Package 'CONCERTDR'

Annotate CONCERTDR Results with Drug Information

Description

Integrate signature matching results with annotations from siginfo_beta.txt and compoundinfo_beta.txt. It produces three analysis-ready tables and one drug context summary table.

Usage

annotate_drug_results(
  results_df,
  sig_info_file,
  comp_info_file,
  drug_info_file = NULL,
  output_file = NULL,
  fuzzy_threshold = 90,
  perfect_match_only = FALSE,
  score_col = "Score",
  padj_col = "pAdjValue",
  p_col = "pValue",
  compound_col = "compound",
  keep_dose_in_drug_view = FALSE,
  output_dir = NULL,
  write_outputs = FALSE,
  verbose = TRUE
)

Arguments

results_df	Data frame containing signature matching results with a 'compound' column
sig_info_file	Path to siginfo_beta.txt file or data frame with signature information
comp_info_file	Path to compound information file or data frame
drug_info_file	Deprecated. Kept for backward compatibility; not used.
output_file	Deprecated single-file output path; when provided, tech_view_all is also written as CSV for compatibility.
fuzzy_threshold	Deprecated. Not used.
perfect_match_only	Deprecated. Not used.
score_col	Score column in results_df (default: "Score")
padj_col	Adjusted p-value column name (default: "pAdjValue")
p_col	Raw p-value column name (default: "pValue")
compound_col	Compound/sig-id column in results_df (default: "compound")
keep_dose_in_drug_view	Logical; whether to keep dose_uM in wetlab_drug_view (default: FALSE)
output_dir	Optional directory to write four TSV outputs. If NULL, files are not written unless write_outputs = TRUE.
write_outputs	Logical; write four TSV outputs (default: FALSE)
verbose	Logical; whether to print progress messages (default: TRUE)

Value

A named list with:

wetlab_drug_view	Drug-focused wetlab view
wetlab_gene_view	Gene-focused wetlab view
tech_view_all	Full technical table with all integrated fields
drug_context_summary	Per-drug context summary
output_files	Named character vector of written files (if any)

Examples

ex_results <- data.frame(
  compound = "CVD001_HEPG2_6H:BRD-K03652504-001-01-9:10.0497",
  Score = -0.72,
  pValue = 0.002,
  pAdjValue = 0.02,
  stringsAsFactors = FALSE
)
ex_siginfo <- data.frame(
  sig_id = ex_results$compound,
  pert_type = "trt_cp",
  pert_id = "BRD-K03652504-001-01-9",
  pert_iname = "imatinib",
  stringsAsFactors = FALSE
)
ex_compinfo <- data.frame(
  pert_id = "BRD-K03652504-001-01-9",
  pert_name = "imatinib",
  cmap_name = "imatinib",
  stringsAsFactors = FALSE
)
views <- annotate_drug_results(
  results_df = ex_results,
  sig_info_file = ex_siginfo,
  comp_info_file = ex_compinfo,
  write_outputs = FALSE,
  verbose = FALSE
)
names(views)


if (file.exists("sig_match_xsum_results.csv") &&
    file.exists("siginfo_beta.txt") &&
    file.exists("compoundinfo_beta.txt")) {
  results <- read.csv("sig_match_xsum_results.csv")

  views <- annotate_drug_results(
    results_df = results,
    sig_info_file = "siginfo_beta.txt",
    comp_info_file = "compoundinfo_beta.txt",
    output_dir = "results",
    write_outputs = TRUE
  )

  head(views$wetlab_drug_view)
}

---

Create a Signature Data Frame from Gene Lists

Description

Converts separate lists of up-regulated and down-regulated genes into a signature data frame compatible with process_signature_with_df and other CONCERTDR functions. This is a convenience wrapper for users who only have gene lists (e.g.\ from a pathway database) rather than continuous fold-change values.

Usage

create_signature_from_gene_lists(
  up_genes,
  down_genes,
  up_value = 1,
  down_value = -1
)

Arguments

up_genes	Character vector of up-regulated gene symbols.
down_genes	Character vector of down-regulated gene symbols.
up_value	Numeric value to assign to up-regulated genes (default: 1).
down_value	Numeric value to assign to down-regulated genes (default: -1).

