miga-base 0.3.0.0 → 0.3.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +21 -4
- data/actions/init.rb +258 -0
- data/actions/run_local.rb +1 -2
- data/actions/test_taxonomy.rb +4 -1
- data/bin/miga +8 -1
- data/lib/miga/dataset.rb +4 -4
- data/lib/miga/dataset_result.rb +7 -4
- data/lib/miga/version.rb +2 -2
- data/scripts/_distances_noref_nomulti.bash +3 -1
- data/scripts/clade_finding.bash +1 -1
- data/scripts/init.bash +1 -1
- data/scripts/miga.bash +1 -1
- data/scripts/mytaxa.bash +78 -72
- data/scripts/mytaxa_scan.bash +67 -62
- data/scripts/ogs.bash +1 -1
- data/scripts/trimmed_fasta.bash +4 -3
- data/utils/enveomics/Examples/aai-matrix.bash +66 -0
- data/utils/enveomics/Examples/ani-matrix.bash +66 -0
- data/utils/enveomics/Examples/essential-phylogeny.bash +105 -0
- data/utils/enveomics/Examples/unus-genome-phylogeny.bash +100 -0
- data/utils/enveomics/LICENSE.txt +73 -0
- data/utils/enveomics/Makefile +52 -0
- data/utils/enveomics/Manifest/Tasks/aasubs.json +103 -0
- data/utils/enveomics/Manifest/Tasks/blasttab.json +703 -0
- data/utils/enveomics/Manifest/Tasks/distances.json +161 -0
- data/utils/enveomics/Manifest/Tasks/fasta.json +571 -0
- data/utils/enveomics/Manifest/Tasks/fastq.json +208 -0
- data/utils/enveomics/Manifest/Tasks/graphics.json +126 -0
- data/utils/enveomics/Manifest/Tasks/ogs.json +339 -0
- data/utils/enveomics/Manifest/Tasks/other.json +746 -0
- data/utils/enveomics/Manifest/Tasks/remote.json +355 -0
- data/utils/enveomics/Manifest/Tasks/sequence-identity.json +454 -0
- data/utils/enveomics/Manifest/Tasks/tables.json +308 -0
- data/utils/enveomics/Manifest/Tasks/trees.json +68 -0
- data/utils/enveomics/Manifest/Tasks/variants.json +111 -0
- data/utils/enveomics/Manifest/categories.json +132 -0
- data/utils/enveomics/Manifest/examples.json +154 -0
- data/utils/enveomics/Manifest/tasks.json +4 -0
- data/utils/enveomics/Pipelines/assembly.pbs/CONFIG.mock.bash +69 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl +56 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl +60 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl +38 -0
- data/utils/enveomics/Pipelines/assembly.pbs/README.md +189 -0
- data/utils/enveomics/Pipelines/assembly.pbs/RUNME-2.bash +112 -0
- data/utils/enveomics/Pipelines/assembly.pbs/RUNME-3.bash +23 -0
- data/utils/enveomics/Pipelines/assembly.pbs/RUNME-4.bash +44 -0
- data/utils/enveomics/Pipelines/assembly.pbs/RUNME.bash +50 -0
- data/utils/enveomics/Pipelines/assembly.pbs/kSelector.R +37 -0
- data/utils/enveomics/Pipelines/assembly.pbs/newbler.pbs +68 -0
- data/utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl +49 -0
- data/utils/enveomics/Pipelines/assembly.pbs/soap.pbs +80 -0
- data/utils/enveomics/Pipelines/assembly.pbs/stats.pbs +57 -0
- data/utils/enveomics/Pipelines/assembly.pbs/velvet.pbs +63 -0
- data/utils/enveomics/Pipelines/blast.pbs/01.pbs.bash +38 -0
- data/utils/enveomics/Pipelines/blast.pbs/02.pbs.bash +73 -0
- data/utils/enveomics/Pipelines/blast.pbs/03.pbs.bash +21 -0
- data/utils/enveomics/Pipelines/blast.pbs/BlastTab.recover_job.pl +72 -0
- data/utils/enveomics/Pipelines/blast.pbs/CONFIG.mock.bash +98 -0
- data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl +55 -0
- data/utils/enveomics/Pipelines/blast.pbs/README.md +127 -0
- data/utils/enveomics/Pipelines/blast.pbs/RUNME.bash +109 -0
- data/utils/enveomics/Pipelines/blast.pbs/TASK.check.bash +128 -0
- data/utils/enveomics/Pipelines/blast.pbs/TASK.dry.bash +16 -0
- data/utils/enveomics/Pipelines/blast.pbs/TASK.eo.bash +22 -0
- data/utils/enveomics/Pipelines/blast.pbs/TASK.pause.bash +26 -0
- data/utils/enveomics/Pipelines/blast.pbs/TASK.run.bash +89 -0
- data/utils/enveomics/Pipelines/blast.pbs/sentinel.pbs.bash +29 -0
- data/utils/enveomics/Pipelines/idba.pbs/README.md +49 -0
- data/utils/enveomics/Pipelines/idba.pbs/RUNME.bash +95 -0
- data/utils/enveomics/Pipelines/idba.pbs/run.pbs +56 -0
- data/utils/enveomics/Pipelines/trim.pbs/README.md +54 -0
- data/utils/enveomics/Pipelines/trim.pbs/RUNME.bash +70 -0
- data/utils/enveomics/Pipelines/trim.pbs/run.pbs +130 -0
- data/utils/enveomics/README.md +40 -0
- data/utils/enveomics/Scripts/AAsubs.log2ratio.rb +171 -0
- data/utils/enveomics/Scripts/Aln.cat.rb +162 -0
- data/utils/enveomics/Scripts/Aln.convert.pl +35 -0
- data/utils/enveomics/Scripts/AlphaDiversity.pl +152 -0
- data/utils/enveomics/Scripts/BlastPairwise.AAsubs.pl +102 -0
- data/utils/enveomics/Scripts/BlastTab.addlen.rb +61 -0
