obitools/ROBITools
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit the man pages and make aggregate public again

Browse Source
This commit is contained in:
Eric Coissac
2018-07-25 21:38:48 +02:00
parent 51f152cca4
commit 052d6edc75
41 changed files with 1659 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.gitignore vendored Normal file
View File

@@ -0,0 +1,4 @@
.Rproj.user
.Rhistory
.RData
loopbenchmark.R

11
R/aggregate.R
View File

@@ -101,9 +101,10 @@ aggregate.metabarcoding.data=function(x, by, FUN,...,
m = matrix(as.character(x[[n]]))
dim(m)=df
}
else
else {
m = x[[n]]
isfact=FALSE
}
aggr.args = list(m,by=by,FUN=f,simplify=FALSE)
lagr = do.call(aggregate,aggr.args)
lagr = as.factor.or.matrix(lagr[,-(1:ncat),drop=FALSE])
@@ -182,15 +183,15 @@ aggregate.metabarcoding.data=function(x, by, FUN,...,
for (n in ln) {
f = layers[[n]]
if (is.factor(x[[n]])){
isfact=is.factor(x[[n]])
if (isfact){
isfact = TRUE
lf = levels(x[[n]])
df = dim(x[[n]])
m = matrix(as.character(x[[n]]))
dim(m)=df
}
else
else
m = x[[n]]
aggr.args = list(t(m),by=by,FUN=f,simplify=FALSE)

34
man/ROBITools-package.Rd Normal file
View File

@@ -0,0 +1,34 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/ROBITools.R
\docType{package}
\name{ROBITools-package}
\alias{ROBITools-package}
\alias{ROBITools}
\title{A package to manipulate DNA metabarcoding data.}
\description{
A package to manipulate DNA metabarcoding data.
}
\details{
This package was written as a following of the OBITools.
\tabular{ll}{
Package: \tab ROBITools\cr
Type: \tab Package\cr
Version: \tab 0.1\cr
Date: \tab 2013-06-27\cr
License: \tab CeCILL 2.0\cr
LazyLoad: \tab yes\cr
}
}
\references{
http://metabarcoding.org/obitools
}
\author{
Frederic Boyer
Aurelie Bonin
Lucie Zinger
Eric Coissac
}

41
man/addS3Class.Rd Normal file
View File

@@ -0,0 +1,41 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/s3objects.R
\name{addS3Class}
\alias{addS3Class}
\title{Adds a class into the class hierarchie attribute.}
\usage{
addS3Class(object, classname)
}
\arguments{
\item{object}{the object to modify}
\item{classname}{the name of the new class}
}
\value{
the object given as parametter casted to the new
class
}
\description{
\code{addS3Class} adds a new class name to the vector
of class associated to the object. This the way to
assign an object to an S3 class. \code{addS3Class} add
the new class name in front of the class vector
}
\note{
for efficiency purpose no check is done on the input
parametters
}
\examples{
x = c(1,3,2,5)
x = addS3Class(x,"my.vector")
class(x)
}
\seealso{
\code{\link{rmS3Class}}
}
\author{
Eric Coissac
}
\keyword{function}
\keyword{system}

52
man/const-threshold-mask-methods.Rd Normal file
View File

@@ -0,0 +1,52 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/metabarcoding_threshold.R
\docType{methods}
\name{const.threshold.mask,metabarcoding.data-method}
\alias{const.threshold.mask,metabarcoding.data-method}
\alias{const.threshold.mask-methods,metabarcoding.data}
\title{Computes a constant thresold mask for filtering read aboundancies.}
\usage{
\S4method{const.threshold.mask}{metabarcoding.data}(data, MARGIN,
threshold = 0.01, operator = "<")
}
\arguments{
\item{data}{The \code{\linkS4class{metabarcoding.data}} instance
on normalisation have to be computed.}
\item{MARGIN}{Indicates if the sums have to be computed across
samples or motus.
Allowed values are :
\itemize{
\item{'sample' or 1} for computing sum across samples
\item{'motu' or 2} for computing sum across motus
}}
\item{threshold}{a numeric value between 0 and 1 indicating which part of
the signal must be conserved. Default value is setup to
0.01 (1% of the normalized signal).}
\item{operator}{is a logical comparison operator.}
}
\value{
A logical matrix usable for selecting cell in the read aboundancy matrix.
}
\description{
The method \code{const.threshold.mask} of the class \code{\linkS4class{metabarcoding.data}}
computes a logical matrix of the same size than the read matrix of the data parameter.
Each cell of this matrix contains a \code{TRUE} or a \code{FALSE} value according to the
relationship existing between the read abondancy and the global theshold.
}
\details{
(computed value) = (normalized read aboundancy) operator (threshold value)
for a cell in the result matrix, \code{(normalized read aboundancy)} is extracted from the read layer
after normalization.
\code{operator} is a comparaison operator and \code{(threshold value)} is estimated with the
\code{\link{theshold}} method.
}
\seealso{
\code{\linkS4class{metabarcoding.data}}, \code{\link{threshold.mask}}, \code{\link{normalize}}
}
\author{
Aurelie Bonin
}

44
man/contaslayer.Rd Normal file
View File

@@ -0,0 +1,44 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/contaslayer.R
\name{contaslayer}
\alias{contaslayer}
\title{Detects contaminants in metabarcoding data}
\usage{
contaslayer(x, controls, clust = NULL)
}
\arguments{
\item{x}{a \code{\link{metabarcoding.data}} object}
\item{controls}{a vector of samples names where conta are suspected to be detected
(typically negative control names).}
\item{clust}{a vector for grouping sequences. Default set to \code{NULL}.}
}
\value{
a vector containing the names of sequences identified as contaminants
}
\description{
Detects sequences/motus in a \code{\link{metabarcoding.data}} object
for which frequencies over the entire dataset are maximum in negative controls and
hence, most likely to be contaminants.
}
\examples{
data(termes)
termes.ok = termes[,colSums(termes$reads)>0]
neg = rownames(termes.ok)[grep("r",rownames(termes.ok))]
#finds contaminants based on neg samples
contaslayer(termes.ok, neg)
# extanding contamininant detection with grouping factor,
# typically obiclean/sumatra cluster or taxonomy membership
contaslayer(termes.ok, neg, termes.ok$motus$scientific_name)
}
\seealso{
\code{\link{threshold}} for further trimming
}
\author{
Lucie Zinger
}

