miga-base 1.2.17.0 → 1.2.17.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/miga/version.rb +1 -1
- data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Archaea_SCG.hmm +41964 -0
- data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Bacteria_SCG.hmm +32439 -0
- data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Complete_SCG_DB.hmm +62056 -0
- data/utils/FastAAI/FastAAI +3659 -0
- data/utils/FastAAI/FastAAI-legacy/FastAAI +1336 -0
- data/utils/FastAAI/FastAAI-legacy/kAAI_v1.0_virus.py +1296 -0
- data/utils/FastAAI/README.md +84 -0
- data/utils/enveomics/Docs/recplot2.md +244 -0
- 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 +790 -0
- data/utils/enveomics/Manifest/Tasks/distances.json +161 -0
- data/utils/enveomics/Manifest/Tasks/fasta.json +802 -0
- data/utils/enveomics/Manifest/Tasks/fastq.json +291 -0
- data/utils/enveomics/Manifest/Tasks/graphics.json +126 -0
- data/utils/enveomics/Manifest/Tasks/mapping.json +137 -0
- data/utils/enveomics/Manifest/Tasks/ogs.json +382 -0
- data/utils/enveomics/Manifest/Tasks/other.json +906 -0
- data/utils/enveomics/Manifest/Tasks/remote.json +355 -0
- data/utils/enveomics/Manifest/Tasks/sequence-identity.json +650 -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 +165 -0
- data/utils/enveomics/Manifest/examples.json +162 -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 +1 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl +1 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl +1 -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 +1 -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 +42 -0
- data/utils/enveomics/Scripts/AAsubs.log2ratio.rb +171 -0
- data/utils/enveomics/Scripts/Aln.cat.rb +221 -0
- data/utils/enveomics/Scripts/Aln.convert.pl +35 -0
- data/utils/enveomics/Scripts/AlphaDiversity.pl +152 -0
- data/utils/enveomics/Scripts/BedGraph.tad.rb +93 -0
- data/utils/enveomics/Scripts/BedGraph.window.rb +71 -0
- data/utils/enveomics/Scripts/BlastPairwise.AAsubs.pl +102 -0
- data/utils/enveomics/Scripts/BlastTab.addlen.rb +63 -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 +104 -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 +48 -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 +123 -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 +60 -0
- data/utils/enveomics/Scripts/FastA.extract.rb +152 -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 +100 -0
- data/utils/enveomics/Scripts/FastA.gc.pl +42 -0
- data/utils/enveomics/Scripts/FastA.interpose.pl +93 -0
- data/utils/enveomics/Scripts/FastA.length.pl +38 -0
- data/utils/enveomics/Scripts/FastA.mask.rb +89 -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.sample.rb +98 -0
- data/utils/enveomics/Scripts/FastA.slider.pl +85 -0
- data/utils/enveomics/Scripts/FastA.split.pl +55 -0
- data/utils/enveomics/Scripts/FastA.split.rb +79 -0
- data/utils/enveomics/Scripts/FastA.subsample.pl +131 -0
- data/utils/enveomics/Scripts/FastA.tag.rb +65 -0
- data/utils/enveomics/Scripts/FastA.toFastQ.rb +69 -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.maskQual.rb +89 -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 +70 -0
- data/utils/enveomics/Scripts/FastQ.test-error.rb +81 -0
- data/utils/enveomics/Scripts/FastQ.toFastA.awk +24 -0
- data/utils/enveomics/Scripts/GFF.catsbj.pl +127 -0
- data/utils/enveomics/Scripts/GenBank.add_fields.rb +84 -0
- data/utils/enveomics/Scripts/HMM.essential.rb +351 -0
- data/utils/enveomics/Scripts/HMM.haai.rb +168 -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 +320 -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/RecPlot2.compareIdentities.R +32 -0
- data/utils/enveomics/Scripts/RefSeq.download.bash +48 -0
- data/utils/enveomics/Scripts/SRA.download.bash +55 -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 +31 -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.prefScore.R +60 -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 +421 -0
- data/utils/enveomics/Scripts/ani.rb +362 -0
- data/utils/enveomics/Scripts/anir.rb +137 -0
- data/utils/enveomics/Scripts/clust.rand.rb +102 -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/dupont_2012_essential.hmm.gz +0 -0
- data/utils/enveomics/Scripts/lib/data/lee_2019_essential.hmm.gz +0 -0
- data/utils/enveomics/Scripts/lib/enveomics.R +1 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/anir.rb +293 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/bm_set.rb +175 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +24 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/errors.rb +17 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/gmm_em.rb +30 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb +253 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/match.rb +88 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/og.rb +182 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/rbm.rb +49 -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/stats/rand.rb +31 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/stats/sample.rb +152 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/stats.rb +3 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/utils.rb +74 -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-legacy.rb +172 -0
- data/utils/enveomics/Scripts/rbm.rb +108 -0
- data/utils/enveomics/Scripts/sam.filter.rb +148 -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 +45 -0
- data/utils/enveomics/enveomics.R/DESCRIPTION +31 -0
- data/utils/enveomics/enveomics.R/NAMESPACE +39 -0
- data/utils/enveomics/enveomics.R/R/autoprune.R +155 -0
- data/utils/enveomics/enveomics.R/R/barplot.R +184 -0
- data/utils/enveomics/enveomics.R/R/cliopts.R +135 -0
- data/utils/enveomics/enveomics.R/R/df2dist.R +154 -0
