Package 'dnaEPICO'

Description

Fit linear models for each surrogate variable against informative Sentrix chip and position factors, perform backward elimination with stats::drop1(), and return the in-memory analysis objects. A constant technical factor is omitted; if both are constant, an intercept-only model is retained.

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

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

Arguments

Value

A list with class 'dnaEPICO_methylationGLM_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 <- annotateMethylationGLMSummaries(
  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

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

Arguments

Value

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

Examples

ex <- dnaEPICO:::exampleMethylationLMEStateDnaEpico()
annotation_data <- annotateMethylationLMESummaries(
  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. The sex column is passed through without validation or recoding.

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 coefficient tables for CpGs selected by the configured target test. Selection uses target-term omnibus p-values when omnibus testing was enabled during fitting, and phenotype main-effect or interaction coefficient p-values otherwise.

Usage

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

Arguments

Value

A list with class 'dnaEPICO_methylationGLM_significant_cpgs'.

Examples

ex <- dnaEPICO:::exampleMethylationGLMStateDnaEpico()
significant_cpgs <- collectSignificantCpGsMethylationGLM(
  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

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

Arguments

Value

A list with class 'dnaEPICO_methylationLME_significant' containing the retained coefficient tables for each phenotype.

Examples

ex <- dnaEPICO:::exampleMethylationLMEStateDnaEpico()
significant_hits <- collectSignificantInteractionsMethylationLME(
  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",
  methylationScale = "beta",
  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

dnaEPICO provides workflows for preprocessing and analyzing Illumina DNA methylation arrays. It supports quality control, normalization, cell-type estimation, surrogate-variable analysis, phenotype preparation, CpG-wise generalised linear models, longitudinal mixed-effects models using lmerTest/lme4 or nlme, and web reporting.

Details

The package supports two 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()

• methylationLME()

• dnamReport()

Author(s)

Maintainer: Paul Ruiz Pinto [email protected] (ORCID)

Authors:

• Paul Ruiz Pinto [email protected] (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 HTML 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.

resultTableSources

Named character vector identifying whether each model table used a streamed sidecar or the compatible XLSX fallback.

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' are list-based results returned by methylationGLM(). They collect the prepared analysis table, compact model results, summaries, diagnostics, annotations, and optional saved files.

Structure

preparedData

Object returned by prepareMethylationGLMData().

distributionPlots

Object returned by plotMethylationGLMDistributions().

modelFits

Object returned by fitMethylationGLMModels().

modelSummaries

Object returned by summarizeMethylationGLMModels().

significantCpGs

Object returned by collectSignificantCpGsMethylationGLM().

diagnosticPlots

Object returned by plotMethylationGLMDiagnostics().

annotation

Object returned by annotateMethylationGLMSummaries().

manhattanPlots

Versioned circular and rectangular Manhattan plots for every raw p-value column in the annotated results.

vennDPlots

Requested coefficient and omnibus model-level Venn plots, worksheet tables, and label mappings.

savedFiles

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

runSettings

High-level settings recorded for the analysis.

See Also

methylationGLM()

Description

Objects of class 'dnaEPICO_methylationLME' are list-based results returned by methylationLME(). They collect the prepared longitudinal analysis table, compact mixed-model results, summaries, diagnostics, annotations, and optional saved files.

Structure

preparedData

Object returned by prepareMethylationLMEData().

modelFits

Object returned by fitMethylationLMEModels().

modelSummaries

Object returned by summarizeMethylationLMEModels().

significantInteractions

Object returned by collectSignificantInteractionsMethylationLME().

diagnosticPlots

Object returned by plotMethylationLMEDiagnostics().

annotation

Object returned by annotateMethylationLMESummaries().

manhattanPlots

Versioned circular and rectangular Manhattan plots for every raw p-value column in the annotated results.

vennDPlots

Requested coefficient and omnibus model-level Venn plots, worksheet tables, and label mappings.

savedFiles

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

runSettings

High-level settings recorded for the analysis.

See Also

methylationLME()

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(), including predicted-sex values and normalization fallback provenance.

normData

Object returned by normalizeMinfiEwasWater(), including the per-sample sex-resolution audit.

