miga-base 0.7.26.0 → 0.7.26.1

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

@@ -0,0 +1,27 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.findPeaks.__emauto_one}
+\alias{enve.recplot2.findPeaks.__emauto_one}
+\title{Enveomics: Recruitment Plot (2) EMauto Peak Finder - Internal Ancillary Function}
+\usage{
+enve.recplot2.findPeaks.__emauto_one(x, comp, do_crit, best, verbose, ...)
+}
+\arguments{
+\item{x}{\code{\link{enve.RecPlot2}} object}
+
+\item{comp}{Components}
+
+\item{do_crit}{Function estimating the criterion}
+
+\item{best}{Best solution thus far}
+
+\item{verbose}{If verbose}
+
+\item{...}{Additional parameters for \code{\link{enve.recplot2.findPeaks.em}}}
+}
+\description{
+Internal ancillary function (see \code{\link{enve.recplot2.findPeaks.emauto}}).
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,41 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.findPeaks.__mow_one}
+\alias{enve.recplot2.findPeaks.__mow_one}
+\title{Enveomics: Recruitment Plot (2) Mowing Peak Finder - Internal Ancillary Function 1}
+\usage{
+enve.recplot2.findPeaks.__mow_one(lsd1, min.points, quant.est, mlv.opts,
+  fitdist.opts, with.skewness, optim.rounds, optim.epsilon, n.total,
+  merge.logdist, verbose, log)
+}
+\arguments{
+\item{lsd1}{Vector of log-transformed sequencing depths}
+
+\item{min.points}{Minimum number of points}
+
+\item{quant.est}{Quantile estimate}
+
+\item{mlv.opts}{List of options for \code{mlv}}
+
+\item{fitdist.opts}{List of options for \code{fitdist}}
+
+\item{with.skewness}{If skewed-normal should be used}
+
+\item{optim.rounds}{Maximum number of optimization rounds}
+
+\item{optim.epsilon}{Minimum difference considered negligible}
+
+\item{n.total}{Global number of windows}
+
+\item{merge.logdist}{Attempted \code{merge.logdist} parameter}
+
+\item{verbose}{If verbose}
+
+\item{log}{If log-transformed depths}
+}
+\description{
+Internall ancillary function (see \code{\link{enve.recplot2.findPeaks.mower}}).
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,17 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.findPeaks.__mower}
+\alias{enve.recplot2.findPeaks.__mower}
+\title{Enveomics: Recruitment Plot (2) Mowing Peak Finder - Internal Ancillary Function 2}
+\usage{
+enve.recplot2.findPeaks.__mower(peaks.opts)
+}
+\arguments{
+\item{peaks.opts}{List of options for \code{\link{enve.recplot2.findPeaks.__mow_one}}}
+}
+\description{
+Internal ancillary function (see \code{\link{enve.recplot2.findPeaks.mower}}).
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,43 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.findPeaks.em}
+\alias{enve.recplot2.findPeaks.em}
+\title{Enveomics: Recruitment Plot (2) Em Peak Finder}
+\usage{
+enve.recplot2.findPeaks.em(x, max.iter = 1000, ll.diff.res = 1e-08,
+  components = 2, rm.top = 0.05, verbose = FALSE, init, log = TRUE)
+}
+\arguments{
+\item{x}{An \code{\link{enve.RecPlot2}} object.}
+
+\item{max.iter}{Maximum number of EM iterations.}
+
+\item{ll.diff.res}{Maximum Log-Likelihood difference to be considered as convergent.}
+
+\item{components}{Number of distributions assumed in the mixture.}
+
+\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 \code{rm.top=0}. The quantile is determined
+\strong{after} removing zero-coverage windows.}
+
+\item{verbose}{Display (mostly debugging) information.}
+
+\item{init}{Initialization parameters. By default, these are derived from k-means
+clustering. A named list with vectors for \code{mu}, \code{sd}, and
+\code{alpha}, each of length \code{components}.}
+
+\item{log}{Logical value indicating if the estimations should be performed in
+natural logarithm units. Do not change unless you know what you're
+doing.}
+}
+\value{
+Returns a list of \code{\link{enve.RecPlot2.Peak}} objects.
