New methylation features added

[JmWangBio]

New DNA methylation features, including ComBat-met, M-value ComBat, and the methylation-related helper functions, have been added.

[jessmcc22]

Please correct all BiocCheck errors, warnings, and notes associated with the files that you have updated. This includes:

Avoid sapply(); use vapply()
Found in files:
R/helper_met.R (line 6, column 36)
R/helper_met.R (line 369, column 17)
R/helper_met.R (line 370, column 14)
R/helper_met.R (line 371, column 15)
R/helper_met.R (line 372, column 17)
R/helper_met.R (line 485, column 11)
R/helper_met.R (line 521, column 16)
R/helper_seq.R (line 28, column 11)

Avoid 1:...; use seq_len() or seq_along()
helper_met.R (line 80, column 19)
helper_met.R (line 95, column 25)
helper_met.R (line 110, column 42)
helper_met.R (line 147, column 25)
helper_met.R (line 147, column 62)
helper_met.R (line 222, column 27)
helper_met.R (line 285, column 15)
helper_met.R (line 327, column 40)
helper_met.R (line 343, column 47)
helper_met.R (line 408, column 31)
helper_met.R (line 475, column 27)
helper_met.R (line 485, column 18)
helper_met.R (line 503, column 42)
helper_met.R (line 526, column 14)
helper_met.R (line 540, column 14)
helper_met.R (line 566, column 13)
helper_met.R (line 567, column 15)

Avoid 'cat' and 'print' outside of 'show' methods
cat() in R/helper_met.R (line 8, column 7)
cat() in R/helper_met.R (line 64, column 5)
cat() in R/helper_met.R (line 75, column 5)
cat() in R/helper_met.R (line 101, column 5)
cat() in R/helper_met.R (line 104, column 5)
cat() in R/helper_met.R (line 122, column 5)
cat() in R/helper_met.R (line 132, column 3)
cat() in R/helper_met.R (line 170, column 3)
cat() in R/helper_met.R (line 389, column 3)
cat() in R/helper_met.R (line 392, column 3)
cat() in R/helper_met.R (line 396, column 5)
cat() in R/helper_met.R (line 406, column 5)
cat() in R/helper_met.R (line 442, column 7)
cat() in R/helper_met.R (line 446, column 5)
cat() in R/helper_met.R (line 538, column 3)

Consider shorter lines; 349 lines (12%) are > 80 characters long.
First few lines:
R/ComBat_met.r#L1 #' Adjust for batch effects using a beta ...
R/ComBat_met.r#L4 #' calculates batch-free distributions, ...
R/ComBat_met.r#L8 #' @param dtype data type: b-value or M- ...
R/ComBat_met.r#L11 #' @param covar_mod optional model matri ...
R/ComBat_met.r#L12 #' @param full_mod Boolean variable indi ...
R/ComBat_met.r#L13 #' @param shrink Boolean variable indica ...
R/ComBat_met.r#L14 #' @param mean.only Boolean variable ind ...
R/ComBat_met.r#L15 #' @param feature.subset.n number of fea ...
R/ComBat_met.r#L16 #' @param pseudo_beta pseudo beta-values ...
R/ComBat_met.r#L18 #' @param ref.batch NULL by default. If ...
R/ComBat_met.r#L19 #' @param ncores number of cores to be u ...
R/ComBat_met.r#L21 #' @return \code{ComBat_met} returns a f ...
R/ComBat_met.r#L31 #' adj_bv_mat <- ComBat_met(bv_mat, dtyp ...
R/ComBat_met.r#L33 #' adj_bv_mat <- ComBat_met(bv_mat, dtyp ...
R/ComBat_met.r#L41 #' adj_mv_mat <- ComBat_met(mv_mat, dtyp ...
R/ComBat_met.r#L43 #' adj_mv_mat <- ComBat_met(mv_mat, dtyp ...
R/ComBat_met.r#L46 #' adj_mv_mat <- ComBat_met(mv_mat, dtyp ...
R/ComBat_met.r#L52 shrink = FALSE, m ...
R/ComBat_met.r#L68 design_data <- prepare_design_matrices ...
R/ComBat_met.r#L83 adjusted_params <- apply_shrinkage(shr ...
R/ComBat_met.r#L84 fea ...
R/helper_met.R#L10 stop("vmat must be a matrix of bet ...
R/helper_met.R#L29 if (dtype == "b-value" && (sum(vmat >= ...
R/helper_met.R#L64 cat("At least one batch contains onl ...
R/helper_met.R#L70 which(apply(vmat[, batch == b], 1, f ...
R/helper_met.R#L85 mean.only.vec <- if (mean.only) rep(TR ...
R/helper_met.R#L87 return(list(vmatOri = vmatOri, vmat = ...
R/helper_met.R#L91 prepare_design_matrices <- function(batc ...
R/helper_met.R#L120 stop("Reference level ref. batch i ...
R/helper_met.R#L132 cat("Adjusting for", ncol(design) - nc ...
R/helper_met.R#L138 return(list(design = design, batchmod ...
R/helper_met.R#L144 stop("The covariate is confounded wi ...
R/helper_met.R#L148 stop('The covariates are confounde ...
R/helper_met.R#L151 stop("At least one covariate is co ...