Value

A data frame with columns Gene and log2FC, suitable for use as the signature_file argument in process_signature_with_df and extract_signature_zscores.

Examples

sig_df <- create_signature_from_gene_lists(
  up_genes   = c("TP53", "MYC", "BRCA1"),
  down_genes = c("EGFR", "VEGFA", "KRAS")
)
head(sig_df)

---

Extract CMap Data Using Siginfo File Directly

Description

Extract expression data from CMap GCTX files using all signatures present in the provided siginfo file. This function processes all signatures found in the siginfo file without requiring a configuration file.

Usage

extract_cmap_data_from_siginfo(
  siginfo_file = "siginfo_beta.txt",
  geneinfo_file = "geneinfo_beta.txt",
  gctx_file = "level5_beta_trt_cp_n720216x12328.gctx",
  max_signatures = NULL,
  filter_quality = TRUE,
  keep_all_genes = TRUE,
  verbose = TRUE,
  landmark = TRUE
)

Arguments

siginfo_file	Path to the signature info file (can be original or pre-filtered)
geneinfo_file	Path to the gene info file
gctx_file	Path to the GCTX file
max_signatures	Integer; maximum number of signatures to process (default: NULL for all)
filter_quality	Logical; whether to filter for pert_type="trt_cp" and is_hiq=1 (default: TRUE)
keep_all_genes	Logical; whether to keep all genes (TRUE) or only common genes (FALSE) (default: TRUE)
verbose	Logical; whether to print progress messages (default: TRUE)
landmark	Logical; whether to restrict to landmark genes only (default: TRUE)

Value

A data frame with expression data for all signatures, with annotation columns indicating sample metadata. Metadata is stored as an attribute.

Examples

# Build a tiny GCTX file so the example is self-contained and runnable.
gctx_file <- tempfile(fileext = ".gctx")
rhdf5::h5createFile(gctx_file)
for (group in c("0", "0/DATA", "0/DATA/0", "0/META",
                "0/META/ROW", "0/META/COL")) {
  rhdf5::h5createGroup(gctx_file, group)
}
rhdf5::h5write(matrix(c(1.2, -0.4, 0.7, -1.1), nrow = 2),
               gctx_file, "0/DATA/0/matrix")
rhdf5::h5write(c("1", "2"), gctx_file, "0/META/ROW/id")
rhdf5::h5write(c("SIG_A", "SIG_B"), gctx_file, "0/META/COL/id")

siginfo <- data.frame(
  sig_id = c("SIG_A", "SIG_B"), is_hiq = 1,
  pert_itime = "24 h", pert_idose = "1 uM", cell_iname = "A375"
)
geneinfo <- data.frame(
  gene_id = c("1", "2"), gene_symbol = c("GENE1", "GENE2"),
  feature_space = "landmark"
)
reference_df <- extract_cmap_data_from_siginfo(
  siginfo_file = siginfo,
  geneinfo_file = geneinfo,
  gctx_file = gctx_file,
  verbose = FALSE
)
reference_df
attr(reference_df, "metadata")
unlink(gctx_file)

---

Extract Compound ID from Signature Matching Results

Description

Helper function to extract compound identifiers from complex compound strings in signature matching results. This function can be customized based on the specific format of compound identifiers in your data.

Usage

extract_compound_id(
  compound_strings,
  method = "split_colon",
  regex_pattern = NULL,
  part_index = 2
)

Arguments

compound_strings	Vector of compound identifier strings
method	Method for extraction: "split_colon" (default), "split_underscore", or "regex"
regex_pattern	Regular expression pattern for extraction (used when method="regex")
part_index	Which part to extract when splitting (default: 2)

Value

Vector of extracted compound identifiers

Examples

extract_compound_id("A:BRD-K03652504-001-01-9:10")


# Example compound strings
compounds <- c("CVD001_HEPG2_6H:BRD-K03652504-001-01-9:10.0497",
               "CVD001_HEPG2_6H:BRD-A37828317-001-03-0:10")

# Extract using colon splitting (default)
ids <- extract_compound_id(compounds)

# Extract using custom regex
ids <- extract_compound_id(compounds, method = "regex",
                          regex_pattern = "BRD-[A-Z0-9-]+")

---

Extract z-score matrix for barcode heatmap

Description

Performs all data-loading and GCTX-extraction steps needed for plot_signature_direction_tile_barcode without producing any plot. The returned matrix can be inspected, filtered, exported, or passed directly to plot_signature_direction_tile_barcode(precomputed = ) to avoid re-reading large files on repeated calls.

