miga-base 0.3.1.7 → 0.3.2.0

data/utils/enveomics/enveomics.R/README.md

@@ -4,45 +4,53 @@
 To install the latest version of `enveomics.R` uploaded to CRAN, execute in R:
 
 ```R
-    install.packages('enveomics.R')
+install.packages('enveomics.R')
 ```
 
 To install the current developer version of `enveomics.R`, execute in R:
 
 ```R
-    install.packages('devtools')
-    library('devtools')
-    install_github('lmrodriguezr/enveomics', subdir='enveomics.R')
+install.packages('devtools')
+library('devtools')
+install_github('lmrodriguezr/enveomics', subdir='enveomics.R')
 ```
 
 ## Using `enveomics.R`
 To load enveomics.R, simply execute:
 
 ```R
-    library(enveomics.R);
+library(enveomics.R);
 ```
 
 And open help messages using any of the following commands:
 
 ```R
-    ?enveomics.R
-    ?enve.barplot
-    ?enve.recplot2
-    ?enve.recplot2.changeCutoff
-    ?enve.recplot2.findPeaks
-    ?enve.recplot2.corePeak
-    ?enve.recplot2.extractWindows
-    ?enve.prune.dist
-    ?enve.tribs
-    ?enve.tribs.test
-    ?enve.growthcurve
-    ?enve.col.alpha
+?enveomics.R
+?enve.barplot
+?enve.recplot2
+?enve.recplot2.compareIdentities
+?enve.recplot2.changeCutoff
+?enve.recplot2.findPeaks
+?enve.recplot2.corePeak
+?enve.recplot2.extractWindows
+?enve.recplot2.coordinates
+?enve.recplot2.seqdepth
+?enve.recplot2.ANIr
+?enve.prune.dist
+?enve.tribs
+?enve.tribs.test
+?enve.growthcurve
+?enve.col.alpha
 ```
 
 You can run some examples using these libraries in the
 [enveomics-GUI](https://github.com/lmrodriguezr/enveomics-gui).
 
+For additional information on recruitment plots, see the
+[Recruitment plots working document](https://github.com/lmrodriguezr/enveomics/blob/master/Docs/recplot2.md).
+
 ## Changelog
+* 1.3: Several bug fixes and new utilities for recruitment plots (recplot2).
 * 1.1.0: New function enve.growthcurve and related class enve.GrowthCurve
   with S3 methods plot and summary.
 * 1.0.2: Fine-tuned default parameters in enve.recplot2.findPeaks and
@@ -50,3 +58,4 @@ You can run some examples using these libraries in the
   datasets when using too many threads.
 * 1.0.1: enve.recplot2 now supports pos.breaks=0 to define a
   bin per subject sequence.
+

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

@@ -17,7 +17,7 @@ be produced by `enve.recplot2` and supports S4 method plot.}
     \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{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.}

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

@@ -0,0 +1,23 @@
+\name{enve.recplot2.ANIr}
+\alias{enve.recplot2.ANIr}
+\title{enve recplot2 ANIr}
+\description{Estimate the Average Nucleotide Identity from reads (ANIr) from a
+recruitment plot}
+\usage{enve.recplot2.ANIr(x, range = c(0, Inf))}
+\arguments{
+  \item{x}{`enve.RecPlot2` object.}
+  \item{range}{Range of identities to be considered. By default, the full range
+is used (note that the upper boundary is `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).}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -4,9 +4,9 @@
 \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, 
-    ...)}
+    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 BlastTab.catsbj.pl output files. At
 least the files .rec and .lim must exist with this prefix.}
@@ -17,6 +17,9 @@ 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.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

