Package 'gDRimport'

Description

Check whether all metadata names are correct

Usage

check_metadata_names(col_df, df_name = "", df_type = NULL)

Arguments

Value

a charvec with corrected colnames of df

Examples

td <- get_test_data()
 m_file <- manifest_path(td)
 m_data <- read_excel_to_dt(m_file)
 result <- check_metadata_names(col_df = colnames(m_data))

Description

Load, convert and process the level 5 PRISM data into a gDR input

Usage

convert_LEVEL5_prism_to_gDR_input(
  prism_data_path,
  meta_data_path,
  readout_min = 1.03
)

Arguments

Value

data.table object with input data for gDR pipeline

Examples

prism_data <- system.file("testdata/prism_sa.csv", package = "gDRimport")
 prism_meta <- system.file("testdata/prism_model.csv", package = "gDRimport")
 convert_LEVEL5_prism_to_gDR_input(prism_data, prism_meta)

Description

Load, convert and process the level 6 PRISM data into a gDR input

Usage

convert_LEVEL6_prism_to_gDR_input(
  prism_data_path,
  cell_line_data_path,
  treatment_data_path,
  meta_data_path,
  readout_min = 1.03
)

Arguments

Value

data.table object with input data for gDR pipeline

Examples

prism_data_path <- system.file("testdata/prism_collapsed_LOGFC.csv", package = "gDRimport")
 cell_line_data_path <- system.file("testdata/prism_cell_lines.csv", package = "gDRimport")
 treatment_data_path <- system.file("testdata/prism_treatment.csv", package = "gDRimport")
 prism_meta <- system.file("testdata/prism_model.csv", package = "gDRimport")
 convert_LEVEL6_prism_to_gDR_input(prism_data_path, cell_line_data_path, treatment_data_path, prism_meta)

Description

This function converts a MultiAssayExperiment generated by gDR into a TreatmentResponseExperiment for use in the PharmacoGx package. The resulting PharmacoSet can be used for pharmacogenomic analysis of drug response.

Usage

convert_MAE_to_PSet(mae, pset_name)

Arguments

Value

A PharmacoSet object.

Examples

# Convert a MultiAssayExperiment object to a PharmacoSet object
m <- 20
n <- 10
rnames <- LETTERS[1:m]
cnames <- letters[1:n]
ref_gr_value <-  matrix(runif(m * n), nrow = m, ncol = n, dimnames = list(rnames, cnames))
se <- SummarizedExperiment::SummarizedExperiment(assays = list(RefGRvalue = ref_gr_value),
                                                 rowData = S4Vectors::DataFrame(rnames),
                                                 colData = S4Vectors::DataFrame(cnames))
mae <- MultiAssayExperiment::MultiAssayExperiment(experiments = list("single-agent" = se))
convert_MAE_to_PSet(mae, "my_pset")

Description

Convert a PharmacoSet to a data.table that is prepare for input into gDR pipeline

Usage

convert_pset_to_df(pharmacoset, run_parallel = TRUE, workers = 2L)

Arguments

Value

data.table of PharmacoSet's dose response data with column names aligned with gDR standard

Author(s)

Jermiah Joseph – collaboration with BHKLab

Examples

pset <- suppressMessages(getPSet(
  "Tavor_2020",
  psetDir = system.file("extdata/pset", package = "gDRimport"),
  use_local_PSets_list = TRUE
))
dt <- convert_pset_to_df(pset)
gDRutils::reset_env_identifiers()

Description

Detect format of results data

Usage

detect_file_format(results_file)

Arguments

Value

string of the detected file format

Examples

td2 <- get_test_Tecan_data()
detect_file_format(td2$r_files[1])

Description

Fix typos using reference data Evaluate given list of ids and try to update them

Usage

fix_typos_with_reference(
  data,
  ref,
  method = c("exact", "grepl", "adist"),
  fix_underscores = FALSE
)

Arguments

Value

list or charvec with corrected data

Description

Object class gdr_test_data is build by function get_test_data()

Value

object class gdr_test_data with primary test data

Slots

manifest_path

character, path to manifest file

result_path

character, path(s) to results file

template_path

character, path(s) to data.table with template data

ref_m_df

character, data.table with manifest data

ref_r1_r2

character, path to reference file with raw data for treated & untreated

ref_r1

character, path to reference file with raw data for treated

ref_t1_t2

character, path to reference template file with treated & untreated data

ref_t1

character, path to reference template file with treated data

Description

Get final results (as a data.table) from raw edited EnVision data.table

Usage

get_df_from_raw_edited_EnVision_df(
  df,
  barcode_idx,
  barcode_col,
  n_row,
  n_col,
  fname,
  sheet_name,
  headers
)

Arguments

Value

data.table derived from EnVision data

Description

Get final results (as a data.table) from raw unedited EnVision data.table

Usage

get_df_from_raw_unedited_EnVision_df(df, n_row, n_col, barcode_col)

Arguments

Value

data.table derived from EnVision data

Description

get exception data

Usage

get_exception_data(status_code = NULL)

Arguments

Value

A data.table row with exception data or all exceptions

Examples

get_exception_data(1)
get_exception_data()

Description

Get names of the sheets expected in templates xlsx

Usage

get_expected_template_sheets(type = c("all", "core", "optional"))

Arguments

Value

string with type of the sheets

Description

load_data and the PRISM converters attach a record of their inputs to the table they return: the gDRimport version, the reader (instrument), every input file with its role, size and md5, and the corrections gDRimport applied on its own. gDRcore keeps the record in the provenance of the processed object (provenance$steps$import).