50
man/createS3Class.Rd Normal file
View File

@@ -0,0 +1,50 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/s3objects.R
\name{createS3Class}
\alias{createS3Class}
\title{create basic functions to manipulate a new S3 class}
\usage{
createS3Class(classname)
}
\arguments{
\item{classname}{a \code{character string} indicating the name
of the new class.}
}
\description{
createS3Class function create in the \code{package:ROBITools}
environment an \code{is.xxx} function and an \code{as.xxx} function
allowing to test if an abject belong the class \code{xxx} and to add
the class \code{xxx} to the class list of an object. \code{xxx} is a
generic class name that is specified through the \code{classname}
argument of the function.
}
\note{
Take care that the new functions are created in the
\code{package:ROBITools} environment.
}
\examples{
# Create a new S3 class named mynewclass
createS3Class('mynewclass')
#create a new vector object
x=c(1,4,6)
# test if it belongs the new class, that is false
is.mynewclass(x)
# Associate x to the new class
as.mynewclass(x)
# test again if x belongs the new class, that is now true
is.mynewclass(x)
}
\seealso{
\code{\link{rmS3Class}}
}
\author{
Eric Coissac
}
\keyword{function}
\keyword{system}

52
man/dbtree.Rd Normal file
View File

@@ -0,0 +1,52 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/taxoDBtree.R
\name{dbtree}
\alias{dbtree}
\title{Construct a taxonomic tree from a list of taxa}
\usage{
dbtree(x)
}
\arguments{
\item{x}{a table containing the taxonomic path of the references. Typically an output from get.classic.taxonomy}
}
\value{
g a directed graph displaying the taxonomy hierarchy of the input data. Stored in a \code{\link{igraph}} object
where the taxonomic ranks of the vertices are added to the vertices attributes
}
\description{
Construct a graph from a table containing the taxonomic path of sequences
}
\examples{
data(termes)
taxo=default.taxonomy()
termes.taxo.table = get.classic.taxonomy(termes, taxo, "taxid")
head(termes.taxo.table)
graph.tax.termes = dbtree(termes.taxo.table[,1:7])
library(igraph)
#plot the tree
coord = layout.reingold.tilford(graph.tax.termes, root=1, circular=F)
v.cex = as.factor(V(graph.tax.termes)$rank)
levels(v.cex) = match(levels(v.cex), colnames(termes.taxo.table))
plot(graph.tax.termes, vertex.size=1, vertex.label.cex=2*(as.numeric(as.vector(v.cex))^-1), edge.arrow.size=0, layout=coord)
#Vizualization with sequence counts
tax.count = log10(colSums(termes$reads)[match(as.vector(V(graph.tax.termes)$name), termes$motus$scientific_name)])
tax.count[is.na(tax.count)|tax.count<0] = 0.01
V(graph.tax.termes)$count = unname(tax.count)
plot(graph.tax.termes, vertex.size=V(graph.tax.termes)$count, vertex.label.cex=2*(as.numeric(as.vector(v.cex))^-1), edge.arrow.size=0, layout=coord)
}
\seealso{
\code{\link{get.classic.taxonomy}}
}
\author{
Lucie Zinger
}

32
man/dist.center.group.Rd Normal file
View File

@@ -0,0 +1,32 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mstat.R
\name{dist.center.group}
\alias{dist.center.group}
\title{Builds the list of sample groups included in a circle around a central sample}
\usage{
dist.center.group(dtable, radius, center = TRUE)
}
\arguments{
\item{dtable}{a distance table between samples as
computed by \code{\link{dist.grid}}}
\item{radius}{the radius of the circle}
\item{center}{a \code{logical} value indicating if the center of
the group must be included in the group}
}
\value{
a list of vectors containing the labels of the group members
}
\description{
Builds the list of sample groups included in a circle around a central sample
}
\examples{
data(termes)
termes.ok = termes[,colSums(termes$reads)>0]
pos = expand.grid(1:3 * 10,1:7 * 10)
labels = rownames(termes.ok)
d = dist.grid(pos[,1],pos[2],labels)
groups = dist.center.group(d,20)
}

31
man/dist.clique.group.Rd Normal file
View File

@@ -0,0 +1,31 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mstat.R
\name{dist.clique.group}
\alias{dist.clique.group}
\title{Builds the list of sample groups including samples closest than a define distance}
\usage{
dist.clique.group(dtable, dmax, center = True)
}
\arguments{
\item{dtable}{a distance table between samples as
computed by \code{\link{dist.grid}}}
\item{dmax}{the maximum distance between two samples}
}
\value{
a list of vectors containing the labels of the group members
}
\description{
A graph is build by applying the threshold \code{dmax} to the distance matrix
A group is a clique max in this graph. Consequently all member pairs of a group
are distant by less or equal to \code{dmax}.
}
\examples{
data(termes)
termes.ok = termes[,colSums(termes$reads)>0]
pos = expand.grid(1:3 * 10,1:7 * 10)
labels = rownames(termes.ok)
d = dist.grid(pos[,1],pos[2],labels)
groups = dist.clique.group(d,20)
}

32
man/dist.grid.Rd Normal file
View File

@@ -0,0 +1,32 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mstat.R
\name{dist.grid}
\alias{dist.grid}
\title{Computes the pairwise distance matrix as a data.frame where}
\usage{
dist.grid(x, y, labels = NULL)
}
\arguments{
\item{x}{a vector for the X coordinates}
\item{y}{a vector for the Y coordinates}
\item{labels}{a vector with the sample names}
}
\value{
a data.frame instance of three columns
- a : The label of the first sample
- b : The label of the second sample
- dist : The euclidian distance beween sample a and b
}
\description{
Computes the pairwise distance matrix as a data.frame where
}
\examples{
data(termes)
termes.ok = termes[,colSums(termes$reads)>0]
pos = expand.grid(1:3 * 10,1:7 * 10)
labels = rownames(termes.ok)
d = dist.grid(pos[,1],pos[2],labels)
}

39
man/dm.univariate.Rd Normal file
View File

@@ -0,0 +1,39 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mstat.R
\name{dm.univariate}
\alias{dm.univariate}
\title{Simulate null distribion of the M statistics by Monte-Carlo}
\usage{
dm.univariate(w, groups, resampling = 100)
}
\arguments{
\item{w}{the weigth matrix indicating the presence probability of each motu
in each samples. Each line corresponds to a sample and each column
to a MOTU. \code{rownames} of the \code{w} matrix must be the sample
names.}
\item{groups}{the list of considered groups as computed by the \code{\link{dist.center.group}}
function}
\item{resampling}{the number of simulation to establish the null distribution}
}
\value{
a matrix of M score under the null hypothesis of random distribution of MOTUs
with a MOTUs per line and a culumn per simulation
}
\description{
Computes the null empirical distribution of the M statistics
by shuffling MOTUs among location.
}
\examples{
data(termes)
termes.ok = termes[,colSums(termes$reads)>0]
pos = expand.grid(1:3 * 10,1:7 * 10)
labels = rownames(termes.ok)
d = dist.grid(pos[,1],pos[2],labels)
groups = dist.center.group(d,20)
w = m.weight(termes.ok)
dnull = dm.univariate(w,groups)
}

