miga-base 0.7.26.0 → 1.0.0.1

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

@@ -0,0 +1,29 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.coordinates}
+\alias{enve.recplot2.coordinates}
+\title{Enveomics: Recruitment Plot (2) Coordinates}
+\usage{
+enve.recplot2.coordinates(x, bins)
+}
+\arguments{
+\item{x}{\code{\link{enve.RecPlot2}} object.}
+
+\item{bins}{Vector of selected bins to return. It can be a vector of logical values
+with the same length as \code{x$pos.breaks-1} or a vector of integers. If
+missing, returns the coordinates of all windows.}
+}
+\value{
+Returns a data.frame with five columns: \code{name.from} (character),
+\code{pos.from} (numeric), \code{name.to} (character), \code{pos.to}
+(numeric), and \code{seq.name} (character).
+The first two correspond to sequence and position of the start point of the
+bin. The next two correspond to the sequence and position of the end point of
+the bin. The last one indicates the name of the sequence (if defined).
+}
+\description{
+Returns the sequence name and coordinates of the requested position bins.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,18 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.corePeak}
+\alias{enve.recplot2.corePeak}
+\title{Enveomics: Recruitment Plot (2) Core Peak Finder}
+\usage{
+enve.recplot2.corePeak(x)
+}
+\arguments{
+\item{x}{\code{list} of \code{\link{enve.RecPlot2.Peak}} objects.}
+}
+\description{
+Finds the peak in a list of peaks that is most likely to represent the
+"core genome" of a population.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,45 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.extractWindows}
+\alias{enve.recplot2.extractWindows}
+\title{Enveomics: Recruitment Plot (2) Extract Windows}
+\usage{
+enve.recplot2.extractWindows(
+  rp,
+  peak,
+  lower.tail = TRUE,
+  significance = 0.05,
+  seq.names = FALSE
+)
+}
+\arguments{
+\item{rp}{Recruitment plot, a \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.}
+
+\item{seq.names}{Returns subject sequence names instead of a vector of Booleans. If
+the recruitment plot was generated with named position bins (e.g, using
+\code{pos.breaks=0} or a two-column \code{pos.breaks.tsv}), it returns a
+vector of characters (the sequence identifiers), otherwise it returns a
+data.frame with a name column and two columns of coordinates.}
+}
+\value{
+Returns a vector of logicals if \code{seq.names = FALSE}.
+If \code{seq.names = TRUE}, it returns a data.frame with five columns:
+\code{name.from}, \code{name.to}, \code{pos.from}, \code{pos.to}, and
+\code{seq.name} (see \code{\link{enve.recplot2.coordinates}}).
+}
+\description{
+Extract windows significantly below (or above) the peak in sequencing
+depth.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,36 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.findPeaks}
+\alias{enve.recplot2.findPeaks}
+\title{Enveomics: Recruitment Plot (2) Peak Finder}
+\usage{
+enve.recplot2.findPeaks(x, method = "emauto", ...)
+}
+\arguments{
+\item{x}{An \code{\link{enve.RecPlot2}} object.}
+
+\item{method}{Peak-finder method. This should be one of:
+\itemize{
+   \item \strong{emauto}
+   (Expectation-Maximization with auto-selection of components)
+   \item \strong{em}
+   (Expectation-Maximization)
+   \item \strong{mower}
+   (Custom distribution-mowing method)
+}}
+
+\item{...}{Any additional parameters supported by
+\code{\link{enve.recplot2.findPeaks}}.}
+}
+\value{
+Returns a list of \code{\link{enve.RecPlot2.Peak}} objects.
+}
+\description{
+Identifies peaks in the population histogram potentially indicating
+sub-population mixtures.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+
+export
+}

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

@@ -0,0 +1,19 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.findPeaks.__em_e}
+\alias{enve.recplot2.findPeaks.__em_e}
+\title{Enveomics: Recruitment Plot (2) EM Peak Finder - Internal Ancillary Function Expectation}
+\usage{
+enve.recplot2.findPeaks.__em_e(x, theta)
+}
+\arguments{
+\item{x}{Vector of log-transformed sequencing depths}
+
+\item{theta}{Parameters list}
+}
+\description{
+Internal ancillary function (see \code{\link{enve.recplot2.findPeaks.em}}).
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,19 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.findPeaks.__em_m}
+\alias{enve.recplot2.findPeaks.__em_m}
+\title{Enveomics: Recruitment Plot (2) Em Peak Finder - Internal Ancillary Function Maximization}
+\usage{
+enve.recplot2.findPeaks.__em_m(x, posterior)
+}
+\arguments{
+\item{x}{Vector of log-transformed sequencing depths}
+
+\item{posterior}{Posterior probability}
+}
+\description{
+Internal ancillary function (see \code{\link{enve.recplot2.findPeaks.em}}).
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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 +1,52 @@
+% 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 +1,51 @@
+% 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 +1,43 @@
+% 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 +1,82 @@
+% 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]
+}