Usage

get_import_provenance(x)

Arguments

Value

The record (a list), or NULL when x carries none.

Examples

td <- get_test_data()
l_data <- load_data(manifest_path(td), template_path(td), result_path(td))
get_import_provenance(l_data$data)$files

Description

get test D300 data

Usage

get_test_D300_data()

Value

list with with input data (manifest/template/result paths) and related reference data (qs2 file paths)

Examples

get_test_D300_data()

Description

get primary test data

Usage

get_test_data()

Value

object class "gdr_test_data" with with input data (manifest/template/result paths) and related reference data (qs2 file paths)

Examples

get_test_data()

Description

get test EnVision data

Usage

get_test_EnVision_data()

Value

list with with input data (manifest/template/result paths) and related reference data (.qs2 file paths)

Examples

get_test_EnVision_data()

Description

get test Tecan data

Usage

get_test_Tecan_data()

Value

list with with input data (manifest/template/result paths) and related reference data (qs2 file paths)

Examples

get_test_Tecan_data()

Description

get test tsv data

Usage

get_test_tsv_data()

Value

list with with input data (manifest/template/result paths) and related reference data (.qs2 file paths)

Examples

get_test_tsv_data()

Description

Get PharmacoSet

Usage

getPSet(
  pset_name,
  psetDir = getwd(),
  canonical = FALSE,
  timeout = 600,
  use_local_PSets_list = FALSE
)

Arguments

Value

PharmacoSet object

Examples

suppressMessages(getPSet(
  "Tavor_2020",
  psetDir = system.file("extdata/pset", package = "gDRimport"),
  use_local_PSets_list = TRUE
))

Description

This functions takes a D300 file and generates corresponding template files

Usage

import_D300(D300_file, destination_path, metadata_file = NULL, day0 = FALSE)

Arguments

Details

For example, wells treated with 2 drugs in combination will result in 4 sheets per plate.

• Sheet 1: Drug 1

• Sheet 2: Conc of Drug 1

• Sheet 3: Drug 2

• Sheet 4: Conc of Drug 2

Value

Create one Excel file per plate. Each sheet in each plate file describes the drugs and corrresponding concentrations of what was tested in each well.

Examples

td3 <- get_test_D300_data()[["f_96w"]]
o_path <- file.path(tempdir(), "td3")
dir.create(o_path)
import_D300(td3$d300, o_path, td3$Gnum)
list.files(o_path)
unlink(o_path, recursive = TRUE)

Description

is_readable_v Check if all paths in vector are readable

Usage

is_readable_v(paths)

Arguments

Value

NULL invisibly.

Examples

td2 <- get_test_Tecan_data()
is_readable_v(td2$r_files)

Description

This functions loads and checks the data file(s)

Usage

load_data(
  manifest_file,
  df_template_files,
  results_file,
  instrument = "EnVision"
)

Arguments

Value

a list with three data.tables for manifest/treatment and results

Examples

td <- get_test_data()
 l_tbl <- load_data(manifest_path(td), template_path(td), result_path(td))

Description

Loads a long/tidy data.table from a delimited text file (CSV/TSV) and checks that it contains the columns required by the gDR pipeline. This offers an input path that does not rely on GeneDataScreeneR: the data can come from a custom export or be provided directly by the user in tabular form, matching the shape of the data_imported object used downstream.

Usage

load_long_table(long_table_file)

Arguments

Details

Required columns follow the current gDR identifiers: Gnumber, clid, Duration and Concentration. The readout column is the fixed header ReadoutValue: there is no "readout" identifier in gDRutils, so this name is not customisable via get_env_identifiers(), matching how ReadoutValue is used across the rest of gDRimport. Combination data may add Gnumber_2 and Concentration_2. Duration, Concentration and ReadoutValue must be numeric.

