Package 'HaploBreedR'

Description

Runs reference and genotype preparation, candidate-gene definition (GWAS LD windows or a gene list), haplotype construction, association testing, the superior-haplotype gates (with BH-FDR), functional annotation of the publication table and, optionally, GO enrichment, for ONE trait. Results are written to 'output_dir'. To analyse several traits call this function once per trait with distinct 'trait_col' / 'output_dir'.

Usage

haplobreed_analysis(
  plink_prefix = NULL,
  plink_path = "plink",
  ref_alt = NULL,
  harmonize_strand = TRUE,
  drop_ambiguous = FALSE,
  gff3 = NULL,
  cds = NULL,
  pep = NULL,
  genome_fasta = NULL,
  reference_source = c("local", "msu7", "rapdb", "ensembl"),
  crop_species = NULL,
  crop_assembly = NULL,
  ensembl_release = NULL,
  reference_cache = NULL,
  pheno_id_col = "ID",
  on_fail = c("stop", "warn"),
  qc_report_dir = NULL,
  skip_validation = FALSE,
  work_dir = tempdir(),
  gwas_snps = NULL,
  gene_list = NULL,
  phenotype_data,
  trait_col,
  trait_label = NULL,
  direction = c("higher", "lower"),
  phenotype_type = c("single_env", "blup", "blue"),
  pc_cols = c("PC1", "PC2", "PC3", "PC4", "PC5"),
  subpop_col = "Subpopulation",
  posthoc = c("tukey", "duncan"),
  n_perm = 1000,
  n_boot = 1000,
  min_cohens_d = 0.3,
  alpha = 0.05,
  trait_threshold = NULL,
  use_all_transcripts = TRUE,
  regions_to_include = c("CDS_nonsynonymous", "5UTR", "3UTR"),
  max_miss_snp = 0.2,
  maf_min = 0.05,
  max_het_ind = 0.1,
  max_miss_ind = 0.1,
  min_individuals_qc = 10,
  min_ind_per_hap = 3,
  min_hap_freq = 0,
  ld_decay_distance = NULL,
  ld_decay_file = NULL,
  output_dir = "HaploBreedR_results",
  save_only_superior = TRUE,
  keep_intergenic = TRUE,
  figure_formats = c("pdf", "tiff", "png"),
  aa_full_names = TRUE,
  gwas_snp_col = "SNP",
  gwas_pos_col = "Position",
  gwas_chr_col = "Chromosome",
  require_fdr = TRUE,
  plot_style = c("gene_list", "per_gene", "both", "none"),
  plot_palette = "haplobreed",
  plot_theme = "haplobreed",
  plot_table_style = c("color_coded", "row_highlight"),
  plot_panels = c("gene_model", "haplotype_network", "haplotype_table", "trait_boxplot"),
  plot_width = 11,
  plot_height = 13,
  plot_combined_pdf = TRUE,
  go_enrichment = FALSE,
  go_enrichment_source = c("msu7", "rapdb"),
  go_enrichment_min_term = 5L,
  go_enrichment_min_superior = 2L,
  go_enrichment_cache = NULL,
  save_breeding_rds = TRUE,
  rds_compress = c("fast", "none", "xz"),
  rds_reference = c("embedded", "separate", "none"),
  save_plot = TRUE,
  store_all_results = FALSE,
  verbose = TRUE
)

Arguments

Value

Invisibly, a list with the pipeline result. Notable elements:

'reference'

the 'hbr_reference' object used, minus the genome FASTA if it was not needed for plotting

'geno_mat'

the 'hbr_genotype' source (streaming or in-memory)

'geno_ids'

character vector of the individuals that survived ID matching

'superior_results'

list per superior gene: 'ns_result', 'geno_data', 'hap_mat', 'hap_data', 'test_res', 'superior', 'sp_freq', 'gene_annotation'

'summary', 'superior_summary', 'attrition'

per-gene tables also written to CSV

'phenotype_data'

the cleaned ID + trait table actually used

'functional_snps_all'

every functional SNP considered across all tested genes

'gate_params'

the gate parameter list, so downstream tools can replay the gate without re-parsing the summary

Examples

toy <- system.file("extdata", "toy", package = "HaploBreedR")
res <- try(haplobreed_analysis(
  plink_prefix     = file.path(toy, "toy"),
  reference_source = "local",
  gff3             = file.path(toy, "toy.gff3"),
  cds              = file.path(toy, "toy.fa"),
  gwas_snps        = read.csv(file.path(toy, "toy_gwas.csv")),
  phenotype_data   = read.csv(file.path(toy, "toy_pheno.csv")),
  trait_col        = "trait",
  direction        = "higher",
  output_dir       = tempdir(),
  save_plot        = FALSE,
  n_perm           = 100L,
  n_boot           = 100L,
  verbose          = FALSE))

Description

Convenience wrapper that runs [hbr_fit_models()] followed by [hbr_cross_design()] and returns the combined 'hgsi_advanced' object. See the two component functions for the full argument descriptions.

Usage

hbr_advanced_decision(
  pipeline_result = NULL,
  pipeline_results = NULL,
  trait_dirs = NULL,
  output_dir = NULL,
  phenotypes = NULL,
  phenotype_id_col = "ID",
  gate_params = NULL,
  min_concordance = 0.6,
  plink_prefix = NULL,
  weights = NULL,
  top_parents = 25L,
  n_cores = 1L,
  seed = 1L,
  verbose = TRUE,
  cv_repeats = 10L,
  cv_folds = 5L,
  top_frac = 0.1,
  min_count = 5L,
  strata = NULL,
  n_strata = 3L,
  strict = TRUE,
  final_model = c("auto", "gblup", "two_kernel"),
  boot = 2000L,
  cM_per_Mb = NULL,
  genetic_map = NULL,
  bin_cM = 1,
  top_crosses = 20L,
  relatedness_max = 0.3,
  mating = c("DH", "RIL"),
  sel_frac = 0.1,
  h_sel = 1,
  cross_rank = c("uc", "blocks", "balanced"),
  haploblock_method = c("recomb", "ld", "fourgamete", "gabriel", "recomb+gabriel",
    "recomb+fourgamete"),
  haploblock_rmax = 0.01,
  haploblock_r2 = 0.5,
  haploblock_ld_max_cM = 3,
  haploblock_max_span_cM = 5,
  haploblock_flank_cM = 1,
  haploblock_max_snps = 400L,
  haploblock_min_gamete = 0.01,
  run_set_selection = TRUE,
  set_size = 8L,
  n_candidates = 60L,
  block_cM = 5
)

Arguments

Value

An 'hgsi_advanced' object.

