Add 30 test files covering ~60 functions, coverage 45% -> ~60%

Tests for data position helpers, find_top_consensus, order_loci,
snps_by_mutation_type, bigwig metadata, save_annotations,
select_genome, GRanges helpers (clean/rbind/filter/overlap),
chromatin state filtering, XGR foreground/background/enrichment,
ROADMAP annotate/merge, NOTT2019 markers/promoters/data,
CORCES2020 data accessors, GOSHIFTER utilities, CS plots,
standardize_celltypes, haplor summary, window_limits.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: bschilder

tests/testthat/test-CORCES2020_data.R

@@ -0,0 +1,39 @@
+test_that("get_CORCES2020_scATACseq_celltype_peaks returns data.table", {
+    skip_if_offline()
+    dat <- echoannot::get_CORCES2020_scATACseq_celltype_peaks()
+    expect_true(data.table::is.data.table(dat))
+    expect_true(nrow(dat) > 0)
+    expect_true("hg38_Chromosome" %in% colnames(dat))
+    expect_true("hg38_Start" %in% colnames(dat))
+    expect_true("hg38_Stop" %in% colnames(dat))
+})
+
+test_that("get_CORCES2020_bulkATACseq_peaks returns data.table", {
+    skip_if_offline()
+    dat <- echoannot::get_CORCES2020_bulkATACseq_peaks()
+    expect_true(data.table::is.data.table(dat))
+    expect_true(nrow(dat) > 0)
+    expect_true("hg38_Chromosome" %in% colnames(dat))
+})
+
+test_that("get_CORCES2020_scATACseq_peaks returns data.table", {
+    skip_if_offline()
+    dat <- echoannot::get_CORCES2020_scATACseq_peaks()
+    expect_true(data.table::is.data.table(dat))
+    expect_true(nrow(dat) > 0)
+})
+
+test_that("get_CORCES2020_cicero_coaccessibility returns data.table", {
+    skip_if_offline()
+    dat <- echoannot::get_CORCES2020_cicero_coaccessibility()
+    expect_true(data.table::is.data.table(dat))
+    expect_true(nrow(dat) > 0)
+    expect_true("Coaccessibility" %in% colnames(dat))
+})
+
+test_that("get_CORCES2020_hichip_fithichip_loop_calls returns data.table", {
+    skip_if_offline()
+    dat <- echoannot::get_CORCES2020_hichip_fithichip_loop_calls()
+    expect_true(data.table::is.data.table(dat))
+    expect_true(nrow(dat) > 0)
+})

tests/testthat/test-CS_plots.R

@@ -0,0 +1,50 @@
+test_that("CS_bin_plot creates plot and data", {
+    dat <- echodata::BST1
+    dat$Locus <- "BST1"
+    result <- suppressWarnings(
+        echoannot::CS_bin_plot(merged_DT = dat, show_plot = FALSE)
+    )
+    expect_true(is.list(result))
+    expect_true("plot" %in% names(result))
+    expect_true("data" %in% names(result))
+    expect_true(methods::is(result$plot, "ggplot"))
+    expect_true(nrow(result$data) > 0)
+})
+
+test_that("CS_counts_plot creates plot and data", {
+    dat <- echodata::BST1
+    dat$Locus <- "BST1"
+    result <- suppressWarnings(
+        echoannot::CS_counts_plot(merged_DT = dat, show_plot = FALSE)
+    )
+    expect_true(is.list(result))
+    expect_true("plot" %in% names(result))
+    expect_true("data" %in% names(result))
+    expect_true(methods::is(result$plot, "ggplot"))
+})
+
+test_that("CS_counts_plot with show_numbers=FALSE", {
+    dat <- echodata::BST1
+    dat$Locus <- "BST1"
+    result <- suppressWarnings(
+        echoannot::CS_counts_plot(
+            merged_DT = dat,
+            show_numbers = FALSE,
+            show_plot = FALSE
+        )
+    )
+    expect_true(methods::is(result$plot, "ggplot"))
+})
+
+test_that("CS_counts_plot label_yaxis=FALSE works", {
+    dat <- echodata::BST1
+    dat$Locus <- "BST1"
+    result <- suppressWarnings(
+        echoannot::CS_counts_plot(
+            merged_DT = dat,
+            label_yaxis = FALSE,
+            show_plot = FALSE
+        )
+    )
+    expect_true(methods::is(result$plot, "ggplot"))
+})