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(), or NULL when the combined object was skipped.

clockFoundation

Object returned by buildClockFoundationInputsPreprocessingPheno(), with original phenotype sex values preserved for 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 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,
  lmeTab = NULL,
  modelSections = c("glm", "lme"),
  logTab = outputDir,
  verbose = FALSE,
  logs = FALSE,
  projectName = "dnaEPICO",
  detPPath = NULL,
  detPThreshold = 0.01,
  cpgDetectionPath = NULL,
  sampleDetectionPath = NULL,
  logoPath = system.file("extdata", "dnaEPICORM.svg", package = "dnaEPICO"),
  imagePattern = "\\.(png|jpg|jpeg|gif|webp|svg|tif|tiff)$",
  recursive = TRUE
)

Arguments

Details

The Quarto command-line interface is required to render the website. It is not required to install or load dnaEPICO, or to use the package's preprocessing and statistical-modeling functions.

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.

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,
  SampleID = "Sample_Name",
  lcRef = "salivaEPIC",
  phenoOrder = paste0("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

Export the example Makefile supplied with dnaEPICO to a user directory.

Usage

extractMake(destDir, overwrite = FALSE)

Arguments

Details

The exported workflow requires GNU Make 4.3 or later. When the Makefile is created, extractMake() records the absolute path to the Rscript executable from the current R installation in the RSCRIPT Make variable. This value can be overridden when running Make, for example ⁠make f4 RSCRIPT=/path/to/Rscript⁠, when another R installation or an HPC module should be used.

Quarto is required only for targets that render reports. The rules use relative project paths and support project directories containing spaces. GNU Make and Quarto are not required to install or load dnaEPICO.

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 probe-exclusion 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,
  probeExclusionPath,
  probeExclusionIdColumn = NULL,
  useEpicV2Manifest = FALSE,
  epicV2ManifestFlags = c(CH_WGBS_evidence = TRUE, CH_BLAT = TRUE, MissingPos = TRUE,
    MismatchPos = FALSE),
  detPtype = "m+u",
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_filterProbesMinfiEwasWater.txt",
  crossReactivePath = NULL,
  crossReactiveIdColumn = NULL
)

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$RGSet,
  pvalThreshold = 1,
  chrToRemove = "chrY",
  snpsToRemove = "SBE",
  mafThreshold = 1,
  probeExclusionPath = ex$probeExclusionPath,
  detPtype = "m+u",
  verbose = FALSE,
  logs = FALSE
)
filtered_data$counts[["probeExclusion"]]

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 prepareMethylationGLMData(). Each native fit is reduced to compact numerical results and discarded before the next batch is returned.

Usage

fitMethylationGLMModels(
  preparedData,
  nCores = 1L,
  libPath = NULL,
  glmLibs = "glm2",
  summaryDir = NULL,
  omnibusTest = FALSE,
  resumeFromSummary = TRUE,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLM.txt"
)

Arguments

Value

A list with class 'dnaEPICO_methylationGLM_models' containing compact coefficient matrices, unfiltered target summaries, formulas, model conditions, hard errors, and phenotype summary artifacts.

Examples

ex <- dnaEPICO:::exampleMethylationGLMStateDnaEpico()
model_results <- fitMethylationGLMModels(
  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 prepareMethylationLMEData(). Each native fit is reduced to compact numerical results and discarded before the next batch is returned.

Usage

fitMethylationLMEModels(
  preparedData,
  nCores = 1L,
  libPath = NULL,
  lmeLibs = "lme4,lmerTest",
  correlationStructure = "none",
  correlationVar = NULL,
  omnibusTest = FALSE,
  omnibusDdf = "Satterthwaite",
  summaryDir = NULL,
  resumeFromSummary = TRUE,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationLME.txt"
)

Arguments

Value

A list with class 'dnaEPICO_methylationLME_models' containing compact coefficient matrices, unfiltered target summaries, formulas, model conditions, omnibus results, hard errors, and phenotype summary artifacts.

Examples

ex <- dnaEPICO:::exampleMethylationLMEStateDnaEpico()
model_results <- fitMethylationLMEModels(
  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() prepares phenotype-plus-methylation data, fits one Gaussian GLM per CpG and phenotype, summarizes and annotates the results, and creates optional coefficient tables and diagnostic plots. It writes outputs only when saveOutputs = TRUE. Numeric CpG columns are passed to glm2::glm2() without a separate methylation-domain filter. Native model messages, warnings, and errors are recorded in one phenotype-specific Model.Message field. Annotated outputs contain CpGs with at least one returned coefficient or omnibus p-value; aggregate availability and condition counts are recorded in workbook metadata.