- data/utils/enveomics/enveomics.R/R/growthcurve.R +331 -0
- data/utils/enveomics/enveomics.R/R/prefscore.R +79 -0
- data/utils/enveomics/enveomics.R/R/recplot.R +354 -0
- data/utils/enveomics/enveomics.R/R/recplot2.R +1631 -0
- data/utils/enveomics/enveomics.R/R/tribs.R +583 -0
- data/utils/enveomics/enveomics.R/R/utils.R +80 -0
- data/utils/enveomics/enveomics.R/README.md +81 -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/cash-enve.GrowthCurve-method.Rd +16 -0
- data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2-method.Rd +16 -0
- data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2.Peak-method.Rd +16 -0
- data/utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd +25 -0
- data/utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd +46 -0
- data/utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd +23 -0
- data/utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd +47 -0
- data/utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd +23 -0
- data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd +23 -0
- data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +40 -0
- data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +103 -0
- data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +67 -0
- data/utils/enveomics/enveomics.R/man/enve.col.alpha.Rd +24 -0
- data/utils/enveomics/enveomics.R/man/enve.col2alpha.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +45 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +44 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +47 -0
- data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +75 -0
- data/utils/enveomics/enveomics.R/man/enve.prefscore.Rd +50 -0
- data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +44 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +139 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd +45 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.ANIr.Rd +24 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +77 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd +25 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd +21 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.compareIdentities.Rd +47 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.coordinates.Rd +29 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +45 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd +36 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_e.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_m.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__emauto_one.Rd +27 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mow_one.Rd +52 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mower.Rd +17 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.em.Rd +51 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.emauto.Rd +43 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.mower.Rd +82 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd +59 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.seqdepth.Rd +27 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.windowDepthThreshold.Rd +36 -0
- data/utils/enveomics/enveomics.R/man/enve.selvector.Rd +23 -0
- data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +68 -0
- data/utils/enveomics/enveomics.R/man/enve.tribs.test.Rd +28 -0
- data/utils/enveomics/enveomics.R/man/enve.truncate.Rd +27 -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 +78 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +46 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +45 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +125 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd +19 -0
- data/utils/enveomics/globals.mk +8 -0
- data/utils/enveomics/manifest.json +9 -0
- data/utils/multitrim/Multitrim How-To.pdf +0 -0
- data/utils/multitrim/README.md +67 -0
- data/utils/multitrim/multitrim.py +1555 -0
- data/utils/multitrim/multitrim.yml +13 -0
- metadata +301 -5
@@ -0,0 +1,47 @@
|
|
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(
|
8
|
+
x,
|
9
|
+
groups,
|
10
|
+
obj1.index = 1,
|
11
|
+
obj2.index = 2,
|
12
|
+
dist.index = 3,
|
13
|
+
empty.rm = TRUE,
|
14
|
+
...
|
15
|
+
)
|
16
|
+
}
|
17
|
+
\arguments{
|
18
|
+
\item{x}{A dataframe (or coercible object) with at least three columns:
|
19
|
+
\enumerate{
|
20
|
+
\item ID of the object 1,
|
21
|
+
\item ID of the object 2, and
|
22
|
+
\item distance between the two objects.}}
|
23
|
+
|
24
|
+
\item{groups}{Named array where the IDs correspond to the object IDs,
|
25
|
+
and the values correspond to the group.}
|
26
|
+
|
27
|
+
\item{obj1.index}{Index of the column containing the ID of the object 1.}
|
28
|
+
|
29
|
+
\item{obj2.index}{Index of the column containing the ID of the object 2.}
|
30
|
+
|
31
|
+
\item{dist.index}{Index of the column containing the distance.}
|
32
|
+
|
33
|
+
\item{empty.rm}{Remove incomplete matrices.}
|
34
|
+
|
35
|
+
\item{...}{Any other parameters supported by
|
36
|
+
\code{\link{enve.df2dist.group}}.}
|
37
|
+
}
|
38
|
+
\value{
|
39
|
+
Returns a \strong{list} of \strong{dist} objects.
|
40
|
+
}
|
41
|
+
\description{
|
42
|
+
Transform a dataframe (or coercible object, like a table)
|
43
|
+
into a \strong{dist} object.
|
44
|
+
}
|
45
|
+
\author{
|
46
|
+
Luis M. Rodriguez-R [aut, cre]
|
47
|
+
}
|
@@ -0,0 +1,75 @@
|
|
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(
|
8
|
+
x,
|
9
|
+
times = 1:nrow(x),
|
10
|
+
triplicates = FALSE,
|
11
|
+
design,
|
12
|
+
new.times = seq(min(times), max(times), length.out = length(times) * 10),
|
13
|
+
level = 0.95,
|
14
|
+
interval = c("confidence", "prediction"),
|
15
|
+
plot = TRUE,
|
16
|
+
FUN = function(t, K, r, P0) K * P0 * exp(r * t)/(K + P0 * (exp(r * t) - 1)),
|
17
|
+
nls.opt = list(),
|
18
|
+
...