tests/testthat/test-GOSHIFTER_extended.R

@@ -0,0 +1,72 @@
+test_that("GOSHIFTER_search_ROADMAP filters by EID", {
+    ref_path <- system.file(
+        "extdata/ROADMAP",
+        "ROADMAP_Epigenomic.js",
+        package = "echoannot"
+    )
+    ## Get all entries first to find a valid EID
+    all_ref <- echoannot:::GOSHIFTER_search_ROADMAP(
+        Roadmap_reference = ref_path,
+        verbose = FALSE
+    )
+    valid_eid <- all_ref$EID[1]
+
+    result <- echoannot:::GOSHIFTER_search_ROADMAP(
+        Roadmap_reference = ref_path,
+        EID_filter = valid_eid,
+        verbose = FALSE
+    )
+    expect_true(nrow(result) >= 1)
+    expect_true(all(result$EID == valid_eid))
+})
+
+test_that("GOSHIFTER_search_ROADMAP filters by GROUP", {
+    ref_path <- system.file(
+        "extdata/ROADMAP",
+        "ROADMAP_Epigenomic.js",
+        package = "echoannot"
+    )
+    all_ref <- echoannot:::GOSHIFTER_search_ROADMAP(
+        Roadmap_reference = ref_path,
+        verbose = FALSE
+    )
+    valid_group <- all_ref$GROUP[1]
+
+    result <- echoannot:::GOSHIFTER_search_ROADMAP(
+        Roadmap_reference = ref_path,
+        GROUP_filter = valid_group,
+        verbose = FALSE
+    )
+    expect_true(nrow(result) >= 1)
+    expect_true(all(result$GROUP == valid_group))
+})
+
+test_that("GOSHIFTER_find_folder errors when NULL and echolocatoR not installed", {
+    ## The NULL path relies on echolocatoR being installed
+    ## If echolocatoR is not installed, this should error
+    skip_if(
+        nzchar(system.file("tools/goshifter", package = "echolocatoR")),
+        "echolocatoR has GoShifter bundled - skip this test"
+    )
+    expect_error(
+        echoannot:::GOSHIFTER_find_folder(goshifter = NULL),
+        "GoShifter directory not found"
+    )
+})
+
+test_that("GOSHIFTER_list_chromatin_states uses custom annotations_path", {
+    ## Test with the default package path explicitly
+    result <- echoannot:::GOSHIFTER_list_chromatin_states(
+        annotations_path = NULL
+    )
+    expect_true(data.table::is.data.table(result))
+    expect_true(nrow(result) > 0)
+})
+
+test_that("GOSHIFTER_bed_names with single EID", {
+    ref <- data.table::data.table(EID = "E099")
+    result <- echoannot:::GOSHIFTER_bed_names(RM_ref = ref)
+    expect_length(result, 1)
+    expect_true(grepl("^E099", result))
+    expect_true(grepl("\\.bed\\.gz$", result))
+})