Examples

toy <- system.file("extdata", "hgsi_toy", package = "HaploBreedR")
td  <- file.path(toy, "trait_YLD")
fit <- try(hbr_advanced_decision(
  trait_dirs   = c(YLD = td),
  plink_prefix = file.path(toy, "geno_toy"),
  output_dir   = tempdir(),
  cv_repeats   = 1L, cv_folds = 2L, strict = FALSE,
  run_set_selection = FALSE,
  save_plot    = FALSE,
  verbose      = FALSE))

Description

Overlaps a set of LD regions with a gene table and labels each region-gene pair with a 'Gene_Relationship' ('GENE_CONTAINED', 'OVERLAPS_LEFT', 'OVERLAPS_RIGHT', 'CONTAINS_REGION', or 'OVERLAPS'). Region list columns (e.g. 'GWAS_SNPs') are preserved through the overlap. When 'keep_intergenic = TRUE', regions with no overlapping gene are retained as 'INTERGENIC'.

Usage

hbr_annotate_regions_with_genes(
  regions,
  genes,
  chr_col = "Chromosome",
  start_col = "Region_Start",
  end_col = "Region_End",
  keep_intergenic = TRUE,
  verbose = TRUE
)

Arguments

Value

A 'data.table' of region-gene overlaps, or 'NULL'.

Examples

regions <- data.table::data.table(
  LD_Region_ID = "R1",
  Chromosome   = "1",
  Region_Start = 1000L,
  Region_End   = 3000L)
genes <- data.table::data.table(
  Gene_ID         = "gene1",
  Gene_Chromosome = "1",
  Gene_Start      = 1000L,
  Gene_End        = 2500L,
  Gene_Strand     = "+")
hbr_annotate_regions_with_genes(regions, genes, verbose = FALSE)

Description

Computes the VanRaden (2008) Method 1 genomic relationship matrix in streaming blocks directly from binary PLINK files.

Usage

hbr_build_grm(
  plink_prefix,
  maf_min = 0.05,
  block_cols = 20000L,
  n_cores = 1L,
  verbose = TRUE,
  train_idx = NULL
)

Arguments

Value

List containing 'A', 'd', 'p', 'keep', 'n', 'm', and 'snps'.

Examples

toy <- system.file("extdata", "toy", package = "HaploBreedR")
if (requireNamespace("BEDMatrix", quietly = TRUE)) {
  grm <- hbr_build_grm(file.path(toy, "toy"), verbose = FALSE)
  length(grm$snps)
}

Description

Reads 'pipeline_result_for_breeding.rds' and the CSVs written by [haplobreed_analysis()] in the same directory, and writes one Excel workbook containing up to 18 sheets covering study summary, gene results, donor tables, breeding decisions, and annotation.

Usage

hbr_build_manuscript_tables(
  rds_file = NULL,
  output_dir = NULL,
  output_file = NULL,
  phenotype_data = NULL,
  id_col = "ID",
  profile = c("manuscript", "supplementary", "full"),
  include_sheets = NULL,
  exclude_sheets = NULL,
  overwrite = TRUE,
  verbose = TRUE
)

Arguments

Value

Invisibly, a list with 'file', 'sheets', 'skipped'.

Examples

res <- structure(
  list(
    traits = list(GY = list(
      name      = "GY",
      source    = "toy",
      trait_col = "GY",
      direction = "higher",
      info      = list(
        source         = "toy",
        rds_path       = NULL,
        trait_col      = "GY",
        direction      = "higher",
        mode           = "GWAS",
        genes_tested   = 10L,
        superior_count = 2L,
        n_perm         = 1000L,
        ld_decay_bp    = NA_real_))),
    parents  = data.frame(rank = 1L, id = "IND01", index = 0.5,
                          SE = 0.1, P_top15 = 0.9, haplo_cov = 0.8,
                          mean_rel = 0.1, n_crosses = 2L,
                          action = "advance"),
    crosses  = data.frame(rank = 1L, p1 = "IND01", p2 = "IND02",
                          mid_index = 0.4, relatedness = 0.1,
                          complement = 0.5, score = 1.4),
    evidence = data.frame(trait = "GY", direction = "higher",
                          mode = "GWAS", tested = 10L,
                          superior = 2L, n_obs = 100L,
                          sigma2_g = 0.5, sigma2_e = 0.5,
                          h2 = 0.5, w_hat = 0.3, n_features = 5L),
    G            = list(G = diag(1), n_total = 5L, n_used = 5L),
    fits         = list(GY = list(ids = "IND01",
                                  g_M0 = 0.1, g_M2 = 0.1,
                                  rel_M2 = 0.8, sigma2_g = 0.5)),
    weights      = c(GY = 1),
    directions   = c(GY = "higher"),
    output_dir   = tempdir(),
    plink_prefix = "toy",
    maf_min      = 0.05,
    parameters   = list(relatedness_max = 0.3,
                        cv = list(folds = 3L,
                                  repeats = 1L,
                                  n_perm = 50L)),
    sup_sets     = list(),
    index        = data.frame(id = "IND01", index = 0.5,
                              SE = 0.1, rank = 1L,
                              P_top15 = 0.9),
    pipeline_summary = data.frame(
      Trait               = "GY",
      Direction           = "higher",
      Mode                = "GWAS",
      Genes_Tested        = 10L,
      Superior_Haplotypes = 2L,
      LD_Decay_bp         = NA_real_,
      Output_Dir          = tempdir(),
      stringsAsFactors    = FALSE)),
  class = c("hgsi_result", "list"))

rds <- file.path(tempdir(), "fake_result.rds")
saveRDS(res, rds)
suppressWarnings(
  hbr_build_manuscript_tables(
    rds_file    = rds,
    output_file = file.path(tempdir(), "tables.xlsx")))

Description

Validates PLINK files, phenotype records, GFF3 features, and sample ID overlap before launching intensive discovery pipelines.

Usage

hbr_check_inputs(
  plink_prefix,
  phenotype_data,
  trait_col,
  pheno_id_col = "ID",
  gff3 = NULL
)

Arguments

Value

A list of class hbr_check detailing compatibility status.

Examples

if (interactive()) {
  pheno <- data.frame(ID = sprintf("IND%02d", 1:10), trait = rnorm(10))
  toy   <- system.file("extdata", "toy", package = "HaploBreedR")
  res   <- hbr_check_inputs(
    plink_prefix   = file.path(toy, "toy"),
    phenotype_data = pheno,
    trait_col      = "trait")
}

Description

Returns the crop-to-species-to-assembly lookup table. If a cached table exists under 'tools::R_user_dir("haplobreed", "cache")', it is returned; otherwise the built-in default from ['.hbr_crop_lookup_default()'] is used.

Usage

hbr_crop_lookup()

Value

A 'data.table' with columns 'crop', 'species', 'assembly'.

Examples

crop <- hbr_crop_lookup()
head(crop)
crop$crop

Description

Takes the 'hgsi_fit' object produced by [hbr_fit_models()], groups the superior haplotypes into haplotype blocks, scores crosses by usefulness (Schnell and Utz, 1975) and by block coverage, and selects a diverse parent set. Returns the full 'hgsi_advanced' object. Because the expensive cross-validation is already done, this function reruns in minutes with a different 'haploblock_method' or a different 'genetic_map'.