|
19
|
+
)
|
20
|
+
}
|
21
|
+
\arguments{
|
22
|
+
\item{x}{Data frame (or coercible) containing the observed growth data
|
23
|
+
(e.g., O.D. values). Each column is an independent growth curve and each
|
24
|
+
row is a time point. \code{NA}'s are allowed.}
|
25
|
+
|
26
|
+
\item{times}{Vector with the times at which each row was taken. By default,
|
27
|
+
all rows are assumed to be part of constantly periodic measurements.}
|
28
|
+
|
29
|
+
\item{triplicates}{If \code{TRUE}, the columns are assumed to be sorted by
|
30
|
+
sample with three replicates by sample. It requires a number of columns
|
31
|
+
multiple of 3.}
|
32
|
+
|
33
|
+
\item{design}{Experimental design of the data. An \strong{array} of mode list
|
34
|
+
with sample names as index and the list of column names in each sample as
|
35
|
+
the values. By default, each column is assumed to be an independent sample
|
36
|
+
if \code{triplicates} is \code{FALSE}, or every three columns are assumed
|
37
|
+
to be a sample if \code{triplicates} is \code{TRUE}. In the latter case,
|
38
|
+
samples are simply numbered.}
|
39
|
+
|
40
|
+
\item{new.times}{Values of time for the fitted curve.}
|
41
|
+
|
42
|
+
\item{level}{Confidence (or prediction) interval in the fitted curve.}
|
43
|
+
|
44
|
+
\item{interval}{Type of interval to be calculated for the fitted curve.}
|
45
|
+
|
46
|
+
\item{plot}{Should the growth curve be plotted?}
|
47
|
+
|
48
|
+
\item{FUN}{Function to fit. By default: logistic growth with paramenters
|
49
|
+
\code{K}: carrying capacity,
|
50
|
+
\code{r}: intrinsic growth rate, and
|
51
|
+
\code{P0}: Initial population.}
|
52
|
+
|
53
|
+
\item{nls.opt}{Any additional options passed to \code{nls}.}
|
54
|
+
|
55
|
+
\item{...}{Any additional parameters to be passed to
|
56
|
+
\code{plot.enve.GrowthCurve}.}
|
57
|
+
}
|
58
|
+
\value{
|
59
|
+
Returns an \code{\link{enve.GrowthCurve}} object.
|
60
|
+
}
|
61
|
+
\description{
|
62
|
+
Calculates growth curves using the logistic growth function.
|
63
|
+
}
|
64
|
+
\examples{
|
65
|
+
# Load data
|
66
|
+
data("growth.curves", package="enveomics.R", envir=environment())
|
67
|
+
# Generate growth curves with different colors
|
68
|
+
g <- enve.growthcurve(growth.curves[,-1], growth.curves[,1], triplicates=TRUE)
|
69
|
+
# Generate black-and-white growth curves with different symbols
|
70
|
+
plot(g, pch=15:17, col="black", band.density=45, band.angle=c(-45,45,0))
|
71
|
+
|
72
|
+
}
|
73
|
+
\author{
|
74
|
+
Luis M. Rodriguez-R [aut, cre]
|
75
|
+
}
|
@@ -0,0 +1,50 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/prefscore.R
|
3
|
+
\name{enve.prefscore}
|
4
|
+
\alias{enve.prefscore}
|
5
|
+
\title{Enveomics: Pref Score}
|
6
|
+
\usage{
|
7
|
+
enve.prefscore(
|
8
|
+
x,
|
9
|
+
set,
|
10
|
+
ignore = NULL,
|
11
|
+
signif.thr,
|
12
|
+
plot = TRUE,
|
13
|
+
col.above = rgb(148, 17, 0, maxColorValue = 255),
|
14
|
+
col.equal = rgb(189, 189, 189, maxColorValue = 255),
|
15
|
+
col.below = rgb(47, 84, 150, maxColorValue = 255),
|
16
|
+
...
|
17
|
+
)
|
18
|
+
}
|
19
|
+
\arguments{
|
20
|
+
\item{x}{Occupancy matrix (logical or numeric binary) with species as rows and samples
|
21
|
+
as columns}
|
22
|
+
|
23
|
+
\item{set}{Vector indicating samples in the test set. It can be any selection vector:
|
24
|
+
boolean (same length as the number of columns in \code{x}), or numeric or
|
25
|
+
character vector with indexes of the \code{x} columns.}
|
26
|
+
|
27
|
+
\item{ignore}{Vector indicating species to ignore. It can be any selection vector with
|
28
|
+
respect to the rows in \code{x} (see \code{set}).}
|
29
|
+
|
30
|
+
\item{signif.thr}{Absolute value of the significance threshold}
|
31
|
+
|
32
|
+
\item{plot}{Indicates if a plot should be generated}
|
33
|
+
|
34
|
+
\item{col.above}{Color for points significantly above zero}
|
35
|
+
|
36
|
+
\item{col.equal}{Color for points not significantly different from zero}
|
37
|
+
|
38
|
+
\item{col.below}{Color for points significantly below zero}
|
39
|
+
|
40
|
+
\item{...}{Any additional parameters supported by \code{plot}}
|
41
|
+
}
|
42
|
+
\value{
|
43
|
+
Returns a named vector of preference scores.