Usage

methylationGLM(
  inputPheno = "rData/preprocessingPheno/mergeData/phenoBT1.RData",
  outputLogs = "logs",
  outputRData = "rData/methylationGLM/models",
  outputPlots = "figures/methylationGLM",
  phenotypes = c("DASS_Depression", "DASS_Anxiety", "DASS_Stress", "PCL5_TotalScore",
    "MHCSF_TotalScore", "BRS_TotalScore"),
  covariates = paste0("Sex,Age,Ethnicity,TraumaDefinition,Leukocytes,",
    "Epithelial.cells"),
  factorVars = "Sex,Ethnicity,TraumaDefinition",
  scaleVars = NULL,
  cpgPrefix = "cg",
  cpgLimit = NA,
  methylationScale = "beta",
  nCores = 32,
  plotWidth = 2000,
  plotHeight = 1000,
  plotDPI = 150,
  interactionTerm = NULL,
  omnibusTest = FALSE,
  vennDPhenotypes = NULL,
  vennDLabels = NULL,
  vennDOmnibusPhenotypes = NULL,
  vennDOmnibusLabels = NULL,
  libPath = NULL,
  glmLibs = "glm2",
  prsMap = NULL,
  summaryPval = NA,
  summaryResidualSD = TRUE,
  saveSignificantCpGs = FALSE,
  significantCpGDir = "preliminaryResults/cpgs/methylationGLM",
  significantCpGPval = 0.05,
  saveTxtSummaries = TRUE,
  chunkSize = NULL,
  summaryTxtDir = "preliminaryResults/summary/methylationGLM",
  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"),
  gencodeHub = FALSE,
  annotatedGLMOut = "data/methylationGLM",
  reportAssetsDir = NULL,
  display = FALSE,
  verbose = FALSE,
  logs = FALSE,
  saveOutputs = FALSE,
  resumeFromSummary = TRUE
)

Arguments

Value

A list with class 'dnaEPICO_methylationGLM'.

preparedData

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

distributionPlots

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

designPlots

Missingness and numeric-correlation plots for the variables used in the model.

modelFits

Object returned by fitMethylationGLMModels() containing compact per-phenotype coefficient, omnibus, and condition results.

modelSummaries

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

significantCpGs

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

diagnosticPlots

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

annotation

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

manhattanPlots

Versioned circular and rectangular Manhattan plots for every raw p-value column in the annotated results.

vennDPlots

Requested coefficient and omnibus model-level Venn plots, worksheet tables, and label mappings.

savedFiles

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

runSettings

High-level run metadata including the generic analysis label, methylation scale, display label, selected merged-object prefix, and internal response-column name.

See dnaEPICO_methylationGLM for a class-level overview.

See Also

dnaEPICO_methylationGLM

Examples

if (requireNamespace(
    "IlluminaHumanMethylation450kanno.ilmn12.hg19",
    quietly = TRUE
)) {
    tmp <- tempdir()
    toy_path <- file.path(tmp, "phenoBT1.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(
        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

methylationLME() prepares longitudinal phenotype-plus-methylation data, fits one mixed-effects model per CpG and phenotype, summarizes and annotates the results, and creates optional interaction tables and diagnostic plots. It writes outputs only when saveOutputs = TRUE. Numeric CpG columns are passed to the selected lmerTest/lme4 or nlme engine without a separate methylation-domain filter. Native model messages, warnings, and errors are recorded in one phenotype-specific Model.Message field. Annotated outputs contain CpGs with at least one returned coefficient or omnibus p-value; aggregate availability and condition counts are recorded in workbook metadata.