20
man/double-open-brace-methods.Rd Normal file
View File

@@ -0,0 +1,20 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/layers.metabarcoding.R
\docType{methods}
\name{[[,metabarcoding.data-method}
\alias{[[,metabarcoding.data-method}
\alias{double-open-brace-methods,metabarcoding.data}
\title{Returns the a layer associated to a \code{\link{metabarcoding.data}}}
\usage{
\method{[[}{unmutable}(x,i)
}
\arguments{
\item{x}{a \code{\link{metabarcoding.data}} instance}
}
\value{
matrix or a factor.
}
\description{
[[ operator Extracts a layer
attached to a \code{\link{metabarcoding.data}} instance.
}

48
man/extracts-obiclean-methods.Rd Normal file
View File

@@ -0,0 +1,48 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/obiclean.R
\docType{methods}
\name{extracts.obiclean,metabarcoding.data-method}
\alias{extracts.obiclean,metabarcoding.data-method}
\alias{extracts.obiclean-methods,metabarcoding.data}
\title{Extracts the obiclean results}
\usage{
\S4method{extracts.obiclean}{metabarcoding.data}(obj)
}
\arguments{
\item{obj}{the \code{\linkS4class{metabarcoding.data}} to analyze}
}
\value{
the modified \code{\linkS4class{metabarcoding.data}} instance
}
\description{
The method \code{extracts.obiclean} of the class \code{\linkS4class{metabarcoding.data}}
extracts \code{obiclean} results from the MOTUs descriptions include in the
\code{\linkS4class{metabarcoding.data}} instance.
When an \code{obitab} file is imported using the \code{\link{import.metabarcoding.data}}
if \code{obiclean} results are present in the file they are stored in the
\code{motu} data.frame. By calling this methods, MOTU descriptors describing
the \code{obiclean} status are moved to a set of layers.
}
\examples{
# load termite data set from the ROBITools sample data
data(termes)
# shows the initial list of layer names
layer.names(t)
# extracts the obiclean status
termes = extracts.obiclean(termes)
# shows the name of the newly created layers
layer.names(t)
}
\seealso{
\code{\linkS4class{metabarcoding.data}}, \code{\link{threshold.mask}}, \code{\link{normalize}}
}
\author{
Eric Coissac
}

65
man/extrapol.freq.Rd Normal file
View File

@@ -0,0 +1,65 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/distrib.extrapol.R
\name{extrapol.freq}
\alias{extrapol.freq}
\title{Read frequencies krigging}
\usage{
extrapol.freq(x, min.coord, max.coord, grid.grain = 100, coords, otus.table,
cutoff = 0.001, return.metabarcoding.data = FALSE)
}
\arguments{
\item{x}{a vector or matrix from a row-normalized read table
\code{\link{metabarcoding.data}} object}
\item{min.coord}{a vector of length = 2 indicating the minimum values of x and y
coordinates to be used for the predicted grid}
\item{max.coord}{a vector of length = 2 indicating the maximum values of x and y
coordinates to be used for the predicted grid}
\item{grid.grain}{an integer indicating the resolution (i.e. nb of subpoints) in x and y
coordinates required for the predicted grid}
\item{coords}{a dataframe containing the x and y coordinates of the abundances
from x to be extrapolated.}
\item{otus.table}{a motus data.frame containing motus informations of x}
\item{cutoff}{a cutoff below which abundances are set to 0.
This threshold also determines the value to be added to 0 values for log10
transformation}
\item{return.metabarcoding.data}{if \code{TRUE}, returns a \code{\link{metabarcoding.data}} object. Default is \code{FALSE}}
}
\value{
either a dataframe or a S3 object with a structure similar to \code{\link{metabarcoding.data}} object.
The number of samples corresponds to the predicted points.
The two last columns (if \code{return.metabarcoding.data==F}) or sample data.frame contains x y coordinates of the predicted grid
The all but last two columns (if \code{return.metabarcoding.data==F}) or read matrix contains the predicted log10 transformed relative abundances
instead of reads counts
If \code{return.metabarcoding.data==F} the motus data.frame contains the motus informations from x
}
\description{
Extrapolates read frequencies from a \code{\link{metabarcoding.data}} object in space for a finer resolution
}
\examples{
data(termes)
#Create dummy spatial coordinates
attr(termes, "samples")[c("x", "y")] = expand.grid(1:7,1:3)
#compute frequencies
attr(termes, "layers")[["reads.freq"]] = normalize(termes, MARGIN=1)$reads
# Getting extrapolations
termes.pred = extrapol.freq(attr(termes, "layers")[["reads.freq"]], min.coord=c(1,1), max.coord=c(7,3),
grid.grain=100,termes$samples[,c("x", "y")], termes$motus, cutoff=1e-3)
head(termes.pred$reads)
}
\seealso{
\code{\link{map.extrapol.freq}} as well as \code{sp} and \code{gstat} packages
}
\author{
Lucie Zinger
}

43
man/get.classic.taxonomy.Rd Normal file
View File

@@ -0,0 +1,43 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/taxonomy_classic_table.R
\name{get.classic.taxonomy}
\alias{get.classic.taxonomy}
\title{Get classical taxonomy format}
\usage{
get.classic.taxonomy(x, taxonomy, coltaxid)
}
\arguments{
\item{x}{a \code{\link{metabarcoding.data}} object}
\item{taxonomy}{a instance of \code{\linkS4class{taxonomy.obitools}}}
\item{coltaxid}{a the name of the column containing taxids to be used for creating classical taxonomic description}
}
\value{
returns a data.frame with the classical taxonomic description ("kingdom", "phylum", "class", "order", "family", "genus", "species"), as well as
sequence taxonomic assignment rank and scientific name for each sequences stored in the \code{\link{metabarcoding.data}} object
}
\description{
Creates a table with the classical taxonomic description (from phylum to species)
}
\examples{
data(termes)
taxo=default.taxonomy()
termes.taxo.table = get.classic.taxonomy(termes, taxo, "taxid")
head(termes.taxo.table)
attr(termes, "motus") = data.frame(termes$motus, termes.taxo.table)
}
\seealso{
\code{\linkS4class{taxonomy.obitools}}, and methods \code{\link{species}},\code{\link{genus}}, \code{\link{family}},\code{\link{kingdom}},
\code{\link{superkingdom}},\code{\link{taxonatrank}}, \code{\link{taxonmicank}}
}
\author{
Lucie Zinger
}
\keyword{taxonomy}

51
man/import.metabarcoding.data.Rd Normal file
View File

@@ -0,0 +1,51 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/import.metabarcoding.R
\name{import.metabarcoding.data}
\alias{import.metabarcoding.data}
\title{Read a data file produced by the \code{obitab} command}
\usage{
import.metabarcoding.data(file, sep = "\\t", sample = "sample",
sample.sep = "\\\\.", attribute = ":")
}
\arguments{
\item{file}{a string containing the file name of the obitab file.}
\item{sep}{Column separator in the obitab file.
The default separator is the tabulation.}
\item{sample}{A regular expression allowing to identify columns
from the file describing abundances of sequences per sample}
\item{sample.sep}{Separator between combined sample name.}
\item{attribute}{Separator used to split between sample 'tag' and sample name.}
}
\value{
a \code{\link{metabarcoding.data}} instance
}
\description{
Read a data file issued from the conversion of a \strong{fasta}
file to a tabular file by the \code{obitab} command of the
\strong{OBITools} package
}
\examples{
require(ROBITools)
\dontshow{# switch the working directory to the data package directory}
\dontshow{setwd(system.file("extdata", package="ROBITools"))}
# read the termes.tab file
termes=import.metabarcoding.data('termes.tab')
# print the number of samples and motus described in the file
dim(termes)
}
\seealso{
\code{\link{metabarcoding.data}}
}
\author{
Eric Coissac
}
\keyword{DNA}
\keyword{metabarcoding}