|
44
|
+
}
|
45
|
+
\description{
|
46
|
+
Estimate preference score of species based on occupancy in biased sample sets
|
47
|
+
}
|
48
|
+
\author{
|
49
|
+
Luis M. Rodriguez-R [aut, cre]
|
50
|
+
}
|
@@ -0,0 +1,44 @@
|
|
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(
|
8
|
+
t,
|
9
|
+
dist.quantile = 0.25,
|
10
|
+
min_dist,
|
11
|
+
quiet = FALSE,
|
12
|
+
max_iters = 100,
|
13
|
+
min_nodes_random = 40000,
|
14
|
+
random_nodes_frx = 1
|
15
|
+
)
|
16
|
+
}
|
17
|
+
\arguments{
|
18
|
+
\item{t}{A \strong{phylo} object or a path to the Newick file.}
|
19
|
+
|
20
|
+
\item{dist.quantile}{The quantile of edge lengths.}
|
21
|
+
|
22
|
+
\item{min_dist}{The minimum distance to allow between two tips.
|
23
|
+
If not set, \code{dist.quantile} is used instead to calculate it.}
|
24
|
+
|
25
|
+
\item{quiet}{Boolean indicating if the function must run without output.}
|
26
|
+
|
27
|
+
\item{max_iters}{Maximum number of iterations.}
|
28
|
+
|
29
|
+
\item{min_nodes_random}{Minimum number of nodes to trigger \emph{tip-pairs} nodes sampling.
|
30
|
+
This sampling is less reproducible and more computationally expensive,
|
31
|
+
but it's the only solution if the cophenetic matrix exceeds \code{2^31-1}
|
32
|
+
entries; above that, it cannot be represented in R.}
|
33
|
+
|
34
|
+
\item{random_nodes_frx}{Fraction of the nodes to be sampled if more than \code{min_nodes_random}.}
|
35
|
+
}
|
36
|
+
\value{
|
37
|
+
Returns a pruned \strong{phylo} object.
|
38
|
+
}
|
39
|
+
\description{
|
40
|
+
Automatically prunes a tree, to keep representatives of each clade.
|
41
|
+
}
|
42
|
+
\author{
|
43
|
+
Luis M. Rodriguez-R [aut, cre]
|
44
|
+
}
|
@@ -0,0 +1,139 @@
|
|
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(
|
8
|
+
prefix,
|
9
|
+
id.min = NULL,
|
10
|
+
id.max = NULL,
|
11
|
+
id.binsize = NULL,
|
12
|
+
id.splines = 0,
|
13
|
+
id.metric = "id",
|
14
|
+
id.summary = "sum",
|
15
|
+
pos.min = 1,
|
16
|
+
pos.max = NULL,
|
17
|
+
pos.binsize = 1000,
|
18
|
+
pos.splines = 0,
|
19
|
+
rec.col1 = "white",
|
20
|
+
rec.col2 = "black",
|
21
|
+
main = NULL,
|
22
|
+
contig.col = grey(0.85),
|
23
|
+
ret.recplot = FALSE,
|
24
|
+
ret.hist = FALSE,
|
25
|
+
ret.mode = FALSE,
|
26
|
+
id.cutoff = NULL,
|
27
|
+
verbose = TRUE,
|
28
|
+
...
|
29
|
+
)
|
30
|
+
}
|
31
|
+
\arguments{
|
32
|
+
\item{prefix}{Path to the prefix of the BlastTab.catsbj.pl output files. At
|
33
|
+
least the files \strong{.rec} and \strong{.lim} must exist with this prefix.}
|
34
|
+
|
35
|
+
\item{id.min}{Minimum identity to be considered. By default, the minimum detected
|
36
|
+
identity. This value is a percentage.}
|
37
|
+
|
38
|
+
\item{id.max}{Maximum identity to be considered. By default, 100\%.}
|
39
|
+
|
40
|
+
\item{id.binsize}{Size of the identity bins (vertical histograms). By default, 0.1 for
|
41
|
+
identity metrics and 5 for bit score.}
|
42
|
+
|
43
|
+
\item{id.splines}{Smoothing parameter for the splines in the identity histogram. Zero (0) for no
|
44
|
+
splines. A generally good value is 1/2. If non-zero, requires the \pkg{stats} package.}
|
45
|
+
|
46
|
+
\item{id.metric}{Metric of identity to be used (Y-axis).
|
47
|
+
It can be any unambiguous prefix of:
|
48
|
+
\itemize{
|
49
|
+
\item "identity"
|
50
|
+
\item "corrected identity"
|
51
|
+
\item "bit score"}}
|
52
|
+
|
53
|
+
\item{id.summary}{Method used to build the identity histogram (Horizontal axis of the right panel).