R/helper_met.R#L180 result_lst <- run_parallel_estimation( ...
R/helper_met.R#L210 run_parallel_estimation <- function(cl, ...
R/helper_met.R#L212 parallel::clusterExport(cl, varlist = ...
R/helper_met.R#L229 estimate_single_feature <- function(k, b ...
R/helper_met.R#L231 result<- list(gamma_hat = NULL, mu_hat ...
R/helper_met.R#L239 variance_check <- check_model_variance ...
R/helper_met.R#L244 glm_fit <- fit_glm_model(k, bv, design ...
R/helper_met.R#L252 calculate_parameters(glm_fit, n_batch, ...
R/helper_met.R#L264 result = list(gamma_hat ...
R/helper_met.R#L265 zero_modva ...
R/helper_met.R#L279 result = list(gamma_hat ...
R/helper_met.R#L280 zero_modva ...
R/helper_met.R#L283 # if precision correction enabled, che ...
R/helper_met.R#L286 if (qr(full_mat[intersect(batches_ ...
R/helper_met.R#L289 result = list(gamma_ ...
R/helper_met.R#L290 zero_m ...
R/helper_met.R#L318 calculate_parameters <- function(glm_f, ...
R/helper_met.R#L320 result <- list(gamma_hat = NULL, mu_ha ...
R/helper_met.R#L323 # compute mean and precision intercept ...
R/helper_met.R#L365 n_zero_modvar_batch <- sum(unlist(lapp ...
R/helper_met.R#L396 cat(sprintf("Found %s features with ...
R/helper_met.R#L404 feature.subs ...
R/helper_met.R#L418 invisible(utils::capture.output( ...
R/helper_met.R#L419 ...
R/helper_met.R#L420 ...
R/helper_met.R#L421 ...
R/helper_met.R#L422 ...
R/helper_met.R#L423 ...
R/helper_met.R#L435 ## set gamma and delta equal to 0 fo ...
R/helper_met.R#L460 monte_carlo_int_beta <- function(dat, mu ...
R/helper_met.R#L474 if (!is.null(feature.subset.n) & is. ...
R/helper_met.R#L527 logit_mu_star_subset <- log(mu_hat_m ...
R/helper_met.R#L529 mu_star_mat[, batches_ind[[jj]]] <- ...
R/helper_met.R#L568 tmp_p <- stats::pbeta(bv_sub[a, b] ...
R/helper_met.R#L573 new_bv_sub[a, b] <- stats::qbeta ...
R/helper_met.R#R/sva-package.R#L3 #' sva has functionality to estimate and ...
R/sva-package.R#L4 #' the \code{\link{sva}} function can be ...
R/sva-package.R#L5 #' the \code{\link{svaseq}} function can ...
R/sva-package.R#L6 #' RNA-sequencing (and other sequencing) ...
R/sva-package.R#L7 #' used to remove known batch effecs fro ...
R/sva-package.R#L11 #' A vignette is available by typing \co ...
R/sva-package.R#L13 #' @references For the package: Leek JT, ...
R/sva-package.R#L14 #' @references For sva: Leek JT and Stor ...
R/sva-package.R#L15 #' @references For sva: Leek JT and Stor ...
R/sva-package.R#L16 #' @references For Combat: Johnson WE, L ...
R/sva-package.R#L17 #' @references For svaseq: Leek JT (2014 ...
R/sva-package.R#L18 #' @references For fsva: Parker HS, Brav ...
R/sva-package.R#L19 #' @references For psva: Parker HS, Leek ...
R/sva-package.R#L22 #' @author Jeffrey T. Leek, W. Evan John ...L574 ...
R/Mvalue_ComBat.R#L1 #' Adjust for batch effects in DNA methy ...
R/
Mvalue_ComBat.R#L4 #' adjusts M-values for batch effects us ...
R/Mvalue_ComBat.R#L6 #' Forward and reverse logit-transformat ...
R/Mvalue_ComBat.R#L10 #' @return \code{Mvalue_ComBat} returns ...
R/sva-package.R#L3 #' sva has functionality to estimate and ...
R/sva-package.R#L4 #' the \code{\link{sva}} function can be ...
R/sva-package.R#L5 #' the \code{\link{svaseq}} function can ...
R/sva-package.R#L6 #' RNA-sequencing (and other sequencing) ...
R/sva-package.R#L7 #' used to remove known batch effecs fro ...
R/sva-package.R#L11 #' A vignette is available by typing \co ...
R/sva-package.R#L13 #' @references For the package: Leek JT, ...
R/sva-package.R#L14 #' @references For sva: Leek JT and Stor ...
R/sva-package.R#L15 #' @references For sva: Leek JT and Stor ...
R/sva-package.R#L16 #' @references For Combat: Johnson WE, L ...
R/sva-package.R#L17 #' @references For svaseq: Leek JT (2014 ...
R/sva-package.R#L18 #' @references For fsva: Parker HS, Brav ...
R/sva-package.R#L19 #' @references For psva: Parker HS, Leek ...
