miga-base 0.7.26.0 → 0.7.26.1

data/utils/enveomics/enveomics.R/R/utils.R

@@ -0,0 +1,50 @@
+#' Enveomics: Color Alpha
+#' 
+#' Modify alpha in a color (or vector of colors).
+#'
+#' @param col Color or vector of colors. It can be any value supported by 
+#' \code{\link[grDevices]{col2rgb}}, such as \code{darkred} or \code{#009988}.
+#' @param alpha Alpha value to add to the color, from 0 to 1.
+#'
+#' @return Returns a color or a vector of colors in \emph{hex} notation, 
+#' including \code{alpha}.
+#'
+#' @author Luis M. Rodriguez-R [aut, cre]
+#'
+#' @export
+
+enve.col.alpha <- function
+    (col,
+    alpha=1/2
+    ){
+  return(
+    apply(col2rgb(col), 2,
+      function(x) do.call(rgb, as.list(c(x[1:3]/256, alpha))) ) )
+}
+
+#' Enveomics: Truncate
+#' 
+#' Removes the \code{n} highest and lowest values from a vector, and applies
+#' summary function. The value of \code{n} is determined such that the central
+#' range is used, corresponding to the \code{f} fraction of values.
+#'
+#' @param x A vector of numbers.
+#' @param f The fraction of values to retain.
+#' @param FUN Summary function to apply to the vectors. To obtain the 
+#' truncated vector itself, use \code{c}.
+#' 
+#' @return Returns the summary \code{(FUN)} of the truncated vector.
+#' 
+#' @author Luis M. Rodriguez-R [aut, cre]
+#'
+#' @export
+
+enve.truncate <- function
+    (x,
+    f=0.95,
+    FUN=mean
+    ){
+  n <- round(length(x)*(1-f)/2)
+  y <- sort(x)[ -c(seq(1, n), seq(length(x)+1-n, length(x))) ]
+  return(FUN(y))
+}

data/utils/enveomics/enveomics.R/README.md

@@ -0,0 +1,80 @@
+# enveomics.R
+
+## Installing `enveomics.R`
+To install the latest version of `enveomics.R` uploaded to CRAN, execute in R:
+
+```R
+install.packages('enveomics.R')
+```
+
+To install the current developer version of `enveomics.R`, execute in R:
+
+```R
+install.packages('devtools')
+library('devtools')
+install_github('lmrodriguezr/enveomics', subdir='enveomics.R')
+```
+
+## Using `enveomics.R`
+To load enveomics.R, simply execute:
+
+```R
+library(enveomics.R);
+```
+
+And open help messages using any of the following commands:
+
+```R
+?enveomics.R
+?enve.barplot
+?enve.recplot2
+?enve.recplot2.compareIdentities
+?enve.recplot2.changeCutoff
+?enve.recplot2.findPeaks
+?enve.recplot2.corePeak
+?enve.recplot2.windowDepthThreshold
+?enve.recplot2.extractWindows
+?enve.recplot2.coordinates
+?enve.recplot2.seqdepth
+?enve.recplot2.ANIr
+?enve.prune.dist
+?enve.tribs
+?enve.tribs.test
+?enve.growthcurve
+?enve.col.alpha
+?enve.truncate
+```
+
+You can run some examples using these libraries in the
+[enveomics-GUI](https://github.com/lmrodriguezr/enveomics-gui).
+
+For additional information on recruitment plots, see the
+[Recruitment plots working document](https://github.com/lmrodriguezr/enveomics/blob/master/Docs/recplot2.md).
+
+## Changelog
+* 1.7.1: Improved efficiency of `enve.df2dist` about five-fold.
+* 1.7.0: Uniformized output for `enve.recplot2.extractWindows` and
+  `enve.recplot2.coordinates` to ease automation. Thanks to Tomeu Viver and
+  Roth Conrad for troubleshooting.
+* 1.6.0: Speed up in recplot2 with proper structure manipulation
+  (by: Kenji Gerhardt). Also, default value for `id.breaks` was changed from
+  300 to 60.
+* 1.5.0: Modernized documentation, now in ROxygen2 (by: Tatyana Kiryutina)
+* 1.4.4: Removes modeest library as requirement, and replaces mower peak-finder
+  initialization to median (instead of mode).
+* 1.4.2: Solved bug #36.
+* 1.4.0: New option `pos.breaks.tsv` for `enve.recplot2`.
+* 1.3.4: Gracefully handles and plots recruitment plots with insufficient data
+  to find peaks.
+* 1.3.3: New function `enve.recplot2.windowDepthThreshold`.
+* 1.3.2: New option `panel.fun` for `plot.enve.RecPlot2`.
+* 1.3.1: New function enve.truncate.
+* 1.3: Several bug fixes and new utilities for recruitment plots (recplot2).
+* 1.1.0: New function enve.growthcurve and related class enve.GrowthCurve
+  with S3 methods plot and summary.
+* 1.0.2: Fine-tuned default parameters in enve.recplot2.findPeaks and
+  solved a minor bug in enve.recplot2 that caused failures in low-coverage
+  datasets when using too many threads.
+* 1.0.1: enve.recplot2 now supports pos.breaks=0 to define a
+  bin per subject sequence.
+