|
54
|
+
It can be any unambiguous prefix of:
|
55
|
+
\itemize{
|
56
|
+
\item "sum"
|
57
|
+
\item "average"
|
58
|
+
\item "median"
|
59
|
+
\item "90\% lower bound"
|
60
|
+
\item "90\% upper bound"
|
61
|
+
\item "95\% lower bound"
|
62
|
+
\item "95\% upper bound" }
|
63
|
+
The last four options
|
64
|
+
correspond to the upper and lower boundaries of the 90\% and 95\% empirical confidence
|
65
|
+
intervals.}
|
66
|
+
|
67
|
+
\item{pos.min}{Minimum (leftmost) position in the reference (concatenated) genome (in bp).}
|
68
|
+
|
69
|
+
\item{pos.max}{Maximum (rightmost) position in the reference (concatenated) genome (in bp).
|
70
|
+
By default: Length of the genome.}
|
71
|
+
|
72
|
+
\item{pos.binsize}{Size of the position bins (horizontal histograms) in bp.}
|
73
|
+
|
74
|
+
\item{pos.splines}{Smoothing parameter for the splines in the position histogram. Zero (0) for no splines.
|
75
|
+
If non-zero, requires the stats package.}
|
76
|
+
|
77
|
+
\item{rec.col1}{Lightest color in the recruitment plot.}
|
78
|
+
|
79
|
+
\item{rec.col2}{Darkest color in the recruitment plot.}
|
80
|
+
|
81
|
+
\item{main}{Title of the plot.}
|
82
|
+
|
83
|
+
\item{contig.col}{Color of the Contig boundaries. Set to \code{NA} to ignore Contig boundaries.}
|
84
|
+
|
85
|
+
\item{ret.recplot}{Indicates if the matrix of the recruitment plot is to be returned.}
|
86
|
+
|
87
|
+
\item{ret.hist}{Ignored, for backwards compatibility.}
|
88
|
+
|
89
|
+
\item{ret.mode}{Indicates if the mode of the identity is to be computed. It requires the
|
90
|
+
\pkg{modeest} package.}
|
91
|
+
|
92
|
+
\item{id.cutoff}{Minimum identity to consider an alignment as "top". By default, it is 0.95 for the
|
93
|
+
identity metrics and 95\% of the best scoring alignment for bit score.}
|
94
|
+
|
95
|
+
\item{verbose}{Indicates if the function should report the advance.}
|
96
|
+
|
97
|
+
\item{...}{Any additional graphic parameters to be passed to plot for all panels except the
|
98
|
+
recruitment plot (lower-left).}
|
99
|
+
}
|
100
|
+
\value{
|
101
|
+
Returns a list with the following elements:
|
102
|
+
|
103
|
+
\describe{
|
104
|
+
\item{\code{pos.marks}}{Midpoints of the position histogram.}
|
105
|
+
\item{\code{id.matrix}}{Midpoints of the identity histogram.}
|
106
|
+
\item{\code{recplot}}{Matrix containing the recruitment plot values
|
107
|
+
(if \code{ret.recplot=TRUE}).}
|
108
|
+
\item{\code{id.mean}}{Mean identity.}
|
109
|
+
\item{\code{id.median}}{Median identity.}
|
110
|
+
\item{\code{id.mode}}{Mode of the identity (if \code{ret.mode=TRUE}). Deprecated.}
|
111
|
+
\item{\code{id.hist}}{Values of the identity histogram (if \code{ret.hist=TRUE}).}
|
112
|
+
\item{\code{pos.hist.low}}{Values of the position histogram (depth) with "low"
|
113
|
+
identity (i.e., below id.cutoff) (if \code{ret.hist=TRUE}).}
|
114
|
+
\item{\code{pos.hist.top}}{Values of the position histogram (depth) with "top"
|
115
|
+
identity (i.e., above id.cutoff) (if \code{ret.hist=TRUE}).}
|
116
|
+
\item{\code{id.max}}{Value of \code{id.max}. This is returned because
|
117
|
+
\code{id.max=NULL} may vary.}
|
118
|
+
\item{\code{id.cutoff}}{Value of \code{id.cutoff}.
|
119
|
+
This is returned because \code{id.cutoff=NULL} may vary.}
|
120
|
+
\item{\code{seqdepth.mean.top}}{Average sequencing depth with identity above
|
121
|
+
\code{id.cutoff}.}
|
122
|
+
\item{\code{seqdepth.mean.low}}{Average sequencing depth with identity below
|
123
|
+
\code{id.cutoff}.}
|
124
|
+
\item{\code{seqdepth.mean.all}}{Average sequencing depth without identity filtering.}
|
125
|
+
\item{\code{seqdepth.median.top}}{Median sequencing depth with identity above
|
126
|
+
\code{id.cutoff}.}
|
127
|
+
\item{\code{seqdepth.median.low}}{Median sequencing depth with identity below
|
128
|
+
\code{id.cutoff}.}
|
129
|
+
\item{\code{seqdepth.median.all}}{Median sequencing depth without identity filtering.}
|
130
|
+
\item{\code{id.metric}}{Full name of the used identity metric.}
|
131
|
+
\item{\code{id.summary}}{Full name of the summary method used to build the identity plot.}}
|
132
|
+
}
|
133
|
+
\description{
|
134
|
+
Produces recruitment plots provided that BlastTab.catsbj.pl has
|
135
|
+
been previously executed. Requires the \pkg{gplots} library.
