Package 'dnaEPICO'

Description

Fit linear models for each surrogate variable against Sentrix chip and Sentrix position, perform backward elimination with MASS::dropterm(), and return the in-memory analysis objects.

Usage

analyzeSvaEnmix(
  sva,
  RGSet,
  SentrixIDColumn = "Sentrix_ID",
  SentrixPositionColumn = "Sentrix_Position",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_analyzeSvaEnmix.txt"
)

Arguments

Value

A list with class "dnaEPICO_svaEnmix_analysis" containing the aligned Sentrix factors, full and reduced linear models, and ANOVA tables.

Examples

ex <- dnaEPICO:::exampleSvaAnalysisStateDnaEpico()
analysis_data <- analyzeSvaEnmix(
  sva = ex$sva,
  RGSet = ex$RGSet,
  SentrixIDColumn = "Sentrix_ID",
  SentrixPositionColumn = "Sentrix_Position",
  verbose = FALSE,
  logs = FALSE
)
analysis_data$K

Description

Merge phenotype-specific CpG summary tables with probe annotation metadata and return a single annotated result table.

Usage

annotateMethylationGLM_T1Summaries(
  modelSummaries,
  annotationObject,
  annotationCols = c("Name", "chr", "pos", "UCSC_RefGene_Group", "UCSC_RefGene_Name",
    "Relation_to_Island", "GencodeV41_Group"),
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLM_T1.txt"
)

Arguments

Value

A list with class "dnaEPICO_methylationGLM_T1_annotation" containing the annotated summary table and any requested annotation columns that were unavailable in the chosen annotation object.

Examples

ex <- dnaEPICO:::exampleMethylationGLMStateDnaEpico()
annotation_data <- annotateMethylationGLM_T1Summaries(
  modelSummaries = ex$modelSummaries,
  annotationObject = ex$annotationData,
  annotationCols = "Name,chr,pos",
  verbose = FALSE,
  logs = FALSE
)
names(annotation_data)

Description

Merge phenotype-specific longitudinal summary tables with probe annotation metadata and return a single annotated result table.

Usage

annotateMethylationGLMM_T1T2Summaries(
  modelSummaries,
  annotationObject,
  annotationCols = c("Name", "chr", "pos", "UCSC_RefGene_Group", "UCSC_RefGene_Name",
    "Relation_to_Island", "GencodeV41_Group"),
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLMM_T1T2.txt"
)

Arguments

Value

A list with class "dnaEPICO_methylationGLMM_T1T2_annotation" containing the annotated summary table and any requested annotation columns that were unavailable in the chosen annotation object.

Examples

ex <- dnaEPICO:::exampleMethylationGLMMStateDnaEpico()
annotation_data <- annotateMethylationGLMM_T1T2Summaries(
  modelSummaries = ex$modelSummaries,
  annotationObject = ex$annotationData,
  annotationCols = "Name,chr,pos",
  verbose = FALSE,
  logs = FALSE
)
names(annotation_data)

Description

Compute minfi QC metrics and detection P values, identify failed samples using the requested threshold, and return the assessment as a single object.

Usage

assessSamplesMinfiEwasWater(
  rawData,
  RGSet,
  qcCutoff = 10.5,
  detPtype = "m+u",
  detPThreshold = 0.05,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_assessSamplesMinfiEwasWater.txt"
)

Arguments

Value

A list with class "dnaEPICO_minfiEwasWater_assessment" containing the QC object, detection P matrix, mean detection P values, and failed sample identifiers.

Examples

ex <- dnaEPICO:::exampleMinfiBaseDataDnaEpico()
raw_data <- buildRawMinfiEwasWater(ex$RGSet, verbose = FALSE, logs = FALSE)
assessment <- assessSamplesMinfiEwasWater(
  rawData = raw_data,
  RGSet = ex$RGSet,
  detPThreshold = 1,
  verbose = FALSE,
  logs = FALSE
)
names(assessment)

Description

Prepare the beta and phenotype tables commonly exported for Clock Foundation style downstream workflows, without writing them to disk.

Usage

buildClockFoundationInputsPreprocessingPheno(
  beta,
  pheno,
  SampleID = "Sample_Name",
  sexColumn = "Sex",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_buildClockFoundationInputsPreprocessingPheno.txt"
)

Arguments

Value

A list with class "dnaEPICO_preprocessingPheno_clock" containing betaCSV and phenoCF.

Examples

ex <- dnaEPICO:::examplePreprocessingPhenoStateDnaEpico()
clock_inputs <- buildClockFoundationInputsPreprocessingPheno(
  beta = ex$timepointData$data[["1"]]$beta,
  pheno = ex$timepointData$data[["1"]]$pheno,
  SampleID = "Sample_Name",
  sexColumn = "Sex",
  verbose = FALSE,
  logs = FALSE
)
names(clock_inputs)

Description

Create a raw MethylSet, RatioSet, and genome-mapped object from an RGChannelSet, and return them together in a single structured object.

Usage

buildRawMinfiEwasWater(
  RGSet,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_buildRawMinfiEwasWater.txt"
)

Arguments

Value

A list with class "dnaEPICO_minfiEwasWater_raw" containing MSet, RatioSet, and GSet.

Examples

ex <- dnaEPICO:::exampleMinfiBaseDataDnaEpico()
raw_data <- buildRawMinfiEwasWater(
  RGSet = ex$RGSet,
  verbose = FALSE,
  logs = FALSE
)
names(raw_data)

Description

Collect the raw coefficient tables for CpGs whose phenotype main effect or interaction p-value passes the requested threshold.

Usage

collectSignificantCpGsMethylationGLM_T1(
  modelResults,
  pvalThreshold = 0.05,
  interactionTerm = NULL,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLM_T1.txt"
)

Arguments

Value

A list with class "dnaEPICO_methylationGLM_T1_significant_cpgs".

Examples

ex <- dnaEPICO:::exampleMethylationGLMStateDnaEpico()
significant_cpgs <- collectSignificantCpGsMethylationGLM_T1(
  modelResults = ex$modelResults,
  pvalThreshold = 1,
  verbose = FALSE,
  logs = FALSE
)
names(significant_cpgs)

Description

Collect raw coefficient tables for CpGs whose phenotype main effect or requested interaction p-value passes the chosen threshold.

Usage

collectSignificantInteractionsMethylationGLMM_T1T2(
  modelResults,
  pvalThreshold = 0.05,
  interactionTerm = NULL,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLMM_T1T2.txt"
)

Arguments

Value

A list with class "dnaEPICO_methylationGLMM_T1T2_significant" containing the retained coefficient tables for each phenotype.

Examples

ex <- dnaEPICO:::exampleMethylationGLMMStateDnaEpico()
significant_hits <- collectSignificantInteractionsMethylationGLMM_T1T2(
  modelResults = ex$modelResults,
  pvalThreshold = 1,
  verbose = FALSE,
  logs = FALSE
)
names(significant_hits)

Description

Combine selected timepoints that were already aligned by splitTimepointsPreprocessingPheno() into the wide phenotype-plus-beta objects used by downstream longitudinal models.

Usage

combineTimepointsPreprocessingPheno(
  timepointData,
  combineTimepoints = "1,2",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_combineTimepointsPreprocessingPheno.txt"
)

Arguments

Value

A list with class "dnaEPICO_preprocessingPheno_combined" containing the combined phenotype table, merged phenotype-plus-beta table, selected timepoints, and output suffix.

Examples

ex <- dnaEPICO:::examplePreprocessingPhenoStateDnaEpico()
combined_data <- combineTimepointsPreprocessingPheno(
  timepointData = ex$timepointData,
  combineTimepoints = "1,2",
  verbose = FALSE,
  logs = FALSE
)
combined_data$suffix

Description

The dnaEPICO package provides a structured workflow for preprocessing and analyzing Illumina DNA methylation array data, including quality control, normalization, cell-type estimation, surrogate-variable analysis, phenotype preparation, cross-sectional modeling, longitudinal mixed-effects modeling, and PDF reporting.

