miga-base 0.4.3.0 → 0.5.0.0

data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd

@@ -1,25 +1,38 @@
-\name{enve.df2dist.group}
-\alias{enve.df2dist.group}
-\title{enve df2dist group}
-\description{Transform a dataframe (or coercible object, like a table) into a `dist` object, where
-there are 1 or more distances between each pair of objects.}
-\usage{enve.df2dist.group(x, obj1.index = 1, obj2.index = 2, dist.index = 3, 
-    summary = median, empty.rm = TRUE)}
-\arguments{
-  \item{x}{A dataframe (or coercible object) with at least three columns: (1) ID of the object 1,
-(2) ID of the object 2, and (3) distance between the two objects.}
-  \item{obj1.index}{Index of the column containing the ID of the object 1.}
-  \item{obj2.index}{Index of the column containing the ID of the object 2.}
-  \item{dist.index}{Index of the column containing the distance.}
-  \item{summary}{Function summarizing the different distances between the two objects.}
-  \item{empty.rm}{Remove rows with empty or NA groups}
-}
-
-\value{Returns a `dist` object.}
-
-\author{Luis M. Rodriguez-R [aut, cre]}
-
-
-
-
-
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/df2dist.R
+\name{enve.df2dist.group}
+\alias{enve.df2dist.group}
+\title{Enveomics: Data Frame to Dist (Group)}
+\usage{
+enve.df2dist.group(x, obj1.index = 1, obj2.index = 2, dist.index = 3,
+  summary = median, empty.rm = TRUE)
+}
+\arguments{
+\item{x}{A dataframe (or coercible object) with at least three columns:
+\enumerate{
+   \item ID of the object 1, 
+   \item ID of the object 2, and 
+   \item distance between the two objects.}}
+
+\item{obj1.index}{Index of the column containing the ID of the object 1.}
+
+\item{obj2.index}{Index of the column containing the ID of the object 2.}
+
+\item{dist.index}{Index of the column containing the distance.}
+
+\item{summary}{Function summarizing the different distances between the 
+two objects.}
+
+\item{empty.rm}{Remove rows with empty or \code{NA} groups.}
+}
+\value{
+Returns a \strong{dist} object.
+}
+\description{
+Transform a dataframe (or coercible object, like a table) into a 
+\strong{dist} object, where there are 1 or more distances between each pair 
+of objects.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd

@@ -1,26 +1,40 @@
-\name{enve.df2dist.list}
-\alias{enve.df2dist.list}
-\title{enve df2dist list}
-\description{Transform a dataframe (or coercible object, like a table) into a `dist` object.}
-\usage{enve.df2dist.list(x, groups, obj1.index = 1, obj2.index = 2, 
-    dist.index = 3, empty.rm = TRUE, ...)}
-\arguments{
-  \item{x}{A dataframe (or coercible object) with at least three columns: (1) ID of the object 1,
-(2) ID of the object 2, and (3) distance between the two objects.}
-  \item{groups}{Named array where the IDs correspond to the object IDs, and the values correspond to
-the group.}
-  \item{obj1.index}{Index of the column containing the ID of the object 1.}
-  \item{obj2.index}{Index of the column containing the ID of the object 2.}
-  \item{dist.index}{Index of the column containing the distance.}
-  \item{empty.rm}{Remove incomplete matrices}
-  \item{\dots}{Any other parameters supported by `enve.df2dist.group`.}
-}
-
-\value{Returns a `list` of `dist` object.}
-
-\author{Luis M. Rodriguez-R [aut, cre]}
-
-
-
-
-
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/df2dist.R
+\name{enve.df2dist.list}
+\alias{enve.df2dist.list}
+\title{Enveomics: Data Frame to Dist (List)}
+\usage{
+enve.df2dist.list(x, groups, obj1.index = 1, obj2.index = 2,
+  dist.index = 3, empty.rm = TRUE, ...)
+}
+\arguments{
+\item{x}{A dataframe (or coercible object) with at least three columns:
+\enumerate{
+   \item ID of the object 1, 
+   \item ID of the object 2, and 
+   \item distance between the two objects.}}
+
+\item{groups}{Named array where the IDs correspond to the object IDs,
+and the values correspond to the group.}
+
+\item{obj1.index}{Index of the column containing the ID of the object 1.}
+
+\item{obj2.index}{Index of the column containing the ID of the object 2.}
+
+\item{dist.index}{Index of the column containing the distance.}
+
+\item{empty.rm}{Remove incomplete matrices.}
+
+\item{...}{Any other parameters supported by
+\code{\link{enve.df2dist.group}}.}
+}
+\value{
+Returns a \strong{list} of \strong{dist} objects.
+}
+\description{
+Transform a dataframe (or coercible object, like a table)
+into a \strong{dist} object.
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -1,49 +1,67 @@
-\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))
-}
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/growthcurve.R
+\name{enve.growthcurve}
+\alias{enve.growthcurve}
+\title{Enveomics: Growth Curve}
+\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. \code{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 \code{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 \strong{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 \code{triplicates} is \code{FALSE}, or every three columns are assumed 
+to be a sample if \code{triplicates} is \code{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
+\code{K}: carrying capacity, 
+\code{r}: intrinsic growth rate, and
+\code{P0}: Initial population.}
+
+\item{nls.opt}{Any additional options passed to \code{nls}.}
+
+\item{...}{Any additional parameters to be passed to 
+\code{plot.enve.GrowthCurve}.}
+}
+\value{
+Returns an \code{\link{enve.GrowthCurve}} object.
+}
+\description{
+Calculates growth curves using the logistic growth function.
+}
+\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))
+
+}
+\author{
+Luis M. Rodriguez-R [aut, cre]
+}

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

@@ -1,28 +1,37 @@
-\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]}
-
-
-
-
-
+% 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

@@ -1,97 +1,122 @@
-\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}{Ignored, for backwards compatibility.}
-  \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. Deprecated.
-
-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]}
-
-
-
-
-
+% 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]
+}