R/sva-package.R#L22 #' @author Jeffrey T. Leek, W. Evan John ...
vignettes/sva.Rnw#L17 \title{The SVA package for removing batc ...
vignettes/sva.Rnw#L18 \author{Jeffrey Leek$^1$*, W. Evan Johns ...
vignettes/sva.Rnw#L30 The \Rpackage{sva} package contains func ...
vignettes/sva.Rnw#L32 The \Rpackage{sva} package can be used t ...
vignettes/sva.Rnw#L36 Batch effects are sub-groups of measurem ...
vignettes/sva.Rnw#L38 The \Rpackage{sva} package includes the ...
vignettes/sva.Rnw#L40 This document provides a tutorial for us ...
vignettes/sva.Rnw#L42 As with any R package, detailed informat ...
vignettes/sva.Rnw#L54 The first step in using the \Rpackage{sv ...
vignettes/sva.Rnw#L56 Two model matrices must be made: the f ... vignettes/sva.Rnw#L61 For the bladder cancer study, the variab ... vignettes/sva.Rnw#L65 The expression data can be obtained from ... vignettes/sva.Rnw#L71 Next we create the full model matrix - i ... vignettes/sva.Rnw#L77 The null model contains only the adjustm ... vignettes/sva.Rnw#L82 Now that the model matrices have been cr ... vignettes/sva.Rnw#L84 \section{Applying the \Rfunction{sva} fu ... vignettes/sva.Rnw#L86 The \Rfunction{sva} function performs tw ... vignettes/sva.Rnw#L99 The \Rfunction{sva} function returns a l ... vignettes/sva.Rnw#L101 \section{Adjusting for surrogate variabl ... vignettes/sva.Rnw#L103 The \Rfunction{f.pvalue} function can be ... vignettes/sva.Rnw#L110 Note that nearly 70\% of the genes are s ... vignettes/sva.Rnw#L120 Now these are the adjusted P-values and ... vignettes/sva.Rnw#L124 The \Rpackage{limma} package is one of t ... vignettes/sva.Rnw#L130 From here, you can use the \Rpackage{lim ... vignettes/sva.Rnw#L133 contrast.matrix <- cbind("C1"=c(-1,1,0,r ... vignettes/sva.Rnw#L137 The next step is to calculate the test s ... vignettes/sva.Rnw#L147 The \Rfunction{ComBat} function adjusts ... vignettes/sva.Rnw#L153 Just as with \Rfunction{sva}, we then ne ... vignettes/sva.Rnw#L159 Note that adjustment variables will be t ... vignettes/sva.Rnw#L161 We now apply the \Rfunction{ComBat} func ... vignettes/sva.Rnw#L164 combat_edata = ComBat(dat=edata, batch=b ... vignettes/sva.Rnw#L167 This returns an expression matrix, with ... vignettes/sva.Rnw#L174 These P-values and Q-values now account ... vignettes/sva.Rnw#L176 There are a few additional options for t ... vignettes/sva.Rnw#L178 Also, we have now added the \texttt{mean ... vignettes/sva.Rnw#L180 Finally, we have now added a \texttt{ref ... vignettes/sva.Rnw#L181 When using the \texttt{mean.only=TRUE} o ... vignettes/sva.Rnw#L186 ComBat-Seq is an improved model based on ... vignettes/sva.Rnw#L196 In ComBat-Seq, user may specify biologic ... vignettes/sva.Rnw#L204 If users wish to specify multiple biolog ... vignettes/sva.Rnw#L217 Direct adjustment for batch effects can ... vignettes/sva.Rnw#L228 The goal of the \Rfunction{sva} is to re ... vignettes/sva.Rnw#L230 In some cases, the latent variables may ... vignettes/sva.Rnw#L232 In contrast, direct adjustment only remo ... vignettes/sva.Rnw#L236 \section{Variance filtering to speed com ... vignettes/sva.Rnw#L238 When the number of features is very larg ... vignettes/sva.Rnw#L246 \section{Applying the \Rfunction{fsva} f ... vignettes/sva.Rnw#L248 The surrogate variable analysis function ... vignettes/sva.Rnw#L250 Frozen'' surrogate variable analysis c ...
vignettes/sva.Rnw#L264 Using these data sets, the \Rpackage{pam ...
vignettes/sva.Rnw#L272 Next, the \Rfunction{sva} function can b ...
vignettes/sva.Rnw#L280 The \Rfunction{fsva} function can be use ...
vignettes/sva.Rnw#L292 In our original work we used the identif ...
vignettes/sva.Rnw#L294 First we set up the data by filtering lo ...
vignettes/sva.Rnw#L307 Now we can apply svaseq to estimate the ...
vignettes/sva.Rnw#L321 In our original work we introduced an al ...
vignettes/sva.Rnw#L328 Here we passed the controls argument, wh ...
vignettes/sva.Rnw#L332 The sva package includes multiple differ ...
vignettes/sva.Rnw#L337 \item Leek JT, Johnson WE, Parker HS, Ja ...
vignettes/sva.Rnw#L342 \item Leek JT and Storey JD. (2008) A ge ...
vignettes/sva.Rnw#L343 \item Leek JT and Storey JD. (2007) Capt ...
vignettes/sva.Rnw#L349 \item Johnson WE, Li C, Rabinovic A (200 ...
vignettes/sva.Rnw#L355 \item Zhang, Y., Jenkins, D. F., Manimar ...
vignettes/sva.Rnw#L361 \item Leek JT (2014) svaseq: removing ba ...
vignettes/sva.Rnw#L367 \item Leek JT (2014) svaseq: removing ba ...
vignettes/sva.Rnw#L368 \item Gagnon-Bartsch JA, Speed TP (2012) ...
vignettes/sva.Rnw#L374 \item Parker HS, Bravo HC, Leek JT (2013 ...
vignettes/sva.Rnw#L380 \item Parker HS, Leek JT, Favorov AV, Co ...