|
136
|
+
}
|
137
|
+
\author{
|
138
|
+
Luis M. Rodriguez-R [aut, cre]
|
139
|
+
}
|
@@ -0,0 +1,45 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\docType{class}
|
4
|
+
\name{enve.RecPlot2-class}
|
5
|
+
\alias{enve.RecPlot2-class}
|
6
|
+
\alias{enve.RecPlot2}
|
7
|
+
\title{Enveomics: Recruitment Plot (2) - S4 Class}
|
8
|
+
\description{
|
9
|
+
Enve-omics representation of Recruitment plots. This object can
|
10
|
+
be produced by \code{\link{enve.recplot2}} and supports S4 method plot.
|
11
|
+
}
|
12
|
+
\section{Slots}{
|
13
|
+
|
14
|
+
\describe{
|
15
|
+
\item{\code{counts}}{\code{(matrix)} Counts as a two-dimensional histogram.}
|
16
|
+
|
17
|
+
\item{\code{pos.counts.in}}{\code{(numeric)} Counts of in-group hits per position bin.}
|
18
|
+
|
19
|
+
\item{\code{pos.counts.out}}{\code{(numeric)} Counts of out-group hits per position bin.}
|
20
|
+
|
21
|
+
\item{\code{id.counts}}{\code{(numeric)} Counts per ID bin.}
|
22
|
+
|
23
|
+
\item{\code{id.breaks}}{\code{(numeric)} Breaks of identity bins.}
|
24
|
+
|
25
|
+
\item{\code{pos.breaks}}{\code{(numeric)} Breaks of position bins.}
|
26
|
+
|
27
|
+
\item{\code{pos.names}}{\code{(character)} Names of the position bins.}
|
28
|
+
|
29
|
+
\item{\code{seq.breaks}}{\code{(numeric)} Breaks of input sequences.}
|
30
|
+
|
31
|
+
\item{\code{peaks}}{\code{(list)} Peaks identified in the recplot.
|
32
|
+
Limits of the subject sequences after concatenation.}
|
33
|
+
|
34
|
+
\item{\code{seq.names}}{\code{(character}) Names of the subject sequences.}
|
35
|
+
|
36
|
+
\item{\code{id.metric}}{\code{(character}) Metric used as 'identity'.}
|
37
|
+
|
38
|
+
\item{\code{id.ingroup}}{\code{(logical}) Identity bins considered in-group.}
|
39
|
+
|
40
|
+
\item{\code{call}}{\code{(call)} Call producing this object.}
|
41
|
+
}}
|
42
|
+
|
43
|
+
\author{
|
44
|
+
Luis M. Rodriguez-R [aut, cre]
|
45
|
+
}
|
@@ -0,0 +1,24 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.ANIr}
|
4
|
+
\alias{enve.recplot2.ANIr}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) ANI Estimate}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.ANIr(x, range = c(0, Inf))
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{x}{\code{\link{enve.RecPlot2}} object.}
|
11
|
+
|
12
|
+
\item{range}{Range of identities to be considered. By default, the full range
|
13
|
+
is used (note that the upper boundary is \code{Inf} and not 100 because
|
14
|
+
recruitment plots can also be built with bit-scores). To use only
|
15
|
+
intra-population matches (with identities), use c(95,100). To use only
|
16
|
+
inter-population values, use c(0,95).}
|
17
|
+
}
|
18
|
+
\description{
|
19
|
+
Estimate the Average Nucleotide Identity from reads (ANIr) from a
|
20
|
+
recruitment plot.
|
21
|
+
}
|
22
|
+
\author{
|
23
|
+
Luis M. Rodriguez-R [aut, cre]
|
24
|
+
}
|
@@ -0,0 +1,77 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2}
|
4
|
+
\alias{enve.recplot2}
|
5
|
+
\title{Enveomics: Recruitment Plot (2)}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2(
|
8
|
+
prefix,
|
9
|
+
plot = TRUE,
|
10
|
+
pos.breaks = 1000,
|
11
|
+
pos.breaks.tsv = NA,
|
12
|
+
id.breaks = 60,
|
13
|
+
id.free.range = FALSE,
|
14
|
+
id.metric = c("identity", "corrected identity", "bit score"),
|
15
|
+
id.summary = sum,
|
16
|
+
id.cutoff = 95,
|
17
|
+
threads = 2,
|
18
|
+
verbose = TRUE,
|
19
|
+
...
|
20
|
+
)
|
21
|
+
}
|
22
|
+
\arguments{
|
23
|
+
\item{prefix}{Path to the prefix of the \code{BlastTab.catsbj.pl} output files. At
|
24
|
+
least the files .rec and .lim must exist with this prefix.}
|
25
|
+
|
26
|
+
\item{plot}{Should the object be plotted?}
|
27
|
+
|
28
|
+
\item{pos.breaks}{Breaks in the positions histogram. It can also be a vector of break
|
29
|
+
points, and values outside the range are ignored. If zero (0), it
|
30
|
+
uses the sequence breaks as defined in the .lim file, which means
|
31
|
+
one bin per contig (or gene, if the mapping is agains genes). Ignored
|
32
|
+
if `pos.breaks.tsv` is passed.}
|
33
|
+
|
34
|
+
\item{pos.breaks.tsv}{Path to a list of (absolute) coordinates to use as position breaks.