Value

a data.table with the validated long table

Examples

path <- tempfile(fileext = ".csv")
 dt <- data.table::data.table(Gnumber = "G1", clid = "CL1", Duration = 72,
                              Concentration = 1, ReadoutValue = 1000)
 data.table::fwrite(dt, path)
 load_long_table(path)

Description

This functions loads and checks the manifest file(s)

Usage

load_manifest(manifest_file)

Arguments

Value

list with manifest data.table and headers

Examples

td <- get_test_data()
 ml <- load_manifest(manifest_path(td))

Description

This functions loads and checks the results file(s)

Usage

load_results(
  df_results_files,
  instrument = "EnVision",
  headers = gDRutils::get_env_identifiers()
)

Arguments

Value

data.table with results' data

Examples

td <- get_test_data()
 r_df <- load_results(result_path(td))

Description

This functions loads and checks the results file(s)

Usage

load_results_EnVision(results_file, headers = gDRutils::get_env_identifiers())

Arguments

Value

data.table with results data

Description

This functions loads incucyte time-course cell count file

Usage

load_results_Incucyte(results_file, headers = gDRutils::get_env_identifiers())

Arguments

Value

data.table derived from Incucyte data

Description

This functions loads and checks the results file

Usage

load_results_Tecan(results_file, headers = gDRutils::get_env_identifiers())

Arguments

Value

data.table derived from Tecan data

Description

This functions loads and checks the results file(s)

Usage

load_results_tsv(results_file, headers)

Arguments

Value

data.table with results data

Description

This functions loads and checks the template file(s)

Usage

load_templates(df_template_files)

Arguments

Value

data.table with templates data

Examples

td <- get_test_data()
 t_df <- load_templates(template_path(td))

Description

This functions loads and checks the template file(s)

Usage

load_templates_tsv(template_file, template_filename = NULL)

Arguments

Value

data.table with template data

Description

This functions loads and checks the template file(s)

Usage

load_templates_xlsx(template_file, template_filename = NULL)

Arguments

Value

data.table with templates data

Description

This function parses a D300 *.tdd file (XML format) into a data.table

Usage

parse_D300_xml(D300_file)

Arguments

Value

data.table representing input D300_file.

Examples

td3 <- get_test_D300_data()
fs <- td3[["f_96w"]]
dose_df <- parse_D300_xml(fs[["d300"]])

Description

Read excel file and transorm it into data.table object

Usage

read_excel_to_dt(path, ...)

Arguments

Value

data.table object with read excel file

Examples

datasets <- readxl::readxl_example("datasets.xlsx")
read_excel_to_dt(datasets)

Description

for each drug create a Gnumber and Concentration information for each well

Usage

save_drug_info_per_well(trt_info, trt_gnumber_conc, wb, idfs)

Arguments

Value

NULL invisibly.

Description

Adjust environment variables to meet gDR standards

Usage

setEnvForPSet()

Value

NULL

Examples

setEnvForPSet()
gDRutils::reset_env_identifiers()

Description

map values to a dictionary

Usage

standardize_record_values(x, dictionary = DICTIONARY)

Arguments

Value

a named array with updated names

Examples

standardize_record_values(c("Vehicle", "vehcle"))

Description

Checks a set of input files and reports every problem it finds, from unreadable files to plate-level anomalies in the readouts. Bench input (a manifest, treatment templates and raw plate-reader files) is loaded with load_data, so a failure reported for load_data is the error the import itself would raise. The checks also flag problems the loaders let through without an error: values in a Concentration sheet that are not numbers (those wells are dropped), raw plates without a barcode, duplicated wells, plates missing from the manifest or from the data, treated wells whose cell line and Duration have no control wells, drugs that appear only at concentration 0, and Duration labels that do not fit the readouts of the control wells. PRISM input, processed MultiAssayExperiments and D300 files are recognised and checked too.

Usage

validate_gdr_input(
  paths,
  type = c("auto", "bench", "prism", "mae", "pre_d300"),
  instrument = NULL,
  id_patterns = list(drug = "^G[0-9]{8}", cellline = NULL),
  fix = FALSE,
  output_dir = NULL
)

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

Arguments

Details

The input files are only read, never modified. With fix = TRUE they are copied to output_dir, the mechanical problems (fix tier "A") are repaired in the copies, and the copies are validated again: files re-encoded as UTF-8, spaces trimmed from file names, long tables saved as .tsv, Gnumber_1 and Concentration_1 sheets renamed, n/a and -99 cleared from templates, and manifest references that only differ from a template file by spaces or the extension rewritten. In xlsx files only the repaired cells change.

Value

An object of class gdr_validation, a list with

verdict

"PASS", "WARN" or "FAIL", the most severe finding ("INFO" counts as "PASS").

data_type

the kind of input that was validated.

files

a data.table with one row per input file: file, path, role and format (the plate-reader format of raw files).

findings

a data.table with one row per finding: check, severity ("PASS", "INFO", "WARN" or "FAIL"), detail, fix_tier ("A" a mechanical fix, "B" a fix to confirm with whoever made the files, "C" a decision about the experiment, NA when there is nothing to fix) and status_code, the matching row of get_exception_data (NA when there is none).

fixes

character, one note per repair (empty without fix).

output_dir

the directory of the repaired copies, NA without fix. With fix = TRUE, files and findings describe the copies after the repairs.

Examples

td <- get_test_data()
res <- validate_gdr_input(c(manifest_path(td), template_path(td), result_path(td)))
res$verdict
res$findings

# repair copies of the files instead of only reporting
fixed <- validate_gdr_input(c(manifest_path(td), template_path(td), result_path(td)),
                            fix = TRUE, output_dir = tempfile())
fixed$fixes