Consider multiples of 4 spaces for line indents; 855 lines (29%) are not.
First few lines:
R/ComBat_met.r#L51 batch, group = NU ...
R/ComBat_met.r#L52 shrink = FALSE, m ...
R/ComBat_met.r#L53 pseudo_beta = 1e- ...
R/ComBat_met.r#L54 # Preparation ...
R/ComBat_met.r#L55 validated <- validate_inputs(vmat, dty ...
R/ComBat_met.r#L56 vmat <- validated$vmat ...
R/ComBat_met.r#L57 batch <- validated$batch ...
R/ComBat_met.r#L58 group <- validated$group ...
R/ComBat_met.r#L60 # Handle extreme values and uniform fe ...
R/ComBat_met.r#L61 processed <- preprocess_data(vmat, dty ...
R/ComBat_met.r#L62 vmatOri <- processed$vmatOri ...
R/ComBat_met.r#L63 vmat <- processed$vmat ...
R/ComBat_met.r#L64 keep <- processed$keep ...
R/ComBat_met.r#L65 mean.only.vec <- processed$mean.only.v ...
R/ComBat_met.r#L67 # Prepare design matrices ...
R/ComBat_met.r#L68 design_data <- prepare_design_matrices ...
R/ComBat_met.r#L69 design <- design_data$design ...
R/ComBat_met.r#L70 batchmod <- design_data$batchmod ...
R/ComBat_met.r#L71 n_batch <- design_data$n_batch ...
R/ComBat_met.r#L72 batches_ind <- design_data$batches_ind ...
R/ComBat_met.r#L73 ref <- design_data$ref ...
R/ComBat_met.r#L75 # Convert to beta values if needed ...
R/ComBat_met.r#L76 bv <- convert_to_beta_values(vmat, dty ...
R/ComBat_met.r#L78 # Estimate parameters ...
R/ComBat_met.r#L79 params <- estimate_parameters(bv, desi ...
R/ComBat_met.r#L82 # Apply shrinkage if requqested ...
R/ComBat_met.r#L83 adjusted_params <- apply_shrinkage(shr ...
R/ComBat_met.r#L84 fea ...
R/ComBat_met.r#L86 # Adjust the data ...
R/ComBat_met.r#L87 adj_vmat <- adjust_data(vmatOri, dtype ...
R/ComBat_met.r#L88 batches_ind, m ...
R/ComBat_met.r#L90 return(adj_vmat) ...
R/helper_met.R#L4 ## check if vmat has the correct forma ...
R/helper_met.R#L5 if (!(is.matrix(vmat) && is.numeric(vm ...
R/helper_met.R#L7 vmat <- as.matrix(vmat) ...
R/helper_met.R#L8 cat("Input is numeric.\n") ...
R/helper_met.R#L10 stop("vmat must be a matrix of bet ...
R/helper_met.R#L12 } ...
R/helper_met.R#L13 ...
R/helper_met.R#L14 ## check if pseudo-beta values are val ...
R/helper_met.R#L15 if (dtype == "b-value" && (pseudo_beta ...
R/helper_met.R#L17 } ...
R/helper_met.R#L18 ...
R/helper_met.R#L19 ## check if coverage matrix, batch, an ...
R/helper_met.R#L20 if (ncol(vmat) != length(batch)) { ...
R/helper_met.R#L22 } ...
R/helper_met.R#L23 ...
R/helper_met.R#L24 if (!is.null(group) && ncol(vmat) != l ...
R/helper_met.R#L26 } ...
R/helper_met.R#L27 ...
R/helper_met.R#L28 ## Does not allow beta values outside ...
R/helper_met.R#L29 if (dtype == "b-value" && (sum(vmat >= ...
R/helper_met.R#L31 } ...
R/helper_met.R#L32 ...
R/helper_met.R#L33 ## check if batch is valid ...
R/helper_met.R#L34 if (length(dim(batch)) > 1) { ...
R/helper_met.R#L36 } ...
R/helper_met.R#L37 ...
R/helper_met.R#L38 batch <- as.factor(batch) ...
R/helper_met.R#L39 if (all(table(batch) <= 1)) { ...
R/helper_met.R#L41 } ...
R/helper_met.R#L42 ...
R/helper_met.R#L43 if (length(levels(batch)) <= 1) { ...
R/helper_met.R#L45 } ...
R/helper_met.R#L46 ...
R/helper_met.R#L47 if (!is.null(group)) { ...
R/helper_met.R#L49 } ...
R/helper_met.R#L50 ...
R/helper_met.R#L51 return(list(vmat = vmat, batch = batch ...
R/helper_met.R#L56 ## convert extreme 0 or 1 values to ps ...
R/helper_met.R#L57 if (dtype == "b-value") { ...
R/helper_met.R#L60 } ...
R/helper_met.R#L61 ...
R/helper_met.R#L62 ## Correct for mean batch effects only ...
