miga-base 0.7.26.0 → 0.7.26.1

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

@@ -0,0 +1,45 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\docType{class}
+\name{enve.RecPlot2-class}
+\alias{enve.RecPlot2-class}
+\alias{enve.RecPlot2}
+\title{Enveomics: Recruitment Plot (2) - S4 Class}
+\description{
+Enve-omics representation of Recruitment plots. This object can
+be produced by \code{\link{enve.recplot2}} and supports S4 method plot.
+}
+\section{Slots}{
+
+\describe{
+\item{\code{counts}}{\code{(matrix)} Counts as a two-dimensional histogram.}
+
+\item{\code{pos.counts.in}}{\code{(numeric)} Counts of in-group hits per position bin.}
+
+\item{\code{pos.counts.out}}{\code{(numeric)} Counts of out-group hits per position bin.}
+
+\item{\code{id.counts}}{\code{(numeric)} Counts per ID bin.}
+
+\item{\code{id.breaks}}{\code{(numeric)} Breaks of identity bins.}
+
+\item{\code{pos.breaks}}{\code{(numeric)} Breaks of position bins.}
+
+\item{\code{pos.names}}{\code{(character)} Names of the position bins.}
+
+\item{\code{seq.breaks}}{\code{(numeric)} Breaks of input sequences.}
+
+\item{\code{peaks}}{\code{(list)} Peaks identified in the recplot.
+Limits of the subject sequences after concatenation.}
+
+\item{\code{seq.names}}{\code{(character}) Names of the subject sequences.}
+
+\item{\code{id.metric}}{\code{(character}) Metric used as 'identity'.}
+
+\item{\code{id.ingroup}}{\code{(logical}) Identity bins considered in-group.}
+
+\item{\code{call}}{\code{(call)} Call producing this object.}
+}}
+
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,24 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.ANIr}
+\alias{enve.recplot2.ANIr}
+\title{Enveomics: Recruitment Plot (2) ANI Estimate}
+\usage{
+enve.recplot2.ANIr(x, range = c(0, Inf))
+}
+\arguments{
+\item{x}{\code{\link{enve.RecPlot2}} object.}
+
+\item{range}{Range of identities to be considered. By default, the full range
+is used (note that the upper boundary is \code{Inf} and not 100 because
+recruitment plots can also be built with bit-scores). To use only
+intra-population matches (with identities), use c(95,100). To use only
+inter-population values, use c(0,95).}
+}
+\description{
+Estimate the Average Nucleotide Identity from reads (ANIr) from a
+recruitment plot.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,68 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2}
+\alias{enve.recplot2}
+\title{Enveomics: Recruitment Plot (2)}
+\usage{
+enve.recplot2(prefix, plot = TRUE, pos.breaks = 1000,
+  pos.breaks.tsv = NA, id.breaks = 60, id.free.range = FALSE,
+  id.metric = c("identity", "corrected identity", "bit score"),
+  id.summary = sum, id.cutoff = 95, threads = 2, verbose = TRUE,
+  ...)
+}
+\arguments{
+\item{prefix}{Path to the prefix of the \code{BlastTab.catsbj.pl} output files. At
+least the files .rec and .lim must exist with this prefix.}
+
+\item{plot}{Should the object be plotted?}
+
+\item{pos.breaks}{Breaks in the positions histogram. It can also be a vector of break
+points, and values outside the range are ignored. If zero (0), it
+uses the sequence breaks as defined in the .lim file, which means
+one bin per contig (or gene, if the mapping is agains genes). Ignored
+if `pos.breaks.tsv` is passed.}
+
+\item{pos.breaks.tsv}{Path to a list of (absolute) coordinates to use as position breaks.
+This tab-delimited file can be produced by \code{GFF.catsbj.pl}, and it
+must contain at least one column: coordinates of the break positions of
+each position bin. If it has a second column, this is used as the name
+of the position bin that ends at the given coordinate (the first row is
+ignored). Any additional columns are currently ignored. If \code{NA},
+position bins are determined by \code{pos.breaks}.}
+
+\item{id.breaks}{Breaks in the identity histogram. It can also be a vector of break
+points, and values outside the range are ignored.}
+
+\item{id.free.range}{Indicates that the range should be freely set from the observed
+values. Otherwise, 70-100\% is included in the identity histogram
+(default).}
+
+\item{id.metric}{Metric of identity to be used (Y-axis). Corrected identity is only
+supported if the original BLAST file included sequence lengths.}
+
+\item{id.summary}{Function summarizing the identity bins. Other recommended options
+include: \code{median} to estimate the median instead of total bins, and
+\code{function(x) mlv(x,method='parzen')$M} to estimate the mode.}
+
+\item{id.cutoff}{Cutoff of identity metric above which the hits are considered
+\code{in-group}. The 95\% identity corresponds to the expectation of
+ANI<95\% within species.}
+
+\item{threads}{Number of threads to use.}
+
+\item{verbose}{Indicates if the function should report the advance.}
+
+\item{...}{Any additional parameters supported by \code{\link{plot.enve.RecPlot2}}.}
+}
+\value{
+Returns an object of class \code{\link{enve.RecPlot2}}.
+}
+\description{
+Produces recruitment plots provided that \code{BlastTab.catsbj.pl} has
+been previously executed.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+
+Kenji Gerhardt [aut]
+}