data/utils/enveomics/enveomics.R/man/cash-enve.GrowthCurve-method.Rd

@@ -0,0 +1,17 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/growthcurve.R
+\docType{methods}
+\name{$,enve.GrowthCurve-method}
+\alias{$,enve.GrowthCurve-method}
+\title{Attribute accessor}
+\usage{
+\S4method{$}{enve.GrowthCurve}(x, name)
+}
+\arguments{
+\item{x}{Object}
+
+\item{name}{Attribute name}
+}
+\description{
+Attribute accessor
+}

data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2-method.Rd

@@ -0,0 +1,17 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\docType{methods}
+\name{$,enve.RecPlot2-method}
+\alias{$,enve.RecPlot2-method}
+\title{Attribute accessor}
+\usage{
+\S4method{$}{enve.RecPlot2}(x, name)
+}
+\arguments{
+\item{x}{Object}
+
+\item{name}{Attribute name}
+}
+\description{
+Attribute accessor
+}

data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2.Peak-method.Rd

@@ -0,0 +1,17 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\docType{methods}
+\name{$,enve.RecPlot2.Peak-method}
+\alias{$,enve.RecPlot2.Peak-method}
+\title{Attribute accessor}
+\usage{
+\S4method{$}{enve.RecPlot2.Peak}(x, name)
+}
+\arguments{
+\item{x}{Object}
+
+\item{name}{Attribute name}
+}
+\description{
+Attribute accessor
+}

data/utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd

@@ -0,0 +1,25 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/growthcurve.R
+\docType{class}
+\name{enve.GrowthCurve-class}
+\alias{enve.GrowthCurve-class}
+\alias{enve.GrowthCurve}
+\title{Enveomics: Growth Curve S4 Class}
+\description{
+Enve-omics representation of fitted growth curves.
+}
+\section{Slots}{
+
+\describe{
+\item{\code{design}}{\code{(array)} Experimental design of the experiment.}
+
+\item{\code{models}}{\code{(list)} Fitted growth curve models.}
+
+\item{\code{predict}}{\code{(list)} Fitted growth curve values.}
+
+\item{\code{call}}{\code{(call)} Call producing this object.}
+}}
+
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

data/utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd

@@ -0,0 +1,46 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/tribs.R
+\docType{class}
+\name{enve.TRIBS-class}
+\alias{enve.TRIBS-class}
+\alias{enve.TRIBS}
+\title{Enveomics: TRIBS S4 Class}
+\description{
+Enve-omics representation of "Transformed-space Resampling In Biased Sets
+(TRIBS)". This object represents sets of distances between objects,
+sampled nearly-uniformly at random in "distance space". Subsampling
+without selection is trivial, since both the distances space and the
+selection occur in the same transformed space. However, it's useful to
+compare randomly subsampled sets against a selected set of objects. This
+is intended to identify overdispersion or overclustering (see
+\code{\link{enve.TRIBStest}}) of a subset against the entire collection of objects
+with minimum impact of sampling biases. This object can be produced by
+\code{\link{enve.tribs}} and supports S4 methods \code{plot} and \code{summary}.
+}
+\section{Slots}{
+
+\describe{
+\item{\code{distance}}{\code{(numeric)} Centrality measurement of the distances 
+between the selected objects (without subsampling).}
+
+\item{\code{points}}{\code{(matrix)}    Position of the different objects in distance
+space.}
+
+\item{\code{distances}}{\code{(matrix)} Subsampled distances, where the rows are 
+replicates and the columns are subsampling levels.}
+
+\item{\code{spaceSize}}{\code{(numeric)} Number of objects.}
+
+\item{\code{selSize}}{\code{(numeric)} Number of selected objects.}
+
+\item{\code{dimensions}}{\code{(numeric)} Number of dimensions in the distance space.}
+
+\item{\code{subsamples}}{\code{(numeric)} Subsampling levels (as fractions, from 
+0 to 1).}
+
+\item{\code{call}}{\code{(call)} Call producing this object.}
+}}
+
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

