miga-base 0.3.0.0 → 0.3.0.1

data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd

@@ -0,0 +1,53 @@
+\name{enve.recplot2.findPeaks}
+\alias{enve.recplot2.findPeaks}
+\title{enve recplot2 findPeaks}
+\description{Identifies peaks in the population histogram potentially indicating
+sub-population mixtures.}
+\usage{enve.recplot2.findPeaks(x, min.points = 10, quant.est = c(0.002, 
+    0.998), mlv.opts = list(method = "parzen"), fitdist.opts.sn = list(distr = "sn", 
+    method = "qme", probs = c(0.1, 0.5, 0.8), start = list(omega = 1, 
+        alpha = -1), lower = c(1e-06, -Inf, 0), upper = c(Inf, 
+        0, Inf)), fitdist.opts.norm = list(distr = "norm", method = "qme", 
+    probs = c(0.4, 0.6), start = list(sd = 1), lower = c(1e-08, 
+        0)), rm.top = 0.05, with.skewness = TRUE, optim.rounds = 200, 
+    optim.epsilon = 1e-08, merge.logdist = log(1.75), verbose = FALSE)}
+\arguments{
+  \item{x}{An `enve.RecPlot2` object.}
+  \item{min.points}{Minimum number of points in the quantile-estimation-range
+(`quant.est`) to estimate a peak.}
+  \item{quant.est}{Range of quantiles to be used in the estimation of a peak's
+parameters.}
+  \item{mlv.opts}{Options passed to `mlv` to estimate the mode.}
+  \item{fitdist.opts.sn}{
+}
+  \item{fitdist.opts.norm}{
+}
+  \item{rm.top}{Top-values to remove before finding peaks, as a quantile probability.
+This step is useful to remove highly conserved regions, but can be
+turned off by setting rm.top=0. The quantile is determined *after*
+removing zero-coverage windows.}
+  \item{with.skewness}{Allow skewness correction of the peaks. Typically, the
+sequencing-depth distribution for a single peak is left-skewed, due
+partly (but not exclusively) to fragmentation and mapping sensitivity.
+See Lindner et al 2013, Bioinformatics 29(10):1260-7 for an
+alternative solution for the first problem (fragmentation) called
+"tail distribution".}
+  \item{optim.rounds}{Maximum rounds of peak optimization.}
+  \item{optim.epsilon}{Trace change at which optimization stops (unless `optim.rounds` is
+reached first). The trace change is estimated as the sum of square
+differences between parameters in one round and those from two rounds
+earlier (to avoid infinite loops from approximation).}
+  \item{merge.logdist}{Maximum value of |log-ratio| between centrality parameters in peaks to
+attempt merging. The default of ~0.22 corresponds to a maximum
+difference of 25\%.}
+  \item{verbose}{Display (mostly debugging) information.}
+}
+
+\value{Returns a list of `enve.RecPlot2.Peak` objects.}
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