R/helper_met.R#L63 if (any(table(batch) == 1)) { ...
R/helper_met.R#L66 } ...
R/helper_met.R#L67 ...
R/helper_met.R#L68 ## Remove features with zero variance ...
R/helper_met.R#L69 zero.var.rows.lst <- lapply(levels(bat ...
R/helper_met.R#L71 }) ...
R/helper_met.R#L72 all.zero.var.rows <- Reduce(intersect, ...
R/helper_met.R#L73 ...
R/helper_met.R#L74 if (length(all.zero.var.rows) > 0) { ...
R/helper_met.R#L78 } ...
R/helper_met.R#L79 ...
R/helper_met.R#L80 keep <- setdiff(1:nrow(vmat), all.zero ...
R/helper_met.R#L81 vmatOri <- vmat ...
R/helper_met.R#L82 vmat <- vmatOri[keep, ] ...
R/helper_met.R#L83 ...
R/helper_met.R#L84 ## Create a vector for correction type ...
R/helper_met.R#L85 mean.only.vec <- if (mean.only) rep(TR ...
R/helper_met.R#L86 ...
R/helper_met.R#L87 return(list(vmatOri = vmatOri, vmat = ...
R/helper_met.R#L92 # number of batches ...
R/helper_met.R#L93 n_batch <- nlevels(batch) ...
R/helper_met.R#L94 # list of samples in each batch ...
R/helper_met.R#L95 batches_ind <- lapply(1:n_batch, funct ...
R/helper_met.R#L97 }) ...
R/helper_met.R#L99 # biological condition matrix ...
R/helper_met.R#L100 if (full_mod & !is.null(group) & nleve ...
R/helper_met.R#L103 } else { ...
R/helper_met.R#L106 } ...
R/helper_met.R#L107 # covariate matrix ...
R/helper_met.R#L108 if (!is.null(covar_mod)) { ...
R/helper_met.R#L110 covar_mod <- do.call(cbind, lapply ...
R/helper_met.R#L112 })) ...
R/helper_met.R#L114 } ...
R/helper_met.R#L115 # combine covariate matrix with biolog ...
R/helper_met.R#L116 mod <- cbind(mod, covar_mod) ...
R/helper_met.R#L117 batchmod <- stats::model.matrix(~-1 + ...
R/helper_met.R#L118 if (!is.null(ref.batch)) { ...
R/helper_met.R#L120 stop("Reference level ref. batch i ...
R/helper_met.R#L124 } else { ...
R/helper_met.R#L126 } ...
R/helper_met.R#L127 ...
R/helper_met.R#L128 design <- cbind(batchmod, mod) ...
R/helper_met.R#L129 ## Check for intercept in covariates, ...
R/helper_met.R#L130 check <- apply(design, 2, function(x) ...
R/helper_met.R#L131 design <- as.matrix(design[, !check]) ...
R/helper_met.R#L132 cat("Adjusting for", ncol(design) - nc ...
R/helper_met.R#L133 ...
R/helper_met.R#L134 if (qr(design)$rank < ncol(design)) { ...
R/helper_met.R#L136 } ...
R/helper_met.R#L137 ...
R/helper_met.R#L138 return(list(design = design, batchmod ...
R/helper_met.R#L143 if (ncol(design) == (n_batch+1)) { ...
R/helper_met.R#L145 } ...
R/helper_met.R#L146 if (ncol(design) > (n_batch+1)) { ...
R/helper_met.R#L148 stop('The covariates are confounde ...
R/helper_met.R#L149 so the design is not confou ...
R/helper_met.R#L151 stop("At least one covariate is co ...
R/helper_met.R#L152 covariates and rerun ComBat ...
R/helper_met.R#L154 } ...
R/helper_met.R#L159 ## convert M-values to beta-values if ...
R/helper_met.R#L160 if (dtype == "b-value") { ...
R/helper_met.R#L162 } else { ...
R/helper_met.R#L164 } ...
R/helper_met.R#L170 cat("Fitting the GLM model\n") ...
R/helper_met.R#L171 ...
R/helper_met.R#L172 # Validate ncores ...
R/helper_met.R#L173 validate_ncores(ncores) ...
R/helper_met.R#L174 ...
R/helper_met.R#L175 # Set up parallel processing ...
R/helper_met.R#L176 cl <- setup_parallel_processing(ncores ...
R/helper_met.R#L177 on.exit(parallel::stopCluster(cl)) ...
R/helper_met.R#L178 ...
R/helper_met.R#L179 # Run parameter estimation in parallel ...
R/helper_met.R#L180 result_lst <- run_parallel_estimation( ...
R/helper_met.R#L182 ...
R/helper_met.R#L183 # Process and summarize results ...
R/helper_met.R#L184 processed_results <- process_estimatio ...
R/helper_met.R#L185 ...
R/helper_met.R#L186 # Report any issues found ...
R/helper_met.R#L187 report_estimation_issues(processed_res ...
R/helper_met.R#L188 processed_res ...
R/helper_met.R#L189 processed_res ...
R/helper_met.R#L190 mean.only.vec ...
R/helper_met.R#L191 ...
R/helper_met.R#L192 return(processed_results) ...
R/helper_met.R#L197 if (!is.numeric(ncores) || ncores != a ...
R/helper_met.R#L199 } ...