Usage

hbr_cross_design(
  fit,
  output_dir = NULL,
  cM_per_Mb = NULL,
  genetic_map = NULL,
  bin_cM = 1,
  top_crosses = 20L,
  relatedness_max = 0.3,
  mating = c("DH", "RIL"),
  sel_frac = 0.1,
  h_sel = 1,
  cross_rank = c("uc", "blocks", "balanced"),
  haploblock_method = c("recomb", "ld", "fourgamete", "gabriel", "recomb+gabriel",
    "recomb+fourgamete"),
  haploblock_rmax = 0.01,
  haploblock_r2 = 0.5,
  haploblock_ld_max_cM = 3,
  haploblock_max_span_cM = 5,
  haploblock_flank_cM = 1,
  haploblock_max_snps = 400L,
  haploblock_min_gamete = 0.01,
  run_set_selection = TRUE,
  set_size = 8L,
  n_candidates = 60L,
  block_cM = 5,
  verbose = TRUE
)

Arguments

Value

An 'hgsi_advanced' object (a superset of the 'hgsi_fit').

Examples

toy <- system.file("extdata", "hgsi_toy", package = "HaploBreedR")
td  <- file.path(toy, "trait_YLD")
fit <- try(hbr_fit_models(
  trait_dirs   = c(YLD = td),
  plink_prefix = file.path(toy, "geno_toy"),
  output_dir   = tempdir(),
  cv_repeats   = 1L, cv_folds = 2L, strict = FALSE,
  verbose      = FALSE))
if (inherits(fit, "hgsi_fit")) {
  try(hbr_cross_design(
    fit,
    output_dir        = tempdir(),
    haploblock_method = "recomb",
    run_set_selection = FALSE,
    verbose           = FALSE))
}

Description

For any pair of parents in a [hbr_advanced_decision()] result — not only the top-ranked crosses — reports which haplotype blocks are fixed, segregating, split between the parents (a recombinant is needed) or missing, the exact probability that a doubled-haploid progeny carries every segregating target haplotype, the F2 probabilities, and the number of plants needed to recover at least one carrier with the requested confidence.

Usage

hbr_cross_plan(
  x,
  parent_a,
  parent_b = NULL,
  mating = c("DH", "RIL"),
  conf = 0.95
)

Arguments

Details

The DH probability is computed at the gene level with Haldane's map function, so linkage in coupling or repulsion enters exactly. F2 probabilities ignore linkage and count one locus per segregating block or per differing gene of a split block. Plant numbers solve '1 - (1 - p)^N >= conf' (Sedcole 1977). The mid-parent index uses the result's multi-trait index (larger is better in the pipeline's direction). Usefulness and progeny SD are reported only for pairs that were computed in the result.

Value

A data.frame with one row per cross, columns 'parent_a', 'parent_b', 'mid_index', 'n_blocks_fixed', 'n_blocks_segregating', 'n_blocks_split', 'n_blocks_incomplete', 'n_blocks_covered', 'n_blocks_target', 'p_pyramid_DH' or 'p_pyramid_RIL', 'p_pyramid_F2_hom', 'plants_needed', and, when available, 'sd_index' and 'uc'.

See Also

[hbr_advanced_decision()], [hbr_pyramid_probability()], [hbr_population_size()].

Examples

# A minimal hgsi_advanced stub, sufficient for planning only
res <- structure(list(
  ids    = c("A", "B", "C"),
  index  = c(1.0, 0.8, 0.6),
  crosses = data.frame(parent_a = "A", parent_b = "B",
                       uc = 1.5, sd_index = 0.4),
  target = list(
    carry = matrix(c(TRUE, FALSE, TRUE, FALSE, TRUE, TRUE),
                   nrow = 3, ncol = 2,
                   dimnames = list(c("A", "B", "C"),
                                   c("GENE01", "GENE02"))),
    block = c(1L, 1L),
    units = data.frame(gene = c("GENE01", "GENE02"),
                       chr  = c("1", "1"),
                       cm   = c(10, 10.5),
                       stringsAsFactors = FALSE))),
  class = "hgsi_advanced")
hbr_cross_plan(res, "A", "B")
hbr_cross_plan(res, c("A", "B"), c("B", "C"))

Description

Computes the Schnell & Utz (1975) Cross Usefulness (UC) and progeny genetic variance analytically using recombination covariance matrices (Zhong & Jannink, 2007).

Usage

hbr_cross_usefulness(
  S,
  gebv,
  bins,
  w_eff,
  pairs,
  sel_frac = 0.1,
  h_sel = 1,
  mating = c("DH", "RIL")
)

Arguments

Value

data.frame with parent indices, mid-parent index, progeny SD, and UC.

Examples

set.seed(1)
S     <- array(rnorm(4 * 3 * 2), dim = c(4, 3, 2))
gebv  <- matrix(rnorm(4 * 2), 4, 2)
bins  <- list(chr = c("1", "1", "2"), center = c(5, 15, 8), n = 3)
pairs <- t(combn(4, 2))
hbr_cross_usefulness(S, gebv, bins, w_eff = c(1, 1), pairs = pairs)

Description

Runs every phenotype-dependent step of the HGSI pipeline: loads the pipeline output, builds the genomic relationship matrix, rebuilds the haplotype codes for all tested genes, replays the discovery gate inside each CV fold (M0 / M2 / M3), fits the final model on all phenotyped individuals, and computes the multi-trait selection index. Returns an 'hgsi_fit' object that [hbr_cross_design()] consumes. Use this function on its own when the same fit will be reused for several cross-design configurations; otherwise call [hbr_advanced_decision()] which runs both parts end to end.

Usage

hbr_fit_models(
  pipeline_result = NULL,
  pipeline_results = NULL,
  trait_dirs = NULL,
  output_dir = NULL,
  phenotypes = NULL,
  phenotype_id_col = "ID",
  gate_params = NULL,
  min_concordance = 0.6,
  plink_prefix = NULL,
  weights = NULL,
  cv_repeats = 10L,
  cv_folds = 5L,
  top_frac = 0.1,
  min_count = 5L,
  strata = NULL,
  n_strata = 3L,
  strict = TRUE,
  final_model = c("auto", "gblup", "two_kernel"),
  top_parents = 25L,
  n_cores = 1L,
  boot = 2000L,
  seed = 1L,
  verbose = TRUE
)

Arguments

Value

An object of class 'hgsi_fit'. Feed it to [hbr_cross_design()].

Examples

toy <- system.file("extdata", "test_data", package = "HaploBreedR")
fit <- try(hbr_fit_models(
  trait_dirs   = c(trait1 = toy),
  plink_prefix = file.path(toy, "test"),
  output_dir   = tempdir(),
  cv_repeats   = 1L, cv_folds = 2L, strict = FALSE,
  verbose      = FALSE))

Description

Reads the per-gene '<gene>_individuals.csv' written by [haplobreed_analysis()] and returns, for every individual in the HGSI result, whether they carry the pipeline's superior haplotype at that gene. Used to colour per-individual figures by carrier status.