data/utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd

@@ -0,0 +1,44 @@
+\name{enve.RecPlot2.Peak-class}
+\Rdversion{1.1}
+\docType{class}
+\alias{enve.RecPlot2.Peak-class}
+\alias{enve.RecPlot2.Peak}
+%% \alias{$}
+
+\title{enve.RecPlot2.Peak S4 class}
+\description{Enve-omics representation of a peak in the sequencing depth histogram
+of a Recruitment plot (see `enve.recplot2.findPeaks`).}
+\section{Objects from the Class}{Objects can be created by calls of the form \code{new(enve.RecPlot2.Peak ...)}}
+\section{Slots}{
+  \describe{
+    \item{\code{dist}:}{(\code{character}) Distribution of the peak. Currently supported: 'norm' (normal) and 'sn'
+(skew-normal).}
+    \item{\code{values}:}{(\code{numeric}) Sequencing depth values predicted to conform the peak.}
+    \item{\code{values.res}:}{(\code{numeric}) Sequencing depth values not explained by this or previously identified
+peaks.}
+    \item{\code{mode}:}{(\code{numeric}) Seed-value of mode anchoring the peak.}
+    \item{\code{param.hat}:}{(\code{list}) Parameters of the distribution. A list of two values if dist='norm' (sd
+and mean), or three values if dist='sn' (omega=scale, alpha=shape, and
+xi=location). Note that the "dispersion" parameter is always first and
+the "location" parameter is always last.}
+    \item{\code{n.hat}:}{(\code{numeric}) Number of bins estimated to be explained by this peak. This should
+ideally be equal to the length of `values`, but it's not and integer.}
+    \item{\code{n.total}:}{(\code{numeric}) Total number of bins from which the peak was extracted. I.e., total
+number of position bins with non-zero sequencing depth in the recruitment
+plot (regardless of peak count).}
+    \item{\code{err.res}:}{(\code{numeric}) Error left after adding the peak.}
+    \item{\code{merge.logdist}:}{(\code{numeric}) Attempted `merge.logdist` parameter.}
+  }
+}
+\section{Methods}{
+  \describe{
+    \item{$}{\code{signature(x = "enve.RecPlot2.Peak")}: ... }
+	 }
+}
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,44 @@
+\name{enve.tribs}
+\alias{enve.tribs}
+\title{enve tribs}
+\description{Subsample any objects in "distance space" to reduce the effect of
+sample-clustering.  This function was originally designed to subsample
+genomes in "phylogenetic distance space", a clear case of strong
+clustering bias in sampling, by Luis M. Rodriguez-R and Michael R
+Weigand.}
+\usage{enve.tribs(dist, selection = labels(dist), replicates = 1000, 
+    summary.fx = median, dist.method = "euclidean", subsamples = seq(0, 
+        1, by = 0.01), dimensions = ceiling(length(selection) * 
+        0.05), metaMDS.opts = list(), threads = 2, verbosity = 1, 
+    points, pre.tribs)}
+\arguments{
+  \item{dist}{Distances as a `dist` object.}
+  \item{selection}{Objects to include in the subsample. By default, all objects are
+selected.}
+  \item{replicates}{Number of replications per point}
+  \item{summary.fx}{Function to summarize the distance distributions in a given replicate. By
+default, the median distance is estimated.}
+  \item{dist.method}{Distance method between random points and samples in the transformed
+space. See `dist`.}
+  \item{subsamples}{Subsampling fractions}
+  \item{dimensions}{Dimensions to use in the NMDS. By default, 5\% of the selection length.}
+  \item{metaMDS.opts}{Any additional options to pass to metaMDS, as `list`.}
+  \item{threads}{Number of threads to use.}
+  \item{verbosity}{Verbosity. Use 0 to run quietly, increase for additional information.}
+  \item{points}{Optional. If passed, the MDS step is skipped and this object is used
+instead.  It can be the `$points` slot of class `metaMDS` (from `vegan`).
+It must be a matrix or matrix-coercible object, with samples as rows and
+dimensions as columns.}
+  \item{pre.tribs}{Optional. If passed, the points are recovered from this object (except if
+`points` is also passed. This should be an `enve.TRIBS` object estimated
+on the same objects (the selection is unimportant).}
+}
+
+\value{Returns an `enve.TRIBS` object.}
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

data/utils/enveomics/enveomics.R/man/enve.tribs.test.Rd

@@ -0,0 +1,21 @@
+\name{enve.tribs.test}
+\alias{enve.tribs.test}
+\title{enve tribs test}
+\description{Estimates the empirical difference between all the distances in a set of
+objects and a subset, together with its statistical significance.}
+\usage{enve.tribs.test(dist, selection, bins = 50, ...)}
+\arguments{
+  \item{dist}{Distances as `dist` object.}
+  \item{selection}{Selection defining the subset.}
+  \item{bins}{Number of bins to evaluate in the range of distances.}
+  \item{\dots}{Any other parameters supported by `enve.tribs`, except `subsamples`.}
+}
+
+\value{Returns an `enve.TRIBStest` object.}
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