- data/utils/enveomics/Scripts/BlastTab.advance.bash +48 -0
- data/utils/enveomics/Scripts/BlastTab.best_hit_sorted.pl +55 -0
- data/utils/enveomics/Scripts/BlastTab.catsbj.pl +106 -0
- data/utils/enveomics/Scripts/BlastTab.cogCat.rb +76 -0
- data/utils/enveomics/Scripts/BlastTab.filter.pl +47 -0
- data/utils/enveomics/Scripts/BlastTab.kegg_pep2path_rest.pl +194 -0
- data/utils/enveomics/Scripts/BlastTab.metaxaPrep.pl +104 -0
- data/utils/enveomics/Scripts/BlastTab.pairedHits.rb +157 -0
- data/utils/enveomics/Scripts/BlastTab.recplot2.R +40 -0
- data/utils/enveomics/Scripts/BlastTab.seqdepth.pl +86 -0
- data/utils/enveomics/Scripts/BlastTab.seqdepth_ZIP.pl +119 -0
- data/utils/enveomics/Scripts/BlastTab.seqdepth_nomedian.pl +86 -0
- data/utils/enveomics/Scripts/BlastTab.subsample.pl +47 -0
- data/utils/enveomics/Scripts/BlastTab.sumPerHit.pl +114 -0
- data/utils/enveomics/Scripts/BlastTab.taxid2taxrank.pl +90 -0
- data/utils/enveomics/Scripts/BlastTab.topHits_sorted.rb +101 -0
- data/utils/enveomics/Scripts/Chao1.pl +97 -0
- data/utils/enveomics/Scripts/CharTable.classify.rb +234 -0
- data/utils/enveomics/Scripts/EBIseq2tax.rb +83 -0
- data/utils/enveomics/Scripts/FastA.N50.pl +56 -0
- data/utils/enveomics/Scripts/FastA.filter.pl +52 -0
- data/utils/enveomics/Scripts/FastA.filterLen.pl +28 -0
- data/utils/enveomics/Scripts/FastA.filterN.pl +60 -0
- data/utils/enveomics/Scripts/FastA.fragment.rb +92 -0
- data/utils/enveomics/Scripts/FastA.gc.pl +42 -0
- data/utils/enveomics/Scripts/FastA.interpose.pl +87 -0
- data/utils/enveomics/Scripts/FastA.length.pl +38 -0
- data/utils/enveomics/Scripts/FastA.per_file.pl +36 -0
- data/utils/enveomics/Scripts/FastA.qlen.pl +57 -0
- data/utils/enveomics/Scripts/FastA.rename.pl +65 -0
- data/utils/enveomics/Scripts/FastA.revcom.pl +23 -0
- data/utils/enveomics/Scripts/FastA.slider.pl +85 -0
- data/utils/enveomics/Scripts/FastA.split.pl +55 -0
- data/utils/enveomics/Scripts/FastA.subsample.pl +131 -0
- data/utils/enveomics/Scripts/FastA.tag.rb +64 -0
- data/utils/enveomics/Scripts/FastA.wrap.rb +48 -0
- data/utils/enveomics/Scripts/FastQ.filter.pl +54 -0
- data/utils/enveomics/Scripts/FastQ.interpose.pl +90 -0
- data/utils/enveomics/Scripts/FastQ.offset.pl +90 -0
- data/utils/enveomics/Scripts/FastQ.split.pl +53 -0
- data/utils/enveomics/Scripts/FastQ.tag.rb +63 -0
- data/utils/enveomics/Scripts/FastQ.toFastA.awk +24 -0
- data/utils/enveomics/Scripts/GenBank.add_fields.rb +84 -0
- data/utils/enveomics/Scripts/HMM.essential.rb +254 -0
- data/utils/enveomics/Scripts/HMMsearch.extractIds.rb +83 -0
- data/utils/enveomics/Scripts/JPlace.distances.rb +88 -0
- data/utils/enveomics/Scripts/JPlace.to_iToL.rb +306 -0
- data/utils/enveomics/Scripts/M5nr.getSequences.rb +81 -0
- data/utils/enveomics/Scripts/MeTaxa.distribution.pl +198 -0
- data/utils/enveomics/Scripts/MyTaxa.fragsByTax.pl +35 -0
- data/utils/enveomics/Scripts/MyTaxa.seq-taxrank.rb +49 -0
- data/utils/enveomics/Scripts/NCBIacc2tax.rb +92 -0
- data/utils/enveomics/Scripts/Newick.autoprune.R +27 -0
- data/utils/enveomics/Scripts/RAxML-EPA.to_iToL.pl +228 -0
- data/utils/enveomics/Scripts/RefSeq.download.bash +48 -0
- data/utils/enveomics/Scripts/SRA.download.bash +50 -0
- data/utils/enveomics/Scripts/TRIBS.plot-test.R +36 -0
- data/utils/enveomics/Scripts/TRIBS.test.R +39 -0
- data/utils/enveomics/Scripts/Table.barplot.R +30 -0
- data/utils/enveomics/Scripts/Table.df2dist.R +30 -0
- data/utils/enveomics/Scripts/Table.filter.pl +61 -0
- data/utils/enveomics/Scripts/Table.merge.pl +77 -0
- data/utils/enveomics/Scripts/Table.replace.rb +69 -0
- data/utils/enveomics/Scripts/Table.round.rb +63 -0
- data/utils/enveomics/Scripts/Table.split.pl +57 -0
- data/utils/enveomics/Scripts/Taxonomy.silva2ncbi.rb +227 -0
- data/utils/enveomics/Scripts/VCF.KaKs.rb +147 -0
- data/utils/enveomics/Scripts/VCF.SNPs.rb +88 -0
- data/utils/enveomics/Scripts/aai.rb +373 -0
- data/utils/enveomics/Scripts/ani.rb +362 -0
- data/utils/enveomics/Scripts/gi2tax.rb +103 -0
- data/utils/enveomics/Scripts/in_silico_GA_GI.pl +96 -0
- data/utils/enveomics/Scripts/lib/data/essential.hmm.gz +0 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +26 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb +253 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/og.rb +182 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb +74 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb +237 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/stat.rb +30 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb +135 -0
