miga-base 0.3.0.0 → 0.3.0.1

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

@@ -0,0 +1,49 @@
+\name{enve.growthcurve}
+\alias{enve.growthcurve}
+\title{enve growthcurve}
+\description{Calculates growth curves using the logistic growth function.}
+\usage{enve.growthcurve(x, times = 1:nrow(x), triplicates = FALSE, design, 
+    new.times = seq(min(times), max(times), length.out = length(times) * 
+        10), level = 0.95, interval = c("confidence", "prediction"), 
+    plot = TRUE, FUN = function(t, K, r, P0) K * P0 * exp(r * 
+        t)/(K + P0 * (exp(r * t) - 1)), nls.opt = list(), ...)}
+\arguments{
+  \item{x}{Data frame (or coercible) containing the observed growth data (e.g.,
+O.D. values). Each column is an independent growth curve and each
+row is a time point. NA's are allowed.}
+  \item{times}{Vector with the times at which each row was taken. By default, all
+rows are assumed to be part of constantly periodic measurements.}
+  \item{triplicates}{If TRUE, the columns are assumed to be sorted by sample with three
+replicates by sample. It requires a number of columns multiple of 3.}
+  \item{design}{Experimental design of the data. An `array` of mode list with sample
+names as index and the list of column names in each sample as the
+values. By default, each column is assumed to be an independent sample
+if `triplicates` is FALSE, or every three columns are assumed to be a
+sample if `triplicates` is TRUE. In the latter case, samples are
+simply numbered.}
+  \item{new.times}{Values of time for the fitted curve.}
+  \item{level}{Confidence (or prediction) interval in the fitted curve.}
+  \item{interval}{Type of interval to be calculated for the fitted curve.}
+  \item{plot}{Should the growth curve be plotted?}
+  \item{FUN}{Function to fit. By default: logistic growth with paramenters `K`:
+carrying capacity, `r`: intrinsic growth rate, and `P0`: Initial
+population.}
+  \item{nls.opt}{Any additional options passed to `nls`.}
+  \item{\dots}{Any additional parameters to be passed to `plot.enve.GrowthCurve`.}
+}
+
+\value{Returns an `enve.GrowthCurve` object.}
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+\examples{
+# Load data
+data("growth.curves", package="enveomics.R", envir=environment())
+# Generate growth curves with different colors
+g <- enve.growthcurve(growth.curves[,-1], growth.curves[,1], triplicates=TRUE)
+# Generate black-and-white growth curves with different symbols
+plot(g, pch=15:17, col="black", band.density=45, band.angle=c(-45,45,0))
+}

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

@@ -0,0 +1,28 @@
+\name{enve.prune.dist}
+\alias{enve.prune.dist}
+\title{enve prune dist}
+\description{Automatically prunes a tree, to keep representatives of each clade.}
+\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 `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, 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 "tip-pairs" nodes sampling. This sampling
+is less reproducible and more computationally expensive, but it's the only
+solution if the cophenetic matrix exceeds 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 `min_nodes_random`.}
+}
+
+\value{Returns a pruned phylo object.}
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,97 @@
+\name{enve.recplot}
+\alias{enve.recplot}
+\title{enve recplot}
+\description{Produces recruitment plots provided that BlastTab.catsbj.pl has
+been previously executed. Requires the gplots library.}
+\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 .rec and .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 stats package.}
+  \item{id.metric}{Metric of identity to be used (Y-axis). It can be any unambiguous prefix
+of "identity", "corrected identity", or "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 "sum", "average", "median", "90\% lower bound",
+"90\% upper bound", "95\% lower bound", and "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 NA to ignore Contig boundaries.}
+  \item{ret.recplot}{Indicates if the matrix of the recruitment plot is to be returned.}
+  \item{ret.hist}{Indicates if the vectors of the identity and position histograms are to be returned.}
+  \item{ret.mode}{Indicates if the mode of the identity is to be computed. It requires the 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{\dots}{Any additional graphic parameters to be passed to plot for all panels except the
+recruitment plot (lower-left).}
+}
+
+\value{A list with the following elements:
+
+pos.marks: Midpoints of the position histogram.
+
+id.matrix: Midpoints of the identity histogram.