data/utils/enveomics/enveomics.R/man/enveomics.R-package.Rd

@@ -0,0 +1,15 @@
+\name{enveomics.R-package}
+\alias{enveomics.R-package}
+\alias{enveomics.R}
+\docType{package}
+\title{Various Utilities for Microbial Genomics and Metagenomics}
+\description{A collection of functions for microbial ecology and other
+applications of genomics and metagenomics. Companion package for the
+Enveomics Collection (Rodriguez-R, L.M. and Konstantinidis, K.T., 2016
+<DOI:10.7287/peerj.preprints.1900v1>).}
+\author{Luis M. Rodriguez-R <lmrodriguezr@gmail.com> [aut, cre]}
+
+\keyword{ package }
+
+
+

data/utils/enveomics/enveomics.R/man/growth.curves.Rd

@@ -0,0 +1,14 @@
+
+\name{growth.curves}
+\docType{data}
+\alias{growth.curves}
+\title{Bacterial growth curves for three Escherichia coli mutants}
+\description{
+  This data set provides time (first column) and three triplicated growth
+  curves as optical density at 600nm (OD_600nm) for different mutants of E.
+  coli.
+}
+\usage{growth.curves}
+\format{A data frame with 16 rows (times) and 10 rows (times and OD_600nm).}
+\keyword{datasets}
+

data/utils/enveomics/enveomics.R/man/phyla.counts.Rd

@@ -0,0 +1,13 @@
+
+\name{phyla.counts}
+\docType{data}
+\alias{phyla.counts}
+\title{Counts of microbial phyla in four sites}
+\description{
+  This data set gives the counts of phyla in three different
+  sites.
+}
+\usage{phyla.counts}
+\format{A data frame with 9 rows (phyla) and 4 rows (sites).}
+\keyword{datasets}
+

data/utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd

@@ -0,0 +1,43 @@
+\name{plot.enve.GrowthCurve}
+\alias{plot.enve.GrowthCurve}
+\title{plot enve GrowthCurve}
+\description{Plots an `enve.GrowthCurve` object.}
+\usage{\method{plot}{enve.GrowthCurve}(x, col, pt.alpha = 0.9, ln.alpha = 1, ln.lwd = 1, 
+    ln.lty = 1, band.alpha = 0.4, band.density = NULL, band.angle = 45, 
+    xp.alpha = 0.5, xp.lwd = 1, xp.lty = 1, pch = 19, new = TRUE, 
+    legend = new, add.params = FALSE, ...)}
+\arguments{
+  \item{x}{`enve.GrowthCurve` object to plot.}
+  \item{col}{Base colors to use for the different samples. Can be recycled. By
+default, grey for one sample or rainbow colors for more than one.}
+  \item{pt.alpha}{Color alpha for the observed data points, using `col` as a base.}
+  \item{ln.alpha}{Color alpha for the fitted growth curve, using `col` as a base.}
+  \item{ln.lwd}{Line width for the fitted curve.}
+  \item{ln.lty}{Line type for the fitted curve.}
+  \item{band.alpha}{Color alpha for the confidence interval band of the fitted growth curve,
+using `col` as a base.}
+  \item{band.density}{Density of the filling pattern in the interval band. If NULL, a solid
+color is used.}
+  \item{band.angle}{Angle of the density filling pattern in the interval band. Ignored if
+`band.density` is NULL.}
+  \item{xp.alpha}{Color alpha for the line connecting individual experiments, using `col`
+as a base.}
+  \item{xp.lwd}{Width of line for the experiments.}
+  \item{xp.lty}{Type of line for the experiments.}
+  \item{pch}{Point character for observed data points.}
+  \item{new}{Should a new plot be generated? If FALSE, the existing canvas is used.}
+  \item{legend}{Should the plot include a legend? If FALSE, no legend is added. If TRUE,
+a legend is added in the bottom-right corner. Otherwise, a legend is
+added in the position specified as `xy.coords`. }
+  \item{add.params}{Should the legend include the parameters of the fitted model?}
+  \item{\dots}{Any other graphic parameters.}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,29 @@
+\name{plot.enve.TRIBS}
+\alias{plot.enve.TRIBS}
+\title{plot enve TRIBS}
+\description{Plot an `enve.TRIBS` object.}
+\usage{\method{plot}{enve.TRIBS}(x, new = TRUE, type = c("boxplot", "points"), 
+    col = "#00000044", pt.cex = 1/2, pt.pch = 19, pt.col = col, 
+    ln.col = col, ...)}
+\arguments{
+  \item{x}{`enve.TRIBS` object to plot.}
+  \item{new}{Should a new canvas be drawn?}
+  \item{type}{Type of plot. The 'points' plot shows all the replicates, the 'boxplot'
+plot represents the values found by `boxplot.stats` as areas, and plots
+the outliers as points.}
+  \item{col}{Color of the areas and/or the points.}
+  \item{pt.cex}{Size of the points.}
+  \item{pt.pch}{Points character.}
+  \item{pt.col}{Color of the points.}
+  \item{ln.col}{Color of the lines.}
+  \item{\dots}{Any additional parameters supported by `plot`.}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd

