variety of analysis. 
+# <img src="biomaesteR.png" align="right" alt="" width="120" />
+# biomaesteR
+This is biomaesteR, an R package with convenience functions commonly requested in various types of genomic analysis within R. This package is specialized to provide bioinformatics infrastructure that can be 
+used in a variety of genomic analysis. 
+
+This repo is also an ongoing project intended for demonstrating and following best-practices in development of R packages. This includes adequate package documentation (functions, bundled data objects, etc.), reproducible unit tests and vignettes. Upon Pull Requests, this repo also executes a GitAction workflow where the package is installed in various environments and thorough testing of the complete code base.

tests/testthat/test-bin_splitter.R

@@ -0,0 +1,29 @@
+#load packages
+library(testthat)
+
+test_that("bin_splitter returns correct number of bins", {
+  result <- bin_splitter(qchrom = c("chr1"), qstart = c(1), qend = c(1001), bin_size = 100)
+  expect_equal(nrow(result), 10)
+})
+
+test_that("bin_splitter returns correct bin size", {
+  result <- bin_splitter(qchrom = c("chr1"), qstart = c(1), qend = c(1000), bin_size = 100)
+  expect_equal(result$bin_end[1] - result$bin_start[1], 100)
+})
+
+test_that("bin_splitter handles multiple regions", {
+  result <- bin_splitter(qchrom = c("chr1", "chr2"), qstart = c(1, 1001), qend = c(1001, 2001), bin_size = 100)
+  expect_equal(nrow(result), 20)
+})
+
+test_that("bin_splitter handles regions data frame", {
+  my_regions <- data.frame(chrom = c("chr1", "chr2"), start = c(1, 1000), end = c(1001, 2001))
+  result <- bin_splitter(these_regions = my_regions, bin_size = 100)
+  expect_equal(nrow(result), 20)
+})
+
+test_that("bin_splitter returns correct chromosome names", {
+  result <- bin_splitter(qchrom = c("chr1", "chr2"), qstart = c(1, 1001), qend = c(1000, 2000), bin_size = 100)
+  expect_equal(unique(result$bin_chr), c("chr1", "chr2"))
+})
+

tests/testthat/test-gene_ranger.R

@@ -0,0 +1,23 @@
+library(testthat)
+
+test_that("gene_ranger throws error with no genes", {
+  expect_error(gene_ranger())
+})
+
+test_that("gene_ranger throws error with invalid projection", {
+  expect_error(gene_ranger(these_genes = "MYC", projection = "invalid"))
+})
+
+test_that("gene_ranger throws error with invalid return format", {
+  expect_error(gene_ranger(these_genes = "MYC", return_as = "invalid"))
+})
+
+test_that("gene_ranger throws error when write_to_bed is TRUE but bed_path, track_name, or track_description is not provided", {
+  expect_error(gene_ranger(these_genes = "MYC", write_to_bed = TRUE), "Provide a path for output bed file")
+  expect_error(gene_ranger(these_genes = "MYC", write_to_bed = TRUE, bed_path = "my_bed"), "Provide a track name for output bed file")
+  expect_error(gene_ranger(these_genes = "MYC", write_to_bed = TRUE, bed_path = "my_bed", track_name = "MYC"), "Provide a track description for output bed file")
+})
+
+test_that("gene_ranger runs successfully with valid input", {
+  expect_silent(gene_ranger(these_genes = "MYC"))
+})

tests/testthat/test-get_gene_info.R

@@ -1,4 +1,4 @@
-#load pacakges
+#load packages
 library(testthat)
 
 

tests/testthat/test-purify_chr.R

@@ -0,0 +1,25 @@
+library(testthat)
+
+test_that("purify_chr throws error with no projection", {
+  expect_error(purify_chr(), "You must provide a valid projection")
+})
+
+test_that("purify_chr throws error with no incoming_table", {
+  expect_error(purify_chr(projection = "hg38"), "You must provide a data table with `incoming_table`")
+})
+
+test_that("purify_chr throws error with invalid projection", {
+  expect_error(purify_chr(projection = "invalid", incoming_table = data.frame(chrom = c("1", "2", "3"))), "This function supports the following projections")
+})
+
+test_that("purify_chr adds 'chr' prefix for hg38 projection", {
+  df = data.frame(chrom = c("1", "2", "3"))
+  result = purify_chr(projection = "hg38", incoming_table = df)
+  expect_equal(result$chrom, c("chr1", "chr2", "chr3"))
+})
+
+test_that("purify_chr removes 'chr' prefix for grch37 projection", {
+  df = data.frame(chrom = c("chr1", "chr2", "chr3"))
+  result = purify_chr(projection = "grch37", incoming_table = df)
+  expect_equal(result$chrom, c("1", "2", "3"))
+})