Usage

extract_signature_zscores(
  results_df,
  signature_file,
  reference_df = NULL,
  gctx_file = NULL,
  geneinfo_file = NULL,
  siginfo_file = NULL,
  data_dir = getOption("CONCERTDR.data_dir", NULL),
  selected_drug = NULL,
  selected_drug_col = NULL,
  pert_id_col = "sig_id",
  score_col = "Score",
  max_genes = 100,
  max_perts = 60,
  split_direction = FALSE,
  output_zscores = NULL,
  verbose = TRUE
)

Arguments

results_df	Data frame containing at least perturbation id and score columns.
signature_file	Path to a signature file with gene and log2FC columns, or a data frame with Gene and log2FC columns.
reference_df	Optional reference matrix with genes as rows and perturbation ids as columns. If supplied, z-scores are taken directly from this object and no GCTX file is required.
gctx_file	Optional path to GCTX expression file.
geneinfo_file	Optional path to geneinfo file.
siginfo_file	Optional path to siginfo file for readable labels.
data_dir	Optional directory containing CMap files.
selected_drug	Optional drug identifier to filter results_df.
selected_drug_col	Column used with selected_drug.
pert_id_col	Perturbation id column (default: "sig_id").
score_col	Score column (default: "Score").
max_genes	Maximum number of signature genes to use (default: 100). When split_direction = FALSE (default) the first max_genes rows of the signature file are taken. When split_direction = TRUE the top max_genes up-regulated genes (by log2FC) and the top max_genes down-regulated genes (by |log2FC|) are selected independently, so the matrix may contain up to 2 * max_genes gene columns in total.
max_perts	Maximum number of perturbations (default: 60).
split_direction	Logical; if TRUE, apply max_genes separately to the up-regulated (log2FC > 0) and down-regulated (log2FC < 0) gene sets rather than to the combined signature. The result contains up to 2 * max_genes columns ordered down-regulated then up-regulated, matching the layout expected by plot_signature_direction_tile_barcode with split_direction = TRUE. Default: FALSE.
output_zscores	Optional TSV path to save the matrix. NULL to skip.
verbose	Logical; print progress messages.

Value

A named list with elements:

z_plot

Numeric matrix — rows = perturbations (labelled cmap_name | dose | time | cell), cols = genes (down→up order).

ordered_genes

Character vector of gene symbols.

logfc_map

Named numeric vector of signature log2FC values.

sig_ids

Character vector of selected sig_ids.

sig_labels

Character vector of human-readable labels.

sig_scores

Numeric vector of score_col values in the same order as sig_ids and the rows of z_plot.

Examples

is.function(extract_signature_zscores)


# Requires the full CMap GCTX file (downloaded from clue.io)
sig_file <- system.file("extdata", "example_signature.txt",
                        package = "CONCERTDR")
ref_file <- system.file("extdata", "example_reference_df.csv",
                        package = "CONCERTDR")
ref_df <- read.csv(ref_file, row.names = 1, check.names = FALSE)
ref_df$gene_symbol <- rownames(ref_df)
demo_sig <- colnames(ref_df)[1]
zmat <- extract_signature_zscores(
  results_df     = data.frame(sig_id = demo_sig, Score = -0.72),
  signature_file = sig_file,
  reference_df   = ref_df,
  pert_id_col    = "sig_id"
)

---

Fuzzy String Matching for Drug Names

Description

Performs fuzzy string matching to find the best matches between query drug names and a reference list of drug names. Uses Levenshtein distance for similarity calculation.