Details

The package supports two complementary usage styles:

• interactive use, where functions return structured in-memory result objects for inspection and composition; and

• file-based pipeline use, where the same functions can write logs, plots, tables, and serialized objects when saveOutputs = TRUE.

The main high-level entry points are:

• preprocessingMinfiEwasWater()

• svaEnmix()

• preprocessingPheno()

• methylationGLM_T1()

• methylationGLMM_T1T2()

• dnamReport()

Author(s)

Maintainer: Paul Ruiz [email protected] (ORCID)

Authors:

• Divya Mehta (ORCID)

See Also

Useful links:

• https://github.com/paulYRP/dnaEPICO

• Report bugs at https://github.com/paulYRP/dnaEPICO/issues

Description

Objects of class "dnaEPICO_dnamReport_prepared" are list-based results returned by prepareDnamReportInputs(). They capture normalized report paths, available figures, and logging metadata before rendering.

Structure

output

Requested output file name.

outputDir

Normalized report output directory.

outputFile

Normalized full path to the intended report output file.

figDir

Normalized directory used by the report template for copied figures.

figureInventory

Named list describing the available figures for each report section.

missingFigureDirectories

Character vector of expected figure directories that were not present at preparation time.

logFile

Resolved path to the optional log file, or NULL when logging was disabled.

See Also

prepareDnamReportInputs()

Description

Objects of class "dnaEPICO_dnamReport_render" are list-based results returned by renderDnamReport(). They describe whether a prepared report was rendered, skipped, or failed.

Structure

preparedReport

The input object supplied to renderDnamReport().

status

Render status string such as "rendered", "skipped", or "failed".

renderedFile

Normalized path to the rendered PDF file when rendering succeeded, otherwise NULL.

errorMessage

Render error or skip message when available, otherwise NULL.

logFile

Resolved path to the optional log file, or NULL when logging was disabled.

See Also

renderDnamReport()

Description

Objects of class "dnaEPICO_dnamReport" are list-based results returned by dnamReport(). They combine the prepared report inputs, render result, and final status metadata into one convenience object.

Structure

preparedReport

Object returned by prepareDnamReportInputs().

renderResult

Structured render metadata created by dnamReport().

status

Final status string such as "rendered", "skipped", or "failed".

outputFile

Path to docs/index.html.

errorMessage

Final render error or skip message when available, otherwise NULL.

logFile

Resolved path to the optional log file, or NULL when logging was disabled.

See Also

dnamReport()

Description

Objects of class "dnaEPICO_methylationGLM_T1" are list-based results returned by methylationGLM_T1(). They collect the prepared analysis table, fitted models, summaries, diagnostics, annotations, and optional saved files.

Structure

preparedData

Object returned by prepareMethylationGLM_T1Data().

distributionPlots

Object returned by plotMethylationGLM_T1Distributions().

modelFits

Object returned by fitMethylationGLM_T1Models().

modelSummaries

Object returned by summarizeMethylationGLM_T1Models().

significantCpGs

Object returned by collectSignificantCpGsMethylationGLM_T1().

diagnosticPlots

Object returned by plotMethylationGLM_T1Diagnostics().

annotation

Object returned by annotateMethylationGLM_T1Summaries().

savedFiles

Object returned by writeMethylationGLM_T1Outputs() when saveOutputs = TRUE, otherwise NULL.

See Also

methylationGLM_T1()

Description

Objects of class "dnaEPICO_methylationGLMM_T1T2" are list-based results returned by methylationGLMM_T1T2(). They collect the prepared longitudinal analysis table, fitted mixed models, summaries, diagnostics, annotations, and optional saved files.

Structure

preparedData

Object returned by prepareMethylationGLMM_T1T2Data().

modelFits

Object returned by fitMethylationGLMM_T1T2Models().

modelSummaries

Object returned by summarizeMethylationGLMM_T1T2Models().

significantInteractions

Object returned by collectSignificantInteractionsMethylationGLMM_T1T2().

diagnosticPlots

Object returned by plotMethylationGLMM_T1T2Diagnostics().

annotation

Object returned by annotateMethylationGLMM_T1T2Summaries().

savedFiles

Object returned by writeMethylationGLMM_T1T2Outputs() when saveOutputs = TRUE, otherwise NULL.

See Also

methylationGLMM_T1T2()

Description

Objects of class "dnaEPICO_preprocessingMinfiEwasWater" are list-based results returned by preprocessingMinfiEwasWater(). They are lightweight S3-style containers rather than formal S4 classes.

Structure

targets

Filtered phenotype table aligned to the retained samples.

RGSet

Filtered RGChannelSet used in downstream preprocessing.

rawData

Object returned by buildRawMinfiEwasWater().

assessment

Object returned by assessSamplesMinfiEwasWater().

sexData

Object returned by predictSexMinfiEwasWater().

normData

Object returned by normalizeMinfiEwasWater().

filterData

Object returned by filterProbesMinfiEwasWater().

metricsData

Object returned by extractMetricsMinfiEwasWater().

lcData

Object returned by estimateLCMinfiEwasWater().

logFile

Resolved path to the optional log file, or NULL when logging was disabled.

See Also

preprocessingMinfiEwasWater()

Description

Objects of class "dnaEPICO_preprocessingPheno" are list-based results returned by preprocessingPheno(). They describe the phenotype data, methylation matrices, timepoint splits, longitudinal merges, and optional exported files.

Structure

pheno

Phenotype table read from phenoFile.

metricsData

Object returned by loadMetricsPreprocessingPheno().

timepointData

Object returned by splitTimepointsPreprocessingPheno().

combinedData

Object returned by combineTimepointsPreprocessingPheno().

clockFoundation

Object returned by buildClockFoundationInputsPreprocessingPheno().

savedFiles

Object returned by writePreprocessingPhenoOutputs() when saveOutputs = TRUE, otherwise NULL.

logFile

Resolved path to the optional log file, or NULL when logging was disabled.

See Also

preprocessingPheno()

Description

Objects of class "dnaEPICO_svaEnmix" are list-based results returned by svaEnmix(). They collect the loaded inputs, surrogate-variable results, association-analysis summaries, and optional file outputs.

Structure

targets

Phenotype table read from phenoFile after any optional row subsetting.

RGSet

Loaded RGChannelSet with sample names reset to match targets.

svaData

Object returned by estimateSvaEnmixControls().

mergedPheno

Phenotype table returned by mergeSvaTargetsEnmix() after surrogate variables were appended.

analysisData

Object returned by analyzeSvaEnmix().

plotFiles

Named list of TIFF output paths for the SVA figures when saveOutputs = TRUE, otherwise NULL entries for plots not written.

savedFiles

Object returned by writeSvaEnmixOutputs() when saveOutputs = TRUE, otherwise NULL.

logFile

Resolved path to the optional log file, or NULL when logging was disabled.

See Also

svaEnmix()

Description

Generate a DNA methylation dashboard report

Usage

dnamReport(
  outputDir = "reports",
  phenoTab = NULL,
  enmixTab = file.path("figures", "preprocessingMinfiEwasWater", "enmix"),
  qcTab = file.path("figures", "preprocessingMinfiEwasWater", "qc"),
  svaTab = file.path("figures", "svaEnmix"),
  metricTab = file.path("figures", "preprocessingMinfiEwasWater", "metrics"),
  glmTab = NULL,
  lmerTab = NULL,
  logTab = outputDir,
  verbose = FALSE,
  logs = FALSE,
  projectName = "dnaEPICO",
  detPPath = NULL,
  detPThreshold = 0.01,
  cpgDetectionPath = NULL,
  sampleDetectionPath = NULL,
  logoPath = system.file("extdata", "dnaEPICO.svg", package = "dnaEPICO"),
  imagePattern = "\\.(png|jpg|jpeg|gif|webp|svg|tif|tiff)$",
  recursive = TRUE
)

Arguments

Value

A list with class "dnaEPICO_dnamReport".