data/utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd

@@ -0,0 +1,23 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/tribs.R
+\name{enve.TRIBS.merge}
+\alias{enve.TRIBS.merge}
+\title{Enveomics: TRIBS Merge}
+\usage{
+enve.TRIBS.merge(x, y)
+}
+\arguments{
+\item{x}{First \code{\link{enve.TRIBS}} object.}
+
+\item{y}{Second \code{\link{enve.TRIBS}} object.}
+}
+\value{
+Returns an \code{\link{enve.TRIBS}} object.
+}
+\description{
+Merges two \code{\link{enve.TRIBS}} objects generated from the same objects at
+different subsampling levels.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

data/utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd

@@ -0,0 +1,47 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/tribs.R
+\docType{class}
+\name{enve.TRIBStest-class}
+\alias{enve.TRIBStest-class}
+\alias{enve.TRIBStest}
+\title{Enveomics: TRIBS Test S4 Class}
+\description{
+Test of significance of overclustering or overdispersion in a selected
+set of objects with respect to the entire set (see \code{\link{enve.TRIBS}}). This
+object can be produced by \code{\link{enve.tribs.test}} and supports S4 methods
+\code{plot} and \code{summary}.
+}
+\section{Slots}{
+
+\describe{
+\item{\code{pval.gt}}{\code{(numeric)}
+P-value for the overdispersion test.}
+
+\item{\code{pval.lt}}{\code{(numeric)}
+P-value for the overclustering test.}
+
+\item{\code{all.dist}}{\code{(numeric)}
+Empiric PDF of distances for the entire dataset (subsampled at selection
+size).}
+
+\item{\code{sel.dist}}{\code{(numeric)}
+Empiric PDF of distances for the selected objects (without subsampling).}
+
+\item{\code{diff.dist}}{\code{(numeric)}
+Empiric PDF of the difference between \code{all.dist} and \code{sel.dist}. 
+The p-values are estimating by comparing areas in this PDF greater than and
+lesser than zero.}
+
+\item{\code{dist.mids}}{\code{(numeric)}
+Midpoints of the empiric PDFs of distances.}
+
+\item{\code{diff.mids}}{\code{(numeric)}
+Midpoints of the empiric PDF of difference of distances.}
+
+\item{\code{call}}{\code{(call)}
+Call producing this object.}
+}}
+
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

data/utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd

@@ -0,0 +1,23 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/autoprune.R
+\name{enve.__prune.iter}
+\alias{enve.__prune.iter}
+\title{Enveomics: Prune Iter (Internal Function)}
+\usage{
+enve.__prune.iter(t, dist, min_dist, quiet)
+}
+\arguments{
+\item{t}{A \strong{phylo} object}
+
+\item{dist}{Cophenetic distance matrix}
+
+\item{min_dist}{Minimum distance}
+
+\item{quiet}{If running quietly}
+}
+\description{
+Internal function for \code{\link{enve.prune.dist}}.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd

@@ -0,0 +1,23 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/autoprune.R
+\name{enve.__prune.reduce}
+\alias{enve.__prune.reduce}
+\title{Enveomics: Prune Reduce (Internal Function)}
+\usage{
+enve.__prune.reduce(t, nodes, min_dist, quiet)
+}
+\arguments{
+\item{t}{A \strong{phylo} object}
+
+\item{nodes}{Vector of nodes}
+
+\item{min_dist}{Minimum distance}
+
+\item{quiet}{If running quietly}
+}
+\description{
+Internal function for \code{\link{enve.prune.dist}}.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd

@@ -0,0 +1,32 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/tribs.R
+\name{enve.__tribs}
+\alias{enve.__tribs}
+\title{Enveomics: TRIBS - Internal Ancillary Function}
+\usage{
+enve.__tribs(rep, frx, selection, dimensions, dots, dist.method,
+  summary.fx, dist)
+}
+\arguments{
+\item{rep}{Replicates}
+
+\item{frx}{Fraction}
+
+\item{selection}{Selection}
+
+\item{dimensions}{Dimensions}
+
+\item{dots}{Sampling points}
+
+\item{dist.method}{Distance method}
+
+\item{summary.fx}{Summary function}
+
+\item{dist}{Distance}
+}
+\description{
+Internal ancillary function (see \code{\link{enve.tribs}}).
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

data/utils/enveomics/enveomics.R/man/enve.barplot.Rd

@@ -0,0 +1,91 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/barplot.R
+\name{enve.barplot}
+\alias{enve.barplot}
+\title{Enveomics: Barplot}
+\usage{
+enve.barplot(x, sizes, top = 25, colors.per.group = 9,
+  bars.width = 4, legend.ncol = 1, other.col = "#000000",
+  add.trend = FALSE, organic.trend = FALSE, sort.by = median,
+  min.report = 101, order = NULL, col, ...)
+}
+\arguments{
+\item{x}{Can be either the input data or the path to the file containing 
+the table. 
+\itemize{
+   \item{If it contains the data, it must be a data frame or an
+   object coercible to a data frame.} 
+   \item{If it is a path, it must point to a
+   tab-delimited file containing a header (first row) and row names 
+   (first column).}
+   }}
+
+\item{sizes}{A numeric vector containing the real size of the samples
+(columns) in the same order of the input table. If set, the values are
+assumed to be 100\%. Otherwise, the sum of the columns is used.}
+
+\item{top}{Maximum number of categories to display. Any additional
+categories will be listed as "Others".}
+
+\item{colors.per.group}{Number of categories in the first two saturation 
+groups of colors. The third group contains the remaining categories if 
+needed.}
+
+\item{bars.width}{Width of the barplot with respect to the legend.}
+
+\item{legend.ncol}{Number of columns in the legend.}
+
+\item{other.col}{Color of the "Others" category.}
+
+\item{add.trend}{Controls if semi-transparent areas are to be plotted
+between the bars to connect the regions (trend regions).}
+
+\item{organic.trend}{Controls if the trend regions are to be smoothed 
+(curves). By default, trend regions have straight edges. If \code{TRUE}, 
+forces \code{add.trend=TRUE}.}
+
+\item{sort.by}{Any function that takes a numeric vector and returns a
+numeric scalar. This function is applied to each row, and the resulting
+values are used to sort the rows (decreasingly). Good options include: 
+\code{sd, min, max, mean, median}.}
+
+\item{min.report}{Minimum percentage to report the value in the plot.
+Any value above 100 indicates that no values are to be reported.}
+
+\item{order}{Controls how the rows should be ordered. 
+\itemize{
+   \item{If \code{NULL} 
+   (default), \code{sort.by} is applied per row and the results are 
+   sorted decreasingly.}
+   \item{If \code{NA}, no sorting is performed, i.e., the original
+   order is respected.}
+   \item{If a vector is provided, it is assumed to be the 
+   custom order to be used (either by numeric index or by row names).}
+   }}
+
+\item{col}{Colors to use. If provided, overrides the variables \code{top}
+and \code{colors.per.group}, but \code{other.col} is still used if the 
+vector is insufficient for all the rows. An additional palette is available with
+\code{col='coto'} (contributed by Luis (Coto) Orellana).}
+
+\item{...}{Any additional parameters to be passed to barplot.}
+}
+\description{
+Creates nice barplots from tab-delimited tables.
+}
+\examples{
+# Load data
+data("phyla.counts", package="enveomics.R", envir=environment())
+# Create a barplot sorted by variance with organic trends
+enve.barplot(
+    phyla.counts, # Counts of phyla in four sites
+    sizes=c(250,100,75,200), # Total sizes of the datasets of each site
+    bars.width=2, # Decrease from default, so the names are fully displayed
+    organic.trend=TRUE, # Nice curvy background
+    sort.by=var # Sort by variance across sites
+    )
+
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}