R/helper_met.R#L204 num_cores <- max(1, parallel::detectCo ...
R/helper_met.R#L205 num_cores <- min(ncores, num_cores) ...
R/helper_met.R#L206 parallel::makeCluster(num_cores) ...
R/helper_met.R#L212 parallel::clusterExport(cl, varlist = ...
R/helper_met.R#L213 ...
R/helper_met.R#L214 ...
R/helper_met.R#L215 ...
R/helper_met.R#L216 ...
R/helper_met.R#L217 ...
R/helper_met.R#L218 ...
R/helper_met.R#L219 envir = enviro ...
R/helper_met.R#L220 ...
R/helper_met.R#L221 # run in parallel ...
R/helper_met.R#L222 parallel::parLapply(cl, 1:nrow(bv), fu ...
R/helper_met.R#L225 }) ...
R/helper_met.R#L231 result<- list(gamma_hat = NULL, mu_hat ...
R/helper_met.R#L233 ...
R/helper_met.R#L234 # Check for NA values ...
R/helper_met.R#L235 na_check <- check_na_values(k, design, ...
R/helper_met.R#L236 if (na_check$has_issue) return(na_chec ...
R/helper_met.R#L237 ...
R/helper_met.R#L238 # Check model variance ...
R/helper_met.R#L239 variance_check <- check_model_variance ...
R/helper_met.R#L240 ...
R/helper_met.R#L241 if (variance_check$has_issue) return(v ...
R/helper_met.R#L242 ...
R/helper_met.R#L243 # Fit GLM ...
R/helper_met.R#L244 glm_fit <- fit_glm_model(k, bv, design ...
R/helper_met.R#L245 # if error with model fitting ...
R/helper_met.R#L246 if (inherits(glm_fit, "error")) { ...
R/helper_met.R#L249 } ...
R/helper_met.R#L250 ...
R/helper_met.R#L251 # Calculate parameters ...
R/helper_met.R#L252 calculate_parameters(glm_fit, n_batch, ...
R/helper_met.R#L257 # mark rows with NA values ...
R/helper_met.R#L258 full_mat <- cbind(design, bv[k, ]) ...
R/helper_met.R#L259 nona <- which(stats::complete.cases(fu ...
R/helper_met.R#L260 ...
R/helper_met.R#L261 # check if the data are all NAs ...
R/helper_met.R#L262 if (length(nona) == 0) { ...
R/helper_met.R#L265 zero_modva ...
R/helper_met.R#L266 } ...
R/helper_met.R#L267 ...
R/helper_met.R#L268 list(has_issue = FALSE, nona = nona) ...
R/helper_met.R#L273 mean.on ...
R/helper_met.R#L274 full_mat <- cbind(design, bv[k, ]) ...
R/helper_met.R#L275 ...
R/helper_met.R#L276 # check if the model has zero model va ...
R/helper_met.R#L277 if (qr(full_mat[nona, ])$rank < ncol(f ...
R/helper_met.R#L280 zero_modva ...
R/helper_met.R#L281 } ...
R/helper_met.R#L282 ...
R/helper_met.R#L283 # if precision correction enabled, che ...
R/helper_met.R#L284 if (!mean.only.vec[k]) { ...
R/helper_met.R#L286 if (qr(full_mat[intersect(batches_ ...
R/helper_met.R#L287 ncol(full_mat) - n_batch + 1) ...
R/helper_met.R#L290 zero_m ...
R/helper_met.R#L291 } ...
R/helper_met.R#L293 } ...
R/helper_met.R#L294 ...
R/helper_met.R#L295 list(has_issue = FALSE) ...
R/helper_met.R#L300 # model fit ...
R/helper_met.R#L301 if (mean.only.vec[k]) { ...
R/helper_met.R#L303 betareg::betareg.fit(x = design[no ...
R/helper_met.R#L305 e ...
R/helper_met.R#L307 } else { ...
R/helper_met.R#L309 betareg::betareg.fit(x = design[no ...
R/helper_met.R#L310 z = batchmod[ ...
R/helper_met.R#L312 e ...
R/helper_met.R#L314 } ...
R/helper_met.R#L319 tmp.mea ...
R/helper_met.R#L320 result <- list(gamma_hat = NULL, mu_ha ...
R/helper_met.R#L321 zero_modvar = 0, zero_m ...
R/helper_met.R#L322 ...
R/helper_met.R#L323 # compute mean and precision intercept ...
R/helper_met.R#L324 if (!is.null(ref.batch)) { ...
R/helper_met.R#L326 } else { ...
R/helper_met.R#L328 as.matrix(colSums(batchmod[nona, ] ...
R/helper_met.R#L329 } ...
R/helper_met.R#L330 ...
R/helper_met.R#L331 if (tmp.mean.only) { ...
R/helper_met.R#L333 } else { ...
R/helper_met.R#L335 alpha_z <- glm_f$coefficients$prec ...
R/helper_met.R#L337 alpha_z <- glm_f$coefficients$prec ...
R/helper_met.R#L340 } ...
R/helper_met.R#L341 ...
R/helper_met.R#L342 # estimate parameters ...
R/helper_met.R#L343 result$gamma_hat <- glm_f$coefficients ...
R/helper_met.R#L344 result$mu_hat <- rep(NA, nrow(batchmod ...