Usage

hbr_gene_carriers(x, trait, gene, trait_dir = NULL, superior_haplotype = NULL)

Arguments

Value

A list with 'carrier' (logical, length 'length(x$ids)'), 'haplotype' (character, the assigned haplotype per individual), 'superior_haplotype' (character), and 'gene' and 'trait'.

Examples

toy <- system.file("extdata", "hgsi_toy", package = "HaploBreedR")
td  <- file.path(toy, "trait_YLD")
if (nzchar(toy) && dir.exists(td)) {
  x <- structure(
    list(ids = sprintf("L%03d", 1:150),
         traits = "YLD",
         trait_dirs = c(YLD = td)),
    class = "hgsi_advanced")
  res <- try(hbr_gene_carriers(
    x, trait = "YLD", gene = "GENE04", trait_dir = td))
}

Description

Runs the three input-QC checks — sequence-resource QC ([hbr_validate_sequence_resources()]), genotype-reference compatibility ([hbr_validate_genotype_reference()]), and ID overlap ([hbr_validate_individual_ids()], when phenotypes are supplied) — and prints a single consolidated report. Optionally writes a plain- text file and/or a full report set (TXT + three CSV tables) to 'out_dir'. Only the TXT and CSV files are written: the HTML duplicate was removed.

Usage

hbr_generate_input_qc_report(
  reference,
  genotype,
  phenotype_data = NULL,
  pheno_id_col = "ID",
  out_file = NULL,
  out_dir = NULL,
  ...
)

Arguments

Value

Invisibly, a list with 'sequence_qc', 'compatibility', 'id_report', 'overall_status', and 'files'.

Examples

if (interactive()) {
  toy <- system.file("extdata", "toy", package = "HaploBreedR")
  # A complete call needs an hbr_reference and hbr_genotype; see the
  # vignette for the construction used here.
}

Description

One-sided Fisher's exact test (over-representation) per GO term, with multiple-testing adjustment over the terms tested in the aspect. Aspects BP (biological process), MF (molecular function), and CC (cellular component) are recognised under all common naming conventions ('BP'/'P'/'biological_process', etc.). Note: candidate genes from GWAS intervals are not independent (LD clusters, overlapping genes), so treat the p-values as exploratory.

Usage

hbr_go_enrichment(
  genes_superior,
  genes_all,
  goslim_dt,
  aspect = c("BP", "MF", "CC", "all"),
  min_term_size = 5L,
  min_superior = 2L,
  p_adjust = "BH",
  top_n = 50L,
  restrict_to_annotated = FALSE,
  verbose = TRUE
)

Arguments

Value

A 'data.table' with columns 'GO_ID', 'GO_Term', 'GO_Aspect', 'N_Superior', 'N_Universe', 'OR', 'P', 'Adjusted_P'.

Examples

goslim <- data.table::data.table(
  Gene_ID   = c("Os01g0100100", "Os01g0100200", "Os01g0100300"),
  GO_ID     = c("GO:0008150", "GO:0008150", "GO:0003674"),
  GO_Aspect = c("P", "P", "F"),
  GO_Term   = c("biological_process", "biological_process",
                "molecular_function"))
hbr_go_enrichment(
  genes_superior = c("Os01g0100100", "Os01g0100200"),
  genes_all      = c("Os01g0100100", "Os01g0100200", "Os01g0100300"),
  goslim_dt      = goslim,
  aspect         = "BP",
  min_term_size  = 1L,
  min_superior   = 1L)

Description

Runs [hbr_haplotype_blocks()] and returns the block summary table alongside the per-locus assignment. The table has one row per block with the block id, chromosome, start and end position in cM, the number of target loci in the block, the number of distinct genes (when 'units' has a 'gene' column) and the concatenated gene and trait names.

Usage

hbr_haplotype_block_table(
  plink_prefix = NULL,
  units,
  cm_snp = NULL,
  chr_snp = NULL,
  traits = NULL,
  method = c("recomb", "ld", "either", "fourgamete", "gabriel", "recomb+gabriel",
    "recomb+fourgamete"),
  flank_cM = 1,
  max_snps = 400L,
  max_span_cM = 5,
  min_gamete = 0.01,
  maf_min = 0.05,
  rmax = 0.01,
  r2 = 0.5,
  ld_max_cM = 3,
  r2_min = 0.25,
  gabriel_grid = 21L,
  carry = NULL
)

Arguments

Value

A list with 'blocks' (the summary table) and 'assignment' (the block id per target locus, in the same order as 'units').

Examples

units <- data.frame(chr = c("1", "1", "1"),
                    cm  = c(10, 10.5, 11),
                    gene = c("g1", "g2", "g3"))
hbr_haplotype_block_table(method = "recomb", units = units)

Description

Groups a set of target loci into haplotype blocks by one of seven methods and reports the block assignment. Two calling conventions are supported.

Usage

hbr_haplotype_blocks(
  plink_prefix = NULL,
  units = NULL,
  cm_snp = NULL,
  chr_snp = NULL,
  method = c("recomb", "ld", "either", "fourgamete", "gabriel", "recomb+gabriel",
    "recomb+fourgamete"),
  flank_cM = 1,
  max_snps = 400L,
  max_span_cM = 5,
  min_gamete = 0.01,
  maf_min = 0.05,
  rmax = 0.01,
  r2 = 0.5,
  ld_max_cM = 3,
  r2_min = 0.25,
  gabriel_grid = 21L,
  carry = NULL,
  genetic_map = NULL,
  cM_per_Mb = NULL,
  verbose = FALSE
)

Arguments

Details

**Low-level.** Supply 'plink_prefix', 'units', 'cm_snp' and 'chr_snp' directly. 'units' must carry 'chr', 'cm' and (for the SNP-level methods) 'snp_col'; 'cm_snp' and 'chr_snp' give the genetic and physical position of every SNP in the PLINK file. The function returns an integer vector of block IDs per row of 'units'. This is the legacy API and is fully backward compatible.

**Run-level.** Pass an 'hbr_run' (from [hbr_read_results()]) as the first positional argument or as 'plink_prefix'. The function reads the superior haplotypes, rebuilds the codes, replays the discovery gate to pick the best haplotype per gene, places each at its genetic map position, and returns a classed 'hbr_blocks' object with the block table, the per-line carrier matrix, and (for SNP-level methods) the SNP windows used.

The seven block methods are:

'"recomb"'

Join neighbours whose Haldane recombination fraction is at most 'rmax'. Describes the recombination expected in a new cross.

'"ld"'

Join neighbours whose carrier indicators have r-squared at least 'r2' within 'ld_max_cM'. Describes LD in the panel.

'"either"'

Union of '"recomb"' and '"ld"'.

