miga-base 0.4.3.0 → 0.5.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +1 -1
- data/lib/miga/cli.rb +43 -223
- data/lib/miga/cli/action/add.rb +91 -62
- data/lib/miga/cli/action/classify_wf.rb +97 -0
- data/lib/miga/cli/action/daemon.rb +14 -10
- data/lib/miga/cli/action/derep_wf.rb +95 -0
- data/lib/miga/cli/action/doctor.rb +83 -55
- data/lib/miga/cli/action/get.rb +68 -52
- data/lib/miga/cli/action/get_db.rb +206 -0
- data/lib/miga/cli/action/index_wf.rb +31 -0
- data/lib/miga/cli/action/init.rb +115 -190
- data/lib/miga/cli/action/init/daemon_helper.rb +124 -0
- data/lib/miga/cli/action/ls.rb +20 -11
- data/lib/miga/cli/action/ncbi_get.rb +199 -157
- data/lib/miga/cli/action/preproc_wf.rb +46 -0
- data/lib/miga/cli/action/quality_wf.rb +45 -0
- data/lib/miga/cli/action/stats.rb +147 -99
- data/lib/miga/cli/action/summary.rb +10 -4
- data/lib/miga/cli/action/tax_dist.rb +61 -46
- data/lib/miga/cli/action/tax_test.rb +46 -39
- data/lib/miga/cli/action/wf.rb +178 -0
- data/lib/miga/cli/base.rb +11 -0
- data/lib/miga/cli/objects_helper.rb +88 -0
- data/lib/miga/cli/opt_helper.rb +160 -0
- data/lib/miga/daemon.rb +7 -4
- data/lib/miga/dataset/base.rb +5 -5
- data/lib/miga/project/base.rb +4 -4
- data/lib/miga/project/result.rb +2 -1
- data/lib/miga/remote_dataset/base.rb +5 -5
- data/lib/miga/remote_dataset/download.rb +1 -1
- data/lib/miga/version.rb +3 -3
- data/scripts/cds.bash +3 -1
- data/scripts/essential_genes.bash +1 -0
- data/scripts/stats.bash +1 -1
- data/scripts/trimmed_fasta.bash +5 -3
- data/utils/distance/runner.rb +3 -0
- data/utils/distance/temporal.rb +10 -1
- data/utils/enveomics/Manifest/Tasks/fasta.json +5 -0
- data/utils/enveomics/Manifest/Tasks/sequence-identity.json +7 -0
- data/utils/enveomics/Scripts/BlastTab.addlen.rb +33 -31
- data/utils/enveomics/Scripts/FastA.tag.rb +42 -41
- data/utils/enveomics/Scripts/HMM.essential.rb +85 -55
- data/utils/enveomics/Scripts/HMM.haai.rb +29 -20
- data/utils/enveomics/Scripts/SRA.download.bash +1 -1
- data/utils/enveomics/Scripts/aai.rb +163 -128
- data/utils/enveomics/build_enveomics_r.bash +11 -10
- data/utils/enveomics/enveomics.R/DESCRIPTION +3 -2
- data/utils/enveomics/enveomics.R/R/autoprune.R +141 -107
- data/utils/enveomics/enveomics.R/R/barplot.R +105 -86
- data/utils/enveomics/enveomics.R/R/cliopts.R +131 -115
- data/utils/enveomics/enveomics.R/R/df2dist.R +144 -106
- data/utils/enveomics/enveomics.R/R/growthcurve.R +201 -133
- data/utils/enveomics/enveomics.R/R/recplot.R +350 -315
- data/utils/enveomics/enveomics.R/R/recplot2.R +1334 -914
- data/utils/enveomics/enveomics.R/R/tribs.R +521 -361
- data/utils/enveomics/enveomics.R/R/utils.R +31 -15
- data/utils/enveomics/enveomics.R/README.md +7 -0
- data/utils/enveomics/enveomics.R/man/cash-enve.GrowthCurve-method.Rd +17 -0
- data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2-method.Rd +17 -0
- data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2.Peak-method.Rd +17 -0
- data/utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd +16 -21
- data/utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd +31 -28
- data/utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd +23 -19
- data/utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd +36 -26
- data/utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd +23 -24
- data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd +23 -24
- data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +32 -33
- data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +91 -64
- data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +57 -37
- data/utils/enveomics/enveomics.R/man/enve.col.alpha.Rd +24 -19
- data/utils/enveomics/enveomics.R/man/enve.col2alpha.Rd +19 -18
- data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +39 -26
- data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +38 -25
- data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +40 -26
- data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +67 -49
- data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +37 -28
- data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +122 -97