tests/testthat/test-purify_regions.R

@@ -0,0 +1,47 @@
+library(testthat)
+
+test_that("purify_regions handles single region string", {
+  result <- purify_regions(these_regions = "chr1:100-500")
+  expect_equal(nrow(result), 1)
+  expect_equal(result$chrom, "chr1")
+  expect_equal(result$start, 100)
+  expect_equal(result$end, 500)
+})
+
+test_that("purify_regions handles multiple region strings", {
+  result <- purify_regions(these_regions = c("chr1:100-500", "chr2:100-500"))
+  expect_equal(nrow(result), 2)
+  expect_equal(result$chrom, c("chr1", "chr2"))
+  expect_equal(result$start, c(100, 100))
+  expect_equal(result$end, c(500, 500))
+})
+
+test_that("purify_regions handles individual region parameters", {
+  result <- purify_regions(qchrom = "chr1", qstart = 100, qend = 500)
+  expect_equal(nrow(result), 1)
+  expect_equal(result$chrom, "chr1")
+  expect_equal(result$start, 100)
+  expect_equal(result$end, 500)
+})
+
+test_that("purify_regions handles multiple individual region parameters", {
+  result <- purify_regions(qchrom = c("chr1", "chr2"), qstart = c(100, 200), qend = c(500, 600))
+  expect_equal(nrow(result), 2)
+  expect_equal(result$chrom, c("chr1", "chr2"))
+  expect_equal(result$start, c(100, 200))
+  expect_equal(result$end, c(500, 600))
+})
+
+test_that("purify_regions handles data frame input", {
+  my_regions <- data.frame(chrom = c("chr1", "chr2"), start = c(100, 200), end = c(500, 600))
+  result <- purify_regions(these_regions = my_regions)
+  expect_equal(nrow(result), 2)
+  expect_equal(result$chrom, c("chr1", "chr2"))
+  expect_equal(result$start, c(100, 200))
+  expect_equal(result$end, c(500, 600))
+})
+
+test_that("purify_regions throws error with incorrect input", {
+  expect_error(purify_regions(qchrom = "chr1", qstart = 100))
+  expect_error(purify_regions(these_regions = data.frame(chrom = c("chr1", "chr2"), start = c(100, 200), end = c(50, 100))))
+})

tests/testthat/test-region_ranger.R

@@ -0,0 +1,23 @@
+library(testthat)
+
+test_that("region_ranger throws error with no regions", {
+  expect_error(region_ranger())
+})
+
+test_that("region_ranger throws error with invalid projection", {
+  expect_error(region_ranger(these_regions = "chr8:127735434-127742951", projection = "invalid"), "This function supports the following projections")
+})
+
+test_that("region_ranger returns correct number of columns when raw is FALSE", {
+  result = region_ranger(these_regions = "chr8:127735434-127742951")
+  expect_equal(ncol(result), 11)
+})
+
+test_that("region_ranger returns all columns when raw is TRUE", {
+  result = region_ranger(these_regions = "chr8:127735434-127742951", raw = TRUE)
+  expect_true(ncol(result) > 11)
+})
+
+test_that("region_ranger returns warning when no genes found", {
+  expect_warning(region_ranger(these_regions = "chr1:1-10"))
+})

tests/testthat/test-sanity_check_regions.R

@@ -0,0 +1,31 @@
+library(testthat)
+
+test_that("sanity_check_regions throws error with no regions", {
+  expect_error(sanity_check_regions(), "No regions provided")
+})
+
+test_that("sanity_check_regions throws error with invalid projection", {
+  my_regions <- data.frame(chrom = c("chr1"), start = c(100), end = c(200))
+  expect_error(sanity_check_regions(incoming_regions = my_regions, projection = "invalid"), "Invalid projection specified")
+})
+
+test_that("sanity_check_regions throws error when start is greater than end", {
+  my_regions <- data.frame(chrom = c("chr1"), start = c(200), end = c(100))
+  expect_error(sanity_check_regions(incoming_regions = my_regions, projection = "hg38"), "start is greater than or equal to end")
+})
+
+test_that("sanity_check_regions throws error when start or end is outside chromosomal range", {
+  my_regions <- data.frame(chrom = c("chr1"), start = c(100), end = c(300000000))
+  expect_error(sanity_check_regions(incoming_regions = my_regions, projection = "hg38"), "Specified start or end coordinates fall outside the actual chromosomal range")
+})
+
+test_that("sanity_check_regions runs successfully with valid input", {
+  my_regions <- data.frame(chrom = c("chr1"), start = c(100), end = c(200))
+  expect_silent(sanity_check_regions(incoming_regions = my_regions, projection = "hg38"))
+})
+
+test_that("sanity_check_regions runs successfully with valid input", {
+  my_regions <- data.frame(chrom = c("1"), start = c(100), end = c(200))
+  expect_silent(sanity_check_regions(incoming_regions = my_regions, projection = "grch37"))
+})
+