miga-base 0.7.26.0 → 1.0.0.1

data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd

@@ -0,0 +1,44 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/autoprune.R
+\name{enve.prune.dist}
+\alias{enve.prune.dist}
+\title{Enveomics: Prune Dist}
+\usage{
+enve.prune.dist(
+  t,
+  dist.quantile = 0.25,
+  min_dist,
+  quiet = FALSE,
+  max_iters = 100,
+  min_nodes_random = 40000,
+  random_nodes_frx = 1
+)
+}
+\arguments{
+\item{t}{A \strong{phylo} object or a path to the Newick file.}
+
+\item{dist.quantile}{The quantile of edge lengths.}
+
+\item{min_dist}{The minimum distance to allow between two tips.
+If not set, \code{dist.quantile} is used instead to calculate it.}
+
+\item{quiet}{Boolean indicating if the function must run without output.}
+
+\item{max_iters}{Maximum number of iterations.}
+
+\item{min_nodes_random}{Minimum number of nodes to trigger \emph{tip-pairs} nodes sampling. 
+This sampling is less reproducible and more computationally expensive,
+but it's the only solution if the cophenetic matrix exceeds \code{2^31-1} 
+entries; above that, it cannot be represented in R.}
+
+\item{random_nodes_frx}{Fraction of the nodes to be sampled if more than \code{min_nodes_random}.}
+}
+\value{
+Returns a pruned \strong{phylo} object.
+}
+\description{
+Automatically prunes a tree, to keep representatives of each clade.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -0,0 +1,139 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/recplot.R
+\name{enve.recplot}
+\alias{enve.recplot}
+\title{Enveomics: Recruitment Plots}
+\usage{
+enve.recplot(
+  prefix,
+  id.min = NULL,
+  id.max = NULL,
+  id.binsize = NULL,
+  id.splines = 0,
+  id.metric = "id",
+  id.summary = "sum",
+  pos.min = 1,
+  pos.max = NULL,
+  pos.binsize = 1000,
+  pos.splines = 0,
+  rec.col1 = "white",
+  rec.col2 = "black",
+  main = NULL,
+  contig.col = grey(0.85),
+  ret.recplot = FALSE,
+  ret.hist = FALSE,
+  ret.mode = FALSE,
+  id.cutoff = NULL,
+  verbose = TRUE,
+  ...
+)
+}
+\arguments{
+\item{prefix}{Path to the prefix of the BlastTab.catsbj.pl output files. At
+least the files \strong{.rec} and \strong{.lim} must exist with this prefix.}
+
+\item{id.min}{Minimum identity to be considered. By default, the minimum detected
+identity. This value is a percentage.}
+
+\item{id.max}{Maximum identity to be considered. By default, 100\%.}
+
+\item{id.binsize}{Size of the identity bins (vertical histograms). By default, 0.1 for
+identity metrics and 5 for bit score.}
+
+\item{id.splines}{Smoothing parameter for the splines in the identity histogram. Zero (0) for no
+splines. A generally good value is 1/2. If non-zero, requires the \pkg{stats} package.}
+
+\item{id.metric}{Metric of identity to be used (Y-axis). 
+It can be any unambiguous prefix of:
+\itemize{
+\item "identity"
+\item "corrected identity" 
+\item "bit score"}}
+
+\item{id.summary}{Method used to build the identity histogram (Horizontal axis of the right panel).
+It can be any unambiguous prefix of: 
+\itemize{
+\item "sum"
+\item "average" 
+\item "median"
+\item "90\% lower bound"
+\item "90\% upper bound"
+\item "95\% lower bound"
+\item "95\% upper bound" }
+The last four options
+correspond to the upper and lower boundaries of the 90\% and 95\% empirical confidence
+intervals.}
+
+\item{pos.min}{Minimum (leftmost) position in the reference (concatenated) genome (in bp).}
+
+\item{pos.max}{Maximum (rightmost) position in the reference (concatenated) genome (in bp).
+By default: Length of the genome.}
+
+\item{pos.binsize}{Size of the position bins (horizontal histograms) in bp.}
+
+\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{rec.col1}{Lightest color in the recruitment plot.}
+
+\item{rec.col2}{Darkest color in the recruitment plot.}
+
+\item{main}{Title of the plot.}
+
+\item{contig.col}{Color of the Contig boundaries. Set to \code{NA} to ignore Contig boundaries.}
+
+\item{ret.recplot}{Indicates if the matrix of the recruitment plot is to be returned.}
+
+\item{ret.hist}{Ignored, for backwards compatibility.}
+
+\item{ret.mode}{Indicates if the mode of the identity is to be computed. It requires the 
+\pkg{modeest} package.}
+
+\item{id.cutoff}{Minimum identity to consider an alignment as "top". By default, it is 0.95 for the
+identity metrics and 95\% of the best scoring alignment for bit score.}
+
+\item{verbose}{Indicates if the function should report the advance.}
+
+\item{...}{Any additional graphic parameters to be passed to plot for all panels except the
+recruitment plot (lower-left).}
+}
+\value{
+Returns a list with the following elements:
+
+\describe{
+\item{\code{pos.marks}}{Midpoints of the position histogram.}
+\item{\code{id.matrix}}{Midpoints of the identity histogram.}
+\item{\code{recplot}}{Matrix containing the recruitment plot values 
+     (if \code{ret.recplot=TRUE}).}
+\item{\code{id.mean}}{Mean identity.}
+\item{\code{id.median}}{Median identity.}
+\item{\code{id.mode}}{Mode of the identity (if \code{ret.mode=TRUE}). Deprecated.}
+\item{\code{id.hist}}{Values of the identity histogram (if \code{ret.hist=TRUE}).}
+\item{\code{pos.hist.low}}{Values of the position histogram (depth) with "low"
+     identity (i.e., below id.cutoff) (if \code{ret.hist=TRUE}).}
+\item{\code{pos.hist.top}}{Values of the position histogram (depth) with "top"
+     identity (i.e., above id.cutoff) (if \code{ret.hist=TRUE}).}
+\item{\code{id.max}}{Value of \code{id.max}. This is returned because 
+     \code{id.max=NULL} may vary.}
+\item{\code{id.cutoff}}{Value of \code{id.cutoff}. 
+     This is returned because \code{id.cutoff=NULL} may vary.}
+\item{\code{seqdepth.mean.top}}{Average sequencing depth with identity above 
+     \code{id.cutoff}.}
+\item{\code{seqdepth.mean.low}}{Average sequencing depth with identity below 
+     \code{id.cutoff}.} 
+\item{\code{seqdepth.mean.all}}{Average sequencing depth without identity filtering.}
+\item{\code{seqdepth.median.top}}{Median sequencing depth with identity above 
+     \code{id.cutoff}.}
+\item{\code{seqdepth.median.low}}{Median sequencing depth with identity below 
+     \code{id.cutoff}.}
+\item{\code{seqdepth.median.all}}{Median sequencing depth without identity filtering.}
+\item{\code{id.metric}}{Full name of the used identity metric.}
+\item{\code{id.summary}}{Full name of the summary method used to build the identity plot.}}
+}
+\description{
+Produces recruitment plots provided that BlastTab.catsbj.pl has
+been previously executed. Requires the \pkg{gplots} library.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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 +1,77 @@
+% 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 +1,47 @@
+% 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]
+}