Examples

report_root <- file.path(tempdir(), "dnaepico-dnam-report")
pheno_file <- file.path(
  report_root,
  "data",
  "model1",
  "preprocessingMinfiEwasWater",
  "phenoLC.csv"
)
dir.create(dirname(pheno_file), recursive = TRUE, showWarnings = FALSE)
utils::write.csv(
  data.frame(
    UID = c("sample1", "sample2"),
    Timepoint = c(1, 2),
    Sex = c("F", "M")
  ),
  pheno_file,
  row.names = FALSE
)

result <- dnamReport(
  outputDir = file.path(report_root, "reports", "model1"),
  phenoTab = pheno_file,
  enmixTab = file.path(
    report_root,
    "figures",
    "model1",
    "preprocessingMinfiEwasWater",
    "enmix"
  ),
  qcTab = file.path(
    report_root,
    "figures",
    "model1",
    "preprocessingMinfiEwasWater",
    "qc"
  ),
  svaTab = file.path(report_root, "figures", "model1", "svaEnmix"),
  metricTab = file.path(
    report_root,
    "figures",
    "model1",
    "preprocessingMinfiEwasWater",
    "metrics"
  ),
  logTab = file.path(report_root, "logs", "model1")
)
result$status

Description

Estimate cell-type proportions with the saliva reference panels bundled in dnaEPICO. This function keeps the original estimateLC() interface used by the package while using the internal reference files distributed in inst/extdata.

Usage

estimateLC(meth, ref, constrained = FALSE)

Arguments

Value

A data.table with one row per sample and one column per estimated cell type.

References

Murat K, et al. Ewastools: Infinium Human Methylation BeadChip pipeline for population epigenetics integrated into Galaxy. GigaScience. 2020;9(5):giaa049. Houseman EA, Accomando WP, Koestler DC, et al. DNA methylation arrays as surrogate measures of cell mixture distribution. BMC Bioinformatics. 2012;13:86. Reinius LE, Acevedo N, Joerink M, et al. Differential DNA methylation in purified human blood cells: implications for cell lineage and studies on disease susceptibility. PLoS One. 2012;7(7):e41361. Bakulski KM, Feinberg JI, Andrews SV, et al. DNA methylation of cord blood cell types: applications for mixed cell birth studies. Epigenetics. 2016;11(5):354-362. de Goede OM, Razzaghian HR, Price EM, et al. Nucleated red blood cells impact DNA methylation and expression analyses of cord blood hematopoietic cells. Clinical Epigenetics. 2015;7:95. Gervin K, Salas LA, Bakulski KM, et al. Cell type specific DNA methylation in cord blood: a 450K reference data set and cell count-based validation of estimated cell type composition. Epigenetics. 2016;11(9):690-698. Gervin K, Salas LA, Bakulski KM, et al. Systematic evaluation and validation of reference and library selection methods for deconvolution of cord blood DNA methylation data. bioRxiv. 2019. doi:10.1101/570457. Salas LA, Koestler DC, Butler RA, et al. An optimized library for reference-based deconvolution of whole-blood biospecimens assayed using the Illumina HumanMethylationEPIC BeadArray. Genome Biology. 2018;19:64. Heiss JA, Just AC, Brenner H. Training a model for estimating leukocyte composition using whole-blood DNA methylation and cell counts as reference. Epigenomics. 2017;9(1):13-20. Middleton LYM, Dou J, Mill J, et al. Saliva cell type DNA methylation reference panel for epidemiology studies in children. 2020.

Examples

ref_file <- system.file("extdata", "saliva.txt", package = "dnaEPICO")
ref_panel <- as.matrix(utils::read.table(ref_file))
meth <- ref_panel[1:20, , drop = FALSE]
colnames(meth) <- c("sample1", "sample2")
estimateLC(
  meth = meth,
  ref = "saliva",
  constrained = FALSE
)

Description

Estimate cell proportions from beta values using estimateLC() for saliva reference panels or ENmix::estimateCellProp() for other supported references, then merge the estimates into the phenotype table.

Usage

estimateLCMinfiEwasWater(
  beta,
  targets,
  lcRef = "salivaEPIC",
  phenoOrder = "Sample_Name;Timepoint;Sex;PredSex;Basename;Sentrix_ID;Sentrix_Position",
  constrained = FALSE,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_estimateLCMinfiEwasWater.txt"
)

Arguments

Value

A list with class "dnaEPICO_minfiEwasWater_lc" containing the cell proportion matrix, merged phenotype table, reference name, and method used.

Examples

ref_file <- system.file("extdata", "saliva.txt", package = "dnaEPICO")
beta <- as.matrix(utils::read.table(ref_file))[1:20, , drop = FALSE]
colnames(beta) <- c("sample1", "sample2")
targets <- data.frame(
  Sample_Name = colnames(beta),
  Timepoint = c("T1", "T2"),
  stringsAsFactors = FALSE
)
lc_data <- estimateLCMinfiEwasWater(
  beta = beta,
  targets = targets,
  lcRef = "saliva",
  phenoOrder = "Sample_Name;Timepoint"
)
stopifnot(is.data.frame(lc_data$phenoLC))

Description

Run ENmix::ctrlsva() on an RGChannelSet and return the surrogate variable matrix as an in-memory object.

Usage

estimateSvaEnmixControls(
  RGSet,
  ctrlSvaPercVar = 0.9,
  ctrlSvaFlag = 1,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_estimateSvaEnmixControls.txt"
)

Arguments

Value

A list with class "dnaEPICO_svaEnmix_sva" containing the surrogate variable matrix and the parameters used to estimate it.

Examples

ex <- dnaEPICO:::exampleMinfiBaseDataDnaEpico()
sva_data <- estimateSvaEnmixControls(
  RGSet = ex$RGSet,
  ctrlSvaPercVar = 0.5,
  ctrlSvaFlag = 1,
  verbose = FALSE,
  logs = FALSE
)
sva_data$K

Description

Copies the example Makefile pipeline shipped with dnaEPICO to a user-specified directory for local execution or modification.

Usage

extractMake(destDir, overwrite = FALSE)

Arguments

Value

Character scalar containing the path to the copied Makefile.

Examples

tmp <- file.path(tempdir(), "dnaEPICO-make-example")
dir.create(tmp, recursive = TRUE, showWarnings = FALSE)
makefile_path <- extractMake(
  destDir = tmp,
  overwrite = TRUE
)
stopifnot(file.exists(makefile_path))

Description

Extract beta, M, and copy-number matrices from a filtered object

Usage

extractMetricsMinfiEwasWater(
  filteredData,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_extractMetricsMinfiEwasWater.txt"
)

Arguments

Value

A list with class "dnaEPICO_minfiEwasWater_metrics" containing beta, m, and cn.

Examples

ex <- dnaEPICO:::exampleMinfiMetricsStateDnaEpico()
metrics_data <- extractMetricsMinfiEwasWater(
  filteredData = ex$filteredData,
  verbose = FALSE,
  logs = FALSE
)
names(metrics_data)

Description

Apply detection P-value, chromosome, SNP, and cross-reactive probe filters to the primary normalized object and return the filtered result.

Usage

filterProbesMinfiEwasWater(
  normData,
  RGSet,
  pvalThreshold = 0.01,
  chrToRemove = "chrX,chrY",
  snpsToRemove = "SBE,CpG",
  mafThreshold = 0.1,
  crossReactivePath,
  detPtype = "m+u",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_filterProbesMinfiEwasWater.txt"
)

Arguments

Value

A list with class "dnaEPICO_minfiEwasWater_filter" containing the filtered object and counts for each filtering stage.