+
+recplot (if ret.recplot=TRUE): Matrix containing the recruitment plot values.
+
+id.mean: Mean identity.
+
+id.median: Median identity.
+
+id.mode (if ret.mode=TRUE): Mode of the identity.
+
+id.hist (if ret.hist=TRUE): Values of the identity histogram.
+
+pos.hist.low (if ret.hist=TRUE): Values of the position histogram (depth) with "low"
+identity (i.e., below id.cutoff).
+
+pos.hist.top (if ret.hist=TRUE): Values of the position histogram (depth) with "top"
+identity (i.e., above id.cutoff).
+
+id.max: Value of id.max. This is returned because id.max=NULL may vary.
+
+id.cutoff: Value of id.cutoff. This is returned because id.cutoff=NULL may vary.
+
+seqdepth.mean.top: Average sequencing depth with identity above id.cutoff.
+
+seqdepth.mean.low: Average sequencing depth with identity below id.cutoff.
+
+seqdepth.mean.all: Average sequencing depth without identity filtering.
+
+seqdepth.median.top: Median sequencing depth with identity above id.cutoff.
+
+seqdepth.median.low: Median sequencing depth with identity below id.cutoff.
+
+seqdepth.median.all: Median sequencing depth without identity filtering.
+
+id.metric: Full name of the used identity metric.
+
+id.summary: Full name of the summary method used to build the identity plot.}
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,40 @@
+\name{enve.RecPlot2-class}
+\Rdversion{1.1}
+\docType{class}
+\alias{enve.RecPlot2-class}
+\alias{enve.RecPlot2}
+%% \alias{$}
+
+\title{enve.RecPlot2 S4 class}
+\description{Enve-omics representation of Recruitment plots. This object can
+be produced by `enve.recplot2` and supports S4 method plot.}
+\section{Objects from the Class}{Objects can be created by calls of the form \code{new(enve.RecPlot2 ...)}}
+\section{Slots}{
+  \describe{
+    \item{\code{counts}:}{(\code{matrix}) Counts as a two-dimensional histogram.}
+    \item{\code{pos.counts.in}:}{(\code{numeric}) Counts of in-group hits per position bin.}
+    \item{\code{pos.counts.out}:}{(\code{numeric}) Counts of out-group hits per position bin.}
+    \item{\code{id.counts}:}{(\code{numeric}) Counts per ID bin.}
+    \item{\code{id.breaks}:}{(\code{numeric}) Breaks of identity bins.}
+    \item{\code{pos.breaks}:}{(\code{numeric}) Breaks of position bins.}
+    \item{\code{seq.breaks}:}{Object of class \code{"numeric"}}
+    \item{\code{peaks}:}{(\code{list}) Peaks identified in the recplot.
+Limits of the subject sequences after concatenation.}
+    \item{\code{seq.names}:}{(\code{character}) Names of the subject sequences.}
+    \item{\code{id.metric}:}{(\code{character}) Metric used as 'identity'.}
+    \item{\code{id.ingroup}:}{(\code{logical}) Identity bins considered in-group.}
+    \item{\code{call}:}{(\code{call}) Call producing this object.}
+  }
+}
+\section{Methods}{
+  \describe{
+    \item{$}{\code{signature(x = "enve.RecPlot2")}: ... }
+	 }
+}
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,40 @@
+\name{enve.recplot2}
+\alias{enve.recplot2}
+\title{enve recplot2}
+\description{Produces recruitment plots provided that BlastTab.catsbj.pl has
+been previously executed.}
+\usage{enve.recplot2(prefix, plot = TRUE, pos.breaks = 1000, id.breaks = 300, 
+    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 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).}
+  \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.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: `median` to estimate the median instead of total bins, and
+`function(x) mlv(x,method='parzen')$M` to estimate the mode.}
+  \item{id.cutoff}{Cutoff of identity metric above which the hits are considered
+'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{\dots}{Any additional parameters supported by `plot.enve.RecPlot2`.}
+}
+
+\value{Returns an object of class `enve.RecPlot2`.}