|
35
|
+
This tab-delimited file can be produced by \code{GFF.catsbj.pl}, and it
|
36
|
+
must contain at least one column: coordinates of the break positions of
|
37
|
+
each position bin. If it has a second column, this is used as the name
|
38
|
+
of the position bin that ends at the given coordinate (the first row is
|
39
|
+
ignored). Any additional columns are currently ignored. If \code{NA},
|
40
|
+
position bins are determined by \code{pos.breaks}.}
|
41
|
+
|
42
|
+
\item{id.breaks}{Breaks in the identity histogram. It can also be a vector of break
|
43
|
+
points, and values outside the range are ignored.}
|
44
|
+
|
45
|
+
\item{id.free.range}{Indicates that the range should be freely set from the observed
|
46
|
+
values. Otherwise, 70-100\% is included in the identity histogram
|
47
|
+
(default).}
|
48
|
+
|
49
|
+
\item{id.metric}{Metric of identity to be used (Y-axis). Corrected identity is only
|
50
|
+
supported if the original BLAST file included sequence lengths.}
|
51
|
+
|
52
|
+
\item{id.summary}{Function summarizing the identity bins. Other recommended options
|
53
|
+
include: \code{median} to estimate the median instead of total bins, and
|
54
|
+
\code{function(x) mlv(x,method='parzen')$M} to estimate the mode.}
|
55
|
+
|
56
|
+
\item{id.cutoff}{Cutoff of identity metric above which the hits are considered
|
57
|
+
\code{in-group}. The 95\% identity corresponds to the expectation of
|
58
|
+
ANI<95\% within species.}
|
59
|
+
|
60
|
+
\item{threads}{Number of threads to use.}
|
61
|
+
|
62
|
+
\item{verbose}{Indicates if the function should report the advance.}
|
63
|
+
|
64
|
+
\item{...}{Any additional parameters supported by \code{\link{plot.enve.RecPlot2}}.}
|
65
|
+
}
|
66
|
+
\value{
|
67
|
+
Returns an object of class \code{\link{enve.RecPlot2}}.
|
68
|
+
}
|
69
|
+
\description{
|
70
|
+
Produces recruitment plots provided that \code{BlastTab.catsbj.pl} has
|
71
|
+
been previously executed.
|
72
|
+
}
|
73
|
+
\author{
|
74
|
+
Luis M. Rodriguez-R [aut, cre]
|
75
|
+
|
76
|
+
Kenji Gerhardt [aut]
|
77
|
+
}
|
@@ -0,0 +1,25 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.__counts}
|
4
|
+
\alias{enve.recplot2.__counts}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Internal Ancillary Function}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.__counts(x, pos.breaks, id.breaks, rec.idcol)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{x}{\code{\link{enve.RecPlot2}} object}
|
11
|
+
|
12
|
+
\item{pos.breaks}{Position breaks}
|
13
|
+
|
14
|
+
\item{id.breaks}{Identity breaks}
|
15
|
+
|
16
|
+
\item{rec.idcol}{Identity column to use}
|
17
|
+
}
|
18
|
+
\description{
|
19
|
+
Internal ancillary function (see \code{\link{enve.recplot2}}).
|
20
|
+
}
|
21
|
+
\author{
|
22
|
+
Luis M. Rodriguez-R [aut, cre]
|
23
|
+
|
24
|
+
Kenji Gerhardt [aut]
|
25
|
+
}
|
@@ -0,0 +1,21 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.__peakHist}
|
4
|
+
\alias{enve.recplot2.__peakHist}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Peak S4 Class - Internal Ancillary Function}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.__peakHist(x, mids, counts = TRUE)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{x}{\code{\link{enve.RecPlot2.Peak}} object}
|
11
|
+
|
12
|
+
\item{mids}{Midpoints}
|
13
|
+
|
14
|
+
\item{counts}{Counts}
|
15
|
+
}
|
16
|
+
\description{
|
17
|
+
Internal ancillary function (see \code{\link{enve.RecPlot2.Peak}}).
|
18
|
+
}
|
19
|
+
\author{
|
20
|
+
Luis M. Rodriguez-R [aut, cre]
|
21
|
+
}
|
@@ -0,0 +1,19 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.__whichClosestPeak}
|
4
|
+
\alias{enve.recplot2.__whichClosestPeak}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Peak Finder - Internal Ancillary Function}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.__whichClosestPeak(peak, peaks)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{peak}{Query \code{\link{enve.RecPlot2.Peak}} object}
|
11
|
+
|
12
|
+
\item{peaks}{list of \code{\link{enve.RecPlot2.Peak}} objects}
|
13
|
+
}
|
14
|
+
\description{
|
15
|
+
Internal ancillary function (see \code{\link{enve.recplot2.findPeaks}}).