tests/testthat/test-NOTT2019_data_extended.R

@@ -0,0 +1,45 @@
+test_that("get_NOTT2019_interactome returns named list", {
+    skip_if_offline()
+    dat <- echoannot:::get_NOTT2019_interactome()
+    expect_true(is.list(dat))
+    expect_true(length(dat) > 0)
+    expect_true(!is.null(names(dat)))
+    ## Should contain sheets with promoter/enhancer/interactome
+    has_promoter <- any(grepl("promoter", names(dat), ignore.case = TRUE))
+    has_enhancer <- any(grepl("enhancer", names(dat), ignore.case = TRUE))
+    has_interactome <- any(grepl("interactome", names(dat), ignore.case = TRUE))
+    expect_true(has_promoter || has_enhancer || has_interactome)
+})
+
+test_that("get_NOTT2019_superenhancer_interactome returns data.table", {
+    skip_if_offline()
+    dat <- echoannot::get_NOTT2019_superenhancer_interactome()
+    expect_true(data.table::is.data.table(dat))
+    expect_true(nrow(dat) > 0)
+    expect_true("chr" %in% colnames(dat))
+})
+
+test_that("NOTT2019_get_regulatory_regions returns data.frame", {
+    skip_if_offline()
+    regions <- echoannot::NOTT2019_get_regulatory_regions(
+        as_granges = FALSE,
+        verbose = FALSE
+    )
+    expect_true(is.data.frame(regions))
+    expect_true(nrow(regions) > 0)
+    expect_true("Cell_type" %in% colnames(regions))
+    expect_true("Element" %in% colnames(regions))
+    ## Cell_type should be standardized
+    valid_celltypes <- c("astrocytes", "neurons", "oligo", "microglia")
+    expect_true(all(regions$Cell_type %in% valid_celltypes))
+})
+
+test_that("NOTT2019_get_regulatory_regions as_granges returns GRanges", {
+    skip_if_offline()
+    regions <- echoannot::NOTT2019_get_regulatory_regions(
+        as_granges = TRUE,
+        verbose = FALSE
+    )
+    expect_true(methods::is(regions, "GRanges"))
+    expect_true(length(regions) > 0)
+})

tests/testthat/test-NOTT2019_marker_and_promoter.R

@@ -0,0 +1,50 @@
+test_that("NOTT2019_get_promoter_celltypes identifies active promoters", {
+    ## Create mock data resembling the NOTT2019 interactome data
+    annot_sub <- data.frame(
+        PU1_active_promoter = c(1, 0, 1),
+        NeuN_active_promoter = c(0, 1, 0),
+        Olig2_active_promoter = c(0, 0, 0),
+        LHX2_active_promoter = c(1, 1, 0)
+    )
+    marker_key <- echoannot:::NOTT2019_marker_key()
+
+    result <- echoannot:::NOTT2019_get_promoter_celltypes(
+        annot_sub = annot_sub,
+        marker_key = marker_key,
+        verbose = FALSE
+    )
+    expect_true(is.character(result))
+    ## PU1 -> microglia, NeuN -> neurons, LHX2 -> astrocytes are all active
+    expect_true(grepl("microglia", result))
+    expect_true(grepl("neurons", result))
+    expect_true(grepl("astrocytes", result))
+    ## Olig2 column sums to 0, so oligo should not appear
+    expect_false(grepl("oligo", result))
+})
+
+test_that("NOTT2019_get_promoter_celltypes returns empty string when none active", {
+    annot_sub <- data.frame(
+        PU1_active_promoter = c(0, 0),
+        NeuN_active_promoter = c(0, 0),
+        Olig2_active_promoter = c(0, 0),
+        LHX2_active_promoter = c(0, 0)
+    )
+    marker_key <- echoannot:::NOTT2019_marker_key()
+
+    result <- echoannot:::NOTT2019_get_promoter_celltypes(
+        annot_sub = annot_sub,
+        marker_key = marker_key,
+        verbose = FALSE
+    )
+    expect_true(is.character(result))
+    expect_equal(result, "")
+})
+
+test_that("NOTT2019_bigwig_metadata is available as package data", {
+    data("NOTT2019_bigwig_metadata", package = "echoannot")
+    expect_true(exists("NOTT2019_bigwig_metadata"))
+    expect_true(is.data.frame(NOTT2019_bigwig_metadata))
+    expect_true(nrow(NOTT2019_bigwig_metadata) > 0)
+    expect_true("name" %in% colnames(NOTT2019_bigwig_metadata) ||
+                "data_link" %in% colnames(NOTT2019_bigwig_metadata))
+})