Examples

ex <- dnaEPICO:::exampleMinfiWorkflowStateDnaEpico()
filtered_data <- filterProbesMinfiEwasWater(
  normData = ex$normData,
  RGSet = ex$sampleData$RGSet,
  pvalThreshold = 1,
  chrToRemove = "chrY",
  snpsToRemove = "SBE",
  mafThreshold = 1,
  crossReactivePath = ex$crossReactivePath,
  detPtype = "m+u",
  verbose = FALSE,
  logs = FALSE
)
filtered_data$counts[["crossReactive"]]

Description

Remove failed samples identified during sample assessment and return the filtered RGChannelSet together with the aligned phenotype table.

Usage

filterSamplesMinfiEwasWater(
  RGSet,
  targets,
  failedSamples = character(0),
  SampleID = "Sample_Name",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_filterSamplesMinfiEwasWater.txt"
)

Arguments

Value

A list with class "dnaEPICO_minfiEwasWater_samples" containing the filtered RGSet, aligned phenotype table, and failed sample identifiers.

Examples

ex <- dnaEPICO:::exampleMinfiBaseDataDnaEpico()
filtered_samples <- filterSamplesMinfiEwasWater(
  RGSet = ex$RGSet,
  targets = ex$targets,
  failedSamples = ex$targets$Sample_Name[1],
  SampleID = "Sample_Name",
  verbose = FALSE,
  logs = FALSE
)
nrow(filtered_samples$targets)

Description

Fit one Gaussian GLM per CpG for each phenotype requested in the object returned by prepareMethylationGLM_T1Data().

Usage

fitMethylationGLM_T1Models(
  preparedData,
  nCores = 1L,
  libPath = NULL,
  glmLibs = "glm2",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLM_T1.txt"
)

Arguments

Value

A list with class "dnaEPICO_methylationGLM_T1_models" containing fitted model lists, model formulas, and counts of failed CpG fits.

Examples

ex <- dnaEPICO:::exampleMethylationGLMStateDnaEpico()
model_results <- fitMethylationGLM_T1Models(
  preparedData = ex$preparedData,
  nCores = 1,
  verbose = FALSE,
  logs = FALSE
)
names(model_results$fits)

Description

Fit one linear mixed-effects model per CpG for each phenotype requested in the object returned by prepareMethylationGLMM_T1T2Data().

Usage

fitMethylationGLMM_T1T2Models(
  preparedData,
  nCores = 1L,
  libPath = NULL,
  lmeLibs = "lme4,lmerTest",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLMM_T1T2.txt"
)

Arguments

Value

A list with class "dnaEPICO_methylationGLMM_T1T2_models" containing fitted model lists, model formulas, and counts of failed CpG fits.

Examples

ex <- dnaEPICO:::exampleMethylationGLMMStateDnaEpico()
model_results <- fitMethylationGLMM_T1T2Models(
  preparedData = ex$preparedData,
  nCores = 1,
  verbose = FALSE,
  logs = FALSE
)
names(model_results$fits)

Description

Load the metric matrices generated by preprocessingMinfiEwasWater() and return them as a single in-memory object for downstream phenotype alignment.

Usage

loadMetricsPreprocessingPheno(
  betaPath,
  mPath,
  cnPath,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_loadMetricsPreprocessingPheno.txt"
)

Arguments

Value

A list with class "dnaEPICO_preprocessingPheno_metrics" containing beta, m, and cn.

Examples

ex <- dnaEPICO:::examplePreprocessingPhenoStateDnaEpico()
metrics_data <- loadMetricsPreprocessingPheno(
  betaPath = ex$betaPath,
  mPath = ex$mPath,
  cnPath = ex$cnPath,
  verbose = FALSE,
  logs = FALSE
)
names(metrics_data)

Description

Merge the surrogate variable matrix back into the phenotype table while preserving the original row order of targets.

Usage

mergeSvaTargetsEnmix(
  targets,
  sva,
  SampleID = "Sample_Name",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_mergeSvaTargetsEnmix.txt"
)

Arguments

Value

A phenotype data frame with the surrogate variables appended.

Examples

ex <- dnaEPICO:::exampleSvaAnalysisStateDnaEpico()
merged_pheno <- mergeSvaTargetsEnmix(
  targets = ex$targets,
  sva = ex$sva,
  SampleID = "Sample_Name",
  verbose = FALSE,
  logs = FALSE
)
colnames(merged_pheno)[seq_len(4)]

Description

methylationGLM_T1() is the high-level coordinator for the one-timepoint GLM stage of the dnaEPICO workflow. It prepares the merged phenotype-plus-beta input, optionally creates exploratory plots, fits one Gaussian GLM per CpG for each requested phenotype, extracts CpG-level summaries, optionally collects significant CpG coefficient tables, generates diagnostic plots, annotates the combined summary table, and optionally writes legacy-style outputs to disk. The default behavior is now in-memory and quiet, which makes the function easier to compose with other package functions and more aligned with typical Bioconductor usage.

Usage

methylationGLM_T1(
  inputPheno = "rData/preprocessingPheno/mergeData/phenoBetaT1.RData",
  outputLogs = "logs",
  outputRData = "rData/methylationGLM_T1/models",
  outputPlots = "figures/methylationGLM_T1",
  phenotypes = c("DASS_Depression", "DASS_Anxiety", "DASS_Stress", "PCL5_TotalScore",
    "MHCSF_TotalScore", "BRS_TotalScore"),
  covariates = "Sex,Age,Ethnicity,TraumaDefinition,Leukocytes,Epithelial.cells",
  factorVars = "Sex,Ethnicity,TraumaDefinition",
  cpgPrefix = "cg",
  cpgLimit = NA,
  nCores = 32,
  plotWidth = 2000,
  plotHeight = 1000,
  plotDPI = 150,
  interactionTerm = NULL,
  libPath = NULL,
  glmLibs = "glm2",
  prsMap = NULL,
  summaryPval = NA,
  summaryResidualSD = TRUE,
  saveSignificantCpGs = FALSE,
  significantCpGDir = "preliminaryResults/cpgs/methylationGLM_T1",
  significantCpGPval = 0.05,
  saveTxtSummaries = TRUE,
  chunkSize = NULL,
  summaryTxtDir = "preliminaryResults/summary/methylationGLM_T1/glm",
  fdrThreshold = 0.05,
  padjmethod = "fdr",
  annotationPackage = "IlluminaHumanMethylationEPICv2anno.20a1.hg38",
  annotationCols = c("Name", "chr", "pos", "UCSC_RefGene_Group", "UCSC_RefGene_Name",
    "Relation_to_Island", "GencodeV41_Group"),
  annotatedGLMOut = "data/methylationGLM_T1",
  display = FALSE,
  verbose = FALSE,
  logs = FALSE,
  saveOutputs = FALSE
)

Arguments

Value

A list with class "dnaEPICO_methylationGLM_T1".

preparedData

Object returned by prepareMethylationGLM_T1Data() containing the merged phenotype-plus-beta analysis table and modeling metadata.

distributionPlots

Object returned by plotMethylationGLM_T1Distributions() describing any exploratory plots that were generated or written.

modelFits

Object returned by fitMethylationGLM_T1Models() containing the per-phenotype CpG model fits.

modelSummaries

Object returned by summarizeMethylationGLM_T1Models() containing the combined CpG summary tables used for reporting and annotation.

significantCpGs

Object returned by collectSignificantCpGsMethylationGLM_T1() containing optional phenotype-specific significant-CpG tables.

diagnosticPlots

Object returned by plotMethylationGLM_T1Diagnostics() describing the diagnostic plot objects and any written TIFF files.

annotation

Object returned by annotateMethylationGLM_T1Summaries() containing the annotated combined summary table.

savedFiles

Object returned by writeMethylationGLM_T1Outputs() when saveOutputs = TRUE, otherwise NULL.

See dnaEPICO_methylationGLM_T1 for a class-level overview.