|
16
|
+
}
|
17
|
+
\author{
|
18
|
+
Luis M. Rodriguez-R [aut, cre]
|
19
|
+
}
|
@@ -0,0 +1,19 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.changeCutoff}
|
4
|
+
\alias{enve.recplot2.changeCutoff}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Change Cutoff}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.changeCutoff(rp, new.cutoff = 98)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{rp}{\code{\link{enve.RecPlot2}} object.}
|
11
|
+
|
12
|
+
\item{new.cutoff}{New cutoff to use.}
|
13
|
+
}
|
14
|
+
\description{
|
15
|
+
Change the intra-species cutoff of an existing recruitment plot.
|
16
|
+
}
|
17
|
+
\author{
|
18
|
+
Luis M. Rodriguez-R [aut, cre]
|
19
|
+
}
|
@@ -0,0 +1,47 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.compareIdentities}
|
4
|
+
\alias{enve.recplot2.compareIdentities}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Compare Identities}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.compareIdentities(
|
8
|
+
x,
|
9
|
+
y,
|
10
|
+
method = "hellinger",
|
11
|
+
smooth.par = NULL,
|
12
|
+
pseudocounts = 0,
|
13
|
+
max.deviation = 0.75
|
14
|
+
)
|
15
|
+
}
|
16
|
+
\arguments{
|
17
|
+
\item{x}{First \code{\link{enve.RecPlot2}} object.}
|
18
|
+
|
19
|
+
\item{y}{Second \code{\link{enve.RecPlot2}} object.}
|
20
|
+
|
21
|
+
\item{method}{Distance method to use. This should be (an unambiguous abbreviation of)
|
22
|
+
one of:
|
23
|
+
\itemize{
|
24
|
+
\item{"hellinger" (\emph{Hellinger, 1090, doi:10.1515/crll.1909.136.210}),}
|
25
|
+
\item{"bhattacharyya" (\emph{Bhattacharyya, 1943, Bull. Calcutta Math. Soc. 35}),}
|
26
|
+
\item{"kl" or "kullback-leibler" (\emph{Kullback & Leibler, 1951,
|
27
|
+
doi:10.1214/aoms/1177729694}), or}
|
28
|
+
\item{"euclidean"}
|
29
|
+
}}
|
30
|
+
|
31
|
+
\item{smooth.par}{Smoothing parameter for cubic spline smoothing. Use 0 for no smoothing.
|
32
|
+
Use \code{NULL} to automatically determine this value using leave-one-out
|
33
|
+
cross-validation (see \code{smooth.spline} parameter \code{spar}).}
|
34
|
+
|
35
|
+
\item{pseudocounts}{Smoothing parameter for Laplace smoothing. Use 0 for no smoothing, or
|
36
|
+
1 for add-one smoothing.}
|
37
|
+
|
38
|
+
\item{max.deviation}{Maximum mean deviation between identity breaks tolerated (as percent
|
39
|
+
identity). Difference in number of \code{id.breaks} is never tolerated.}
|
40
|
+
}
|
41
|
+
\description{
|
42
|
+
Compare the distribution of identities between two
|
43
|
+
\code{\link{enve.RecPlot2}} objects.
|
44
|
+
}
|
45
|
+
\author{
|
46
|
+
Luis M. Rodriguez-R [aut, cre]
|
47
|
+
}
|
@@ -0,0 +1,29 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.coordinates}
|
4
|
+
\alias{enve.recplot2.coordinates}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Coordinates}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.coordinates(x, bins)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{x}{\code{\link{enve.RecPlot2}} object.}
|
11
|
+
|
12
|
+
\item{bins}{Vector of selected bins to return. It can be a vector of logical values
|
13
|
+
with the same length as \code{x$pos.breaks-1} or a vector of integers. If
|
14
|
+
missing, returns the coordinates of all windows.}
|
15
|
+
}
|
16
|
+
\value{
|
17
|
+
Returns a data.frame with five columns: \code{name.from} (character),
|
18
|
+
\code{pos.from} (numeric), \code{name.to} (character), \code{pos.to}
|
19
|
+
(numeric), and \code{seq.name} (character).
|
20
|
+
The first two correspond to sequence and position of the start point of the
|
21
|
+
bin. The next two correspond to the sequence and position of the end point of
|
22
|
+
the bin. The last one indicates the name of the sequence (if defined).
|
23
|
+
}
|
24
|
+
\description{
|
25
|
+
Returns the sequence name and coordinates of the requested position bins.
|
26
|
+
}
|
27
|
+
\author{
|
28
|
+
Luis M. Rodriguez-R [aut, cre]
|
29
|
+
}
|
@@ -0,0 +1,18 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.corePeak}
|
4
|
+
\alias{enve.recplot2.corePeak}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Core Peak Finder}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.corePeak(x)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{x}{\code{list} of \code{\link{enve.RecPlot2.Peak}} objects.}
|
11
|
+
}
|
12
|
+
\description{
|
13
|
+
Finds the peak in a list of peaks that is most likely to represent the
|
14
|
+
"core genome" of a population.
|
15
|
+
}
|
16
|
+
\author{
|
17
|
+
Luis M. Rodriguez-R [aut, cre]
|
18
|
+
}
|