R/helper_met.R#L345 result$mu_hat[nona] <- glm_f$fitted.va ...
R/helper_met.R#L346 result$phi_hat <- as.numeric(exp(alpha ...
R/helper_met.R#L347 ...
R/helper_met.R#L348 if (tmp.mean.only) { ...
R/helper_met.R#L350 } else { ...
R/helper_met.R#L352 } ...
R/helper_met.R#L353 ...
R/helper_met.R#L354 result ...
R/helper_met.R#L359 gamma_hat_lst <- lapply(result_lst, fu ...
R/helper_met.R#L360 mu_hat_lst <- lapply(result_lst, funct ...
R/helper_met.R#L361 phi_hat_lst <- lapply(result_lst, func ...
R/helper_met.R#L362 delta_hat_lst <- lapply(result_lst, fu ...
R/helper_met.R#L363 ...
R/helper_met.R#L364 n_zero_modvar <- sum(unlist(lapply(res ...
R/helper_met.R#L365 n_zero_modvar_batch <- sum(unlist(lapp ...
R/helper_met.R#L366 n_moderr <- sum(unlist(lapply(result_l ...
R/helper_met.R#L367 ...
R/helper_met.R#L368 # convert NULLs to NAs ...
R/helper_met.R#L369 gamma_hat_lst[sapply(gamma_hat_lst, is ...
R/helper_met.R#L370 mu_hat_lst[sapply(mu_hat_lst, is.null) ...
R/helper_met.R#L371 phi_hat_lst[sapply(phi_hat_lst, is.nul ...
R/helper_met.R#L372 delta_hat_lst[sapply(delta_hat_lst, is ...
R/helper_met.R#L373 ...
R/helper_met.R#L374 # reformat lists as matrices ...
R/helper_met.R#L375 list( ...
R/helper_met.R#L383 ) ...
R/helper_met.R#L388 n_m ...
R/helper_met.R#L389 cat(sprintf("Found %s features with ze ...
R/helper_met.R#L390 these features won't be ad ...
R/helper_met.R#L391 n_zero_modvar)) ...
R/helper_met.R#L392 cat(sprintf("Errors encountered in %s ...
R/helper_met.R#L393 these features won't be ad ...
R/helper_met.R#L394 n_moderr)) ...
R/helper_met.R#L395 if (!all(mean.only.vec)) { ...
R/helper_met.R#L399 } ...
R/helper_met.R#L405 if (shrink) { ...
R/helper_met.R#L409 if (ii == 1) { ...
R/helper_met.R#L411 mu = params$m ...
R/helper_met.R#L412 gamma = param ...
R/helper_met.R#L413 phi = params$ ...
R/helper_met.R#L414 delta = param ...
R/helper_met.R#L415 feature.subse ...
R/helper_met.R#L416 ncores = ncor ...
R/helper_met.R#L417 } else { ...
R/helper_met.R#L419 ...
R/helper_met.R#L420 ...
R/helper_met.R#L421 ...
R/helper_met.R#L422 ...
R/helper_met.R#L423 ...
R/helper_met.R#L424 ...
R/helper_met.R#L425 } ...
R/helper_met.R#L426 return(mcres) ...
R/helper_met.R#L437 gamma_star_mat[, ref] <- 0 ...
R/helper_met.R#L438 delta_star_mat[, ref] <- 0 ...
R/helper_met.R#L442 cat("Apply shrinkage to mean only\ ...
R/helper_met.R#L443 delta_star_mat <- params$delta_hat ...
R/helper_met.R#L445 } else { ...
R/helper_met.R#L449 } ...
R/helper_met.R#L450 ...
R/helper_met.R#L451 return(list(gamma_star_mat = gamma_sta ...
R/helper_met.R#L456 return(matrix(rep(vec, n_times), ncol ...
R/helper_met.R#L461 cl <- parallel::makeCluster(ncores) ...
R/helper_met.R#L462 ...
R/helper_met.R#L463 MC_int <- function(i) { ...
R/helper_met.R#L465 delta.star = NA) ...
R/helper_met.R#L475 mcint_ind <- sample(1:(nrow(dat) - ...
R/helper_met.R#L476 m <- m[mcint_ind, ] ...
R/helper_met.R#L477 p <- p[mcint_ind, ] ...
R/helper_met.R#L478 gamma_sub <- gamma_sub[mcint_ind] ...
R/helper_met.R#L479 delta_sub <- delta_sub[mcint_ind] ...
R/helper_met.R#L480 G_sub <- feature.subset.n ...
R/helper_met.R#L482 G_sub <- nrow(dat) - 1 ...
R/helper_met.R#L486 prod(stats::dbeta(x, shape1 = m[j, ...
R/helper_met.R#L491 pos_res <- c(gamma.star = as.numer ...
R/helper_met.R#L492 delta.star = as.numer ...
R/helper_met.R#L494 pos_res["gamma.star"] <- sum(gamma ...
R/helper_met.R#L496 pos_res["delta.star"] <- sum(delta ...
R/helper_met.R#L500 } ...
R/helper_met.R#L501 ...
R/helper_met.R#L502 # run in parallel ...
R/helper_met.R#L503 pos_res_lst <- parallel::parLapply(cl, ...