@@ -0,0 +1,30 @@
+\name{plot.enve.TRIBStest}
+\alias{plot.enve.TRIBStest}
+\title{plot enve TRIBStest}
+\description{Plots an `enve.TRIBStest` object.}
+\usage{\method{plot}{enve.TRIBStest}(x, type = c("overlap", "difference"), col = "#00000044", 
+    col1 = col, col2 = "#44001144", ylab = "Probability", xlim = range(attr(x, 
+        "dist.mids")), ylim = c(0, max(c(attr(x, "all.dist"), 
+        attr(x, "sel.dist")))), ...)}
+\arguments{
+  \item{x}{`enve.TRIBStest` object to plot.}
+  \item{type}{What to plot. 'overlap' generates a plot of the two contrasting empirical
+PDFs (to compare against each other), 'difference' produces a plot of the
+differences between the empirical PDFs (to compare against zero).}
+  \item{col}{Main color of the plot if type='difference'.}
+  \item{col1}{First color of the plot if type='overlap'.}
+  \item{col2}{Second color of the plot if type='overlap'.}
+  \item{ylab}{Y-axis label.}
+  \item{xlim}{X-axis limits.}
+  \item{ylim}{Y-axis limits.}
+  \item{\dots}{Any other graphical arguments.}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd

@@ -0,0 +1,71 @@
+\name{plot.enve.RecPlot2}
+\alias{plot.enve.RecPlot2}
+\title{plot enve RecPlot2}
+\description{Plots an `enve.RecPlot2` object.}
+\usage{\method{plot}{enve.RecPlot2}(x, layout = matrix(c(5, 5, 2, 1, 4, 3), nrow = 2), 
+    widths = c(1, 7, 2), heights = c(1, 2), palette = grey((100:0)/100), 
+    underlay.group = TRUE, peaks.col = "darkred", id.lim = range(x$id.breaks), 
+    pos.lim = range(x$pos.breaks), pos.units = c("Mbp", "Kbp", 
+        "bp"), mar = list(`1` = c(5, 4, 1, 1) + 0.1, `2` = c(ifelse(any(layout == 
+        1), 1, 5), 4, 4, 1) + 0.1, `3` = c(5, ifelse(any(layout == 
+        1), 1, 4), 1, 2) + 0.1, `4` = c(ifelse(any(layout == 
+        1), 1, 5), ifelse(any(layout == 2), 1, 4), 4, 2) + 0.1, 
+        `5` = c(5, 3, 4, 1) + 0.1, `6` = c(5, 4, 4, 2) + 0.1), 
+    pos.splines = 0, id.splines = 1/2, in.lwd = ifelse(pos.splines > 
+        0, 1/2, 2), out.lwd = ifelse(pos.splines > 0, 1/2, 2), 
+    id.lwd = ifelse(id.splines > 0, 1/2, 2), in.col = "darkblue", 
+    out.col = "lightblue", id.col = "black", breaks.col = "#AAAAAA40", 
+    peaks.opts = list(), ...)}
+\arguments{
+  \item{x}{`enve.RecPlot2` object to plot.}
+  \item{layout}{Matrix indicating the position of the different panels in the layout,
+where:
+0: Empty space,
+1: Counts matrix,
+2: position histogram (sequencing depth),
+3: identity histogram,
+4: Populations histogram (histogram of sequencing depths),
+5: Color scale for the counts matrix (vertical),
+6: Color scale of the counts
+matrix (horizontal). Only panels indicated here will be plotted. To
+plot only one panel simply set this to the number of the panel you
+want to plot.}
+  \item{widths}{Relative widths of the columns of `layout`.}
+  \item{heights}{Relative heights of the rows of `layout`.}
+  \item{palette}{Colors to be used to represent the counts matrix, sorted from no hits