45
man/import.ngsfilter.data.Rd Normal file
View File

@@ -0,0 +1,45 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/import.ngsfilter.R
\name{import.ngsfilter.data}
\alias{import.ngsfilter.data}
\title{Read ngsfilter text file}
\usage{
import.ngsfilter.data(file, platewell = NULL)
}
\arguments{
\item{file}{a string containing the file name for the \code{ngsfilter} command.}
\item{platewell}{a string corresponding to the tag used for storing the sample location
in the PCR plate. Should be of the form "nbPlate_Well" (e.g. "01_A02").
Default is \code{NULL}}
}
\value{
\code{\link{import.ngsfilter.data}} returns a \code{\link{data.frame}} instance
}
\description{
Reads the text file used for assigning reads to samples with the
\code{ngsfilter} command of the \strong{OBITools} package.
}
\examples{
\dontshow{# switch the working directory to the data package directory}
\dontshow{setwd(system.file("extdata", package="ROBITools"))}
data(termes)
# reading the termes_ngsfilt.txt file
termes.ngs=import.ngsfilter.data('termes_ngsfilt.txt', platewell="position")
# including ngsfilter data into termes data
attr(termes, "samples") = termes.ngs[rownames(termes),]
colnames(termes$samples)
}
\seealso{
\code{\link{import.metabarcoding.data}} and \code{\link{read.obitab}} for other methods of data importation
}
\author{
Lucie Zinger
}
\keyword{DNA}
\keyword{metabarcoding}

14
man/initialize-methods.Rd Normal file
View File

@@ -0,0 +1,14 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/02_class_metabarcoding.data.R
\docType{methods}
\name{initialize,metabarcoding.data-method}
\alias{initialize,metabarcoding.data-method}
\alias{initialize-methods,metabarcoding.data}
\title{metabarcoding.data constructor}
\usage{
\S4method{initialize}{metabarcoding.data}(.Object, reads, samples, motus,
taxonomy = NULL, taxid = NULL, sample.margin = NA, layers = list())
}
\description{
metabarcoding.data constructor
}

21
man/layer.names-methods.Rd Normal file
View File

@@ -0,0 +1,21 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/layers.metabarcoding.R
\docType{methods}
\name{layer.names,metabarcoding.data-method}
\alias{layer.names,metabarcoding.data-method}
\alias{layer.names-methods,metabarcoding.data}
\title{Returns the names of all the layers}
\usage{
\S4method{layer.names}{metabarcoding.data}(obj)
}
\arguments{
\item{obj}{a \code{\link{metabarcoding.data}} instance}
}
\value{
a vector of type \code{character} containing the
list of all the layer names.
}
\description{
\code{layer.names} extracts the list of all the layer
names attached to a \code{\link{metabarcoding.data}} instance.
}

54
man/m.bivariate.Rd Normal file
View File

@@ -0,0 +1,54 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mstat.R
\name{m.bivariate}
\alias{m.bivariate}
\title{Computes the bivariate M statistics}
\usage{
m.bivariate(w1, w2 = NULL, groups)
}
\arguments{
\item{w1}{the weigth matrix indicating the presence probability of each motu
used as focus species in each samples. Each line corresponds to a sample and each column
to a MOTU. \code{rownames} of the \code{w} matrix must be the sample
names. It is nice but not mandatory if the \code{colnames} refer to the MOTU id.}
\item{w2}{the weigth matrix indicating the presence probability of each motu
used as target species in each samples. Each line corresponds to a sample and each column
to a MOTU. \code{rownames} of the \code{w} matrix must be the sample
names. It is nice but not mandatory if the \code{colnames} refer to the MOTU id.
if \code{w2} is not set, w1 is also used as target species. in this case the diagonal
of the matrix return contains the univariate M statistic for the diferent species.}
\item{groups}{the list of considered groups as computed by the \code{\link{dist.center.group}}
function}
}
\value{
a matrix of M bivariate statistics with one focus species by row and one target species
by columns If \code{w2} is not specified the diagonal of the matrix is equal to the univariate
M statistic of the corresponding species.
}
\description{
The function computes the bivariate M statiscics for a set of target species around a set of
focus species.
}
\examples{
data(termes)
termes.ok = termes[,colSums(termes$reads)>0]
pos = expand.grid(1:3 * 10,1:7 * 10)
labels = rownames(termes.ok)
d = dist.grid(pos[,1],pos[2],labels)
groups = dist.center.group(d,20)
w = m.weight(termes.ok)
m = m.bivariate(w,groups)
}
\references{
Marcon, E., Puech, F., and Traissac, S. (2012).
Characterizing the relative spatial structure of point patterns.
International Journal of Ecology, 2012.
}
\seealso{
\code{\link{dist.center.group}}
\code{\link{m.weight}}
}

41
man/m.univariate.Rd Normal file
View File

@@ -0,0 +1,41 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mstat.R
\name{m.univariate}
\alias{m.univariate}
\title{Computes the univariate M statistics}
\usage{
m.univariate(w, groups)
}
\arguments{
\item{w}{the weigth matrix indicating the presence probability of each motu
in each samples. Each line corresponds to a sample and each column
to a MOTU. \code{rownames} of the \code{w} matrix must be the sample
names. It is nice but not mandatory if the \code{colnames} refer to the MOTU id.}
\item{groups}{the list of considered groups as computed by the \code{\link{dist.center.group}}
function}
}
\description{
Computes the univariate M statistics
}
\examples{
data(termes)
termes.ok = termes[,colSums(termes$reads)>0]
pos = expand.grid(1:3 * 10,1:7 * 10)
labels = rownames(termes.ok)
d = dist.grid(pos[,1],pos[2],labels)
groups = dist.center.group(d,20)
w = m.weight(termes.ok)
m = m.univariate(w,groups)
}
\references{
Marcon, E., Puech, F., and Traissac, S. (2012).
Characterizing the relative spatial structure of point patterns.
International Journal of Ecology, 2012.
}
\seealso{
\code{\link{dist.center.group}}
\code{\link{m.weight}}
}