See Also

dnaEPICO_methylationGLM_T1

Examples

if (requireNamespace("IlluminaHumanMethylation450kanno.ilmn12.hg19", quietly = TRUE)) {
  tmp <- tempdir()
  toy_path <- file.path(tmp, "phenoBetaT1.RData")
  phenoBT1 <- data.frame(
    Sample_Name = c("S1", "S2", "S3", "S4"),
    status = factor(c("Case", "Case", "Control", "Control")),
    sex = factor(c("F", "M", "F", "M")),
    cg00000029 = c(0.20, 0.25, 0.22, 0.27),
    cg00000108 = c(0.60, 0.55, 0.52, 0.58),
    check.names = FALSE
  )
  save(phenoBT1, file = toy_path)

  result <- methylationGLM_T1(
    inputPheno = toy_path,
    phenotypes = "status",
    covariates = "sex",
    factorVars = "status,sex",
    cpgLimit = 2,
    nCores = 1,
    summaryPval = 1,
    annotationPackage = "IlluminaHumanMethylation450kanno.ilmn12.hg19",
    annotationCols = "Name,chr,pos",
    display = FALSE,
    verbose = FALSE,
    logs = FALSE,
    saveOutputs = FALSE
  )

  class(result)
}

Description

methylationGLMM_T1T2() is the high-level coordinator for the longitudinal linear mixed-effects stage of the dnaEPICO workflow. It prepares the merged phenotype-plus-beta input, fits one mixed-effects model per CpG for each requested phenotype, extracts phenotype-specific coefficient summaries, optionally collects significant interaction tables, generates diagnostic plots, annotates the combined summary table, and optionally writes legacy-style outputs to disk. The default behavior is now in-memory and quiet, which makes the function easier to compose with other package functions and more aligned with typical Bioconductor usage.

Usage

methylationGLMM_T1T2(
  inputPheno = "rData/preprocessingPheno/mergeData/phenoBetaT1T2.RData",
  outputLogs = "logs",
  outputRData = "rData/methylationGLMM_T1T2/models",
  outputPlots = "figures/methylationGLMM_T1T2",
  personVar = "person",
  timeVar = "Timepoint",
  phenotypes = c("DASS_Depression", "DASS_Anxiety", "DASS_Stress", "PCL5_TotalScore",
    "MHCSF_TotalScore", "BRS_TotalScore"),
  covariates = "Sex,Age,Ethnicity,TraumaDefinition,Leukocytes,Epithelial.cells",
  factorVars = "Sex,Ethnicity,TraumaDefinition,Timepoint",
  lmeLibs = "lme4,lmerTest",
  prsMap = NULL,
  libPath = NULL,
  cpgPrefix = "cg",
  cpgLimit = NA,
  nCores = 32,
  summaryPval = NA,
  plotWidth = 2000,
  plotHeight = 1000,
  plotDPI = 150,
  interactionTerm = NULL,
  saveSignificantInteractions = TRUE,
  significantInteractionDir = "preliminaryResults/cpgs/methylationGLMM_T1T2",
  significantInteractionPval = 0.05,
  saveTxtSummaries = TRUE,
  chunkSize = NULL,
  summaryTxtDir = "preliminaryResults/summary/methylationGLMM_T1T2/lmer",
  fdrThreshold = 0.05,
  padjmethod = "fdr",
  annotationPackage = "IlluminaHumanMethylationEPICv2anno.20a1.hg38",
  annotationCols = c("Name", "chr", "pos", "UCSC_RefGene_Group", "UCSC_RefGene_Name",
    "Relation_to_Island", "GencodeV41_Group"),
  annotatedLMEOut = "data/methylationGLMM_T1T2",
  display = FALSE,
  verbose = FALSE,
  logs = FALSE,
  saveOutputs = FALSE
)

Arguments

Value

A list with class "dnaEPICO_methylationGLMM_T1T2".

preparedData

Object returned by prepareMethylationGLMM_T1T2Data() containing the merged longitudinal phenotype-plus-beta analysis table and modeling metadata.

modelFits

Object returned by fitMethylationGLMM_T1T2Models() containing the per-phenotype CpG mixed-effects model fits.

modelSummaries

Object returned by summarizeMethylationGLMM_T1T2Models() containing the combined CpG summary tables used for reporting and annotation.

significantInteractions

Object returned by collectSignificantInteractionsMethylationGLMM_T1T2() containing optional phenotype-specific significant-interaction tables.

diagnosticPlots

Object returned by plotMethylationGLMM_T1T2Diagnostics() describing the diagnostic plot objects and any written TIFF files.

annotation

Object returned by annotateMethylationGLMM_T1T2Summaries() containing the annotated combined summary table.

savedFiles

Object returned by writeMethylationGLMM_T1T2Outputs() when saveOutputs = TRUE, otherwise NULL.

See dnaEPICO_methylationGLMM_T1T2 for a class-level overview.

See Also

dnaEPICO_methylationGLMM_T1T2

Examples

if (
  requireNamespace("IlluminaHumanMethylation450kanno.ilmn12.hg19", quietly = TRUE) &&
    requireNamespace("lmerTest", quietly = TRUE)
) {
  tmp <- tempdir()
  toy_path <- file.path(tmp, "phenoBetaT1T2.RData")
  phenoBT1T2 <- data.frame(
    SID = c("P1A", "P1B", "P2A", "P2B", "P3A", "P3B", "P4A", "P4B"),
    person = c(1, 1, 2, 2, 3, 3, 4, 4),
    Timepoint = factor(c("1", "2", "1", "2", "1", "2", "1", "2")),
    score = c(10, 12, 9, 11, 13, 14, 8, 9),
    sex = factor(c("F", "F", "M", "M", "F", "F", "M", "M")),
    cg00000029 = c(0.25, 0.27, 0.20, 0.22, 0.30, 0.31, 0.18, 0.20),
    cg00000108 = c(0.50, 0.53, 0.55, 0.57, 0.48, 0.49, 0.60, 0.61),
    check.names = FALSE
  )
  save(phenoBT1T2, file = toy_path)

  result <- methylationGLMM_T1T2(
    inputPheno = toy_path,
    phenotypes = "score",
    covariates = "sex",
    factorVars = "sex,Timepoint",
    cpgLimit = 2,
    nCores = 1,
    summaryPval = 1,
    annotationPackage = "IlluminaHumanMethylation450kanno.ilmn12.hg19",
    annotationCols = "Name,chr,pos",
    display = FALSE,
    verbose = FALSE,
    logs = FALSE,
    saveOutputs = FALSE
  )

  class(result)
}

Description

Apply one or more supported normalization methods to a filtered RGSet and return all normalized objects together in a single result object.

Usage

normalizeMinfiEwasWater(
  sampleData,
  sexColumn = "Sex",
  normMethods = "adjustedfunnorm",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_normalizeMinfiEwasWater.txt"
)

Arguments

Value

A list with class "dnaEPICO_minfiEwasWater_norm" containing the requested normalized objects and the first method as primary.

Examples

ex <- dnaEPICO:::exampleMinfiBaseDataDnaEpico()
sample_data <- filterSamplesMinfiEwasWater(
  RGSet = ex$RGSet,
  targets = ex$targets,
  failedSamples = character(0),
  SampleID = "Sample_Name",
  verbose = FALSE,
  logs = FALSE
)
norm_data <- normalizeMinfiEwasWater(
  sampleData = sample_data,
  sexColumn = "Sex",
  normMethods = "quantile",
  verbose = FALSE,
  logs = FALSE
)
names(norm_data$normalized)

Description

Draw either the minfi QC plot or the detection P-value plot from an assessment object returned by assessSamplesMinfiEwasWater().

Usage

plotAssessmentMinfiEwasWater(
  assessment,
  plot = c("qc", "detection"),
  display = FALSE,
  file = NULL,
  width = 2000L,
  height = 1000L,
  res = 150L,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_plotAssessmentMinfiEwasWater.txt"
)

Arguments

Value

Invisibly returns the saved TIFF path when file is supplied, otherwise NULL.