+to the maximum sequencing depth.}
+  \item{underlay.group}{If TRUE, it indicates the in-group and out-group areas couloured based
+on `in.col` and `out.col`. Requires support for semi-transparency.}
+  \item{peaks.col}{If not NA, it attempts to represent peaks in the population histogram
+in the specified color. Set to NA to avoid peak-finding.}
+  \item{id.lim}{Limits of identities to represent.}
+  \item{pos.lim}{Limits of positions to represent (in bp, regardless of `pos.units`).}
+  \item{pos.units}{Units in which the positions should be represented (powers of 1,000
+base pairs).}
+  \item{mar}{
+}
+  \item{pos.splines}{Smoothing parameter for the splines in the position histogram. Zero
+(0) for no splines. If non-zero, requires the stats package.}
+  \item{id.splines}{Smoothing parameter for the splines in the identity histogram. Zero
+(0) for no splines. If non-zero, requires the stats package.}
+  \item{in.lwd}{Line width for the sequencing depth of in-group matches.}
+  \item{out.lwd}{Line width for the sequencing depth of out-group matches.}
+  \item{id.lwd}{Line width for the identity histogram.}
+  \item{in.col}{Color associated to in-group matches.}
+  \item{out.col}{Color associated to out-group matches.}
+  \item{id.col}{Color for the identity histogram.}
+  \item{breaks.col}{Color of the vertical lines indicating sequence breaks.}
+  \item{peaks.opts}{Options passed to `enve.recplot2.findPeaks`, if `peaks.col` is not NA.}
+  \item{\dots}{Any other graphic parameters (currently ignored).}
+}
+
+\value{Returns a list of `enve.RecPlot2.Peak` objects (see
+`enve.recplot2.findPeaks`). If `peaks.col`=NA or `layout` doesn't include
+4, returns NA.}
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd

@@ -0,0 +1,18 @@
+\name{summary.enve.GrowthCurve}
+\alias{summary.enve.GrowthCurve}
+\title{summary enve GrowthCurve}
+\description{Summary of an `enve.GrowthCurve` object.}
+\usage{\method{summary}{enve.GrowthCurve}(object, ...)}
+\arguments{
+  \item{object}{`enve.GrowthCurve` object.}
+  \item{\dots}{No additional parameters are currently supported.}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,18 @@
+\name{summary.enve.TRIBS}
+\alias{summary.enve.TRIBS}
+\title{summary enve TRIBS}
+\description{Summary of an `enve.TRIBS` object.}
+\usage{\method{summary}{enve.TRIBS}(object, ...)}
+\arguments{
+  \item{object}{`enve.TRIBS` object.}
+  \item{\dots}{No additional parameters are currently supported.}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd

@@ -0,0 +1,18 @@
+\name{summary.enve.TRIBStest}
+\alias{summary.enve.TRIBStest}
+\title{summary enve TRIBStest}
+\description{Summary of an `enve.TRIBStest` object.}
+\usage{\method{summary}{enve.TRIBStest}(object, ...)}
+\arguments{
+  \item{object}{`enve.TRIBStest` object.}
+  \item{\dots}{No additional parameters are currently supported.}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+