Usage

fuzzy_drug_match(
  query_names,
  reference_names,
  method = "levenshtein",
  threshold = 80,
  top_n = 1
)

Arguments

query_names	Vector of query drug names
reference_names	Vector of reference drug names to match against
method	Similarity method: "levenshtein" (default), "jaro", or "jarowinkler"
threshold	Minimum similarity threshold (0-100)
top_n	Number of top matches to return for each query (default: 1)

Value

Data frame with query names, matched names, and similarity scores

Examples

if (requireNamespace("RecordLinkage", quietly = TRUE)) {
  fuzzy_drug_match(c("asprin"), c("aspirin", "ibuprofen"), threshold = 70)
}


if (requireNamespace("RecordLinkage", quietly = TRUE)) {
  query <- c("aspirin", "ibuprofen", "acetaminophen")
  reference <- c("aspirin", "ibuprofen", "acetaminophen", "naproxen", "diclofenac")
  matches <- fuzzy_drug_match(query, reference, threshold = 80)
  print(matches)
}

---

Plot 2D Barcode Heatmap from GCTX (Single Drug Context)

Description

Build a 2D barcode heatmap using z-scores extracted from a GCTX file. Genes are ordered by signature direction (down then up), and perturbations are chosen as top max_perts rows by best (lowest) score_col from the provided technical results table.

Usage

plot_signature_direction_tile_barcode(
  results_df = NULL,
  signature_file = NULL,
  reference_df = NULL,
  gctx_file = NULL,
  geneinfo_file = NULL,
  siginfo_file = NULL,
  data_dir = getOption("CONCERTDR.data_dir", NULL),
  selected_drug = NULL,
  selected_drug_col = NULL,
  pert_id_col = "sig_id",
  score_col = "Score",
  max_genes = 100,
  max_perts = 60,
  cluster_rows = TRUE,
  cluster_method = "complete",
  show_row_dendrogram = TRUE,
  cluster_cols = FALSE,
  cluster_method_cols = "complete",
  show_col_dendrogram = TRUE,
  split_direction = FALSE,
  gap_width = 5,
  precomputed = NULL,
  save_png = FALSE,
  output_png = "barcode_heatmap.png",
  output_zscores = NULL,
  width = NULL,
  height = NULL,
  dpi = 150,
  verbose = TRUE
)

Arguments

results_df	Data frame (typically tech_view_all) containing at least perturbation id and score columns.
signature_file	Path to a signature file with gene and log2FC columns, or a data frame with Gene and log2FC columns.
reference_df	Optional reference matrix with genes as rows and perturbation ids as columns. If supplied, no GCTX file is needed and the heatmap is built directly from this matrix.
gctx_file	Optional path to GCTX expression file. If NULL, the function tries (in order): option CONCERTDR.gctx_file, env var CONCERTDR_GCTX_FILE, data_dir/level5_beta_all_n1201944x12328.gctx, then a file with that name in the working directory.
geneinfo_file	Optional path to geneinfo file with gene_symbol and gene_id columns. If NULL, the function tries option CONCERTDR.geneinfo_file, env var CONCERTDR_GENEINFO_FILE, data_dir/geneinfo_beta.txt, then geneinfo_beta.txt in the working directory.
siginfo_file	Optional path to siginfo file for readable perturbation labels. If NULL, the function tries option CONCERTDR.siginfo_file, env var CONCERTDR_SIGINFO_FILE, data_dir/siginfo_beta.txt, then siginfo_beta.txt in the working directory.
data_dir	Optional directory containing CMap files. Useful to avoid repeatedly passing full file paths.
selected_drug	Optional drug identifier to filter results_df before selecting perturbations.
selected_drug_col	Optional column used with selected_drug. If NULL, auto-detect from perturbation_name, display_name, pert_id, cmap_name, pert_name.
pert_id_col	Perturbation id column in results_df (default: "sig_id"; falls back to "compound" for older results).
score_col	Score column in results_df (default: "Score").
max_genes	Maximum number of signature genes to use (default: 100).
max_perts	Maximum number of perturbations to show (default: 60).
cluster_rows	Logical; cluster perturbation rows (default: TRUE).
cluster_method	Clustering linkage method for row clustering (default: "complete").
show_row_dendrogram	Logical; whether to draw a row dendrogram when cluster_rows = TRUE (default: TRUE).
cluster_cols	Logical; cluster gene columns (default: FALSE - genes are kept in signature direction order: down then up).
cluster_method_cols	Clustering linkage method for column clustering (default: "complete").
show_col_dendrogram	Logical; whether to draw a column dendrogram when cluster_cols = TRUE (default: TRUE).
split_direction	Logical; if TRUE, split the heatmap into two side-by-side panels — up-regulated genes (log2FC > 0) on the left and down-regulated genes (log2FC < 0) on the right — with a small gap between them. Row order is determined by clustering the full matrix so both panels stay aligned. Default: FALSE (original single-panel behaviour).
gap_width	Width of the gap between the two panels in mm when split_direction = TRUE. Default: 5.
precomputed	Optional; the output of extract_signature_zscores. If provided, skips all data-loading and GCTX-extraction steps - all data-related arguments (results_df, signature_file, gctx_file, etc.) are ignored.
save_png	Logical; save PNG output (default: FALSE).
output_png	Output PNG path.
output_zscores	Optional TSV path for exported z-score matrix. Default is NULL, so no file is written unless explicitly requested.
width, height	Figure dimensions in inches for PNG. If NULL (default), dimensions are computed automatically from the number of genes and perturbations (~0.22 in/gene width, ~0.28 in/perturbation height).
dpi	PNG resolution.
verbose	Logical; print progress messages.