+}
+\description{
+Identifies peaks in the population histogram using a Gaussian Mixture
+Model Expectation Maximization (GMM-EM) method.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,37 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.findPeaks.emauto}
+\alias{enve.recplot2.findPeaks.emauto}
+\title{Enveomics: Recruitment Plot (2) Emauto Peak Finder}
+\usage{
+enve.recplot2.findPeaks.emauto(x, components = seq(1, 5),
+  criterion = "aic", merge.tol = 2L, verbose = FALSE, ...)
+}
+\arguments{
+\item{x}{An \code{\link{enve.RecPlot2}} object.}
+
+\item{components}{A vector of number of components to evaluate.}
+
+\item{criterion}{Criterion to use for components selection. Must be one of:
+\code{aic} (Akaike Information Criterion), \code{bic} or \code{sbc}
+(Bayesian Information Criterion or Schwarz Criterion).}
+
+\item{merge.tol}{When attempting to merge peaks with very similar sequencing depth, use
+this number of significant digits (in log-scale).}
+
+\item{verbose}{Display (mostly debugging) information.}
+
+\item{...}{Any additional parameters supported by
+\code{\link{enve.recplot2.findPeaks.em}}.}
+}
+\value{
+Returns a list of \code{\link{enve.RecPlot2.Peak}} objects.
+}
+\description{
+Identifies peaks in the population histogram using a Gaussian Mixture
+Model Expectation Maximization (GMM-EM) method with number of components
+automatically detected.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,74 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.findPeaks.mower}
+\alias{enve.recplot2.findPeaks.mower}
+\title{Enveomics: Recruitment Plot (2) Mowing Peak Finder}
+\usage{
+enve.recplot2.findPeaks.mower(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(0, -Inf,
+  -Inf)), fitdist.opts.norm = list(distr = "norm", method = "qme", probs
+  = c(0.4, 0.6), start = list(sd = 1), lower = c(0, -Inf)),
+  rm.top = 0.05, with.skewness = TRUE, optim.rounds = 200,
+  optim.epsilon = 1e-04, merge.logdist = log(1.75), verbose = FALSE,
+  log = TRUE)
+}
+\arguments{
+\item{x}{An \code{\link{enve.RecPlot2}} object.}
+
+\item{min.points}{Minimum number of points in the quantile-estimation-range
+\code{(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}{Ignored. For backwards compatibility.}
+
+\item{fitdist.opts.sn}{Options passed to \code{fitdist} to estimate the standard deviation if
+\code{with.skewness=TRUE}. Note that the \code{start} parameter will be
+ammended with \code{xi=estimated} mode for each peak.}
+
+\item{fitdist.opts.norm}{Options passed to \code{fitdist} to estimate the standard deviation if
+\code{with.skewness=FALSE}. Note that the \code{start} parameter will be
+ammended with \code{mean=estimated} mode for each peak.}
+
+\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 \code{rm.top=0}. The quantile is determined
+\strong{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 \emph{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 \code{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 \code{|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.}
+
+\item{log}{Logical value indicating if the estimations should be performed in
+natural logarithm units. Do not change unless you know what you're
+doing.}
+}
+\value{
+Returns a list of \code{\link{enve.RecPlot2.Peak}} objects.
+}
+\description{
+Identifies peaks in the population histogram potentially indicating
+sub-population mixtures, using a custom distribution-mowing method.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,59 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\docType{class}
+\name{enve.RecPlot2.Peak-class}
+\alias{enve.RecPlot2.Peak-class}
+\alias{enve.RecPlot2.Peak}
+\title{Enveomics: Recruitment Plot (2) Peak - S4 Class}
+\description{
+Enve-omics representation of a peak in the sequencing depth histogram
+of a Recruitment plot (see \code{\link{enve.recplot2.findPeaks}}).