Examples

assessment <- list(
  meanDetP = c(S1 = 0.01, S2 = 0.02, S3 = 0.04),
  detPThreshold = 0.05
)
plotAssessmentMinfiEwasWater(
  assessment = assessment,
  plot = "detection",
  display = FALSE,
  verbose = FALSE,
  logs = FALSE
)

Description

Call ENmix::plotCtrl() for a supplied RGSet. This function only writes files when output_dir is provided because ENmix::plotCtrl() produces JPG files on disk rather than returning a plot object.

Usage

plotCtrlMinfiEwasWater(
  RGSet,
  output_dir = NULL,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_plotCtrlMinfiEwasWater.txt"
)

Arguments

Value

Invisibly returns output_dir.

Examples

ex <- dnaEPICO:::exampleMinfiBaseDataDnaEpico()
output_dir <- file.path(tempdir(), "enmix-control-plots")
plotCtrlMinfiEwasWater(
  RGSet = ex$RGSet,
  output_dir = output_dir,
  verbose = FALSE,
  logs = FALSE
)
dir.exists(output_dir)

Description

Create Q-Q and residual-diagnostic plots from the CpG summary tables returned by summarizeMethylationGLM_T1Models().

Usage

plotMethylationGLM_T1Diagnostics(
  modelSummaries,
  preparedData,
  fdrThreshold = 0.05,
  padjmethod = "fdr",
  outputDir = NULL,
  plotWidth = 2000L,
  plotHeight = 1000L,
  plotDPI = 150L,
  display = FALSE,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLM_T1.txt"
)

Arguments

Value

A list with class "dnaEPICO_methylationGLM_T1_diagnostic_plots" containing the generated ggplot2 objects, genomic inflation factors, and any saved TIFF file paths.

Examples

ex <- dnaEPICO:::exampleMethylationGLMStateDnaEpico()
diagnostic_plots <- plotMethylationGLM_T1Diagnostics(
  modelSummaries = ex$modelSummaries,
  preparedData = ex$preparedData,
  display = FALSE,
  verbose = FALSE,
  logs = FALSE
)
names(diagnostic_plots$plots)

Description

Create phenotype, factor-variable, and numeric-covariate distribution plots from the object returned by prepareMethylationGLM_T1Data().

Usage

plotMethylationGLM_T1Distributions(
  preparedData,
  plotWidth = 2000L,
  plotHeight = 1000L,
  plotDPI = 150L,
  outputDir = NULL,
  display = FALSE,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLM_T1.txt"
)

Arguments

Value

A list with class "dnaEPICO_methylationGLM_T1_distribution_plots" containing the generated ggplot2 objects and any saved TIFF file paths.

Examples

ex <- dnaEPICO:::exampleMethylationGLMStateDnaEpico()
distribution_plots <- plotMethylationGLM_T1Distributions(
  preparedData = ex$preparedData,
  display = FALSE,
  verbose = FALSE,
  logs = FALSE
)
names(distribution_plots)

Description

Create Q-Q and standard-error diagnostic plots from the mixed-effects summary tables returned by summarizeMethylationGLMM_T1T2Models().

Usage

plotMethylationGLMM_T1T2Diagnostics(
  modelSummaries,
  preparedData,
  fdrThreshold = 0.05,
  padjmethod = "fdr",
  outputDir = NULL,
  plotWidth = 2000L,
  plotHeight = 1000L,
  plotDPI = 150L,
  display = FALSE,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLMM_T1T2.txt"
)

Arguments

Value

A list with class "dnaEPICO_methylationGLMM_T1T2_diagnostic_plots" containing the generated ggplot2 objects, genomic inflation factors, and any saved TIFF file paths.

Examples

ex <- dnaEPICO:::exampleMethylationGLMMStateDnaEpico()
diagnostic_plots <- plotMethylationGLMM_T1T2Diagnostics(
  modelSummaries = ex$modelSummaries,
  preparedData = ex$preparedData,
  display = FALSE,
  verbose = FALSE,
  logs = FALSE
)
names(diagnostic_plots$plots)

Description

Plot multidimensional scaling or density summaries from final metrics

Usage

plotMetricsMinfiEwasWater(
  metricsData,
  targets,
  plot = c("mds", "density"),
  plotGroupVar = "Sex",
  sexColumn = "Sex",
  display = FALSE,
  file = NULL,
  width = 2000L,
  height = 1000L,
  res = 150L,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_plotMetricsMinfiEwasWater.txt"
)

Arguments

Value

Invisibly returns the saved TIFF path when file is supplied, otherwise NULL.

Examples

ex <- dnaEPICO:::exampleMinfiMetricsStateDnaEpico()
plotMetricsMinfiEwasWater(
  metricsData = ex$metricsData,
  targets = ex$targets,
  plot = "density",
  plotGroupVar = "Sex",
  sexColumn = "Sex",
  display = FALSE,
  verbose = FALSE,
  logs = FALSE
)

Description

Draw the density comparison plot used to inspect raw versus normalized data.

Usage

plotNormalizationMinfiEwasWater(
  RGSet,
  normData,
  targets,
  sexColumn = "Sex",
  display = FALSE,
  file = NULL,
  width = 2000L,
  height = 1000L,
  res = 150L,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_plotNormalizationMinfiEwasWater.txt"
)

Arguments

Value

Invisibly returns the saved TIFF path when file is supplied, otherwise NULL.

Examples

ex <- dnaEPICO:::exampleMinfiMetricsStateDnaEpico()
plotNormalizationMinfiEwasWater(
  RGSet = ex$beta,
  normData = ex$normData,
  targets = ex$targets,
  sexColumn = "Sex",
  display = FALSE,
  verbose = FALSE,
  logs = FALSE
)

Description

Draw the pre-normalization beta density plot from a raw minfi object and a grouping variable in the phenotype table.

Usage

plotRawDensityMinfiEwasWater(
  rawData,
  targets,
  plotGroupVar = "Sex",
  display = FALSE,
  file = NULL,
  width = 2000L,
  height = 1000L,
  res = 150L,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_plotRawDensityMinfiEwasWater.txt"
)

Arguments

Value

Invisibly returns the saved TIFF path when file is supplied, otherwise NULL.

Examples

ex <- dnaEPICO:::exampleMinfiMetricsStateDnaEpico()
plotRawDensityMinfiEwasWater(
  rawData = ex$rawData,
  targets = ex$targets,
  plotGroupVar = "Sex",
  display = FALSE,
  verbose = FALSE,
  logs = FALSE
)

Description

Plot predicted or clinical sex from predictSexMinfiEwasWater()

Usage

plotSexMinfiEwasWater(
  sexData,
  type = c("predicted", "clinical"),
  display = FALSE,
  file = NULL,
  width = 2000L,
  height = 1000L,
  res = 70L,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_plotSexMinfiEwasWater.txt"
)

Arguments

Value

Invisibly returns the saved TIFF path when file is supplied, otherwise NULL.

Examples

ex <- dnaEPICO:::exampleSexPlotStateDnaEpico()
plotSexMinfiEwasWater(
  sexData = ex,
  type = "predicted",
  display = FALSE,
  verbose = FALSE,
  logs = FALSE
)

Description

Draw one of the standard surrogate-variable plots used by svaEnmix().

Usage

plotSvaEnmix(
  analysisData,
  plot = c("sentrix_id", "sentrix_position", "matrix"),
  display = FALSE,
  file = NULL,
  width = 2000L,
  height = 1000L,
  res = 150L,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_plotSvaEnmix.txt"
)

Arguments

Value

Invisibly returns file when a TIFF is written, otherwise NULL.