- data/utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd +35 -31
- data/utils/enveomics/enveomics.R/man/enve.recplot2.ANIr.Rd +24 -23
- data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +68 -51
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd +25 -24
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd +21 -22
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd +19 -20
- data/utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd +19 -18
- data/utils/enveomics/enveomics.R/man/enve.recplot2.compareIdentities.Rd +41 -32
- data/utils/enveomics/enveomics.R/man/enve.recplot2.coordinates.Rd +29 -24
- data/utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd +18 -18
- data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +40 -34
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd +36 -24
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_e.Rd +19 -20
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_m.Rd +19 -20
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__emauto_one.Rd +27 -29
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mow_one.Rd +41 -42
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mower.Rd +17 -18
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.em.Rd +43 -33
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.emauto.Rd +36 -28
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.mower.Rd +74 -56
- data/utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd +44 -31
- data/utils/enveomics/enveomics.R/man/enve.recplot2.seqdepth.Rd +27 -22
- data/utils/enveomics/enveomics.R/man/enve.recplot2.windowDepthThreshold.Rd +32 -26
- data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +59 -44
- data/utils/enveomics/enveomics.R/man/enve.tribs.test.Rd +28 -21
- data/utils/enveomics/enveomics.R/man/enve.truncate.Rd +27 -22
- data/utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd +63 -43
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +38 -29
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +38 -30
- data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +111 -83
- data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd +19 -18
- data/utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd +19 -18
- data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd +19 -18
- data/utils/find-medoid.R +3 -2
- data/utils/representatives.rb +5 -3
- data/utils/subclade/pipeline.rb +22 -11
- data/utils/subclade/runner.rb +5 -1
- data/utils/subclades-compile.rb +1 -1
- data/utils/subclades.R +9 -3
- metadata +15 -4
- data/utils/enveomics/enveomics.R/man/enveomics.R-package.Rd +0 -15
- data/utils/enveomics/enveomics.R/man/z$-methods.Rd +0 -26
@@ -1,25 +1,38 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
\
|
4
|
-
\
|
5
|
-
|
6
|
-
\usage{
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/df2dist.R
|
3
|
+
\name{enve.df2dist.group}
|
4
|
+
\alias{enve.df2dist.group}
|
5
|
+
\title{Enveomics: Data Frame to Dist (Group)}
|
6
|
+
\usage{
|
7
|
+
enve.df2dist.group(x, obj1.index = 1, obj2.index = 2, dist.index = 3,
|
8
|
+
summary = median, empty.rm = TRUE)
|
9
|
+
}
|
10
|
+
\arguments{
|
11
|
+
\item{x}{A dataframe (or coercible object) with at least three columns:
|
12
|
+
\enumerate{
|
13
|
+
\item ID of the object 1,
|
14
|
+
\item ID of the object 2, and
|
15
|
+
\item distance between the two objects.}}
|
16
|
+
|
17
|
+
\item{obj1.index}{Index of the column containing the ID of the object 1.}
|
18
|
+
|
19
|
+
\item{obj2.index}{Index of the column containing the ID of the object 2.}
|
20
|
+
|
21
|
+
\item{dist.index}{Index of the column containing the distance.}
|
22
|
+
|
23
|
+
\item{summary}{Function summarizing the different distances between the
|
24
|
+
two objects.}
|
25
|
+
|
26
|
+
\item{empty.rm}{Remove rows with empty or \code{NA} groups.}
|
27
|
+
}
|
28
|
+
\value{
|
29
|
+
Returns a \strong{dist} object.
|
30
|
+
}
|
31
|
+
\description{
|
32
|
+
Transform a dataframe (or coercible object, like a table) into a
|
33
|
+
\strong{dist} object, where there are 1 or more distances between each pair
|
34
|
+
of objects.