Usage

methylationLME(
  inputPheno = "rData/preprocessingPheno/mergeData/phenoBT1T2.RData",
  outputLogs = "logs",
  outputRData = "rData/methylationLME/models",
  outputPlots = "figures/methylationLME",
  personVar = "person",
  timeVar = "Timepoint",
  phenotypes = c("DASS_Depression", "DASS_Anxiety", "DASS_Stress", "PCL5_TotalScore",
    "MHCSF_TotalScore", "BRS_TotalScore"),
  covariates = paste0("Sex,Age,Ethnicity,TraumaDefinition,Leukocytes,",
    "Epithelial.cells"),
  factorVars = "Sex,Ethnicity,TraumaDefinition",
  scaleVars = NULL,
  lmeLibs = "lme4,lmerTest",
  correlationStructure = "none",
  correlationVar = NULL,
  prsMap = NULL,
  libPath = NULL,
  cpgPrefix = "cg",
  cpgLimit = NA,
  methylationScale = "beta",
  nCores = 32,
  summaryPval = NA,
  plotWidth = 2000,
  plotHeight = 1000,
  plotDPI = 150,
  interactionTerm = NULL,
  omnibusTest = FALSE,
  omnibusDdf = "Satterthwaite",
  vennDPhenotypes = NULL,
  vennDLabels = NULL,
  vennDOmnibusPhenotypes = NULL,
  vennDOmnibusLabels = NULL,
  saveSignificantInteractions = TRUE,
  significantInteractionDir = "preliminaryResults/cpgs/methylationLME",
  significantInteractionPval = 0.05,
  saveTxtSummaries = TRUE,
  chunkSize = NULL,
  summaryTxtDir = "preliminaryResults/summary/methylationLME",
  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"),
  gencodeHub = FALSE,
  annotatedLMEOut = "data/methylationLME",
  reportAssetsDir = NULL,
  display = FALSE,
  verbose = FALSE,
  logs = FALSE,
  saveOutputs = FALSE,
  resumeFromSummary = TRUE,
  SampleID = "SID"
)

Arguments

Value

A list with class 'dnaEPICO_methylationLME'.

preparedData

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

distributionPlots

Distributions of the model variables, longitudinal observation counts, time values, and numeric phenotype trajectories.

designPlots

Missingness and numeric-correlation plots for the variables used in the model.

modelFits

Object returned by fitMethylationLMEModels() containing compact per-phenotype coefficient, omnibus, and condition results.

modelSummaries

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

significantInteractions

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

diagnosticPlots

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

annotation

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

manhattanPlots

Versioned circular and rectangular Manhattan plots for every raw p-value column in the annotated results.

vennDPlots

Requested coefficient and omnibus model-level Venn plots, worksheet tables, and label mappings.

savedFiles

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

runSettings

High-level run metadata including the generic analysis label, methylation scale, display label, selected merged-object prefix, internal response-column name, and longitudinal time variable.

See dnaEPICO_methylationLME for a class-level overview.

See Also

dnaEPICO_methylationLME

Examples

if (
    requireNamespace(
        "IlluminaHumanMethylation450kanno.ilmn12.hg19",
        quietly = TRUE
    ) &&
        requireNamespace("lmerTest", quietly = TRUE)
) {
    tmp <- tempdir()
    toy_path <- file.path(tmp, "phenoBT1T2.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 <- methylationLME(
        inputPheno = toy_path,
        phenotypes = "score",
        covariates = "sex",
        factorVars = "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

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, the first method as primary, and a sexResolution audit table describing reported-sex and PredSex use.

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 summarizeMethylationGLMModels().

Usage

plotMethylationGLMDiagnostics(
  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.txt"
)

Arguments

Value

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

Examples

ex <- dnaEPICO:::exampleMethylationGLMStateDnaEpico()
diagnostic_plots <- plotMethylationGLMDiagnostics(
  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 prepareMethylationGLMData().

Usage

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

Arguments

Value

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

Examples

ex <- dnaEPICO:::exampleMethylationGLMStateDnaEpico()
distribution_plots <- plotMethylationGLMDistributions(
  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 summarizeMethylationLMEModels().

Usage

plotMethylationLMEDiagnostics(
  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_methylationLME.txt"
)

Arguments

Value

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

Examples

ex <- dnaEPICO:::exampleMethylationLMEStateDnaEpico()
diagnostic_plots <- plotMethylationLMEDiagnostics(
  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(). An empty association result is recorded in the log without creating a placeholder figure.

Usage

plotSvaEnmix(
  analysisData,
  plot = c("sentrix_id", "sentrix_position", "matrix", "association"),
  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 saved TIFF path(s), otherwise NULL. Association output is omitted when no technical-factor association is estimable.

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, mismatch table, and a sexResolution audit showing where PredSex would replace an unusable reported value during sex-aware normalization.

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"),
  lmeDir = file.path("figures", "methylationLME"),
  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-methylation input object, validate the requested modeling variables, convert selected variables to factors, and return a single in-memory object for downstream helpers.