Value

Invisibly returns a list containing the plotted matrix, selected perturbation ids, and file paths.

Examples

is.function(plot_signature_direction_tile_barcode)


if (requireNamespace("ComplexHeatmap", quietly = TRUE) &&
    requireNamespace("circlize", quietly = TRUE)) {
  sig_file <- system.file("extdata", "example_signature.txt",
                          package = "CONCERTDR")
  ref_df <- read.csv(system.file("extdata", "example_reference_df.csv",
                                 package = "CONCERTDR"),
                     row.names = 1, check.names = FALSE)
  ref_df$gene_symbol <- rownames(ref_df)
  demo_sig <- colnames(ref_df)[1]
  plot_signature_direction_tile_barcode(
    results_df    = data.frame(sig_id = demo_sig, Score = -0.72),
    signature_file = sig_file,
    reference_df  = ref_df,
    pert_id_col   = "sig_id"
  )
}

---

Plot method for cmap_signature_result objects

Description

Plot method for cmap_signature_result objects

Usage

## S3 method for class 'cmap_signature_result'
plot(x, method = NULL, plot_type = "scores", top_n = 20, ...)

Arguments

x	A cmap_signature_result object
method	Which method to plot (default: first method in results)
plot_type	Type of plot: "scores", "volcano", or "heatmap" (default: "scores")
top_n	Number of compounds to include (default: 20)
...	Additional arguments passed to plotting functions

Value

A ggplot object

Examples

mock_res <- structure(
  list(
    results = list(
      ks = data.frame(compound = c("imatinib", "dasatinib", "doxorubicin"),
                      Score = c(-0.72, -0.45, 0.31),
                      pValue = c(0.002, 0.041, 0.280),
                      pAdjValue = c(0.020, 0.205, 0.560),
                      stringsAsFactors = FALSE)
    ),
    summary = data.frame(compound = "imatinib", method = "ks",
                         Score = -0.72, pValue = 0.002, global_rank = 1L,
                         stringsAsFactors = FALSE),
    gene_data    = data.frame(Gene = c("TP53", "MYC"),
                              log2FC = c(1.5, -2.1), stringsAsFactors = FALSE),
    settings     = list(signature_file = "ex.txt",
                        time_completed = Sys.time(), time_taken_mins = 0.1,
                        methods = "ks", permutations = 10),
    common_genes = list(up   = list(found = "TP53", count = 1L, percent = 50),
                        down = list(found = "MYC",  count = 1L, percent = 50))
  ), class = "cmap_signature_result"
)
if (requireNamespace("ggplot2", quietly = TRUE)) {
  plot(mock_res, method = "ks", plot_type = "scores")
}

---

Print method for cmap_signature_result objects

Description

Print method for cmap_signature_result objects

Usage

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

Arguments

x	A cmap_signature_result object
...	Additional arguments (not used)