|
35
|
+
}
|
36
|
+
\author{
|
37
|
+
Luis M. Rodriguez-R [aut, cre]
|
38
|
+
}
|
@@ -1,26 +1,40 @@
|
|
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
|
-
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/df2dist.R
|
3
|
+
\name{enve.df2dist.list}
|
4
|
+
\alias{enve.df2dist.list}
|
5
|
+
\title{Enveomics: Data Frame to Dist (List)}
|
6
|
+
\usage{
|
7
|
+
enve.df2dist.list(x, groups, obj1.index = 1, obj2.index = 2,
|
8
|
+
dist.index = 3, empty.rm = TRUE, ...)
|
9
|
+
}
|
10
|
+
\arguments{
|
11
|
+
\item{x}{A dataframe (or coercible object) with at least three columns:
|
12
|
+
\enumerate{
|
13
|
+
\item ID of the object 1,
|
14
|
+
\item ID of the object 2, and
|
15
|
+
\item distance between the two objects.}}
|
16
|
+
|
17
|
+
\item{groups}{Named array where the IDs correspond to the object IDs,
|
18
|
+
and the values correspond to the group.}
|
19
|
+
|
20
|
+
\item{obj1.index}{Index of the column containing the ID of the object 1.}
|
21
|
+
|
22
|
+
\item{obj2.index}{Index of the column containing the ID of the object 2.}
|
23
|
+
|
24
|
+
\item{dist.index}{Index of the column containing the distance.}
|
25
|
+
|
26
|
+
\item{empty.rm}{Remove incomplete matrices.}
|
27
|
+
|
28
|
+
\item{...}{Any other parameters supported by
|
29
|
+
\code{\link{enve.df2dist.group}}.}
|
30
|
+
}
|
31
|
+
\value{
|
32
|
+
Returns a \strong{list} of \strong{dist} objects.
|
33
|
+
}
|
34
|
+
\description{
|
35
|
+
Transform a dataframe (or coercible object, like a table)
|
36
|
+
into a \strong{dist} object.
|
37
|
+
}
|
38
|
+
\author{
|
39
|
+
Luis M. Rodriguez-R [aut, cre]
|
40
|
+
}
|
@@ -1,49 +1,67 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
\
|
4
|
-
\
|
5
|
-
\
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
sample
|
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
|
-
plot
|
49
|
-
}
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/growthcurve.R
|
3
|
+
\name{enve.growthcurve}
|
4
|
+
\alias{enve.growthcurve}
|
5
|
+
\title{Enveomics: Growth Curve}
|
6
|
+
\usage{
|
7
|
+
enve.growthcurve(x, times = 1:nrow(x), triplicates = FALSE, design,
|
8
|
+
new.times = seq(min(times), max(times), length.out = length(times) *
|
9
|
+
10), level = 0.95, interval = c("confidence", "prediction"),
|
10
|
+
plot = TRUE, FUN = function(t, K, r, P0) K * P0 * exp(r * t)/(K + P0
|
11
|
+
* (exp(r * t) - 1)), nls.opt = list(), ...)