Examples

ex <- dnaEPICO:::exampleSvaAnalysisStateDnaEpico()
plotSvaEnmix(
  analysisData = ex$analysisData,
  plot = "sentrix_id",
  display = FALSE,
  verbose = FALSE,
  logs = FALSE
)

Description

Predict sample sex from a genome-mapped methylation object, align the predictions with phenotype data, and return a structured object that can be plotted or merged into downstream phenotype tables.

Usage

predictSexMinfiEwasWater(
  rawData,
  targets,
  SampleID = "Sample_Name",
  sexColumn = "Sex",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_predictSexMinfiEwasWater.txt"
)

Arguments

Value

A list with class "dnaEPICO_minfiEwasWater_sex" containing the sex prediction result, aligned phenotype data, plotting data, and mismatch table.

Examples

ex <- dnaEPICO:::exampleMinfiWorkflowStateDnaEpico()
sex_data <- predictSexMinfiEwasWater(
  rawData = ex$rawFiltered,
  targets = ex$sampleData$targets,
  SampleID = "Sample_Name",
  sexColumn = "Sex",
  verbose = FALSE,
  logs = FALSE
)
names(sex_data)

Description

Prepare inputs for a DNA methylation report

Usage

prepareDnamReportInputs(
  outputDir = "reports",
  qcDir = file.path("figures", "preprocessingMinfiEwasWater", "enmix"),
  preprocessingDir = file.path("figures", "preprocessingMinfiEwasWater", "qc"),
  postprocessingDir = file.path("figures", "preprocessingMinfiEwasWater", "metrics"),
  svaDir = file.path("figures", "svaEnmix"),
  glmDir = file.path("figures", "methylationGLM_T1"),
  glmmDir = file.path("figures", "methylationGLMM_T1T2"),
  figDir = file.path(outputDir, "assets", "figures"),
  verbose = FALSE,
  logs = FALSE,
  logDir = outputDir
)

Arguments

Value

A list with class "dnaEPICO_dnamReport_prepared".

Examples

report_root <- file.path(tempdir(), "dnaepico-report-inputs")
prepared <- prepareDnamReportInputs(
  outputDir = file.path(report_root, "reports"),
  qcDir = file.path(
    report_root,
    "figures",
    "preprocessingMinfiEwasWater",
    "enmix"
  ),
  preprocessingDir = file.path(
    report_root,
    "figures",
    "preprocessingMinfiEwasWater",
    "qc"
  ),
  postprocessingDir = file.path(
    report_root,
    "figures",
    "preprocessingMinfiEwasWater",
    "metrics"
  ),
  svaDir = file.path(report_root, "figures", "svaEnmix")
)
inherits(prepared, "dnaEPICO_dnamReport_prepared")

Description

Load the merged phenotype-plus-beta input object, validate the requested modeling variables, convert selected variables to factors, and return a single in-memory object for downstream helpers.

Usage

prepareMethylationGLM_T1Data(
  inputPheno,
  phenotypes,
  covariates,
  factorVars,
  cpgPrefix = "cg",
  cpgLimit = NA,
  interactionTerm = NULL,
  prsMap = NULL,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLM_T1.txt"
)

Arguments

Value

A list with class "dnaEPICO_methylationGLM_T1_data" containing the prepared analysis data, parsed variable selections, CpG columns, and exploratory summaries.

Examples

ex <- dnaEPICO:::exampleMethylationGLMStateDnaEpico()
prepared_data <- prepareMethylationGLM_T1Data(
  inputPheno = ex$inputPath,
  phenotypes = "status",
  covariates = "sex,age",
  factorVars = "status,sex",
  cpgLimit = 2,
  verbose = FALSE,
  logs = FALSE
)
names(prepared_data)

Description

Load the merged longitudinal phenotype-plus-beta object, ensure that a subject identifier column is available, validate the requested modeling variables, convert selected variables to factors, and return a single in-memory object for downstream mixed-effects modeling helpers.

Usage

prepareMethylationGLMM_T1T2Data(
  inputPheno,
  personVar = "person",
  timeVar = "Timepoint",
  phenotypes,
  covariates,
  factorVars,
  prsMap = NULL,
  cpgPrefix = "cg",
  cpgLimit = NA,
  interactionTerm = NULL,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLMM_T1T2.txt"
)

Arguments

Value

A list with class "dnaEPICO_methylationGLMM_T1T2_data" containing the prepared analysis data, parsed variable selections, CpG columns, timepoint summaries, and subject-ID diagnostics.

Examples

ex <- dnaEPICO:::exampleMethylationGLMMStateDnaEpico()
prepared_data <- prepareMethylationGLMM_T1T2Data(
  inputPheno = ex$inputPath,
  personVar = "person",
  timeVar = "Timepoint",
  phenotypes = "score",
  covariates = "sex",
  factorVars = "sex,Timepoint",
  cpgLimit = 2,
  verbose = FALSE,
  logs = FALSE
)
names(prepared_data)

Description

Run the dnaEPICO preprocessing workflow as a convenience wrapper around the smaller minfi/ENmix/wateRmelon helper functions in this package. The wrapper now returns a structured result object containing the in-memory outputs from each stage. Legacy files are written only when saveOutputs = TRUE.

Usage

preprocessingMinfiEwasWater(
  phenoFile = "data/preprocessingMinfiEwasWater/pheno.csv",
  idatFolder = "data/preprocessingMinfiEwasWater/idats",
  outputLogs = "logs",
  nSamples = NA,
  SampleID = "Sample_Name",
  arrayType = "IlluminaHumanMethylationEPICv2",
  annotationVersion = "20a1.hg38",
  scriptLabel = "preprocessingMinfiEwasWater",
  baseDataFolder = "rData",
  figureBaseDir = "figures",
  sepType = "",
  tiffWidth = 2000,
  tiffHeight = 1000,
  tiffRes = 150,
  qcCutoff = 10.5,
  detPtype = "m+u",
  detPThreshold = 0.05,
  normMethods = "adjustedfunnorm",
  sexColumn = "Sex",
  pvalThreshold = 0.01,
  chrToRemove = "chrX,chrY",
  snpsToRemove = "SBE,CpG",
  mafThreshold = 0.1,
  crossReactivePath = "data/preprocessingMinfiEwasWater/12864_2024_10027_MOESM8_ESM.csv",
  plotGroupVar = "Sex",
  lcRef = "salivaEPIC",
  phenoOrder = "Sample_Name;Timepoint;Sex;PredSex;Basename;Sentrix_ID;Sentrix_Position",
  lcPhenoDir = "data/preprocessingMinfiEwasWater",
  display = FALSE,
  verbose = FALSE,
  logs = FALSE,
  saveOutputs = FALSE
)

Arguments

Value

A list with class "dnaEPICO_preprocessingMinfiEwasWater".

targets

Filtered phenotype table aligned to the retained samples.

RGSet

Filtered RGChannelSet used in downstream preprocessing and available for direct interactive inspection.

rawData

Object returned by buildRawMinfiEwasWater() containing the raw MSet, RatioSet, and genome-mapped object derived from RGSet.

assessment

Object returned by assessSamplesMinfiEwasWater() containing detection P values, QC summaries, and failed-sample tracking.

sexData

Object returned by predictSexMinfiEwasWater() containing predicted sex labels, mismatch summaries, and plotting data.

normData

Object returned by normalizeMinfiEwasWater() containing the requested normalized objects and metadata on the methods that were run.

filterData

Object returned by filterProbesMinfiEwasWater() containing the probe-filtered methylation objects at each filtering stage.

metricsData

Object returned by extractMetricsMinfiEwasWater() containing the beta-value, M-value, and copy-number matrices used by later workflow steps.

lcData

Object returned by estimateLCMinfiEwasWater() containing the estimated cell-type proportions and the phenotype table augmented with those proportions.

logFile

Resolved path to the optional log file, or NULL when logging was disabled.

See dnaEPICO_preprocessingMinfiEwasWater for a class-level overview.

