Changes in version 1.0.6 o associations of metavariables found to be fully reducible to the supplied random/fixed effects allone are now removed from list potential confounders of other metavariables associated to the same feature. o instabilities resulting from parallel processing within an Rstudio GUI on Unix systems have been adressed Changes in version 1.0.5 (2026-02-04) o "confounded confounders" will now be removed from the status label of a confounded variable. o Example: If the association of D with feature Y is confounded by C1 and C2, but the association of C1 with Y is in turn confounded by C2, then only C2 will be listed as confounder of Y~D o improvments in some logging messages o featureMat is now checked for non-numeric columns at start-up. Changes in version 1.0.4 o MetaDeconfound() o improved error handling for glms/glmers whith highly collinear metavariables o bugfix in confidence interval calculations o bugfix for ncol(fatureMat) == 1 o new optional input argument "mediationMat" o perform mediation analysis between features of featureMat and mediadtionMat, controlled for effects from variables in metaMat o features in mediationMat will not be tested for confounding effects on each other or variables from metaMat o new optinoal argument "mediationMat" o supply a second omics space to perform mediation analysis between featureMat and mediationMat o new optional argument "adjustLevel" o specify different multiple testing p-value correction approaches o 1: correct for number of features per metavariable (default) o 2: correct for number of features x number of meatavariables o 3: correct for number of features x number of mediationMat features (default when mediationMat is supllied) o BuildHeatmap() o new options "starSize" and "starNudge_y" to control size and positioning of confounding status asterisks/circles o metavariables can be split into separate groups by adding a "grounpingVar" columns to metaDeconfOutput. o this is done by default when mediationMat is supplied to MetaDeconfound() o uses facet_grid(), so output can be tweaked using "+ theme(strip.XXX)" options o BuildConfounderMap() o new plot generating function o for each feature it creates a circos plot of confounder-confounded relations between metavariables associated to this feature. o returns a list of ggraph ggplot2 plots o ggraph package must be loaded for plotting elements of the returned list. Changes in version 1.0.3 o implementation of new funtion GetPartialEfSizes() o adds partial R-squared as additional effect size metric o new output column "partial": additional variance of a feature explained by adding a metavariable to a linear (mixed effects) model containing all other metavariables associated to the feature o new output column "partialRel": proportion of explainable variance of a feature tracable to a metavariable (e.g. partialRel = 0.5 --> metavariable x can explain 50% of all explainable variance of fature y -- all other metavariables significantly associated to feature y can explain the remaining 50% of overall explainable variance of fature y) o new output column "PartialNorm": proportion of explained variance of a metavariable set in relation to maximally explainable variance (i.e. variance not explainable by all other metavariables) o bug fix of bug disabling computation of confidence intervalls of lrts o implementaion of truly linear computation mode when nnodes = 1 o additional test to filter out non trustworthy lrts in some scenarios with highly colinear metavariables o stricter tests for complete separaion when glms are computed o BuildHeatmap() o added "plotPartial" argument to choose between o "marginal": plotting naive/marginal effect sizes based on CLiff's Delta/Spearman's Rho o "partial": plotting signed partial R-squared, including an additional column showing the total explainable variance per feature o "partialRel": plotting proportion of explainable variance of a feature tracable to a metavariable o "partialNorm": plotting respective normalized partial effect size Changes in version 1.0.2 (2024-06-25) o CRAN release Changes in version 1.0.1 o fixes for CRAN resubmission Changes in version 1.0.0 o CRAN submission Changes in version 0.3.1 o reduced side effects after interrupted metadeconfoundR runs (tmp file removal) o bugfix: Qcutoff now correctly used to collect potential confounders from naive associations o improved initial input data quality control (order, problematic row-/colnames, class) o minor bugfixes in Buildheatmap() o added LogLevel argument to change verbositiy of logging Changes in version 0.3.0 o randomVar argument is now simplified: just supply character vector of metaMat variables to be treated as random effects (e.g. randomVar = c("var1", "var5")) o NEW fixedVar argument implemented: same usage as randomVar, but adds fixed effect terms to all models o implemented computational speed-up for datasets with large number of metavariables o metadeconfoundR is now compatible with Unix AND Windows operation systems o fixed a bug that lead to an error when a feature with extremely low number non-NA values was present in featureMat o improved error messaging for an error in BuildHeatmap function o addition of NEW "rawCount" mode, that runs modelling steps on not normalized/rarefied data by including totalReadCount per sample information into glm/glmer comparisons o for naive significance test and effect size calculation, rawCounts will be normalized by dividing by totalReadCount per sample o updated implementation of logistic regression mode: test for association of binary features to metavariables by setting "logistic = TRUE" o experimental NEW feature: return all computed models alongside normal Metadeconfound() output by setting collectMods = TRUE. WARNING: For now, this only works without utilizing parallel processing in the model building step. Larger datasets might take a lot of time processing. o NEW BuildHeatmap() argument "tileBordCol" sets tile border color (Default "black") o NEW BuildHeatmap() argument "reOrder" to turn on/of sorting of features and metavariables in the reulsting plot Changes in version 0.2.8 o changes in status label names and corresponding plotting behavior o reversed default color scheme for effect size plotting (red = low, blue= high) o computation of confidence intervals in model building step now default (with added OK_d label for deconfounded but doubtful associations) Changes in version 0.2.7 o improved error messages and behavior for no/low number of significant associations o can now plot results with only a single feature/and or metadata Changes in version 0.2.6 o fixed bug in legend creation of BuildHeatmap(cuneiform = TRUE), direction of association now labeled correctly Changes in version 0.2.5 o fixed bug in "keepFeature" functionality of BuildHeatmap() o fixed bug in BuildHeatmap() that resulted in incomplete removal of features showing not a single significant association o implemented speedup for runs of Metadeconfound(startStop = "naiveStop") with large number of metadata Changes in version 0.2.4 o Buildheatmap(cuneiform = TRUE) can now handle NA or zero effect sizes (added NEW symbol) Changes in version 0.2.3 o fixed bug that only occurred when metadata only has one column o implemented speedup when startStop = "naiveStop" Changes in version 0.2.2 o added functionality to BuildHeatmap() o range of shown effectsizes in using d_range parameter (set to "full" for consistent legend between plots) o range of colors used to show effect sizes can be changed using d_col o matavariables and features, that should be kept in the plot even without passing q_cutoff and d_cutoff cutoffs, can be supplied using keepMeta and keepFeature parameters Changes in version 0.2.1 o added functionality to Metadeconfound() o output can now also be generated in long format o added functionality to BuildHeatmap() o input can now also be read in long format o "human readable"" names for features and metadata can be supplied in addition to the Metadeconfound() output and will be plotted instead of "machine readable" names o slightly improved help pages Changes in version 0.2.0 o NEW function ImportLongPrior() to easily import prior knowledge of feature metadata associations present in the current dataset. o slightly improved help pages Changes in version 0.1.9 o bugfix concerning random effect variable behavior o minor aesthetic improvements in BuildHeatmap() output Changes in version 0.1.8 o introduction of global parameter "logistic" o logistic = TRUE: analyzing binary features instead of continuous using logistic regression models Changes in version 0.1.7 o bug fix in BuildHeatmap function Changes in version 0.1.2 o critical bug fixed, that resulted in greatly increased "NS" status labeling