R/helper_met.R#L504 parallel::stopCluster(cl) ...
R/helper_met.R#L505 pos_res_mat <- do.call(rbind, pos_res_ ...
R/helper_met.R#L506 res <- list(gamma_star = pos_res_mat[, ...
R/helper_met.R#L507 delta_star = pos_res_mat[, ...
R/helper_met.R#L508 return(res) ...
R/helper_met.R#L514 gamma_star_mat <- adjusted_params$gamm ...
R/helper_met.R#L515 delta_star_mat <- adjusted_params$delt ...
R/helper_met.R#L516 mu_hat_mat <- params$mu_hat_mat ...
R/helper_met.R#L517 phi_hat_mat <- params$phi_hat_mat ...
R/helper_met.R#L518 delta_hat_mat <- params$delta_hat_mat ...
R/helper_met.R#L519 ...
R/helper_met.R#L520 n_batch <- length(batches_ind) ...
R/helper_met.R#L521 n_batches <- sapply(batches_ind, lengt ...
R/helper_met.R#L522 ...
R/helper_met.R#L523 mu_star_mat <- matrix(NA, nrow = nrow( ...
R/helper_met.R#L524 phi_star_mat <- phi_hat_mat ...
R/helper_met.R#L525 ...
R/helper_met.R#L526 for (jj in 1:n_batch) { ...
R/helper_met.R#L528 vec2mat_met(gamma_star_mat[, jj], ...
R/helper_met.R#L531 log_phi_star_subset <- log(phi_hat ...
R/helper_met.R#L534 phi_star_mat[, batches_ind[[jj]]] ...
R/helper_met.R#L536 } ...
R/helper_met.R#L537 ...
R/helper_met.R#L538 cat("Adjusting the data\n") ...
R/helper_met.R#L539 adj_bv_raw <- matrix(NA, nrow = nrow(b ...
R/helper_met.R#L540 for (kk in 1:n_batch) { ...
R/helper_met.R#L551 } ...
R/helper_met.R#L552 ...
R/helper_met.R#L553 if (dtype == "b-value") { ...
R/helper_met.R#L556 } else { ...
R/helper_met.R#L559 } ...
R/helper_met.R#L560 return(adj_vmat) ...
R/helper_met.R#L565 new_bv_sub <- matrix(NA, nrow = nrow(b ...
R/helper_met.R#L566 for (a in 1:nrow(bv_sub)) { ...
R/helper_met.R#L568 tmp_p <- stats::pbeta(bv_sub[a, b] ...
R/helper_met.R#L570 if (is.na(tmp_p)) { ...
R/helper_met.R#L572 } else { ...
R/helper_met.R#L574 ...
R/helper_met.R#L575 } ...
R/helper_met.R#L577 } ...
R/helper_met.R#L578 return(new_bv_sub) ...
R/Mvalue_ComBat.R#L40 batch, group = ...
R/Mvalue_ComBat.R#L41 covar_mod = NU ...
R/Mvalue_ComBat.R#L42 mean.only = FA ...
R/Mvalue_ComBat.R#L43 ref.batch = NU ...
R/Mvalue_ComBat.R#L44 ## convert extreme 0 or 1 values to ps ...
R/Mvalue_ComBat.R#L45 if (dtype == "b-value") { ...
R/Mvalue_ComBat.R#L47 stop("Invalid pseudo beta-values." ...
R/Mvalue_ComBat.R#L51 } ...
R/Mvalue_ComBat.R#L52 ...
R/Mvalue_ComBat.R#L53 ## convert beta values to M values if ...
R/Mvalue_ComBat.R#L54 if (dtype == "b-value") { ...
R/Mvalue_ComBat.R#L56 } else { ...
R/Mvalue_ComBat.R#L58 } ...
R/Mvalue_ComBat.R#L59 ...
R/Mvalue_ComBat.R#L60 ## construct the model matrix ...
R/Mvalue_ComBat.R#L61 mod <- covar_mod ...
R/Mvalue_ComBat.R#L62 if (full_mod) { ...
R/Mvalue_ComBat.R#L64 } ...
R/Mvalue_ComBat.R#L65 ...
R/Mvalue_ComBat.R#L66 ## run ComBat ...
R/Mvalue_ComBat.R#L67 if (mean.only) { ...
R/Mvalue_ComBat.R#L69 par.prior = TRUE, r ...
R/Mvalue_ComBat.R#L70 } else { ...
R/Mvalue_ComBat.R#L72 par.prior = TRUE, r ...
R/Mvalue_ComBat.R#L73 } ...
R/Mvalue_ComBat.R#L74 ...
R/Mvalue_ComBat.R#L75 ## convert adjusted M values back to b ...
R/Mvalue_ComBat.R#L76 if (dtype == "b-value") { ...
R/Mvalue_ComBat.R#L78 } else { ...
R/Mvalue_ComBat.R#L80 } ...
R/Mvalue_ComBat.R#L81 return(adj_vmat) ...
vignettes/sva.Rnw#L190 nrow=50, ncol=8) ...
vignettes/sva.Rnw#L195 ...
vignettes/sva.Rnw#L201 group=grou ...
vignettes/sva.Rnw#L203 ...
vignettes/sva.Rnw#L211 group=NULL ...
vignettes/sva.Rnw#L213 ...