'"fourgamete"'

Four-gamete rule on the SNPs around the genes (Wang et al. 2002; Haploview default).

'"gabriel"'

Gabriel-type D-prime confidence intervals (Gabriel et al. 2002).

'"recomb+gabriel"'

Union of '"recomb"' and '"gabriel"', then capped at 'max_span_cM'.

'"recomb+fourgamete"'

Union of '"recomb"' and '"fourgamete"', then capped.

Blocks never span chromosomes. '"recomb"', '"ld"' and '"either"' operate on the loci directly; the SNP-level methods read a window of 'flank_cM' around each cluster of target genes.

Value

For the low-level API, an integer vector of block IDs per row of 'units'. For the run-level API, an object of class 'hbr_blocks' with elements 'blocks', 'units', 'lines', 'full', 'snp_clusters', 'settings' and 'map_source'.

See Also

[hbr_read_results()] to build the run input, [hbr_haplotype_block_table()] for the legacy low-level wrapper.

Examples

# Legacy low-level API — no genotypes needed for the map methods
units <- data.frame(chr = c("1", "1", "1", "2", "2"),
                    cm  = c(10, 10.5, 50, 5, 5.2))
hbr_haplotype_blocks(method = "recomb", units = units)

# Run-level API on the bundled toy data
toy <- system.file("extdata", "hgsi_toy", package = "HaploBreedR")
if (nzchar(toy) && dir.exists(toy) &&
    requireNamespace("BEDMatrix", quietly = TRUE)) {
  run <- hbr_read_results(file.path(toy, "trait_YLD"))
  blk <- hbr_haplotype_blocks(
    run, plink_prefix = file.path(toy, "geno_toy"),
    method = "recomb")
  blk$blocks
}

Description

Return 'n' colours from a named palette

Usage

hbr_palette(name = "haplobreed", n = NULL)

Arguments

Value

Character vector of hex colours.

Examples

hbr_palette("okabe_ito", n = 4)
hbr_palette("haplobreed")

Description

Names of the built-in colour palettes

Usage

hbr_palette_names()

Value

A character vector of palette names accepted by [hbr_palette()].

Examples

hbr_palette_names()

Description

Visualises how the ranking of recommended crosses changes when progeny variance is accounted for. Each point is one cross; the x-axis is the rank by mid-parent index alone, the y-axis is the rank by usefulness (Schnell and Utz, 1975). Points on the diagonal are crosses whose recommendation is identical under the two criteria; points off the diagonal are crosses whose rank depends on progeny variance. The most displaced cross is optionally highlighted and labelled.

Usage

hbr_plot_cross_ranking(
  x,
  top_n = 20L,
  highlight = c("auto"),
  label_size = 3,
  palette = "haplobreed",
  theme = "haplobreed",
  output_dir = NULL,
  file_name = "cross_ranking",
  width = 6,
  height = 6,
  formats = c("pdf", "png"),
  verbose = TRUE
)

Arguments

Details

Use this to document that the genetic map is doing real work in the cross-design step, or to justify why a cross with a lower mid-parent index is nonetheless recommended.

Value

Invisibly, a list with 'plot' (the ggplot object) and 'files' (the paths written, or 'character(0)' if 'output_dir' is 'NULL'). The 'plot' element can be assigned and modified further with ggplot2.

Examples

toy <- system.file("extdata", "toy", package = "HaploBreedR")
crosses <- data.frame(
  parent_a  = sprintf("IRIS_%04d", 1:20),
  parent_b  = sprintf("IRIS_%04d", 21:40),
  mid_index = runif(20, 5, 12),
  uc        = runif(20, 5, 15))
hbr_plot_cross_ranking(crosses, top_n = 20)

Description

Displays the paired CV comparison of M2 vs M0, M3 vs M0 and M3 vs M2 per trait, with bootstrap confidence intervals. Points whose interval excludes zero are coloured by the palette's superior colour; the rest are drawn in the muted text colour. Use this as the headline figure for the honest-vs-naive comparison.

Usage

hbr_plot_cv_forest(
  x,
  metric = "r",
  palette = "haplobreed",
  theme = "haplobreed",
  output_dir = NULL,
  file_name = "cv_forest",
  width = 8,
  height = NULL,
  formats = c("pdf", "png"),
  verbose = TRUE
)

Arguments

Value

Invisibly, 'list(plot = <ggplot>, files = <character>)'.

Examples

cmp <- data.frame(
  trait     = rep(c("YLD", "DTF"), each = 3),
  method    = rep(c("M2", "M3", "M3"), 2),
  baseline  = rep(c("M0", "M0", "M2"), 2),
  metric    = "r",
  mean_diff = c(0.05, 0.02, 0.03, 0.04, 0.01, 0.03),
  boot_lo   = c(0.01, -0.01, 0.00, 0.01, -0.02, 0.00),
  boot_hi   = c(0.09, 0.05, 0.06, 0.07, 0.04, 0.06),
  stringsAsFactors = FALSE)
hbr_plot_cv_forest(cmp)

Description

Draws UTRs, exons, intron chevrons (strand-aware), and optional functional-variant markers for one or more genes. When 'facet_rows = FALSE' and more than one gene is requested, a combined- axis facet figure is also written.

Usage

hbr_plot_gene_structure(
  gene_list,
  reference = NULL,
  gff3_path = NULL,
  annotation_source = c("MSU7", "RAPDB", "CUSTOM"),
  cdna_path = NULL,
  cds_path = NULL,
  pep_path = NULL,
  genome_fasta_path = NULL,
  output_dir = NULL,
  figures_dir = "figures",
  n_gene = NULL,
  sort_by = c("Cohens_d", "Superior_Mean"),
  fun_variants = NULL,
  variant_panel_dir = NULL,
  show_variants = TRUE,
  variant_shape_by_region = TRUE,
  aa_full_names = TRUE,
  facet_rows = TRUE,
  palette = "haplobreed",
  theme = "scientific",
  width = 10,
  height = 4,
  formats = c("pdf", "png"),
  combined_pdf = TRUE,
  verbose = TRUE
)

Arguments

Value

Invisibly, a list with 'plots', 'files', 'combined_pdf', 'missing_genes'.

Examples

toy <- system.file("extdata", "toy", package = "HaploBreedR")
hbr_plot_gene_structure(
  gene_list         = "gene1",
  gff3_path         = file.path(toy, "toy.gff3"),
  genome_fasta_path = file.path(toy, "toy.fa"),
  output_dir        = tempdir(),
  formats           = "pdf",
  verbose           = FALSE)

Description

Draws a two-panel figure: a haplotype boxplot (with jittered points, mean +/- SE overlay, and post-hoc letters) and a haplotype summary table (N, frequency, per-SNP alleles, mean/SE, superior marker). The function has two modes: **pipeline mode** (supply 'gene_id' + 'hap_data' + 'test_res') and **CSV mode** (supply 'gene_csv' or 'gene_data' + optional individuals/genotype files).