47
man/m.univariate.test.Rd Normal file
View File

@@ -0,0 +1,47 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mstat.R
\name{m.univariate.test}
\alias{m.univariate.test}
\title{Test the significance of the M statistics by Monte-Carlo}
\usage{
m.univariate.test(w, groups, resampling = 100, alternative = "two.sided")
}
\arguments{
\item{w}{the weigth matrix indicating the presence probability of each motu
in each samples. Each line corresponds to a sample and each column
to a MOTU. \code{rownames} of the \code{w} matrix must be the sample
names.}
\item{groups}{the list of considered groups as computed by the \code{\link{dist.center.group}}
function}
\item{resampling}{the number of simulation to establish the null distribution}
\item{alternative}{a character value in \code{c('two.sided','less','greater')}
- two.sided : the m stat is check against the two side of the empirical
M distribution
- less : test if the M stat is lesser than the M observed in the the empirical
M distribution (exlusion hypothesis)
- greater : test if the M stat is greater than the M observed in the the empirical
M distribution (aggregation hypothesis)}
}
\value{
a vector of p.value with an attribute \code{m.stat} containing the actual M stat
for each MOTUs
}
\description{
Computes computes the p.value the M statistics asociated to a MOTU
by shuffling MOTUs among location.
}
\examples{
data(termes)
termes.ok = termes[,colSums(termes$reads)>0]
pos = expand.grid(1:3 * 10,1:7 * 10)
labels = rownames(termes.ok)
d = dist.grid(pos[,1],pos[2],labels)
groups = dist.center.group(d,20)
w = m.weight(termes.ok)
pval = m.univariate.test(w,groups)
}

25
man/m.weight.Rd Normal file
View File

@@ -0,0 +1,25 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mstat.R
\name{m.weight}
\alias{m.weight}
\title{Computes a weigth matrix from a \code{\linkS4class{metabarcoding.data}}}
\usage{
m.weight(data)
}
\arguments{
\item{data}{a \code{\linkS4class{metabarcoding.data}} instance}
}
\value{
a weight matrix usable for M statistics
}
\description{
The weight can be considered as a propability of presence of a MOTU in a
given sample. This function defines this probability as the fraction of
the maximal occurrence frequency over all samples.
}
\examples{
data(termes)
termes.ok = termes[,colSums(termes$reads)>0]
w = m.weight(termes.ok)
}

61
man/map.extrapol.freq.Rd Normal file
View File

@@ -0,0 +1,61 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/distrib.extrapol.R
\name{map.extrapol.freq}
\alias{map.extrapol.freq}
\title{Maps of krigged log10-transformed frequencies}
\usage{
map.extrapol.freq(x, path = NULL, col.name = NULL, index, cutoff = 0.001,
add.points = NULL, adj = 4)
}
\arguments{
\item{x}{an extrapol.freq output}
\item{path}{the path of the folder to export the map. Default is \code{NULL} and map is printed in Rplot/quartz}
\item{index}{an integer indicating column number of the motu/sequence to be plotted.}
\item{cutoff}{lower motu frequency accepted to consider motu abundance as different
from 0. Should be the same than the one used in extrapol.freq}
\item{add.points}{a 3-column data.frame containing factor levels and associated x and y coordinates
to be added to the map. Typically taxa observed in the field.}
\item{adj}{a value used for adjusting text position in the map. Default is \code{4}}
\item{col.names}{a vector containing the names of the columns to be used for defining the file name. Typically
the column names containing the taxonomic information and/or sequence/motus id.}
}
\value{
a map/png file displaying motus distribution.
}
\description{
Maps the output of extrapol.freq
}
\examples{
data(termes)
attr(termes, "samples")[c("x", "y")] = expand.grid(1:7,1:3)
#compute frequencies
attr(termes, "layers")[["reads.freq"]] = normalize(termes, MARGIN=1)$reads
# Getting extrapolations
termes.pred = extrapol.freq(attr(termes, "layers")[["reads.freq"]],
grid.grain=100,termes$samples[,c("x", "y")], termes$motus, cutoff=1e-3)
#mapping the distribution of the 3 most abundant sequences (caution, mfrow does not work for lattice's levelplot)
map.extrapol.freq(termes.pred, path=NULL, col.name=NULL, 1, cutoff=1e-3)
map.extrapol.freq(termes.pred, path=NULL, col.name=NULL, 2, cutoff=1e-3)
map.extrapol.freq(termes.pred, path=NULL, col.name=NULL, 3, cutoff=1e-3)
#dummy observationnal data
termes.obs = data.frame(x=c(2,3,5), y=c(2.7,2,2.6), taxa = rep("Isoptera Apicotermitinae", 3))
map.extrapol.freq(termes.pred, path=NULL, col.name=NULL, 3, cutoff=1e-3, add.points=termes.obs)
}
\seealso{
\code{\link{extrapol.freq}}, and \code{levelplot} from \code{lattice} package
}
\author{
Lucie Zinger
}

50
man/marginalsum-methods.Rd Normal file
View File

@@ -0,0 +1,50 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/metabarcoding_threshold.R
\docType{methods}
\name{marginalsum,metabarcoding.data-method}
\alias{marginalsum,metabarcoding.data-method}
\alias{marginalsum-methods,metabarcoding.data}
\title{Computes marginal sums over read counts.}
\usage{
\S4method{marginalsum}{metabarcoding.data}(data, MARGIN = "sample",
na.rm = FALSE)
}
\arguments{
\item{data}{The \code{\linkS4class{metabarcoding.data}} instance
on which marginal sums have to be computed.}
\item{MARGIN}{Indicates if the sums have to be computed across
samples or motus.
Allowed values are :
\itemize{
\item{'sample' or 1} for computing sum across samples
\item{'motu' or 2} for computing sum across motus
}}
\item{na.rm}{Logical. Should missing values be omitted from the
calculations?}
}
\value{
Returns the vector of marginal sums as a \code{numeric} vector
}
\description{
Method \code{marginalsum} computes marginal sums over read counts of
a \code{\link{metabarcoding.data}} instance.
}
\examples{
# load termite data set from the ROBITools sample data
data(termes)
# Computes marginal sums per sample
ssum = marginalsum(termes,MARGIN="sample")
# Computes marginal sums per MOTU
msum = marginalsum(termes,MARGIN="motu")
}
\seealso{
\code{\linkS4class{metabarcoding.data}}
}
\author{
Aurelie Bonin
}