- data/utils/enveomics/Scripts/ogs.annotate.rb +88 -0
- data/utils/enveomics/Scripts/ogs.core-pan.rb +160 -0
- data/utils/enveomics/Scripts/ogs.extract.rb +125 -0
- data/utils/enveomics/Scripts/ogs.mcl.rb +186 -0
- data/utils/enveomics/Scripts/ogs.rb +104 -0
- data/utils/enveomics/Scripts/ogs.stats.rb +131 -0
- data/utils/enveomics/Scripts/rbm.rb +137 -0
- data/utils/enveomics/Tests/Makefile +10 -0
- data/utils/enveomics/Tests/Mgen_M2288.faa +3189 -0
- data/utils/enveomics/Tests/Mgen_M2288.fna +8282 -0
- data/utils/enveomics/Tests/Mgen_M2321.fna +8288 -0
- data/utils/enveomics/Tests/Nequ_Kin4M.faa +2970 -0
- data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.tribs.Rdata +0 -0
- data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.txt +7 -0
- data/utils/enveomics/Tests/Xanthomonas_oryzae.aai-mat.tsv +17 -0
- data/utils/enveomics/Tests/Xanthomonas_oryzae.aai.tsv +137 -0
- data/utils/enveomics/Tests/a_mg.cds-go.blast.tsv +123 -0
- data/utils/enveomics/Tests/a_mg.reads-cds.blast.tsv +200 -0
- data/utils/enveomics/Tests/a_mg.reads-cds.counts.tsv +55 -0
- data/utils/enveomics/Tests/alkB.nwk +1 -0
- data/utils/enveomics/Tests/anthrax-cansnp-data.tsv +13 -0
- data/utils/enveomics/Tests/anthrax-cansnp-key.tsv +17 -0
- data/utils/enveomics/Tests/hiv1.faa +59 -0
- data/utils/enveomics/Tests/hiv1.fna +134 -0
- data/utils/enveomics/Tests/hiv2.faa +70 -0
- data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv +233 -0
- data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.lim +1 -0
- data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.rec +233 -0
- data/utils/enveomics/Tests/phyla_counts.tsv +10 -0
- data/utils/enveomics/Tests/primate_lentivirus.ogs +11 -0
- data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv1.rbm +9 -0
- data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv2.rbm +8 -0
- data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-siv.rbm +6 -0
- data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-hiv2.rbm +9 -0
- data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-siv.rbm +6 -0
- data/utils/enveomics/Tests/primate_lentivirus.rbm/siv-siv.rbm +6 -0
- data/utils/enveomics/build_enveomics_r.bash +44 -0
- data/utils/enveomics/enveomics.R/DESCRIPTION +31 -0
- data/utils/enveomics/enveomics.R/NAMESPACE +35 -0
- data/utils/enveomics/enveomics.R/R/autoprune.R +121 -0
- data/utils/enveomics/enveomics.R/R/barplot.R +165 -0
- data/utils/enveomics/enveomics.R/R/cliopts.R +119 -0
- data/utils/enveomics/enveomics.R/R/df2dist.R +117 -0
- data/utils/enveomics/enveomics.R/R/growthcurve.R +263 -0
- data/utils/enveomics/enveomics.R/R/recplot.R +320 -0
- data/utils/enveomics/enveomics.R/R/recplot2.R +745 -0
- data/utils/enveomics/enveomics.R/R/tribs.R +423 -0
- data/utils/enveomics/enveomics.R/R/utils.R +16 -0
- data/utils/enveomics/enveomics.R/README.md +52 -0
- data/utils/enveomics/enveomics.R/data/growth.curves.rda +0 -0
- data/utils/enveomics/enveomics.R/data/phyla.counts.rda +0 -0
- data/utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd +30 -0
- data/utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd +43 -0
- data/utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd +37 -0
- data/utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd +24 -0
- data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd +24 -0
- data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +33 -0
- data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +64 -0
- data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +37 -0
- data/utils/enveomics/enveomics.R/man/enve.col.alpha.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.col2alpha.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +26 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +25 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +26 -0
- data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +49 -0
- data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +28 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +97 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd +40 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +40 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd +24 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__findPeak.Rd +40 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__findPeaks.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd +22 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd +20 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +27 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd +53 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd +44 -0