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,24 @@
+\name{enve.recplot2.__counts}
+\alias{enve.recplot2.__counts}
+\title{enve recplot2   counts}
+\description{Internal ancilliary function (see `enve.recplot2`).}
+\usage{enve.recplot2.__counts(x, pos.breaks, id.breaks, rec.idcol)}
+\arguments{
+  \item{x}{
+}
+  \item{pos.breaks}{
+}
+  \item{id.breaks}{
+}
+  \item{rec.idcol}{
+}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,40 @@
+\name{enve.recplot2.__findPeak}
+\alias{enve.recplot2.__findPeak}
+\title{enve recplot2   findPeak}
+\description{Internall ancilliary function (see `enve.recplot2.findPeaks`).}
+\usage{enve.recplot2.__findPeak(lsd1, min.points, quant.est, mlv.opts, 
+    fitdist.opts, with.skewness, optim.rounds, optim.epsilon, 
+    n.total, merge.logdist, verbose)}
+\arguments{
+  \item{lsd1}{
+}
+  \item{min.points}{
+}
+  \item{quant.est}{
+}
+  \item{mlv.opts}{
+}
+  \item{fitdist.opts}{
+}
+  \item{with.skewness}{
+}
+  \item{optim.rounds}{
+}
+  \item{optim.epsilon}{
+}
+  \item{n.total}{
+}
+  \item{merge.logdist}{
+}
+  \item{verbose}{
+}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,18 @@
+\name{enve.recplot2.__findPeaks}
+\alias{enve.recplot2.__findPeaks}
+\title{enve recplot2   findPeaks}
+\description{Internal ancilliary function (see `enve.recplot2.findPeaks`).}
+\usage{enve.recplot2.__findPeaks(peaks.opts)}
+\arguments{
+  \item{peaks.opts}{
+}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,22 @@
+\name{enve.recplot2.__peakHist}
+\alias{enve.recplot2.__peakHist}
+\title{enve recplot2   peakHist}
+\description{Internal ancilliary function (see `enve.RecPlot2.Peak`).}
+\usage{enve.recplot2.__peakHist(x, mids, counts = TRUE)}
+\arguments{
+  \item{x}{
+}
+  \item{mids}{
+}
+  \item{counts}{
+}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,20 @@
+\name{enve.recplot2.__whichClosestPeak}
+\alias{enve.recplot2.__whichClosestPeak}
+\title{enve recplot2   whichClosestPeak}
+\description{Internal ancilliary function (see `enve.recplot2.findPeaks`).}
+\usage{enve.recplot2.__whichClosestPeak(peak, peaks)}
+\arguments{
+  \item{peak}{
+}
+  \item{peaks}{
+}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,18 @@
+\name{enve.recplot2.changeCutoff}
+\alias{enve.recplot2.changeCutoff}
+\title{enve recplot2 changeCutoff}
+\description{Change the intra-species cutoff of an existing recruitment plot.}
+\usage{enve.recplot2.changeCutoff(rp, new.cutoff = 98)}
+\arguments{
+  \item{rp}{enve.RecPlot2 object.}
+  \item{new.cutoff}{New cutoff to use.}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,18 @@
+\name{enve.recplot2.corePeak}
+\alias{enve.recplot2.corePeak}
+\title{enve recplot2 corePeak}
+\description{Finds the peak in a list of peaks that is most likely to represent the
+"core genome" of a population.}
+\usage{enve.recplot2.corePeak(x)}
+\arguments{
+  \item{x}{`list` of `enve.RecPlot2.Peak` objects.}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,27 @@
+\name{enve.recplot2.extractWindows}
+\alias{enve.recplot2.extractWindows}
+\title{enve recplot2 extractWindows}
+\description{Extract windows significantly below (or above) the peak in sequencing
+depth.}
+\usage{enve.recplot2.extractWindows(rp, peak, lower.tail = TRUE, significance = 0.05, 
+    seq.names = FALSE)}
+\arguments{
+  \item{rp}{Recruitment plot, a enve.Recplot2 object.}
+  \item{peak}{Peak, a enve.RecPlot2.Peak object. If list, it is assumed to be a list
+of enve.RecPlot2.Peak objects, in which case the core peak is used
+(see enve.recplot2.corePeak).}
+  \item{lower.tail}{If 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. It
+assumes that the recruitment plot was generated with pos.breaks=0.}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+