68
man/metabarcoding-data-class.Rd Normal file
View File

@@ -0,0 +1,68 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/02_class_metabarcoding.data.R
\docType{class}
\name{metabarcoding.data}
\alias{metabarcoding.data}
\title{DNA metabarcoding experiment description class}
\description{
A S4 class describing a DNA metabarcoding experiment. It groups
three data frames describing samples, motus and occurrences of
MOTUs per sample
}
\section{Slots}{
\describe{
\item{\code{reads}:}{Matrix of class \code{"numeric"},
containing the counts of reads per samples
\itemize{
\item{1 samples per line}
\item{1 sequence per column}
}
}
\item{\code{samples}:}{Object of class \code{"data.frame"}, describing samples
\itemize{
\item{1 samples per line}
\item{1 property per column}
}
}
\item{\code{motus}:}{Object of class \code{"data.frame"}, describing MOTUs (sequences)
\itemize{
\item{1 MOTU per line}
\item{1 property per column}
}
}
\item{\code{layers}:}{Object of class \code{"list"}, containing a set of data layers
linking motus and samples. Each element of the list is a matrix
of the same size than the \code{read} slot with
\itemize{
\item{1 samples per line}
\item{1 sequence per column}
}
}
\item{\code{scount}:}{Object of class \code{"integer"}, containing the count of sample}
\item{\code{mcount}:}{Object of class \code{"integer"}, containing the count of MOTUs}
\item{\code{sample.margin}:}{Vector of class \code{"numeric"}, describing the total count of
sequence per sample. By default this slot is set by applying sum
to the reads data.frame lines}
\item{\code{taxonomy}:}{Object of class \code{"taxonomy.obitools"}, linking the DNA metabarcoding
experiment to a taxonomy}
\item{\code{taxid}:}{Vector of class \code{"character"}, list of MOTUs' attributes to manage as taxid}
}
}
\seealso{
\code{\link{taxonomy.obitools}},
}
\author{
Eric Coissac
}
\keyword{DNA}
\keyword{metabarcoding}

34
man/motu-methods.Rd Normal file
View File

@@ -0,0 +1,34 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/02_class_metabarcoding.data.R
\docType{methods}
\name{motus,metabarcoding.data-method}
\alias{motus,metabarcoding.data-method}
\alias{motu-methods,metabarcoding.data}
\title{Extracts the MOTU descriptions \code{data.frame}}
\usage{
\S4method{motus}{metabarcoding.data}(obj)
}
\arguments{
\item{obj}{a \code{\link{metabarcoding.data}} instance}
}
\value{
a data.frame containing data about MOTU
}
\description{
Extract the MOTUs description \code{data.frame} from a
\code{\link{metabarcoding.data}} instance.
}
\examples{
# load termite data set from the ROBITools sample data
data(termes)
# Extract the data.frame describing MOTUs
d = motus(termes)
head(d)
}
\seealso{
\code{\link{metabarcoding.data}},
\code{\link{reads}}, \code{\link{samples}}
}

57
man/normalize-methods.Rd Normal file
View File

@@ -0,0 +1,57 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/metabarcoding_threshold.R
\docType{methods}
\name{normalize,metabarcoding.data-method}
\alias{normalize,metabarcoding.data-method}
\alias{normalize-methods,metabarcoding.data}
\title{Normalizes read counts by sample or by MOTU.}
\usage{
\S4method{normalize}{metabarcoding.data}(data, MARGIN = "sample",
as.matrix = FALSE)
}
\arguments{
\item{data}{The \code{\linkS4class{metabarcoding.data}} instance
on normalisation have to be computed.}
\item{MARGIN}{Indicates if the sums have to be computed across
samples or motus.
Allowed values are :
\itemize{
\item{'sample' or 1} for computing sum across samples
\item{'motu' or 2} for computing sum across motus
}}
\item{as.matrix}{Logical indicating if the normalized aboundancies
must be returned as a simple \code{matrix} (TRUE) or as a new
instance of the \code{\linkS4class{metabarcoding.data}} class
(FALSE, the default case).}
}
\value{
Returns a new instance of \code{\linkS4class{metabarcoding.data}}
or a \code{numeric} matrix according to the \code{return.as.matrix}
parameter.
}
\description{
Method \code{normalize} computes a normalized read aboundancy matrix
(relative frequency matrix) of a \code{\link{metabarcoding.data}} instance.
Normalization can be done according aboundancies per sample or per MOTU.
}
\examples{
# load termite data set from the ROBITools sample data
data(termes)
# Computes normalized aboundancies per sample
termes.norm = normalize(termes,MARGIN="sample")
# Computes normalized aboundancies per sample and
# stores the result as a new layer into the thermes
# structure
termes$normalized = normalize(termes,MARGIN="sample",as.matrix=TRUE)
}
\seealso{
\code{\linkS4class{metabarcoding.data}}
}
\author{
Aurelie Bonin
}

65
man/plot.PCRplate.Rd Normal file
View File

@@ -0,0 +1,65 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/plot.PCRplate.R
\name{plot.PCRplate}
\alias{plot.PCRplate}
\title{Plot PCR plates}
\usage{
\method{plot}{PCRplate}(x, samples = NULL, col = "cyan2", different = T,
...)
}
\arguments{
\item{x}{a \code{\link{metabarcoding.data}} object}
\item{samples}{a character vector containing names of problematic samples. Default is \code{NULL}}
\item{different}{a boolean indicating whether different tags where used in forward and reverse to identify samples. Default is \code{TRUE}}
\item{...}{arguments ot be passed to methods, such as graphical parameters}
}
\value{
\code{\link{plot.PCRplate}} returns a plot displaying no more than 4 PCR plates, with problematic sample localization
}
\description{
Plots samples localization in PCR plates, and points out problematic samples if provided.
}
\examples{
\dontshow{# switch the working directory to the data package directory}
\dontshow{setwd(system.file("extdata", package="ROBITools"))}
data(termes)
# reading the termes_ngsfilt.txt file
termes.ngs=import.ngsfilter.data('termes_ngsfilt.txt', platewell="position")
# including ngsfilter data into termes data
attr(termes, "samples") = termes.ngs[rownames(termes),]
#plot PCR plate plan
col = rep("green", nrow(termes))
col[grep("r", rownames(termes))] = "red"
plot.PCRplate(termes, col=col)
#highlighting location of samples with low identification score
#low quality taxonomic assignements identification
library(plotrix)
weighted.hist(termes$motus$best_identity, colSums(termes$reads), breaks = 20, ylab = "Nb reads", xlab = "Ecotag scores", xaxis=F)
axis(1, labels = T)
lowqual.seq = rownames(termes$motus)[termes$motus$best_identity < 0.7]
#identification and localization (in PCR plate) of samples with high proportions of low quality taxonomic assignements
termes.freq= normalize(termes, MARGIN=1)$reads
hist(log10(rowSums(termes.freq[,lowqual.seq]) + 1e-05), breaks = 20, xlab = "Prop low quality reads")
lowqual.sample = rownames(termes)[log10(rowSums(termes.freq[, lowqual.seq]) + 1e-05) > -0.5]
plot.PCRplate(termes, lowqual.sample, col=col)
}
\seealso{
\code{\link{import.metabarcoding.data}}
}
\author{
Lucie Zinger
}
\keyword{DNA}
\keyword{metabarcoding}