- data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +44 -0
- data/utils/enveomics/enveomics.R/man/enve.tribs.test.Rd +21 -0
- data/utils/enveomics/enveomics.R/man/enveomics.R-package.Rd +15 -0
- data/utils/enveomics/enveomics.R/man/growth.curves.Rd +14 -0
- data/utils/enveomics/enveomics.R/man/phyla.counts.Rd +13 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd +43 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +29 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +30 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +71 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/z$-methods.Rd +27 -0
- data/utils/enveomics/globals.mk +8 -0
- data/utils/enveomics/manifest.json +9 -0
- data/utils/index_metadata.rb +0 -0
- data/utils/plot-taxdist.R +0 -0
- data/utils/requirements.txt +19 -19
- metadata +242 -2
@@ -0,0 +1,49 @@
|
|
1
|
+
\name{enve.growthcurve}
|
2
|
+
\alias{enve.growthcurve}
|
3
|
+
\title{enve growthcurve}
|
4
|
+
\description{Calculates growth curves using the logistic growth function.}
|
5
|
+
\usage{enve.growthcurve(x, times = 1:nrow(x), triplicates = FALSE, design,
|
6
|
+
new.times = seq(min(times), max(times), length.out = length(times) *
|
7
|
+
10), level = 0.95, interval = c("confidence", "prediction"),
|
8
|
+
plot = TRUE, FUN = function(t, K, r, P0) K * P0 * exp(r *
|
9
|
+
t)/(K + P0 * (exp(r * t) - 1)), nls.opt = list(), ...)}
|
10
|
+
\arguments{
|
11
|
+
\item{x}{Data frame (or coercible) containing the observed growth data (e.g.,
|
12
|
+
O.D. values). Each column is an independent growth curve and each
|
13
|
+
row is a time point. NA's are allowed.}
|
14
|
+
\item{times}{Vector with the times at which each row was taken. By default, all
|
15
|
+
rows are assumed to be part of constantly periodic measurements.}
|
16
|
+
\item{triplicates}{If TRUE, the columns are assumed to be sorted by sample with three
|
17
|
+
replicates by sample. It requires a number of columns multiple of 3.}
|
18
|
+
\item{design}{Experimental design of the data. An `array` of mode list with sample
|
19
|
+
names as index and the list of column names in each sample as the
|
20
|
+
values. By default, each column is assumed to be an independent sample
|
21
|
+
if `triplicates` is FALSE, or every three columns are assumed to be a
|
22
|
+
sample if `triplicates` is TRUE. In the latter case, samples are
|
23
|
+
simply numbered.}
|
24
|
+
\item{new.times}{Values of time for the fitted curve.}
|
25
|
+
\item{level}{Confidence (or prediction) interval in the fitted curve.}
|
26
|
+
\item{interval}{Type of interval to be calculated for the fitted curve.}
|
27
|
+
\item{plot}{Should the growth curve be plotted?}
|
28
|
+
\item{FUN}{Function to fit. By default: logistic growth with paramenters `K`:
|
29
|
+
carrying capacity, `r`: intrinsic growth rate, and `P0`: Initial
|
30
|
+
population.}
|
31
|
+
\item{nls.opt}{Any additional options passed to `nls`.}
|
32
|
+
\item{\dots}{Any additional parameters to be passed to `plot.enve.GrowthCurve`.}
|
33
|
+
}
|
34
|
+
|
35
|
+
\value{Returns an `enve.GrowthCurve` object.}
|
36
|
+
|
37
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
38
|
+
|
39
|
+
|
40
|
+
|
41
|
+
|
42
|
+
\examples{
|
43
|
+
# Load data
|
44
|
+
data("growth.curves", package="enveomics.R", envir=environment())
|
45
|
+
# Generate growth curves with different colors
|
46
|
+
g <- enve.growthcurve(growth.curves[,-1], growth.curves[,1], triplicates=TRUE)
|
47
|
+
# Generate black-and-white growth curves with different symbols
|
48
|
+
plot(g, pch=15:17, col="black", band.density=45, band.angle=c(-45,45,0))
|
49
|
+
}
|
@@ -0,0 +1,28 @@
|
|
1
|
+
\name{enve.prune.dist}
|
2
|
+
\alias{enve.prune.dist}
|
3
|
+
\title{enve prune dist}
|
4
|
+
\description{Automatically prunes a tree, to keep representatives of each clade.}
|
5
|
+
\usage{enve.prune.dist(t, dist.quantile = 0.25, min_dist, quiet = FALSE,
|
6
|
+
max_iters = 100, min_nodes_random = 40000, random_nodes_frx = 1)}
|
7
|
+
\arguments{
|
8
|
+
\item{t}{A `phylo` object or a path to the Newick file.}
|
9
|
+
\item{dist.quantile}{The quantile of edge lengths.}
|
10
|
+
\item{min_dist}{The minimum distance to allow between two tips. If not set, dist.quantile is