tests/testthat/test-ROADMAP_annotate.R

@@ -0,0 +1,47 @@
+test_that("ROADMAP_annotate adds Source column to GRanges list", {
+    ## Create a simple GRanges list with EID metadata
+    gr1 <- GenomicRanges::GRanges(
+        seqnames = c("chr1", "chr1"),
+        ranges = IRanges::IRanges(start = c(100, 200), end = c(150, 250))
+    )
+    GenomicRanges::mcols(gr1)$EID <- "E003"
+    GenomicRanges::mcols(gr1)$name <- "test"
+
+    grlist <- list(item1 = gr1)
+
+    ## Get the ROADMAP reference to find a valid EID
+    ref <- echoannot::ROADMAP_construct_reference(verbose = FALSE)
+
+    result <- echoannot:::ROADMAP_annotate(
+        grlist = grlist,
+        ref = ref,
+        verbose = FALSE
+    )
+    expect_true(is.list(result))
+    expect_true(length(result) == 1)
+    gr_out <- result[[1]]
+    expect_true("Source" %in% colnames(GenomicRanges::mcols(gr_out)))
+})
+
+test_that("ROADMAP_annotate uses keyword_query when ref is NULL", {
+    gr1 <- GenomicRanges::GRanges(
+        seqnames = "chr1",
+        ranges = IRanges::IRanges(start = 100, end = 200)
+    )
+    ## Use a real EID that exists in the reference
+    ref <- echoannot::ROADMAP_construct_reference(verbose = FALSE)
+    real_eid <- ref$EID[1]
+    GenomicRanges::mcols(gr1)$EID <- real_eid
+    GenomicRanges::mcols(gr1)$name <- "test"
+
+    grlist <- list(item1 = gr1)
+    result <- echoannot:::ROADMAP_annotate(
+        grlist = grlist,
+        ref = NULL,
+        keyword_query = NULL,
+        verbose = FALSE
+    )
+    expect_true(is.list(result))
+    gr_out <- result[[1]]
+    expect_true("Source" %in% colnames(GenomicRanges::mcols(gr_out)))
+})

tests/testthat/test-ROADMAP_merge_and_process.R

@@ -0,0 +1,62 @@
+test_that("ROADMAP_merge_and_process merges and filters", {
+    ## Create a GRangesList with Source metadata
+    gr1 <- GenomicRanges::GRanges(
+        seqnames = c("chr4", "chr4", "chr4"),
+        ranges = IRanges::IRanges(
+            start = c(15723865, 15737348, 15750000),
+            end = c(15724000, 15737500, 15751000)
+        )
+    )
+    GenomicRanges::mcols(gr1)$name <- c("1_TssA", "2_Enh", "3_Quies")
+    GenomicRanges::mcols(gr1)$EID <- "E001"
+    GenomicRanges::mcols(gr1)$Source <- "Brain_Tissue"
+
+    grl <- GenomicRanges::GRangesList(test = gr1)
+
+    ## Use BST1 as the query
+    gr_snp <- echodata::BST1
+
+    result <- echoannot:::ROADMAP_merge_and_process(
+        grl.roadmap = grl,
+        gr.snp = gr_snp,
+        n_top = NULL,
+        verbose = FALSE
+    )
+    expect_true(methods::is(result, "GRanges"))
+})
+
+test_that("ROADMAP_merge_and_process n_top limits sources", {
+    ## Create GRanges with multiple sources
+    gr1 <- GenomicRanges::GRanges(
+        seqnames = rep("chr4", 5),
+        ranges = IRanges::IRanges(
+            start = seq(15723865, 15724265, 100),
+            end = seq(15724865, 15725265, 100)
+        )
+    )
+    GenomicRanges::mcols(gr1)$Source <- "SourceA"
+    GenomicRanges::mcols(gr1)$name <- paste0("1_TssA")
+
+    gr2 <- GenomicRanges::GRanges(
+        seqnames = rep("chr4", 2),
+        ranges = IRanges::IRanges(
+            start = c(15723865, 15723965),
+            end = c(15724865, 15724965)
+        )
+    )
+    GenomicRanges::mcols(gr2)$Source <- "SourceB"
+    GenomicRanges::mcols(gr2)$name <- paste0("2_Enh")
+
+    grl <- GenomicRanges::GRangesList(a = gr1, b = gr2)
+    gr_snp <- echodata::BST1
+
+    result <- echoannot:::ROADMAP_merge_and_process(
+        grl.roadmap = grl,
+        gr.snp = gr_snp,
+        n_top = 1,
+        verbose = FALSE
+    )
+    expect_true(methods::is(result, "GRanges"))
+    ## Should only keep the top source
+    expect_true(length(unique(result$Source)) <= 1)
+})