|
12
|
+
}
|
13
|
+
\arguments{
|
14
|
+
\item{x}{Data frame (or coercible) containing the observed growth data
|
15
|
+
(e.g., O.D. values). Each column is an independent growth curve and each
|
16
|
+
row is a time point. \code{NA}'s are allowed.}
|
17
|
+
|
18
|
+
\item{times}{Vector with the times at which each row was taken. By default,
|
19
|
+
all rows are assumed to be part of constantly periodic measurements.}
|
20
|
+
|
21
|
+
\item{triplicates}{If \code{TRUE}, the columns are assumed to be sorted by
|
22
|
+
sample with three replicates by sample. It requires a number of columns
|
23
|
+
multiple of 3.}
|
24
|
+
|
25
|
+
\item{design}{Experimental design of the data. An \strong{array} of mode list
|
26
|
+
with sample names as index and the list of column names in each sample as
|
27
|
+
the values. By default, each column is assumed to be an independent sample
|
28
|
+
if \code{triplicates} is \code{FALSE}, or every three columns are assumed
|
29
|
+
to be a sample if \code{triplicates} is \code{TRUE}. In the latter case,
|
30
|
+
samples are simply numbered.}
|
31
|
+
|
32
|
+
\item{new.times}{Values of time for the fitted curve.}
|
33
|
+
|
34
|
+
\item{level}{Confidence (or prediction) interval in the fitted curve.}
|
35
|
+
|
36
|
+
\item{interval}{Type of interval to be calculated for the fitted curve.}
|
37
|
+
|
38
|
+
\item{plot}{Should the growth curve be plotted?}
|
39
|
+
|
40
|
+
\item{FUN}{Function to fit. By default: logistic growth with paramenters
|
41
|
+
\code{K}: carrying capacity,
|
42
|
+
\code{r}: intrinsic growth rate, and
|
43
|
+
\code{P0}: Initial population.}
|
44
|
+
|
45
|
+
\item{nls.opt}{Any additional options passed to \code{nls}.}
|
46
|
+
|
47
|
+
\item{...}{Any additional parameters to be passed to
|
48
|
+
\code{plot.enve.GrowthCurve}.}
|
49
|
+
}
|
50
|
+
\value{
|
51
|
+
Returns an \code{\link{enve.GrowthCurve}} object.
|
52
|
+
}
|
53
|
+
\description{
|
54
|
+
Calculates growth curves using the logistic growth function.
|
55
|
+
}
|
56
|
+
\examples{
|
57
|
+
# Load data
|
58
|
+
data("growth.curves", package="enveomics.R", envir=environment())
|
59
|
+
# Generate growth curves with different colors
|
60
|
+
g <- enve.growthcurve(growth.curves[,-1], growth.curves[,1], triplicates=TRUE)
|
61
|
+
# Generate black-and-white growth curves with different symbols
|
62
|
+
plot(g, pch=15:17, col="black", band.density=45, band.angle=c(-45,45,0))
|
63
|
+
|
64
|
+
}
|
65
|
+
\author{
|
66
|
+
Luis M. Rodriguez-R [aut, cre]
|
67
|
+
}
|
@@ -1,28 +1,37 @@
|
|
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
|
-
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/autoprune.R
|
3
|
+
\name{enve.prune.dist}
|
4
|
+
\alias{enve.prune.dist}
|
5
|
+
\title{Enveomics: Prune Dist}
|
6
|
+
\usage{
|
7
|
+
enve.prune.dist(t, dist.quantile = 0.25, min_dist, quiet = FALSE,
|
8
|
+
max_iters = 100, min_nodes_random = 40000, random_nodes_frx = 1)
|
9
|
+
}
|
10
|
+
\arguments{
|
11
|
+
\item{t}{A \strong{phylo} object or a path to the Newick file.}
|
12
|
+
|
13
|
+
\item{dist.quantile}{The quantile of edge lengths.}
|
14
|
+
|
15
|
+
\item{min_dist}{The minimum distance to allow between two tips.
|
16
|
+
If not set, \code{dist.quantile} is used instead to calculate it.}
|
17
|
+
|
18
|
+
\item{quiet}{Boolean indicating if the function must run without output.}
|
19
|
+
|
20
|
+
\item{max_iters}{Maximum number of iterations.}
|
21
|
+
|
22
|
+
\item{min_nodes_random}{Minimum number of nodes to trigger \emph{tip-pairs} nodes sampling.
|
23
|
+
This sampling is less reproducible and more computationally expensive,
|
24
|
+
but it's the only solution if the cophenetic matrix exceeds \code{2^31-1}
|
25
|
+
entries; above that, it cannot be represented in R.}
|
26
|
+
|
27
|
+
\item{random_nodes_frx}{Fraction of the nodes to be sampled if more than \code{min_nodes_random}.}
|
28
|
+
}
|
29
|
+
\value{
|
30
|
+
Returns a pruned \strong{phylo} object.
|
31
|
+
}
|
32
|
+
\description{
|
33
|
+
Automatically prunes a tree, to keep representatives of each clade.