|
11
|
+
used instead to calculate it.}
|
12
|
+
\item{quiet}{Boolean indicating if the function must run without output.}
|
13
|
+
\item{max_iters}{Maximum number of iterations.}
|
14
|
+
\item{min_nodes_random}{Minimum number of nodes to trigger "tip-pairs" nodes sampling. This sampling
|
15
|
+
is less reproducible and more computationally expensive, but it's the only
|
16
|
+
solution if the cophenetic matrix exceeds 2^31-1 entries; above that, it
|
17
|
+
cannot be represented in R.}
|
18
|
+
\item{random_nodes_frx}{Fraction of the nodes to be sampled if more than `min_nodes_random`.}
|
19
|
+
}
|
20
|
+
|
21
|
+
\value{Returns a pruned phylo object.}
|
22
|
+
|
23
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
24
|
+
|
25
|
+
|
26
|
+
|
27
|
+
|
28
|
+
|
@@ -0,0 +1,97 @@
|
|
1
|
+
\name{enve.recplot}
|
2
|
+
\alias{enve.recplot}
|
3
|
+
\title{enve recplot}
|
4
|
+
\description{Produces recruitment plots provided that BlastTab.catsbj.pl has
|
5
|
+
been previously executed. Requires the gplots library.}
|
6
|
+
\usage{enve.recplot(prefix, id.min = NULL, id.max = NULL, id.binsize = NULL,
|
7
|
+
id.splines = 0, id.metric = "id", id.summary = "sum", pos.min = 1,
|
8
|
+
pos.max = NULL, pos.binsize = 1000, pos.splines = 0, rec.col1 = "white",
|
9
|
+
rec.col2 = "black", main = NULL, contig.col = grey(0.85),
|
10
|
+
ret.recplot = FALSE, ret.hist = FALSE, ret.mode = FALSE,
|
11
|
+
id.cutoff = NULL, verbose = TRUE, ...)}
|
12
|
+
\arguments{
|
13
|
+
\item{prefix}{Path to the prefix of the BlastTab.catsbj.pl output files. At
|
14
|
+
least the files .rec and .lim must exist with this prefix.}
|
15
|
+
\item{id.min}{Minimum identity to be considered. By default, the minimum detected
|
16
|
+
identity. This value is a percentage.}
|
17
|
+
\item{id.max}{Maximum identity to be considered. By default, 100.}
|
18
|
+
\item{id.binsize}{Size of the identity bins (vertical histograms). By default, 0.1 for
|
19
|
+
identity metrics and 5 for bit score.}
|
20
|
+
\item{id.splines}{Smoothing parameter for the splines in the identity histogram. Zero (0) for no
|
21
|
+
splines. A generally good value is 1/2. If non-zero, requires the stats package.}
|
22
|
+
\item{id.metric}{Metric of identity to be used (Y-axis). It can be any unambiguous prefix
|
23
|
+
of "identity", "corrected identity", or "bit score".}
|
24
|
+
\item{id.summary}{Method used to build the identity histogram (Horizontal axis of the right panel).
|
25
|
+
It can be any unambiguous prefix of "sum", "average", "median", "90\% lower bound",
|
26
|
+
"90\% upper bound", "95\% lower bound", and "95\% upper bound". The last four options
|
27
|
+
correspond to the upper and lower boundaries of the 90\% and 95\% empirical confidence
|
28
|
+
intervals.}
|
29
|
+
\item{pos.min}{Minimum (leftmost) position in the reference (concatenated) genome (in bp).}
|
30
|
+
\item{pos.max}{Maximum (rightmost) position in the reference (concatenated) genome (in bp).
|
31
|
+
By default: Length of the genome.}
|
32
|
+
\item{pos.binsize}{Size of the position bins (horizontal histograms) in bp.}
|
33
|
+
\item{pos.splines}{Smoothing parameter for the splines in the position histogram. Zero (0) for no splines.
|
34
|
+
If non-zero, requires the stats package.}
|
35
|
+
\item{rec.col1}{Lightest color in the recruitment plot.}
|
36
|
+
\item{rec.col2}{Darkest color in the recruitment plot.}
|
37
|
+
\item{main}{Title of the plot.}
|
38
|
+
\item{contig.col}{Color of the Contig boundaries. Set to NA to ignore Contig boundaries.}
|
39
|
+
\item{ret.recplot}{Indicates if the matrix of the recruitment plot is to be returned.}
|
40
|
+
\item{ret.hist}{Indicates if the vectors of the identity and position histograms are to be returned.}
|
41
|
+
\item{ret.mode}{Indicates if the mode of the identity is to be computed. It requires the modeest
|
42
|
+
package.}
|
43
|
+
\item{id.cutoff}{Minimum identity to consider an alignment as "top". By default, it is 0.95 for the
|
44
|
+
identity metrics and 95\% of the best scoring alignment for bit score.}
|
45
|
+
\item{verbose}{Indicates if the function should report the advance.}
|
46
|
+
\item{\dots}{Any additional graphic parameters to be passed to plot for all panels except the
|
47
|
+
recruitment plot (lower-left).}
|
48
|
+
}
|
49
|
+
|
50
|
+
\value{A list with the following elements:
|
51
|
+
|
52
|
+
pos.marks: Midpoints of the position histogram.
