1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
|
\name{makeSummarizedExperimentFromDataFrame}
\alias{makeSummarizedExperimentFromDataFrame}
\title{Make a RangedSummarizedExperiment from a data.frame or DataFrame}
\description{
\code{makeSummarizedExperimentFromDataFrame} uses \code{data.frame}
or \code{DataFrame} column names to create a \link{GRanges} object for the
\code{rowRanges} of the resulting \link{SummarizedExperiment} object.
It requires that non-range data columns be coercible into a \code{numeric}
\code{matrix} for the \link{SummarizedExperiment} constructor. All columns
that are not part of the row ranges attribute are assumed to be experiment
data; thus, keeping metadata columns will not be supported. Note that this
function only returns \link{SummarizedExperiment} objects with a single
assay.
If metadata columns are to be kept, one can first construct the row ranges
attribute by using the \link{makeGRangesFromDataFrame} function and
subsequently creating the \link{SummarizedExperiment}.
}
\usage{
makeSummarizedExperimentFromDataFrame(df,
...,
seqinfo = NULL,
starts.in.df.are.0based = FALSE)
}
\arguments{
\item{df}{
A data.frame or \link[S4Vectors]{DataFrame} object. If not, then
the function first tries to turn \code{df} into a data frame with
\code{as.data.frame(df)}.
}
\item{...}{
Additional arguments passed on to \link{makeGRangesFromDataFrame}
}
\item{seqinfo}{
Either \code{NULL}, or a \link{Seqinfo} object, or a character vector
of seqlevels, or a named numeric vector of sequence lengths.
When not \code{NULL}, it must be compatible with the genomic ranges
in \code{df} i.e. it must include at least the sequence levels
represented in \code{df}.
}
\item{starts.in.df.are.0based}{
\code{TRUE} or \code{FALSE} (the default).
If \code{TRUE}, then the start positions of the genomic ranges in
\code{df} are considered to be \emph{0-based} and are converted to
\emph{1-based} in the returned \link{GRanges} object.
This feature is intended to make it more convenient to handle input
that contains data obtained from resources using the "0-based
start" convention. A notorious example of such resource is the UCSC
Table Browser (\url{http://genome.ucsc.edu/cgi-bin/hgTables}).
}
}
\value{
A \link{RangedSummarizedExperiment} object with rowRanges and a single assay
}
\author{
M. Ramos
}
\seealso{
\itemize{
\item \link{makeGRangesFromDataFrame}
}
}
\examples{
## ---------------------------------------------------------------------
## BASIC EXAMPLES
## ---------------------------------------------------------------------
# Note that rownames of the data.frame are also rownames of the result
df <- data.frame(chr="chr2", start = 11:15, end = 12:16,
strand = c("+", "-", "+", "*", "."), expr0 = 3:7,
expr1 = 8:12, expr2 = 12:16,
row.names = paste0("GENE", letters[5:1]))
df
exRSE <- makeSummarizedExperimentFromDataFrame(df)
exRSE
assay(exRSE)
rowRanges(exRSE)
}
|