Value

x invisibly

Examples

mock_res <- structure(
  list(
    results = list(
      ks = data.frame(compound = c("imatinib", "dasatinib"),
                      Score = c(-0.72, -0.45), pValue = c(0.002, 0.041),
                      pAdjValue = c(0.020, 0.205), stringsAsFactors = FALSE)
    ),
    summary = data.frame(compound = "imatinib", method = "ks",
                         Score = -0.72, pValue = 0.002, global_rank = 1L,
                         stringsAsFactors = FALSE),
    gene_data    = data.frame(Gene = c("TP53", "MYC"),
                              log2FC = c(1.5, -2.1), stringsAsFactors = FALSE),
    settings     = list(signature_file = "ex.txt",
                        time_completed = Sys.time(), time_taken_mins = 0.1,
                        methods = "ks", permutations = 10),
    common_genes = list(up   = list(found = "TP53", count = 1L, percent = 50),
                        down = list(found = "MYC",  count = 1L, percent = 50))
  ), class = "cmap_signature_result"
)
print(mock_res)

---

Process Multiple Combinations of Time, Dose, and Cell Line

Description

Process Multiple Combinations of Time, Dose, and Cell Line

Usage

process_combinations_file(
  combinations_file,
  task_id = NULL,
  geneinfo_file = "geneinfo_beta.txt",
  siginfo_file = "siginfo_beta.txt",
  gctx_file = "level5_beta_trt_cp_n720216x12328.gctx",
  output_dir = "."
)

Arguments

combinations_file	Path to a file containing combinations to process
task_id	Specific task ID to process (for SLURM array jobs)
geneinfo_file	Path to the gene info file
siginfo_file	Path to the signature info file
gctx_file	Path to the GCTX file
output_dir	Directory to save output files

Value

List of processed files (invisibly)

Examples

combinations <- data.frame(
  itime = "24 h",
  idose = "1 uM",
  cell = "K562",
  stringsAsFactors = FALSE
)
combinations_file <- tempfile(fileext = ".tsv")
utils::write.table(
  combinations,
  combinations_file,
  sep = "\t",
  row.names = FALSE,
  quote = FALSE
)
file.exists(combinations_file)

# With real CMap files available locally, run:
# process_combinations_file(
#   combinations_file = combinations_file,
#   geneinfo_file = "path/to/geneinfo_beta.txt",
#   siginfo_file = "path/to/siginfo_beta.txt",
#   gctx_file = "path/to/level5_beta_all_n1201944x12328.gctx",
#   output_dir = tempdir()
# )

---

Process drug response signatures against reference data in a dataframe

Description

Process drug response signatures against reference data in a dataframe

Usage

process_signature_with_df(
  signature_file,
  reference_df,
  output_dir = "results",
  permutations = 100,
  methods = c("ks", "xcos", "xsum", "gsea0", "gsea1", "gsea2", "zhang"),
  topN = 4,
  read_method = "auto",
  save_files = FALSE
)

Arguments

signature_file	Path to a signature gene list file with log2FC values, or a data frame with columns Gene and log2FC. When a data frame is supplied the read_method argument is ignored. You can create a suitable data frame from gene lists using create_signature_from_gene_lists.
reference_df	Dataframe containing reference data (combined across all conditions)
output_dir	Directory for output files (default: "results")
permutations	Number of permutations for statistical testing (default: 100)
methods	Vector of method names to run (default: all) Options: "ks", "xcos", "xsum", "gsea0", "gsea1", "gsea2", "zhang"
topN	Integer; number of top-ranked genes to use for XCos and XSum methods (default: 4)
read_method	Character; method to use for reading signature file ("auto", "fread", or "read.table") (default: "auto")
save_files	Logical; whether to save results to files (default: FALSE)

Value

A structured list containing:

results	List containing results for each method
summary	Data frame of top hits across all methods
gene_data	Original signature gene data
settings	List of parameters used for the analysis
common_genes	Counts of genes found in reference data

Use print() or summary() methods to get a quick overview of results

Examples

sig_file <- system.file("extdata", "example_signature.txt",
                        package = "CONCERTDR")
ref_file <- system.file("extdata", "example_reference_df.csv",
                        package = "CONCERTDR")
ref_df <- read.csv(ref_file, row.names = 1, check.names = FALSE)
ref_df$gene_symbol <- rownames(ref_df)
results <- process_signature_with_df(
  signature_file = sig_file,
  reference_df = ref_df,
  output_dir = tempdir(),
  permutations = 10,
  methods = "ks",
  save_files = FALSE
)
summary(results, top_n = 3)