|
53
|
+
|
54
|
+
id.matrix: Midpoints of the identity histogram.
|
55
|
+
|
56
|
+
recplot (if ret.recplot=TRUE): Matrix containing the recruitment plot values.
|
57
|
+
|
58
|
+
id.mean: Mean identity.
|
59
|
+
|
60
|
+
id.median: Median identity.
|
61
|
+
|
62
|
+
id.mode (if ret.mode=TRUE): Mode of the identity.
|
63
|
+
|
64
|
+
id.hist (if ret.hist=TRUE): Values of the identity histogram.
|
65
|
+
|
66
|
+
pos.hist.low (if ret.hist=TRUE): Values of the position histogram (depth) with "low"
|
67
|
+
identity (i.e., below id.cutoff).
|
68
|
+
|
69
|
+
pos.hist.top (if ret.hist=TRUE): Values of the position histogram (depth) with "top"
|
70
|
+
identity (i.e., above id.cutoff).
|
71
|
+
|
72
|
+
id.max: Value of id.max. This is returned because id.max=NULL may vary.
|
73
|
+
|
74
|
+
id.cutoff: Value of id.cutoff. This is returned because id.cutoff=NULL may vary.
|
75
|
+
|
76
|
+
seqdepth.mean.top: Average sequencing depth with identity above id.cutoff.
|
77
|
+
|
78
|
+
seqdepth.mean.low: Average sequencing depth with identity below id.cutoff.
|
79
|
+
|
80
|
+
seqdepth.mean.all: Average sequencing depth without identity filtering.
|
81
|
+
|
82
|
+
seqdepth.median.top: Median sequencing depth with identity above id.cutoff.
|
83
|
+
|
84
|
+
seqdepth.median.low: Median sequencing depth with identity below id.cutoff.
|
85
|
+
|
86
|
+
seqdepth.median.all: Median sequencing depth without identity filtering.
|
87
|
+
|
88
|
+
id.metric: Full name of the used identity metric.
|
89
|
+
|
90
|
+
id.summary: Full name of the summary method used to build the identity plot.}
|
91
|
+
|
92
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
93
|
+
|
94
|
+
|
95
|
+
|
96
|
+
|
97
|
+
|
@@ -0,0 +1,40 @@
|
|
1
|
+
\name{enve.RecPlot2-class}
|
2
|
+
\Rdversion{1.1}
|
3
|
+
\docType{class}
|
4
|
+
\alias{enve.RecPlot2-class}
|
5
|
+
\alias{enve.RecPlot2}
|
6
|
+
%% \alias{$}
|
7
|
+
|
8
|
+
\title{enve.RecPlot2 S4 class}
|
9
|
+
\description{Enve-omics representation of Recruitment plots. This object can
|
10
|
+
be produced by `enve.recplot2` and supports S4 method plot.}
|
11
|
+
\section{Objects from the Class}{Objects can be created by calls of the form \code{new(enve.RecPlot2 ...)}}
|
12
|
+
\section{Slots}{
|
13
|
+
\describe{
|
14
|
+
\item{\code{counts}:}{(\code{matrix}) Counts as a two-dimensional histogram.}
|
15
|
+
\item{\code{pos.counts.in}:}{(\code{numeric}) Counts of in-group hits per position bin.}
|
16
|
+
\item{\code{pos.counts.out}:}{(\code{numeric}) Counts of out-group hits per position bin.}
|
17
|
+
\item{\code{id.counts}:}{(\code{numeric}) Counts per ID bin.}
|
18
|
+
\item{\code{id.breaks}:}{(\code{numeric}) Breaks of identity bins.}
|
19
|
+
\item{\code{pos.breaks}:}{(\code{numeric}) Breaks of position bins.}
|
20
|
+
\item{\code{seq.breaks}:}{Object of class \code{"numeric"}}
|
21
|
+
\item{\code{peaks}:}{(\code{list}) Peaks identified in the recplot.