|
34
|
+
}
|
35
|
+
\author{
|
36
|
+
Luis M. Rodriguez-R [aut, cre]
|
37
|
+
}
|
@@ -1,97 +1,122 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
\
|
4
|
-
\
|
5
|
-
|
6
|
-
\usage{
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
identity
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
of
|
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
|
-
pos.
|
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
|
-
|
88
|
-
id.
|
89
|
-
|
90
|
-
|
91
|
-
|
92
|
-
\
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot.R
|
3
|
+
\name{enve.recplot}
|
4
|
+
\alias{enve.recplot}
|
5
|
+
\title{Enveomics: Recruitment Plots}
|
6
|
+
\usage{
|
7
|
+
enve.recplot(prefix, id.min = NULL, id.max = NULL, id.binsize = NULL,
|
8
|
+
id.splines = 0, id.metric = "id", id.summary = "sum",
|
9
|
+
pos.min = 1, pos.max = NULL, pos.binsize = 1000, pos.splines = 0,
|
10
|
+
rec.col1 = "white", rec.col2 = "black", main = NULL,
|
11
|
+
contig.col = grey(0.85), ret.recplot = FALSE, ret.hist = FALSE,
|
12
|
+
ret.mode = FALSE, id.cutoff = NULL, verbose = TRUE, ...)
|
13
|
+
}
|
14
|
+
\arguments{
|
15
|
+
\item{prefix}{Path to the prefix of the BlastTab.catsbj.pl output files. At
|
16
|
+
least the files \strong{.rec} and \strong{.lim} must exist with this prefix.}
|
17
|
+
|
18
|
+
\item{id.min}{Minimum identity to be considered. By default, the minimum detected
|
19
|
+
identity. This value is a percentage.}
|
20
|
+
|
21
|
+
\item{id.max}{Maximum identity to be considered. By default, 100\%.}
|
22
|
+
|
23
|
+
\item{id.binsize}{Size of the identity bins (vertical histograms). By default, 0.1 for
|
24
|
+
identity metrics and 5 for bit score.}
|
25
|
+
|
26
|
+
\item{id.splines}{Smoothing parameter for the splines in the identity histogram. Zero (0) for no
|
27
|
+
splines. A generally good value is 1/2. If non-zero, requires the \pkg{stats} package.}
|
28
|
+
|
29
|
+
\item{id.metric}{Metric of identity to be used (Y-axis).
|
30
|
+
It can be any unambiguous prefix of:
|
31
|
+
\itemize{
|
32
|
+
\item "identity"
|
33
|
+
\item "corrected identity"
|
34
|
+
\item "bit score"}}
|
35
|
+
|
36
|
+
\item{id.summary}{Method used to build the identity histogram (Horizontal axis of the right panel).
|
37
|
+
It can be any unambiguous prefix of:
|
38
|
+
\itemize{
|
39
|
+
\item "sum"
|
40
|
+
\item "average"
|
41
|
+
\item "median"
|
42
|
+
\item "90\% lower bound"
|
43
|
+
\item "90\% upper bound"
|
44
|
+
\item "95\% lower bound"
|
45
|
+
\item "95\% upper bound" }
|
46
|
+
The last four options
|
47
|
+
correspond to the upper and lower boundaries of the 90\% and 95\% empirical confidence
|
48
|
+
intervals.}
|
49
|
+
|
50
|
+
\item{pos.min}{Minimum (leftmost) position in the reference (concatenated) genome (in bp).}
|
51
|
+
|
52
|
+
\item{pos.max}{Maximum (rightmost) position in the reference (concatenated) genome (in bp).
|
53
|
+
By default: Length of the genome.}
|
54
|
+
|
55
|
+
\item{pos.binsize}{Size of the position bins (horizontal histograms) in bp.}
|
56
|
+
|
57
|
+
\item{pos.splines}{Smoothing parameter for the splines in the position histogram. Zero (0) for no splines.