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

@@ -0,0 +1,32 @@
+\name{enve.recplot2.compareIdentities}
+\alias{enve.recplot2.compareIdentities}
+\title{enve recplot2 compareIdentities}
+\description{Compare the distribution of identities between two enve.RecPlot2 objects.}
+\usage{enve.recplot2.compareIdentities(x, y, method = "hellinger", smooth.par = NULL, 
+    pseudocounts = 0, max.deviation = 0.75)}
+\arguments{
+  \item{x}{First enve.RecPlot2 object.}
+  \item{y}{Second enve.RecPlot2 object.}
+  \item{method}{Distance method to use. This should be (an unambiguous abbreviation of)
+one of:
+"hellinger" (Hellinger, 1090, doi:10.1515/crll.1909.136.210),
+"bhattacharyya" (Bhattacharyya, 1943, Bull. Calcutta Math. Soc. 35),
+"kl" or "kullback-leibler" (Kullback & Leibler, 1951,
+doi:10.1214/aoms/1177729694), or "euclidean".}
+  \item{smooth.par}{Smoothing parameter for cubic spline smoothing. Use 0 for no smoothing.
+Use NULL to automatically determine this value using leave-one-out
+cross-validation (see `smooth.spline` parameter `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 id.breaks is never tolerated.}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,24 @@
+\name{enve.recplot2.coordinates}
+\alias{enve.recplot2.coordinates}
+\title{enve recplot2 coordinates}
+\description{Returns the sequence name and coordinates of the requested position bins.}
+\usage{enve.recplot2.coordinates(x, bins)}
+\arguments{
+  \item{x}{`enve.RecPlot2` object.}
+  \item{bins}{Vector of selected bins to return. It can be a vector of logical values
+with the same length as `x$pos.breaks`-1 or a vector of integers. If
+missing, returns the coordinates of all windows.}
+}
+
+\value{Returns a data.frame with four columns: name.from (character), pos.from
+(numeric) name.to (character), and pos.to (numeric). The first two
+correspond to sequence and position of the start point of the bin, the
+last two correspond to the sequence and position of the end point of the
+bin.}
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -6,18 +6,23 @@ 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{rp}{Recruitment plot, a enve.RecPlot2 object.}
+  \item{peak}{Peak, an `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.}
+  \item{seq.names}{Returns subject sequence names instead of a vector of Booleans. If
+the recruitment plot was generated with pos.breaks=0 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 `seq.names=FALSE`. If `seq.names=TRUE`,
+it returns a vector of characters if the object was built with
+`pos.breaks=0` or a data.frame with four columns otherwise: name.from,
+name.to, pos.from, and pos.to (see `enve.recplot2.coordinates`).}
 
 \author{Luis M. Rodriguez-R [aut, cre]}
 

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

@@ -2,45 +2,16 @@
 \alias{enve.recplot2.findPeaks}
 \title{enve recplot2 findPeaks}
 \description{Identifies peaks in the population histogram potentially indicating
-sub-population mixtures.}
-\usage{enve.recplot2.findPeaks(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(1e-06, -Inf, 0), upper = c(Inf, 
-        0, Inf)), fitdist.opts.norm = list(distr = "norm", method = "qme", 
-    probs = c(0.4, 0.6), start = list(sd = 1), lower = c(1e-08, 
-        0)), rm.top = 0.05, with.skewness = TRUE, optim.rounds = 200, 
-    optim.epsilon = 1e-08, merge.logdist = log(1.75), verbose = FALSE)}
+sub-population mixtures}
+\usage{enve.recplot2.findPeaks(x, method = "emauto", ...)}
 \arguments{
   \item{x}{An `enve.RecPlot2` object.}
-  \item{min.points}{Minimum number of points in the quantile-estimation-range
-(`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}{Options passed to `mlv` to estimate the mode.}
-  \item{fitdist.opts.sn}{
-}
-  \item{fitdist.opts.norm}{
-}
-  \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 rm.top=0. The quantile is determined *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 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 `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 |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{method}{Peak-finder method. This should be one of:
+"emauto" (Expectation-Maximization with auto-selection of components),
+"em" (Expectation-Maximization),
+"mower" (Custom distribution-mowing method).}
+  \item{\dots}{Any additional parameters supported by
+`enve.recplot2.findPeaks.<method>`.}
 }
 
 \value{Returns a list of `enve.RecPlot2.Peak` objects.}

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

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

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

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

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

@@ -0,0 +1,29 @@
+\name{enve.recplot2.findPeaks.__emauto_one}
+\alias{enve.recplot2.findPeaks.__emauto_one}
+\title{enve recplot2 findPeaks   emauto one}
+\description{Internal ancilliary function (see `enve.recplot2.findPeaks.emauto).}
+\usage{enve.recplot2.findPeaks.__emauto_one(x, comp, do_crit, best, 
+    verbose, ...)}
+\arguments{
+  \item{x}{
+}
+  \item{comp}{
+}
+  \item{do_crit}{
+}
+  \item{best}{
+}
+  \item{verbose}{
+}
+  \item{\dots}{
+}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

@@ -0,0 +1,42 @@
+\name{enve.recplot2.findPeaks.__mow_one}
+\alias{enve.recplot2.findPeaks.__mow_one}
+\title{enve recplot2 findPeaks   mow one}
+\description{Internall ancilliary function (see `enve.recplot2.findPeaks.mower`).}
+\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}{
+}
+  \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}{
+}
+  \item{log}{
+}
+}
+
+
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+

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

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

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

@@ -0,0 +1,33 @@
+\name{enve.recplot2.findPeaks.em}
+\alias{enve.recplot2.findPeaks.em}
+\title{enve recplot2 findPeaks em}
+\description{Identifies peaks in the population histogram using a Gaussian Mixture
+Model Expectation Maximization (GMM-EM) method.}
+\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 `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 rm.top=0. The quantile is determined *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 'mu', 'sd', and 'alpha', each
+of length `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 `enve.RecPlot2.Peak` objects.}
+
+\author{Luis M. Rodriguez-R [aut, cre]}
+
+
+
+
+