|
22
|
+
Limits of the subject sequences after concatenation.}
|
23
|
+
\item{\code{seq.names}:}{(\code{character}) Names of the subject sequences.}
|
24
|
+
\item{\code{id.metric}:}{(\code{character}) Metric used as 'identity'.}
|
25
|
+
\item{\code{id.ingroup}:}{(\code{logical}) Identity bins considered in-group.}
|
26
|
+
\item{\code{call}:}{(\code{call}) Call producing this object.}
|
27
|
+
}
|
28
|
+
}
|
29
|
+
\section{Methods}{
|
30
|
+
\describe{
|
31
|
+
\item{$}{\code{signature(x = "enve.RecPlot2")}: ... }
|
32
|
+
}
|
33
|
+
}
|
34
|
+
|
35
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
36
|
+
|
37
|
+
|
38
|
+
|
39
|
+
|
40
|
+
|
@@ -0,0 +1,40 @@
|
|
1
|
+
\name{enve.recplot2}
|
2
|
+
\alias{enve.recplot2}
|
3
|
+
\title{enve recplot2}
|
4
|
+
\description{Produces recruitment plots provided that BlastTab.catsbj.pl has
|
5
|
+
been previously executed.}
|
6
|
+
\usage{enve.recplot2(prefix, plot = TRUE, pos.breaks = 1000, id.breaks = 300,
|
7
|
+
id.metric = c("identity", "corrected identity", "bit score"),
|
8
|
+
id.summary = sum, id.cutoff = 95, threads = 2, verbose = TRUE,
|
9
|
+
...)}
|
10
|
+
\arguments{
|
11
|
+
\item{prefix}{Path to the prefix of the BlastTab.catsbj.pl output files. At
|
12
|
+
least the files .rec and .lim must exist with this prefix.}
|
13
|
+
\item{plot}{Should the object be plotted?}
|
14
|
+
\item{pos.breaks}{Breaks in the positions histogram. It can also be a vector of break
|
15
|
+
points, and values outside the range are ignored. If zero (0), it
|
16
|
+
uses the sequence breaks as defined in the .lim file, which means
|
17
|
+
one bin per contig (or gene, if the mapping is agains genes).}
|
18
|
+
\item{id.breaks}{Breaks in the identity histogram. It can also be a vector of break
|
19
|
+
points, and values outside the range are ignored.}
|
20
|
+
\item{id.metric}{Metric of identity to be used (Y-axis). Corrected identity is only
|
21
|
+
supported if the original BLAST file included sequence lengths.}
|
22
|
+
\item{id.summary}{Function summarizing the identity bins. Other recommended options
|
23
|
+
include: `median` to estimate the median instead of total bins, and
|
24
|
+
`function(x) mlv(x,method='parzen')$M` to estimate the mode.}
|
25
|
+
\item{id.cutoff}{Cutoff of identity metric above which the hits are considered
|
26
|
+
'in-group'. The 95\% identity corresponds to the expectation of
|
27
|
+
ANI<95\% within species.}
|
28
|
+
\item{threads}{Number of threads to use.}
|
29
|
+
\item{verbose}{Indicates if the function should report the advance.}
|
30
|
+
\item{\dots}{Any additional parameters supported by `plot.enve.RecPlot2`.}
|
31
|
+
}
|
32
|
+
|
33
|
+
\value{Returns an object of class `enve.RecPlot2`.}
|
34
|
+
|
35
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
36
|
+
|
37
|
+
|
38
|
+
|
39
|
+
|
40
|
+
|
@@ -0,0 +1,24 @@
|
|
1
|
+
\name{enve.recplot2.__counts}
|
2
|
+
\alias{enve.recplot2.__counts}
|
3
|
+
\title{enve recplot2 counts}
|
4
|
+
\description{Internal ancilliary function (see `enve.recplot2`).}
|
5
|
+
\usage{enve.recplot2.__counts(x, pos.breaks, id.breaks, rec.idcol)}
|
6
|
+
\arguments{
|
7
|
+
\item{x}{
|
8
|
+
}
|
9
|
+
\item{pos.breaks}{
|
10
|
+
}
|
11
|
+
\item{id.breaks}{
|
12
|
+
}
|
13
|
+
\item{rec.idcol}{
|
14
|
+
}
|
15
|
+
}
|
16
|
+
|
17
|
+
|
18
|
+
|
19
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
20
|
+
|
21
|
+
|
22
|
+
|
23
|
+
|
24
|
+
|
@@ -0,0 +1,40 @@
|
|
1
|
+
\name{enve.recplot2.__findPeak}
|
2
|
+
\alias{enve.recplot2.__findPeak}
|
3
|
+
\title{enve recplot2 findPeak}
|
4
|
+
\description{Internall ancilliary function (see `enve.recplot2.findPeaks`).}
|
5
|
+
\usage{enve.recplot2.__findPeak(lsd1, min.points, quant.est, mlv.opts,
|
6
|
+
fitdist.opts, with.skewness, optim.rounds, optim.epsilon,
|
7
|
+
n.total, merge.logdist, verbose)}
|
8
|
+
\arguments{
|
9
|
+
\item{lsd1}{
|
10
|
+
}
|
11
|
+
\item{min.points}{
|
12
|
+
}
|
13
|
+
\item{quant.est}{
|
14
|
+
}
|
15
|
+
\item{mlv.opts}{
|
16
|
+
}
|
17
|
+
\item{fitdist.opts}{
|
18
|
+
}
|
19
|
+
\item{with.skewness}{
|
20
|
+
}
|
21
|
+
\item{optim.rounds}{