|
58
|
+
If non-zero, requires the stats package.}
|
59
|
+
|
60
|
+
\item{rec.col1}{Lightest color in the recruitment plot.}
|
61
|
+
|
62
|
+
\item{rec.col2}{Darkest color in the recruitment plot.}
|
63
|
+
|
64
|
+
\item{main}{Title of the plot.}
|
65
|
+
|
66
|
+
\item{contig.col}{Color of the Contig boundaries. Set to \code{NA} to ignore Contig boundaries.}
|
67
|
+
|
68
|
+
\item{ret.recplot}{Indicates if the matrix of the recruitment plot is to be returned.}
|
69
|
+
|
70
|
+
\item{ret.hist}{Ignored, for backwards compatibility.}
|
71
|
+
|
72
|
+
\item{ret.mode}{Indicates if the mode of the identity is to be computed. It requires the
|
73
|
+
\pkg{modeest} package.}
|
74
|
+
|
75
|
+
\item{id.cutoff}{Minimum identity to consider an alignment as "top". By default, it is 0.95 for the
|
76
|
+
identity metrics and 95\% of the best scoring alignment for bit score.}
|
77
|
+
|
78
|
+
\item{verbose}{Indicates if the function should report the advance.}
|
79
|
+
|
80
|
+
\item{...}{Any additional graphic parameters to be passed to plot for all panels except the
|
81
|
+
recruitment plot (lower-left).}
|
82
|
+
}
|
83
|
+
\value{
|
84
|
+
Returns a list with the following elements:
|
85
|
+
|
86
|
+
\describe{
|
87
|
+
\item{\code{pos.marks}}{Midpoints of the position histogram.}
|
88
|
+
\item{\code{id.matrix}}{Midpoints of the identity histogram.}
|
89
|
+
\item{\code{recplot}}{Matrix containing the recruitment plot values
|
90
|
+
(if \code{ret.recplot=TRUE}).}
|
91
|
+
\item{\code{id.mean}}{Mean identity.}
|
92
|
+
\item{\code{id.median}}{Median identity.}
|
93
|
+
\item{\code{id.mode}}{Mode of the identity (if \code{ret.mode=TRUE}). Deprecated.}
|
94
|
+
\item{\code{id.hist}}{Values of the identity histogram (if \code{ret.hist=TRUE}).}
|
95
|
+
\item{\code{pos.hist.low}}{Values of the position histogram (depth) with "low"
|
96
|
+
identity (i.e., below id.cutoff) (if \code{ret.hist=TRUE}).}
|
97
|
+
\item{\code{pos.hist.top}}{Values of the position histogram (depth) with "top"
|
98
|
+
identity (i.e., above id.cutoff) (if \code{ret.hist=TRUE}).}
|
99
|
+
\item{\code{id.max}}{Value of \code{id.max}. This is returned because
|
100
|
+
\code{id.max=NULL} may vary.}
|
101
|
+
\item{\code{id.cutoff}}{Value of \code{id.cutoff}.
|
102
|
+
This is returned because \code{id.cutoff=NULL} may vary.}
|
103
|
+
\item{\code{seqdepth.mean.top}}{Average sequencing depth with identity above
|
104
|
+
\code{id.cutoff}.}
|
105
|
+
\item{\code{seqdepth.mean.low}}{Average sequencing depth with identity below
|
106
|
+
\code{id.cutoff}.}
|
107
|
+
\item{\code{seqdepth.mean.all}}{Average sequencing depth without identity filtering.}
|
108
|
+
\item{\code{seqdepth.median.top}}{Median sequencing depth with identity above
|
109
|
+
\code{id.cutoff}.}
|
110
|
+
\item{\code{seqdepth.median.low}}{Median sequencing depth with identity below
|
111
|
+
\code{id.cutoff}.}
|
112
|
+
\item{\code{seqdepth.median.all}}{Median sequencing depth without identity filtering.}
|
113
|
+
\item{\code{id.metric}}{Full name of the used identity metric.}
|
114
|
+
\item{\code{id.summary}}{Full name of the summary method used to build the identity plot.}}
|
115
|
+
}
|
116
|
+
\description{
|
117
|
+
Produces recruitment plots provided that BlastTab.catsbj.pl has
|
118
|
+
been previously executed. Requires the \pkg{gplots} library.
|
119
|
+
}
|
120
|
+
\author{
|
121
|
+
Luis M. Rodriguez-R [aut, cre]
|
122
|
+
}
|