Usage

hbr_plot_haplotype(
  gene_id = NULL,
  hap_data = NULL,
  test_res = NULL,
  trait_col = "trait",
  output_dir = NULL,
  superior_info = NULL,
  functional_snps_used = NULL,
  adjusted_p = NA_real_,
  aa_full_names = TRUE,
  formats = c("pdf", "tiff", "png"),
  gene_list = NULL,
  gene_data = NULL,
  individuals_csv = NULL,
  individuals_data = NULL,
  geno_file = NULL,
  geno_matrix = NULL,
  geno_format = NULL,
  plink_path = "plink",
  gene_csv = NULL
)

Arguments

Value

Invisibly, a list with 'plot' (the composed grob) and 'files' (named list of paths written).

Examples

toy <- system.file("extdata", "toy", package = "HaploBreedR")
hbr_plot_haplotype(
  gene_list       = "gene1",
  gene_csv        = file.path(toy, "gene1_viz.csv"),
  individuals_csv = file.path(toy, "gene1_individuals.csv"),
  trait_col       = "trait_value",
  output_dir      = tempdir(),
  formats         = "pdf")

Description

Renders a minimal spanning graph of a gene's haplotypes: nodes sized by frequency, edges drawn when two haplotypes differ by exactly one SNP. Optionally highlights and labels the superior haplotype.

Usage

hbr_plot_haplotype_network(
  gene_list,
  output_dir = NULL,
  summary_csv = NULL,
  per_gene_dir = NULL,
  result = NULL,
  reference = NULL,
  gff3_path = NULL,
  trait_col = "NT",
  n_gene = NULL,
  sort_by = c("Cohens_d", "Superior_Mean"),
  colour_by_superior = TRUE,
  label_superior = TRUE,
  layout = c("circle", "grid"),
  node_scale = 1,
  palette = "haplobreed",
  theme = "haplobreed",
  width = 8,
  height = 7,
  formats = c("pdf", "png"),
  combined_pdf = TRUE,
  figures_dir = "figures",
  verbose = TRUE
)

Arguments

Value

Invisibly, a list with 'plots', 'files', 'missing_genes', 'combined_pdf'.

Examples

toy <- system.file("extdata", "toy", package = "HaploBreedR")
hbr_plot_haplotype_network(
  gene_list    = "gene1",
  output_dir   = tempdir(),
  per_gene_dir = toy,
  trait_col    = "trait_value",
  formats      = "pdf",
  combined_pdf = FALSE,
  verbose      = FALSE)

Description

Calculates the number of plants required to recover at least one pyramided genotype at 95 percent confidence using Sedcole (1977).

Usage

hbr_population_size(p, conf = 0.95)

Arguments

Value

Numeric vector of required population sizes.

Examples

hbr_population_size(c(0.01, 0.05, 0.10))

Description

Computes the exact joint transmission probability of pyramiding target loci across chromosomes under linkage.

Usage

hbr_pyramid_probability(chr, cm, donor, mating = c("DH", "RIL"))

Arguments

Value

Numeric. Probability of inheriting all target favorable alleles.

Examples

hbr_pyramid_probability(
  chr = c("1", "1", "1"),
  cm = c(10, 10.5, 11),
  donor = c(0, 0, 0),
  mating = "DH")

Description

Reads a GFF3 file, extracts 'gene'-type features, decodes the 'ID'/'gene_id'/'locus_tag', 'Name', and 'Note'/'description'/ 'product' attributes, standardizes chromosome names via [hbr_standardize_chr()], and returns a deduplicated gene table.

Usage

hbr_read_gff3_genes(gff3, verbose = TRUE)

Arguments

Value

A 'data.table' with 'Gene_ID', 'Gene_Name', 'Gene_Function', 'Gene_Chromosome', 'Gene_Start', 'Gene_End', 'Gene_Strand'. Empty if no gene features are present.

Examples

regions <- data.table::data.table(
  LD_Region_ID = "R1",
  Chromosome   = "1",
  Region_Start = 1000L,
  Region_End   = 3000L)
genes <- data.table::data.table(
  Gene_ID         = "gene1",
  Gene_Chromosome = "1",
  Gene_Start      = 1000L,
  Gene_End        = 2500L,
  Gene_Strand     = "+")
hbr_annotate_regions_with_genes(regions, genes, verbose = FALSE)

Description

Loads the output of [haplobreed_analysis()] — either the in-memory result or its output directory — into one object that carries the trait direction, the effective gate settings, the PCs the run adjusted for (none if it used no PCs), the tested and superior gene lists, the functional SNPs per gene, the phenotype table, and the publication-style results table. [hbr_advanced_decision()], [hbr_regate()] and [hbr_haplotype_blocks()] consume runs the same way.

Usage

hbr_read_results(
  x = NULL,
  trait = NULL,
  phenotypes = NULL,
  phenotype_id_col = "ID",
  gate_params = NULL,
  path = NULL,
  traits = NULL
)

Arguments

Details

A single pipeline directory or result returns one 'hbr_run'. A named character vector of directories or a named list of results returns one 'hbr_run' per element, classed as 'hbr_run_list'.

Value

An object of class 'hbr_run' (a list), or a named list of them classed as 'hbr_run_list'. Elements of a run:

'trait', 'direction', 'mode'

run identity and the trait direction ('"higher"' or '"lower"')

'gate'

effective gate settings

'phenotype', 'pcs', 'pc_cols'

trait table and PC columns

'gene_snps'

functional SNPs per tested gene

'tested', 'superior', 'superior_label'

gene lists

'table', 'table_source'

publication-style results table and the file it came from

'summary', 'pipeline_summary'

the pipeline-summary row

See Also

[hbr_regate()] to re-apply the gate with different settings, [hbr_haplotype_blocks()] to group superior haplotypes into blocks.

Examples

toy <- system.file("extdata", "hgsi_toy", "trait_YLD",
                   package = "HaploBreedR")
if (nzchar(toy) && dir.exists(toy)) {
  run <- hbr_read_results(toy)
  run$trait
  length(run$superior)
  head(run$table)
}

Description

The pipeline calls a haplotype superior when four gates pass: a nominal significance threshold on the trait association (A), a permutation-based significance threshold (B), an effect-size minimum on the best-versus-runner-up comparison (C), and — when requested — an absolute trait value the best haplotype must reach (D). 'hbr_regate()' recomputes which genes pass these gates under new thresholds, using the statistics already stored in the run, and reports how the call changes.

Usage

hbr_regate(
  x,
  alpha = NULL,
  min_cohens_d = NULL,
  require_fdr = NULL,
  trait_threshold = NULL,
  direction = NULL,
  ...
)

Arguments

Details

Two calling conventions are supported.

**Data.frame input.** When 'x' is a data.frame carrying at least a 'P_value' column (and, for the effect-size gate, 'Cohens_d' or 'Hedges_g'), the function returns a copy of the table with 'Adjusted_P', 'Significant_FDR', 'Significant_Nominal' and 'Is_Superior' recomputed. This is the legacy behaviour and is fully backward compatible.