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

@@ -0,0 +1,25 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.__counts}
+\alias{enve.recplot2.__counts}
+\title{Enveomics: Recruitment Plot (2) Internal Ancillary Function}
+\usage{
+enve.recplot2.__counts(x, pos.breaks, id.breaks, rec.idcol)
+}
+\arguments{
+\item{x}{\code{\link{enve.RecPlot2}} object}
+
+\item{pos.breaks}{Position breaks}
+
+\item{id.breaks}{Identity breaks}
+
+\item{rec.idcol}{Identity column to use}
+}
+\description{
+Internal ancillary function (see \code{\link{enve.recplot2}}).
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+
+Kenji Gerhardt [aut]
+}

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

@@ -0,0 +1,21 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.__peakHist}
+\alias{enve.recplot2.__peakHist}
+\title{Enveomics: Recruitment Plot (2) Peak S4 Class - Internal Ancillary Function}
+\usage{
+enve.recplot2.__peakHist(x, mids, counts = TRUE)
+}
+\arguments{
+\item{x}{\code{\link{enve.RecPlot2.Peak}} object}
+
+\item{mids}{Midpoints}
+
+\item{counts}{Counts}
+}
+\description{
+Internal ancillary function (see \code{\link{enve.RecPlot2.Peak}}).
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,19 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.__whichClosestPeak}
+\alias{enve.recplot2.__whichClosestPeak}
+\title{Enveomics: Recruitment Plot (2) Peak Finder - Internal Ancillary Function}
+\usage{
+enve.recplot2.__whichClosestPeak(peak, peaks)
+}
+\arguments{
+\item{peak}{Query \code{\link{enve.RecPlot2.Peak}} object}
+
+\item{peaks}{list of \code{\link{enve.RecPlot2.Peak}} objects}
+}
+\description{
+Internal ancillary function (see \code{\link{enve.recplot2.findPeaks}}).
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,19 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.changeCutoff}
+\alias{enve.recplot2.changeCutoff}
+\title{Enveomics: Recruitment Plot (2) Change Cutoff}
+\usage{
+enve.recplot2.changeCutoff(rp, new.cutoff = 98)
+}
+\arguments{
+\item{rp}{\code{\link{enve.RecPlot2}} object.}
+
+\item{new.cutoff}{New cutoff to use.}
+}
+\description{
+Change the intra-species cutoff of an existing recruitment plot.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,41 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot2.R
+\name{enve.recplot2.compareIdentities}
+\alias{enve.recplot2.compareIdentities}
+\title{Enveomics: Recruitment Plot (2) Compare Identities}
+\usage{
+enve.recplot2.compareIdentities(x, y, method = "hellinger",
+  smooth.par = NULL, pseudocounts = 0, max.deviation = 0.75)
+}
+\arguments{
+\item{x}{First \code{\link{enve.RecPlot2}} object.}
+
+\item{y}{Second \code{\link{enve.RecPlot2}} object.}
+
+\item{method}{Distance method to use. This should be (an unambiguous abbreviation of)
+one of:
+\itemize{
+   \item{"hellinger" (\emph{Hellinger, 1090, doi:10.1515/crll.1909.136.210}),}
+   \item{"bhattacharyya" (\emph{Bhattacharyya, 1943, Bull. Calcutta Math. Soc. 35}),}
+   \item{"kl" or "kullback-leibler" (\emph{Kullback & Leibler, 1951,
+   doi:10.1214/aoms/1177729694}), or}
+   \item{"euclidean"}
+}}
+
+\item{smooth.par}{Smoothing parameter for cubic spline smoothing. Use 0 for no smoothing.
+Use \code{NULL} to automatically determine this value using leave-one-out
+cross-validation (see \code{smooth.spline} parameter \code{spar}).}
+
+\item{pseudocounts}{Smoothing parameter for Laplace smoothing. Use 0 for no smoothing, or
+1 for add-one smoothing.}
+
+\item{max.deviation}{Maximum mean deviation between identity breaks tolerated (as percent
+identity). Difference in number of \code{id.breaks} is never tolerated.}
+}
+\description{
+Compare the distribution of identities between two
+\code{\link{enve.RecPlot2}} objects.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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 +1,40 @@
+% 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]
+}