# You can also pass a data.frame directly:
sig_df <- read.delim(sig_file)
results2 <- process_signature_with_df(
  signature_file = sig_df,
  reference_df = ref_df,
  permutations = 10,
  methods = "ks",
  save_files = FALSE
)

---

Subset siginfo_beta file interactively with smart preview

Description

Enhanced interactive filtering that shows what options will be available in subsequent parameters based on your current selection, helping you make informed decisions about the filtering sequence.

Usage

subset_siginfo_beta(
  siginfo_file,
  output_file = NULL,
  interactive = TRUE,
  filters = NULL,
  verbose = TRUE,
  show_preview = TRUE
)

Arguments

siginfo_file	Path to siginfo_beta.txt file
output_file	Path to save the filtered siginfo file (optional)
interactive	Logical; whether to run in interactive mode (default: TRUE)
filters	List of pre-defined filters to apply in non-interactive mode
verbose	Logical; whether to print progress messages (default: TRUE)
show_preview	Logical; whether to show preview of subsequent options (default: TRUE)

Value

A filtered data frame of the siginfo file

Examples

ex_sig <- data.frame(
  pert_type = c("trt_cp", "trt_cp", "trt_sh"),
  pert_itime = c("6 h", "24 h", "24 h"),
  pert_idose = c("10 uM", "10 uM", "5 uM"),
  cell_iname = c("A375", "MCF7", "A375"),
  stringsAsFactors = FALSE
)
ex_sig_file <- tempfile(fileext = ".txt")
write.table(ex_sig, ex_sig_file, sep = "\t", row.names = FALSE, quote = FALSE)
subset_siginfo_beta(
  ex_sig_file,
  interactive = FALSE,
  filters = list(pert_type = "trt_cp"),
  verbose = FALSE,
  show_preview = FALSE
)


ex_file <- system.file("extdata", "example_siginfo.txt", package = "CONCERTDR")

# Interactive mode (run only in an interactive R session)
if (interactive() && nzchar(ex_file)) {
  filtered_siginfo <- subset_siginfo_beta(ex_file)
}

# Non-interactive mode with pre-defined filters
if (nzchar(ex_file)) {
  filtered_siginfo <- subset_siginfo_beta(
    ex_file,
    interactive = FALSE,
    filters = list(
      pert_type = "trt_cp",
      pert_itime = c("6 h", "24 h"),
      pert_idose = "10 uM",
      cell_iname = c("A375", "MCF7")
    ),
    verbose = FALSE,
    show_preview = FALSE
  )
}

---

Summary method for cmap_signature_result objects

Description

Summary method for cmap_signature_result objects

Usage

## S3 method for class 'cmap_signature_result'
summary(object, top_n = 10, ...)

Arguments

object	A cmap_signature_result object
top_n	Number of top compounds to show (default: 10)
...	Additional arguments (not used)

Value

A data frame with the top compounds

Examples

mock_res <- structure(
  list(
    results = list(
      ks = data.frame(compound = c("imatinib", "dasatinib"),
                      Score = c(-0.72, -0.45), pValue = c(0.002, 0.041),
                      pAdjValue = c(0.020, 0.205), stringsAsFactors = FALSE)
    ),
    summary = data.frame(compound = c("imatinib", "dasatinib"),
                         method = c("ks", "ks"),
                         Score = c(-0.72, -0.45), pValue = c(0.002, 0.041),
                         global_rank = 1:2, stringsAsFactors = FALSE),
    gene_data    = data.frame(Gene = c("TP53", "MYC"),
                              log2FC = c(1.5, -2.1), stringsAsFactors = FALSE),
    settings     = list(signature_file = "ex.txt",
                        time_completed = Sys.time(), time_taken_mins = 0.1,
                        methods = "ks", permutations = 10),
    common_genes = list(up   = list(found = "TP53", count = 1L, percent = 50),
                        down = list(found = "MYC",  count = 1L, percent = 50))
  ), class = "cmap_signature_result"
)
summary(mock_res, top_n = 2)

---