|
22
|
+
}
|
23
|
+
\item{optim.epsilon}{
|
24
|
+
}
|
25
|
+
\item{n.total}{
|
26
|
+
}
|
27
|
+
\item{merge.logdist}{
|
28
|
+
}
|
29
|
+
\item{verbose}{
|
30
|
+
}
|
31
|
+
}
|
32
|
+
|
33
|
+
|
34
|
+
|
35
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
36
|
+
|
37
|
+
|
38
|
+
|
39
|
+
|
40
|
+
|
@@ -0,0 +1,18 @@
|
|
1
|
+
\name{enve.recplot2.__findPeaks}
|
2
|
+
\alias{enve.recplot2.__findPeaks}
|
3
|
+
\title{enve recplot2 findPeaks}
|
4
|
+
\description{Internal ancilliary function (see `enve.recplot2.findPeaks`).}
|
5
|
+
\usage{enve.recplot2.__findPeaks(peaks.opts)}
|
6
|
+
\arguments{
|
7
|
+
\item{peaks.opts}{
|
8
|
+
}
|
9
|
+
}
|
10
|
+
|
11
|
+
|
12
|
+
|
13
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
14
|
+
|
15
|
+
|
16
|
+
|
17
|
+
|
18
|
+
|
@@ -0,0 +1,22 @@
|
|
1
|
+
\name{enve.recplot2.__peakHist}
|
2
|
+
\alias{enve.recplot2.__peakHist}
|
3
|
+
\title{enve recplot2 peakHist}
|
4
|
+
\description{Internal ancilliary function (see `enve.RecPlot2.Peak`).}
|
5
|
+
\usage{enve.recplot2.__peakHist(x, mids, counts = TRUE)}
|
6
|
+
\arguments{
|
7
|
+
\item{x}{
|
8
|
+
}
|
9
|
+
\item{mids}{
|
10
|
+
}
|
11
|
+
\item{counts}{
|
12
|
+
}
|
13
|
+
}
|
14
|
+
|
15
|
+
|
16
|
+
|
17
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
18
|
+
|
19
|
+
|
20
|
+
|
21
|
+
|
22
|
+
|
@@ -0,0 +1,20 @@
|
|
1
|
+
\name{enve.recplot2.__whichClosestPeak}
|
2
|
+
\alias{enve.recplot2.__whichClosestPeak}
|
3
|
+
\title{enve recplot2 whichClosestPeak}
|
4
|
+
\description{Internal ancilliary function (see `enve.recplot2.findPeaks`).}
|
5
|
+
\usage{enve.recplot2.__whichClosestPeak(peak, peaks)}
|
6
|
+
\arguments{
|
7
|
+
\item{peak}{
|
8
|
+
}
|
9
|
+
\item{peaks}{
|
10
|
+
}
|
11
|
+
}
|
12
|
+
|
13
|
+
|
14
|
+
|
15
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
16
|
+
|
17
|
+
|
18
|
+
|
19
|
+
|
20
|
+
|
@@ -0,0 +1,18 @@
|
|
1
|
+
\name{enve.recplot2.changeCutoff}
|
2
|
+
\alias{enve.recplot2.changeCutoff}
|
3
|
+
\title{enve recplot2 changeCutoff}
|
4
|
+
\description{Change the intra-species cutoff of an existing recruitment plot.}
|
5
|
+
\usage{enve.recplot2.changeCutoff(rp, new.cutoff = 98)}
|
6
|
+
\arguments{
|
7
|
+
\item{rp}{enve.RecPlot2 object.}
|
8
|
+
\item{new.cutoff}{New cutoff to use.}
|
9
|
+
}
|
10
|
+
|
11
|
+
|
12
|
+
|
13
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
14
|
+
|
15
|
+
|
16
|
+
|
17
|
+
|
18
|
+
|
@@ -0,0 +1,18 @@
|
|
1
|
+
\name{enve.recplot2.corePeak}
|
2
|
+
\alias{enve.recplot2.corePeak}
|
3
|
+
\title{enve recplot2 corePeak}
|
4
|
+
\description{Finds the peak in a list of peaks that is most likely to represent the
|
5
|
+
"core genome" of a population.}
|
6
|
+
\usage{enve.recplot2.corePeak(x)}
|
7
|
+
\arguments{
|
8
|
+
\item{x}{`list` of `enve.RecPlot2.Peak` objects.}
|
9
|
+
}
|
10
|
+
|
11
|
+
|
12
|
+
|
13
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
14
|
+
|
15
|
+
|
16
|
+
|
17
|
+
|
18
|
+
|
@@ -0,0 +1,27 @@
|
|
1
|
+
\name{enve.recplot2.extractWindows}
|
2
|
+
\alias{enve.recplot2.extractWindows}
|
3
|
+
\title{enve recplot2 extractWindows}
|
4
|
+
\description{Extract windows significantly below (or above) the peak in sequencing
|
5
|
+
depth.}
|
6
|
+
\usage{enve.recplot2.extractWindows(rp, peak, lower.tail = TRUE, significance = 0.05,
|
7
|
+
seq.names = FALSE)}
|
8
|
+
\arguments{
|
9
|
+
\item{rp}{Recruitment plot, a enve.Recplot2 object.}
|
10
|
+
\item{peak}{Peak, a enve.RecPlot2.Peak object. If list, it is assumed to be a list
|
11
|
+
of enve.RecPlot2.Peak objects, in which case the core peak is used
|
12
|
+
(see enve.recplot2.corePeak).}
|
13
|
+
\item{lower.tail}{If FALSE, it returns windows significantly above the peak in
|
14
|
+
sequencing depth.}
|
15
|
+
\item{significance}{Significance threshold (alpha) to select windows.}
|
16
|
+
\item{seq.names}{Returns subject sequence names instead of a vector of Booleans. It
|
17
|
+
assumes that the recruitment plot was generated with pos.breaks=0.}
|
18
|
+
}
|
19
|
+
|
20
|
+
|
21
|
+
|
22
|
+
\author{Luis M. Rodriguez-R [aut, cre]}
|
23
|
+
|
24
|
+
|
25
|
+
|
26
|
+
|
27
|
+
|