**Run input.** When 'x' is an 'hbr_run' (from [hbr_read_results()]) or anything that function accepts, all four gates are recomputed — including the permutation gate and, when the pipeline stored a trait threshold, the trait gate. Arguments left at ‘NULL' inherit the run’s stored values, so the default call reproduces the pipeline exactly. The return is a classed object with the per-gene calls, the effective settings, the genes gained and lost versus the stored call, and a Jaccard overlap statistic.

The PCs the pipeline used and the Hedges correction cannot be changed here, because both alter the stored statistics; re-run the pipeline for that.

Value

When 'x' is a data.frame: a 'data.table' with the recomputed columns. When 'x' is an 'hbr_run': an object of class 'hbr_regate' with elements 'genes', 'settings', 'overlap' and 'check'.

See Also

[hbr_read_results()] to build the run input, [haplobreed_analysis()] for the pipeline that produced it.

Examples

# Legacy: data.frame input
summary_table <- data.frame(
  P_value  = c(0.001, 0.02, 0.5),
  Cohens_d = c(0.8, 0.4, 0.1))
hbr_regate(summary_table, alpha = 0.05, min_cohens_d = 0.3)

# New: hbr_run input re-applies all four gates
toy <- system.file("extdata", "hgsi_toy", "trait_YLD",
                   package = "HaploBreedR")
if (nzchar(toy) && dir.exists(toy)) {
  run <- hbr_read_results(toy)
  rg  <- hbr_regate(run, alpha = 0.01, min_cohens_d = 0.5)
  rg$overlap$gained
}

Description

Estimates variance components for a two-kernel mixed model using Kang et al. (2008) spectral profiling over a convex kernel mixture weight.

Usage

hbr_reml_two_kernel(
  y,
  X,
  G_R,
  K_H = NULL,
  w_grid = seq(0, 1, by = 0.1),
  refine = TRUE
)

Arguments

Value

List containing 'w', 's2g', 's2e', 's2R', 's2H', and 'negll'.

Examples

set.seed(1)
n <- 30
X <- cbind(1, rnorm(n))
Z <- matrix(rnorm(n * 20), n, 20)
G <- tcrossprod(Z) / 20
y <- rnorm(n)
hbr_reml_two_kernel(y, X, G)

Description

Returns the Nagamura et al. (1997) rice linkage-map anchors (n ~ 1,450 RFLP markers with both physical and genetic positions; total map length 1,510 cM) that ship with the package. The engine interpolates these anchors onto the physical positions of any PLINK '.bim' at run time, so the same table is valid for any rice panel. Use the result as the 'genetic_map' argument of [hbr_advanced_decision()] when you want to inspect it, subset it, or combine it with additional markers.

Usage

hbr_rice_genetic_map()

Value

A data.frame with columns 'chr' (character), 'bp' (numeric, IRGSP-1.0 coordinates) and 'cm' (numeric, Haldane/Kosambi-agnostic; the engine uses Haldane's map function). The 'source' attribute records the reference and marker count.

Examples

m <- hbr_rice_genetic_map()
head(m)
attr(m, "source")

Description

Return a named HaploBreedR ggplot2 theme

Usage

hbr_theme(
  name = "haplobreed",
  base_size = 12,
  base_family = "sans",
  axis_text_angle = 0,
  legend_pos = "right"
)

Arguments

Value

A 'ggplot2' theme object.

Examples

hbr_theme("minimal")
hbr_theme("haplobreed", base_size = 10)

Description

Names of the built-in ggplot2 themes

Usage

hbr_theme_names()

Value

A character vector of theme names accepted by [hbr_theme()].

Examples

hbr_theme_names()

Description

Identifies pleiotropic genes where the superior haplotype differs across distinct breeding traits.

Usage

hbr_trait_conflicts(sup_tables)

Arguments

Value

data.table summarizing pleiotropic concordance or conflict.

Examples

sup <- list(
  YLD = data.frame(gene = c("g1", "g2"), hap = c("Hap1", "Hap2")),
  DTF = data.frame(gene = c("g1", "g3"), hap = c("Hap1", "Hap1")))
hbr_trait_conflicts(sup)

Description

Plot an hbr_run object

Usage

## S3 method for class 'hbr_run'
plot(x, type = c("gene_list", "haplotype", "ld_decay"), gene = NULL, ...)

Arguments

Value

Invisibly, the return value of the dispatched plotting helper.

Examples

x <- structure(list(), class = "hbr_run")
plot(x, type = "ld_decay")

Description

Plot an hgsi_advanced object

Usage

## S3 method for class 'hgsi_advanced'
plot(x, type = c("crosses", "cv", "parents"), ...)

Arguments

Value

Invisibly, the return value of the dispatched plotting helper.

Examples

x <- structure(
  list(crosses = data.frame(
    parent_a = c("A", "B"), parent_b = c("C", "D"),
    mid_index = c(1, 2), uc = c(1.5, 2.5))),
  class = "hgsi_advanced")
plot(x, type = "crosses")

Description

Print an 'hbr_blocks' result

Usage

## S3 method for class 'hbr_blocks'
print(x, ...)

Arguments

Value

'x', invisibly.

Examples

toy <- system.file("extdata", "hgsi_toy", package = "HaploBreedR")
if (nzchar(toy) && dir.exists(toy) &&
    requireNamespace("BEDMatrix", quietly = TRUE)) {
  run <- hbr_read_results(file.path(toy, "trait_YLD"))
  print(hbr_haplotype_blocks(
    run, plink_prefix = file.path(toy, "geno_toy"),
    method = "recomb"))
}

Description

Print a genotype-reference compatibility report

Usage

## S3 method for class 'hbr_compat_report'
print(x, ...)

Arguments

Value

'x', invisibly.

Examples

x <- structure(
  list(status = "PASS",
       summary = data.table::data.table(
         Reference_genome = "TOY", Reference_annotation = "CUSTOM",
         Declared_genotype_build = NA_character_,
         Individuals = 1L, Total_variants = 1L,
         Chromosomes_matched = 1L, Chromosomes_total_reference = 1L,
         Chromosome_match_pct = 100, Valid_position_pct = 100,
         REF_check_coverage = "genome_fasta",
         REF_checked_n = 1L, REF_match_pct = 100,
         Duplicate_positions = 0L, Multiallelic_variants = 0L,
         Reference_mismatches = 0L, Unknown_chromosomes = 0L)),
  class = "hbr_compat_report")
print(x)

Description

Print an hbr_genotype object

Usage

## S3 method for class 'hbr_genotype'
print(x, ...)

Arguments

Value

'x', invisibly.