45
man/plot.seqinsample.Rd Normal file
View File

@@ -0,0 +1,45 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/plot.seqinsample.R
\name{plot.seqinsample}
\alias{plot.seqinsample}
\title{Plot sequence abundance in samples}
\usage{
\method{plot}{seqinsample}(x, seqset, seqtype, controls = NULL)
}
\arguments{
\item{x}{a \code{\link{metabarcoding.data}} object}
\item{seqset}{a vetcor with sequences names}
\item{seqtype}{a string indicating what type of sequences are displayed}
\item{controls}{a vector indicating the negative controls names in the x object.
Default is \code{NULL}}
}
\value{
returns a plot with the log10 transformed relative porportion of
selected MOTUs in each samples. If the number of samples is > 96,
then the plot is displayed in 4 panels
}
\description{
Plots relative abundances of a set of sequences in all samples (log10 transformed)
}
\examples{
data(termes)
seqset = rownames(termes$motus)[which(termes$motus$genus_name=="Anoplotermes")]
plot.seqinsample(termes, seqset, "Anoplotermes")
controls = rownames(termes)[grep("r", rownames(termes))]
seqset = rownames(termes$motus)[which(termes$motus$best_identity<0.7)]
plot.seqinsample(termes, seqset, "Not assigned", controls)
}
\seealso{
\code{\linkS4class{taxonomy.obitools}}, and method \code{\link{taxonmicank}}
}
\author{
Lucie Zinger
}
\keyword{metabarcoding}

37
man/read-methods.Rd Normal file
View File

@@ -0,0 +1,37 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/02_class_metabarcoding.data.R
\docType{methods}
\name{reads,metabarcoding.data-method}
\alias{reads,metabarcoding.data-method}
\alias{read-methods,metabarcoding.data}
\title{Extracts the matrix describing MOTUs abondances}
\usage{
\S4method{reads}{metabarcoding.data}(obj)
}
\arguments{
\item{obj}{a \code{\link{metabarcoding.data}} instance}
}
\value{
a matrix containing data about reads
}
\description{
Extract the the matrix describing MOTUs abondances (read counts)
from a \code{\link{metabarcoding.data}} instance.
}
\examples{
# load termite data set from the ROBITools sample data
data(termes)
# Extract the matrix describing MOTUs abondances
d = reads(termes)
head(d)
}
\seealso{
\code{\link{metabarcoding.data}},
\code{\link{motus}}, \code{\link{samples}}
}
\author{
Eric Coissac
}

21
man/read.ngsfilter.Rd Normal file
View File

@@ -0,0 +1,21 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/read.ngsfilter.R
\name{read.ngsfilter}
\alias{read.ngsfilter}
\title{Read an OBITools ngsfilter file}
\usage{
read.ngsfilter(filename, decimal = ".", as.is = !stringsAsFactors,
stringsAsFactors = default.stringsAsFactors())
}
\description{
Reads a ngsfilter file as formatted for the OBITools. For now, needs to be tab delimited till the "F" column.
Any additionnal information needs to be space delimited.
}
\seealso{
\code{\link{import.metabarcoding.data}}
}
\author{
Lucie Zinger
}
\keyword{data}
\keyword{import}

40
man/read.obitab.Rd Normal file
View File

@@ -0,0 +1,40 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/read.obitab.R
\name{read.obitab}
\alias{read.obitab}
\title{Reads a data file produced by the obitab command}
\usage{
read.obitab(filename, sep = "\\t")
}
\arguments{
\item{sep}{Column separator in the obitab file.
The default separator is the tabulation.}
\item{file}{a string containing the file name of the obitab file.}
}
\value{
a \code{data.frame} instance containing the obitab file
}
\description{
Read a data file issued from the convertion of a fasta
file to a tabular file by the obitab command
}
\examples{
require(ROBITools)
\dontshow{# switch the working directory to the data package directory}
\dontshow{setwd(system.file("extdata", package="ROBITools"))}
# read the termes.tab file
termes=read.obitab('termes.tab')
# print the dimensions of the data.frame
dim(termes)
}
\seealso{
\code{\link{import.metabarcoding.data}}
}
\author{
Eric Coissac
}

41
man/rmS3Class.Rd Normal file
View File

@@ -0,0 +1,41 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/s3objects.R
\name{rmS3Class}
\alias{rmS3Class}
\title{Removes a class from the class hierarchie attribute.}
\usage{
rmS3Class(object, classname)
}
\arguments{
\item{object}{the object to modify}
\item{classname}{the name of the class to remove}
}
\value{
the object given as parametter.
}
\description{
\code{rmS3Class} removes a class name from the vector
of class associated to the object. This the way to
remove the association between an object and a S3 class.
}
\note{
for efficiency purpose no check is done on the input
parametters
}
\examples{
x = c(1,3,2,5)
x = addS3Class(x,"my.vector")
class(x)
x = rmS3Class(x,"my.vector")
class(x)
}
\seealso{
\code{\link{addS3Class}}
}
\author{
Eric Coissac
}
\keyword{function}
\keyword{system}

37
man/samples-methods.Rd Normal file
View File

@@ -0,0 +1,37 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/02_class_metabarcoding.data.R
\docType{methods}
\name{samples,metabarcoding.data-method}
\alias{samples,metabarcoding.data-method}
\alias{samples-methods,metabarcoding.data}
\title{Extracts the samples description data.frame}
\usage{
\S4method{samples}{metabarcoding.data}(obj)
}
\arguments{
\item{obj}{a \code{\link{metabarcoding.data}} instance}
}
\value{
a data.frame containing data about sample
}
\description{
Extract the sample description data.frame from a
\code{\link{metabarcoding.data}} instance.
}
\examples{
# load termite data set from the ROBITools sample data
data(termes)
# Extract the data frame describing samples
d = samples(termes)
head(d)
}
\seealso{
\code{\link{metabarcoding.data}},
\code{\link{motus}}, \code{\link{reads}}
}
\author{
Eric Coissac
}

43
man/summary.taxores.Rd Normal file
View File

@@ -0,0 +1,43 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/taxonomic.resolution.R
\name{summary.taxores}
\alias{summary.taxores}
\title{Dataset taxonomic resolution summary.}
\usage{
\method{summary}{taxores}(x, colranks, colscores, thresh = 0.7)
}
\arguments{
\item{x}{a \code{\link{metabarcoding.data}} object}
\item{colranks}{a string indicating column name where ranks are stored in \code{x}}
\item{colscores}{a string indicating column name where taxonomic identification scores are stored in \code{x}}
\item{thresh}{a threshold for defining at which taxonomic identification scores a sequence can be considered as "not assigned".
Default is \code{0.7}}
}
\value{
returns a data.frame and piecharts of the number/proportion of MOTUs/reads assigned to each taxonomic levels
}
\description{
Summarizes the taxonomic relution of reads and MOTUs over the entire dataset
}
\examples{
data(termes)
taxo=default.taxonomy()
termes.taxo.table = get.classic.taxonomy(termes, taxo, "taxid")
attr(termes, "motus") = data.frame(termes$motus, termes.taxo.table)
attr(termes, "motus")["count"] = colSums(termes$reads)
summary.taxores(termes, "taxonomic_rank_ok","best_identity")
}
\seealso{
\code{\linkS4class{taxonomy.obitools}}, and method \code{\link{taxonmicank}}
}
\author{
Lucie Zinger
}
\keyword{taxonomy}