Usage

prepareMethylationGLMData(
  inputPheno,
  phenotypes,
  covariates,
  factorVars,
  scaleVars = NULL,
  cpgPrefix = "cg",
  cpgLimit = NA,
  methylationScale = "beta",
  interactionTerm = NULL,
  prsMap = NULL,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationGLM.txt"
)

Arguments

Value

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

Examples

ex <- dnaEPICO:::exampleMethylationGLMStateDnaEpico()
prepared_data <- prepareMethylationGLMData(
  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-methylation 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

prepareMethylationLMEData(
  inputPheno,
  personVar = "person",
  timeVar = "Timepoint",
  phenotypes,
  covariates,
  factorVars,
  scaleVars = NULL,
  prsMap = NULL,
  cpgPrefix = "cg",
  cpgLimit = NA,
  methylationScale = "beta",
  interactionTerm = NULL,
  verbose = FALSE,
  logs = FALSE,
  log_dir = NULL,
  log_file = "log_methylationLME.txt",
  SampleID = "SID"
)

Arguments

Value

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

Examples

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

Description

Run the dnaEPICO preprocessing workflow with the package's minfi/ENmix/wateRmelon helper functions. The function returns the output from each stage and writes files 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",
  idatForce = FALSE,
  scriptLabel = "preprocessingMinfiEwasWater",
  baseDataFolder = "rData",
  figureBaseDir = "figures",
  sepType = NULL,
  tiffWidth = 2000,
  tiffHeight = 1000,
  tiffRes = 150,
  qcCutoff = 10.5,
  detPtype = "m+u",
  detPThreshold = 0.05,
  normMethods = "adjustedfunnorm",
  sexColumn = "Sex",
  removeSexMismatch = FALSE,
  pvalThreshold = 0.01,
  chrToRemove = "chrX,chrY",
  snpsToRemove = "SBE,CpG",
  mafThreshold = 0.1,
  probeExclusionPath = paste0("data/preprocessingMinfiEwasWater/",
    "12864_2024_10027_MOESM8_ESM.csv"),
  probeExclusionIdColumn = NULL,
  useEpicV2Manifest = FALSE,
  epicV2ManifestFlags = c(CH_WGBS_evidence = TRUE, CH_BLAT = TRUE, MissingPos = TRUE,
    MismatchPos = FALSE),
  plotGroupVar = "Sex",
  lcRef = "salivaEPIC",
  phenoOrder = paste0("Sample_Name;Timepoint;Sex;PredSex;Basename;",
    "Sentrix_ID;Sentrix_Position"),
  lcPhenoDir = "data/preprocessingMinfiEwasWater",
  display = FALSE,
  verbose = FALSE,
  logs = FALSE,
  saveOutputs = FALSE,
  crossReactivePath = NULL,
  crossReactiveIdColumn = NULL
)

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, normalization-sex provenance, plotting data, and the sample IDs removed when removeSexMismatch = TRUE.

normData

Object returned by normalizeMinfiEwasWater() containing the selected normalized objects, method metadata, and the reported-sex or PredSex value used for each sample.

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$tempDir, "figures"),
    detPThreshold = 1,
    normMethods = "quantile",
    sexColumn = "Sex",
    pvalThreshold = 1,
    chrToRemove = "",
    snpsToRemove = "SBE",
    mafThreshold = 1,
    probeExclusionPath = ex$probeExclusionPath,
    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

Align the phenotype table with preprocessed beta, M-value, and copy-number matrices, split the data by timepoint, optionally prepare longitudinal objects for the selected modeling scale, and build Clock Foundation export tables. The function writes files only when saveOutputs = TRUE.

Usage

preprocessingPheno(
  phenoFile = "data/preprocessingMinfiEwasWater/phenoLC.csv",
  sepType = NULL,
  betaPath = paste0("rData/preprocessingMinfiEwasWater/metrics/",
    "beta_NomFilt_MSetF_Flt_Rxy_Ds_Rc.RData"),
  mPath = paste0("rData/preprocessingMinfiEwasWater/metrics/",
    "m_NomFilt_MSetF_Flt_Rxy_Ds_Rc.RData"),
  cnPath = paste0("rData/preprocessingMinfiEwasWater/metrics/",
    "cn_NomFilt_MSetF_Flt_Rxy_Ds_Rc.RData"),
  SampleID = "Sample_Name",
  timeVar = "Timepoint",
  timepoints = "1,2",
  combineTimepoints = "1,2",
  methylationScale = "beta",
  outputPheno = "data/preprocessingPheno",
  outputRData = "rData/preprocessingPheno/metrics",
  outputRDataMerge = "rData/preprocessingPheno/mergeData",
  sexColumn = "Sex",
  outputLogs = "logs",
  outputDir = "data/preprocessingPheno",
  verbose = FALSE,
  logs = FALSE,
  saveOutputs = FALSE
)