Examples

g <- structure(
  list(genotypes      = matrix(c(0, 1, 2), nrow = 1),
       variants       = data.frame(SNP = "s1", CHR = "1",
                                   POS = 100, REF = "A", ALT = "T"),
       individuals    = "ind1",
       source_format  = "PLINK",
       source_path    = NA_character_,
       declared_build = NA_character_,
       n_individuals  = 1L,
       n_variants     = 1L,
       streaming      = FALSE),
  class = "hbr_genotype")
print(g)

Description

Print an individual-ID match report

Usage

## S3 method for class 'hbr_id_report'
print(x, ...)

Arguments

Value

'x', invisibly.

Examples

rep <- structure(
  list(status = "PASS",
       summary = data.table::data.table(
         N_phenotyped              = 3L,
         N_genotyped               = 2L,
         N_matched                 = 2L,
         N_phenotype_only          = 1L,
         N_genotype_only           = 0L,
         Overlap_pct_of_phenotyped = 66.67),
       matched_ids        = c("a", "b"),
       phenotype_only_ids = "c",
       genotype_only_ids  = character(0),
       id_cleaning_changed = data.table::data.table(
         Original = character(0),
         Cleaned  = character(0))),
  class = "hbr_id_report")
print(rep)

Description

Print an hbr_reference object

Usage

## S3 method for class 'hbr_reference'
print(x, ...)

Arguments

Value

'x', invisibly.

Examples

ref <- structure(
  list(genome = "TOY", annotation = "CUSTOM",
       genes       = data.frame(gene_id = "g1"),
       transcripts = data.frame(gene_id = "g1",
                                transcript_id = "g1.1"),
       has_cds = FALSE, has_pep = FALSE, has_genome_fasta = FALSE,
       validation = list(status = "PASS")),
  class = "hbr_reference")
print(ref)

Description

Print an 'hbr_regate' result

Usage

## S3 method for class 'hbr_regate'
print(x, ...)

Arguments

Value

'x', invisibly.

Examples

toy <- system.file("extdata", "hgsi_toy", "trait_YLD",
                   package = "HaploBreedR")
if (nzchar(toy) && dir.exists(toy)) {
  run <- hbr_read_results(toy)
  print(hbr_regate(run, alpha = 0.01))
}

Description

Print an hbr_run object

Usage

## S3 method for class 'hbr_run'
print(x, ...)

Arguments

Value

'x', invisibly.

Examples

x <- structure(
  list(pipeline_summary = data.frame(
         Trait = "YLD", Direction = "higher",
         Genes_Tested = 8L, Superior_Haplotypes = 2L)),
  class = "hbr_run")
print(x)

Description

Print a sequence-resource QC report

Usage

## S3 method for class 'hbr_sequence_qc'
print(x, ...)

Arguments

Value

'x', invisibly.

Examples

x <- structure(
  list(status = "PASS",
       summary = data.table::data.table(
         GFF3_transcripts = 0L, CDS_sequences = 0L,
         PEP_sequences = 0L, Complete_CDS_PEP = 0L,
         CDS_only = 0L, PEP_only = 0L,
         Translation_mismatch = 0L, Invalid_CDS_length = 0L)),
  class = "hbr_sequence_qc")
print(x)

Description

Console summary of a completed [hbr_advanced_decision()] or [hbr_cross_design()] run: evaluation labels, traits, models, parent and cross counts, block and set summaries, genetic-map source and any warnings recorded during the run.

Usage

## S3 method for class 'hgsi_advanced'
print(x, ...)

Arguments

Value

'x', invisibly.

Examples

x <- structure(
  list(evaluation_label = c(YLD = "honest_discovery_in_fold"),
       traits = "YLD",
       model_used = c(YLD = "gblup"),
       ids = sprintf("IND%02d", 1:5),
       parents = data.frame(id = sprintf("IND%02d", 1:5), index = 5:1),
       crosses = data.frame(parent_a = "IND01", parent_b = "IND02",
                            uc = 1.2),
       map_source = "bundled rice map",
       warnings = character(0),
       output_dir = tempdir()),
  class = c("hgsi_advanced", "list"))
print(x)

Description

Print an hgsi_fit object

Usage

## S3 method for class 'hgsi_fit'
print(x, ...)

Arguments

Value

'x', invisibly. #' Print an hgsi_fit object

'x', invisibly.

Examples

fit <- structure(
  list(traits = "YLD",
       evaluation_label = c(YLD = "honest_discovery_in_fold"),
       model_used = c(YLD = "gblup"),
       ids = sprintf("IND%02d", 1:5),
       parents = data.frame(id = sprintf("IND%02d", 1:5), index = 5:1),
       warnings = character(0),
       output_dir = tempdir()),
  class = c("hgsi_fit", "list"))
print(fit)

Description

Summary of an hbr_run object

Usage

## S3 method for class 'hbr_run'
summary(object, ...)

Arguments

Value

'object', invisibly.

Examples

x <- structure(
  list(pipeline_summary = data.frame(
         Trait = "YLD", Direction = "higher",
         Genes_Tested = 8L, Superior_Haplotypes = 2L)),
  class = "hbr_run")
summary(x)

Description

Prints the console summary from [print.hgsi_advanced()] followed by the cross-validation summary table, the paired comparisons, the top ten ranked parents and, when available, the top ten crosses.

Usage

## S3 method for class 'hgsi_advanced'
summary(object, ...)

Arguments

Value

'object', invisibly.

Examples

x <- structure(
  list(evaluation_label = c(YLD = "honest_discovery_in_fold"),
       traits = "YLD",
       model_used = c(YLD = "gblup"),
       ids = sprintf("IND%02d", 1:5),
       parents = data.frame(id = sprintf("IND%02d", 1:5), index = 5:1),
       crosses = data.frame(parent_a = "IND01", parent_b = "IND02",
                            uc = 1.2),
       cv_summary = data.frame(trait = "YLD", method = "M0", r = 0.5),
       cv_compare = data.frame(trait = "YLD", method = "M3",
                               baseline = "M0", mean_diff = 0.01),
       map_source = "bundled rice map",
       warnings = character(0),
       output_dir = tempdir()),
  class = c("hgsi_advanced", "list"))
summary(x)

Description

Summarise an hgsi_fit object

Usage

## S3 method for class 'hgsi_fit'
summary(object, ...)

Arguments

Value

'object', invisibly. #' Summarise an hgsi_fit object

'object', invisibly.

Examples

fit <- structure(
  list(traits = "YLD",
       evaluation_label = c(YLD = "honest_discovery_in_fold"),
       model_used = c(YLD = "gblup"),
       ids = sprintf("IND%02d", 1:5),
       parents = data.frame(id = sprintf("IND%02d", 1:5), index = 5:1),
       cv_summary = data.frame(trait = "YLD", method = "M0", r = 0.5),
       cv_compare = data.frame(trait = "YLD", method = "M3",
                               baseline = "M0", mean_diff = 0.01),
       warnings = character(0),
       output_dir = tempdir()),
  class = c("hgsi_fit", "list"))
summary(fit)