60
man/taxo.decider.Rd Normal file
View File

@@ -0,0 +1,60 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/choose.taxonomy.R
\name{taxo.decider}
\alias{taxo.decider}
\title{Choose between databases for taxonomic classifications}
\usage{
taxo.decider(x, taxonomy, dbrank, thresh = 0.95)
}
\arguments{
\item{x}{a \code{\link{metabarcoding.data}} object}
\item{taxonomy}{a \code{\linkS4class{taxonomy.obitools}} instance}
\item{dbrank}{string or vector indicating reference database names ranked by order of preference}
\item{thresh}{a best_identity threshold for applying priority. Default is \code{0.95}}
}
\value{
returns a data.frame with the refined taxonomic assignement and classic taxonomy description.
}
\description{
Chooses a sequence taxonomic assignment in order of preference for the different
reference databases that have been used when the assignment is above a certain threshold
}
\examples{
data(termes)
taxo=default.taxonomy()
#create artificial taxonomic assignments
attr(termes, "motus")["best_identity:DB1"] = sample(seq(0.5,1,0.001),size=nrow(termes$motus), replace=T)
attr(termes, "motus")["best_identity:DB2"] = sample(seq(0.5,1,0.001),size=nrow(termes$motus), replace=T)
attr(termes, "motus")["best_identity:DB3"] = sample(seq(0.5,1,0.001),size=nrow(termes$motus), replace=T)
attr(termes, "motus")["taxid_by_db:DB1"] = termes$motus$taxid
attr(termes, "motus")["taxid_by_db:DB2"] = sample(termes$motus$taxid,size=nrow(termes$motus), replace=F)
attr(termes, "motus")["taxid_by_db:DB3"] = sample(termes$motus$taxid,size=nrow(termes$motus), replace=F)
#Run taxo.decider
termes.ok = taxo.decider(termes, taxo, "DB2", 0.95)
head(termes.ok$motus[union(grep("DB", colnames(termes.ok$motus)), grep("_ok", colnames(termes.ok$motus)))])
termes.ok = taxo.decider(termes, taxo, c("DB3", "DB1"), 0.95)
head(termes.ok$motus[union(grep("DB", colnames(termes.ok$motus)), grep("_ok", colnames(termes.ok$motus)))])
#Quick look at the enhancement in taxonomic assignements
par(mfrow=c(1,4))
for(i in grep("best_identity.", colnames(termes.ok$motus))){
hist(termes.ok$motus[,i], breaks=20, ylim=c(1,21), main=colnames(termes.ok$motus)[i], xlab="assignment score")
}
}
\seealso{
\code{\linkS4class{taxonomy.obitools}}, and methods \code{\link{species}},\code{\link{genus}}, \code{\link{family}},\code{\link{kingdom}},
\code{\link{superkingdom}},\code{\link{taxonatrank}}, \code{\link{taxonmicank}}
}
\author{
Lucie Zinger
}
\keyword{taxonomy}

52
man/threshold-mask-methods.Rd Normal file
View File

@@ -0,0 +1,52 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/metabarcoding_threshold.R
\docType{methods}
\name{threshold.mask,metabarcoding.data-method}
\alias{threshold.mask,metabarcoding.data-method}
\alias{threshold.mask-methods,metabarcoding.data}
\title{Computes a cumulatif thresold mask for filtering read aboundancies.}
\usage{
\S4method{threshold.mask}{metabarcoding.data}(data, MARGIN, threshold = 0.97,
operator = "<")
}
\arguments{
\item{data}{The \code{\linkS4class{metabarcoding.data}} instance
on normalisation have to be computed.}
\item{MARGIN}{Indicates if the sums have to be computed across
samples or motus.
Allowed values are :
\itemize{
\item{'sample' or 1} for computing sum across samples
\item{'motu' or 2} for computing sum across motus
}}
\item{threshold}{a numeric value between 0 and 1 indicating which part of
the signal must be conserved. Default value is setup to
0.97 (97% of the total signal).}
\item{operator}{is a logical comparison operator.}
}
\value{
A logical matrix usable for selecting cell in the read aboundancy matrix.
}
\description{
The method \code{threshold.mask} of the class \code{\linkS4class{metabarcoding.data}}
computes a logical matrix of the same size than the read matrix of the data parameter.
Each cell of this matrix contains a \code{TRUE} or a \code{FALSE} value according to the
relationship existing between the read abondancy and the corresponding theshold as computed
by the \code{\link{theshold}} method.
}
\details{
(computed value) = (read aboundancy) operator (threshold value)
for a cell in the result matrix, \code{(read aboundancy)} is extracted from the read layer.
\code{operator} is a comparaison operator and \code{(threshold value)} is estimated with the
\code{\link{theshold}} method.
}
\seealso{
\code{\linkS4class{metabarcoding.data}}, \code{\link{threshold.mask}}, \code{\link{threshold}}
}
\author{
Aurelie Bonin
}

55
man/threshold-methods.Rd Normal file
View File

@@ -0,0 +1,55 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/metabarcoding_threshold.R
\docType{methods}
\name{threshold,metabarcoding.data-method}
\alias{threshold,metabarcoding.data-method}
\alias{threshold-methods,metabarcoding.data}
\title{Compute the cumulative threshold of read aboundances.}
\usage{
\S4method{threshold}{metabarcoding.data}(data, MARGIN = "sample",
threshold = 0.97)
}
\arguments{
\item{data}{The \code{\linkS4class{metabarcoding.data}} instance
on normalisation have to be computed.}
\item{MARGIN}{Indicates if the sums have to be computed across
samples or motus.
Allowed values are :
\itemize{
\item{'sample' or 1} for computing sum across samples
\item{'motu' or 2} for computing sum across motus
}}
\item{threshold}{a numeric value between 0 and 1 indicating which part of
the signal must be conserved. Default value is setup to
0.97 (97% of the total signal).}
}
\value{
a numeric vector containing the limit aboundancy to consider for
each sample or each MOTU according to the value of the \code{MARGIN}
parameter.
}
\description{
The method \code{threshold} of the class \code{\linkS4class{metabarcoding.data}}
computes the thresold to be used for conserving just a part of the global
signal. This thresold is computed by ranking aboundances by decreasing order.
The cululative sums of these ranked abondencies are computed and the aboundance
corresponding to the first sum greater than the threshold is returned as result.
}
\examples{
# load termite data set from the ROBITools sample data
data(termes)
# computes threshold value to used for keep 95\% of
# the reads per MOTU
t = threshold(termes,MARGIN='motu',threshold=0.95)
}
\seealso{
\code{\linkS4class{metabarcoding.data}}, \code{\link{threshold.mask}}
}
\author{
Aurelie Bonin
}

2
src/.gitignore vendored Normal file
View File

@@ -0,0 +1,2 @@
ROBITools.so
*.o