+}
+\section{Slots}{
+
+\describe{
+\item{\code{dist}}{\code{(character)}
+Distribution of the peak. Currently supported: \code{norm} (normal) and \code{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=\code{norm} (sd
+and mean), or three values if dist=\code{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  \code{values}, but it's not an 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 (mower) or log-likelihood (em or emauto).}
+
+\item{\code{merge.logdist}}{\code{(numeric)}
+Attempted \code{merge.logdist} parameter.}
+
+\item{\code{seq.depth}}{\code{(numeric)}
+Best estimate available for the sequencing depth of the peak (centrality).}
+
+\item{\code{log}}{\code{(logical)}
+Indicates if the estimation was performed in natural logarithm space.}
+}}
+
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,27 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.seqdepth}
+\alias{enve.recplot2.seqdepth}
+\title{Enveomics: Recruitment Plot (2) Sequencing Depth}
+\usage{
+enve.recplot2.seqdepth(x, sel, low.identity = FALSE)
+}
+\arguments{
+\item{x}{\code{\link{enve.RecPlot2}} object.}
+
+\item{sel}{Window(s) for which the sequencing depth is to be calculated. If not
+passed, it returns the sequencing depth of all windows.}
+
+\item{low.identity}{A logical indicating if the sequencing depth is to be estimated only
+with low-identity matches. By default, only high-identity matches are
+used.}
+}
+\value{
+Returns a numeric vector of sequencing depths (in bp/bp).
+}
+\description{
+Calculate the sequencing depth of the given window(s).
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,32 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.windowDepthThreshold}
+\alias{enve.recplot2.windowDepthThreshold}
+\title{Enveomics: Recruitment Plot (2) Window Depth Threshold}
+\usage{
+enve.recplot2.windowDepthThreshold(rp, peak, lower.tail = TRUE,
+  significance = 0.05)
+}
+\arguments{
+\item{rp}{Recruitment plot, an \code{\link{enve.RecPlot2}} object.}
+
+\item{peak}{Peak, an \code{\link{enve.RecPlot2.Peak}} object. If list, it is assumed to be a
+list of \code{\link{enve.RecPlot2.Peak}} objects, in which case the core peak is
+used (see \code{\link{enve.recplot2.corePeak}}).}
+
+\item{lower.tail}{If \code{FALSE}, it returns windows significantly above the peak in
+sequencing depth.}
+
+\item{significance}{Significance threshold (alpha) to select windows.}
+}
+\value{
+Returns a float. The units are depth if the peaks were estimated in
+linear scale, or log-depth otherwise (\code{peak$log}).
+}
+\description{
+Identifies the threshold below which windows should be identified as
+variable or absent.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,59 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/tribs.R
+\name{enve.tribs}
+\alias{enve.tribs}
+\title{Enveomics: TRIBS}
+\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 \code{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 \code{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 \code{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 \code{$points} slot of class \code{metaMDS} 
+(from \code{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
+\code{points} is also passed. This should be an \code{\link{enve.TRIBS}} object 
+estimated on the same objects (the selection is unimportant).}
+}
+\value{
+Returns an \code{\link{enve.TRIBS}} object.
+}
+\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.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,28 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/tribs.R
+\name{enve.tribs.test}
+\alias{enve.tribs.test}
+\title{Enveomics: TRIBS Test}
+\usage{
+enve.tribs.test(dist, selection, bins = 50, ...)
+}
+\arguments{
+\item{dist}{Distances as \code{dist} object.}
+
+\item{selection}{Selection defining the subset.}
+
+\item{bins}{Number of bins to evaluate in the range of distances.}
+
+\item{...}{Any other parameters supported by \code{\link{enve.tribs}}, 
+except \code{subsamples}.}
+}
+\value{
+Returns an \code{\link{enve.TRIBStest}} object.
+}
+\description{
+Estimates the empirical difference between all the distances in a set of
+objects and a subset, together with its statistical significance.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}