See Also

dnaEPICO_preprocessingMinfiEwasWater

Examples

if (requireNamespace("minfiData", quietly = TRUE) &&
    requireNamespace("IlluminaHumanMethylation450kmanifest", quietly = TRUE) &&
    requireNamespace("IlluminaHumanMethylation450kanno.ilmn12.hg19", quietly = TRUE)) {
  ex <- dnaEPICO:::exampleMinfiIdatInputsDnaEpico(n = 4)
  result <- preprocessingMinfiEwasWater(
    phenoFile = ex$phenoFile,
    idatFolder = ex$idatFolder,
    outputLogs = file.path(ex$tempDir, "logs"),
    nSamples = 4,
    SampleID = "Sample_Name",
    arrayType = ex$arrayType,
    annotationVersion = ex$annotationVersion,
    scriptLabel = "preprocessingMinfiEwasWater",
    baseDataFolder = file.path(ex$tempDir, "rData"),
    figureBaseDir = file.path(ex$tempDir, "figures"),
    detPThreshold = 1,
    normMethods = "quantile",
    sexColumn = "Sex",
    pvalThreshold = 1,
    chrToRemove = "",
    snpsToRemove = "SBE",
    mafThreshold = 1,
    crossReactivePath = ex$crossReactivePath,
    plotGroupVar = "Sex",
    lcRef = "saliva",
    phenoOrder = "Sample_Name;Sex;Basename;Sentrix_ID;Sentrix_Position",
    lcPhenoDir = ex$tempDir,
    saveOutputs = FALSE,
    verbose = FALSE,
    logs = FALSE
  )
  inherits(result, "dnaEPICO_preprocessingMinfiEwasWater")
}

Description

Read the phenotype table and the preprocessed beta, M-value, and copy-number matrices; align them by sample identifier; split them by timepoint; prepare combined longitudinal objects; and build Clock Foundation export tables. The function returns a structured in-memory result, while legacy files are written only when saveOutputs = TRUE.

Usage

preprocessingPheno(
  phenoFile = "data/preprocessingMinfiEwasWater/phenoLC.csv",
  sepType = "",
  betaPath =
    "rData/preprocessingMinfiEwasWater/metrics/beta_NomFilt_MSetF_Flt_Rxy_Ds_Rc.RData",
  mPath = "rData/preprocessingMinfiEwasWater/metrics/m_NomFilt_MSetF_Flt_Rxy_Ds_Rc.RData",
  cnPath =
    "rData/preprocessingMinfiEwasWater/metrics/cn_NomFilt_MSetF_Flt_Rxy_Ds_Rc.RData",
  SampleID = "Sample_Name",
  timeVar = "Timepoint",
  timepoints = "1,2",
  combineTimepoints = "1,2",
  outputPheno = "data/preprocessingPheno",
  outputRData = "rData/preprocessingPheno/metrics",
  outputRDataMerge = "rData/preprocessingPheno/mergeData",
  sexColumn = "Sex",
  outputLogs = "logs",
  outputDir = "data/preprocessingPheno",
  verbose = FALSE,
  logs = FALSE,
  saveOutputs = FALSE
)

Arguments

Value

A list with class "dnaEPICO_preprocessingPheno".

pheno

Phenotype table read from phenoFile.

metricsData

Object returned by loadMetricsPreprocessingPheno() containing the beta-value, M-value, and copy-number matrices loaded from betaPath, mPath, and cnPath.

timepointData

Object returned by splitTimepointsPreprocessingPheno() containing per-timepoint phenotype tables and methylation matrices.

combinedData

Object returned by combineTimepointsPreprocessingPheno() containing the merged longitudinal phenotype-plus-beta object and the timepoint combination metadata.

clockFoundation

Object returned by buildClockFoundationInputsPreprocessingPheno() containing the beta table and phenotype table prepared for Clock Foundation export.

savedFiles

Object returned by writePreprocessingPhenoOutputs() when saveOutputs = TRUE, otherwise NULL.

logFile

Resolved path to the optional log file, or NULL when logging was disabled.

See dnaEPICO_preprocessingPheno for a class-level overview.

See Also

dnaEPICO_preprocessingPheno

Examples

tmp <- tempdir()
pheno <- data.frame(
  Sample_Name = c("S1", "S2", "S3"),
  Timepoint = c("1", "1", "2"),
  Sex = c(0, 1, 0),
  stringsAsFactors = FALSE
)
beta <- matrix(
  c(0.10, 0.20, 0.30, 0.40, 0.50, 0.60),
  nrow = 2,
  dimnames = list(c("cg1", "cg2"), pheno$Sample_Name)
)
m <- beta * 10
cn <- beta * 100
pheno_file <- file.path(tmp, "pheno.csv")
beta_path <- file.path(tmp, "beta.RData")
m_path <- file.path(tmp, "m.RData")
cn_path <- file.path(tmp, "cn.RData")
utils::write.csv(pheno, pheno_file, row.names = FALSE)
save(beta, file = beta_path)
save(m, file = m_path)
save(cn, file = cn_path)
result <- preprocessingPheno(
  phenoFile = pheno_file,
  betaPath = beta_path,
  mPath = m_path,
  cnPath = cn_path,
  SampleID = "Sample_Name",
  timeVar = "Timepoint",
  timepoints = "1,2",
  combineTimepoints = "1,2",
  outputPheno = file.path(tmp, "data", "preprocessingPheno"),
  outputRData = file.path(tmp, "rData", "preprocessingPheno", "metrics"),
  outputRDataMerge = file.path(tmp, "rData", "preprocessingPheno", "mergeData"),
  sexColumn = "Sex",
  outputLogs = file.path(tmp, "logs"),
  outputDir = file.path(tmp, "clockFoundation"),
  saveOutputs = FALSE
)
stopifnot(inherits(result, "dnaEPICO_preprocessingPheno"))

Description

Print a DNA methylation report result

Usage

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

Arguments

Value

Invisibly returns x.

Description

Read the phenotype table used by shared dnaEPICO workflows, validate the sample identifier column, optionally subset the first nSamples, and return the targets as a base data.frame.

Usage

readPhenotypeTargets(
  phenoFile,
  sepType = "",
  nSamples = NA,
  SampleID = "Sample_Name",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_readPhenotypeTargets.txt"
)

Arguments

Value

A data.frame containing the phenotype targets.

Examples

tmp <- tempdir()
pheno <- data.frame(
  Sample_Name = c("S1", "S2"),
  Sex = c("F", "M"),
  stringsAsFactors = FALSE
)
pheno_file <- file.path(tmp, "pheno.csv")
utils::write.csv(pheno, pheno_file, row.names = FALSE)
targets <- readPhenotypeTargets(
  phenoFile = pheno_file,
  SampleID = "Sample_Name"
)
stopifnot(is.data.frame(targets))
stopifnot(nrow(targets) == 2L)

Description

Read methylation-array IDAT files with minfi::read.metharray.exp(), set sample names from the phenotype table, apply the requested annotation, and return the resulting RGChannelSet.

Usage

readRGSetMinfiEwasWater(
  idatFolder,
  targets,
  SampleID = "Sample_Name",
  arrayType = "IlluminaHumanMethylationEPICv2",
  annotationVersion = "20a1.hg38",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_readRGSetMinfiEwasWater.txt"
)

Arguments

Value

An annotated RGChannelSet.

Examples

if (requireNamespace("minfiData", quietly = TRUE) &&
    requireNamespace("IlluminaHumanMethylation450kmanifest", quietly = TRUE) &&
    requireNamespace("IlluminaHumanMethylation450kanno.ilmn12.hg19", quietly = TRUE)) {
  ex <- dnaEPICO:::exampleMinfiIdatInputsDnaEpico(n = 4)
  rgset <- readRGSetMinfiEwasWater(
    idatFolder = ex$idatFolder,
    targets = ex$targets,
    SampleID = "Sample_Name",
    arrayType = ex$arrayType,
    annotationVersion = ex$annotationVersion
  )
  class(rgset)
}