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 +1,45 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.extractWindows}
|
4
|
+
\alias{enve.recplot2.extractWindows}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Extract Windows}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.extractWindows(
|
8
|
+
rp,
|
9
|
+
peak,
|
10
|
+
lower.tail = TRUE,
|
11
|
+
significance = 0.05,
|
12
|
+
seq.names = FALSE
|
13
|
+
)
|
14
|
+
}
|
15
|
+
\arguments{
|
16
|
+
\item{rp}{Recruitment plot, a \code{\link{enve.RecPlot2}} object.}
|
17
|
+
|
18
|
+
\item{peak}{Peak, an \code{\link{enve.RecPlot2.Peak}} object. If list, it is assumed to be a
|
19
|
+
list of \code{\link{enve.RecPlot2.Peak}} objects, in which case the core peak is
|
20
|
+
used (see \code{\link{enve.recplot2.corePeak}}).}
|
21
|
+
|
22
|
+
\item{lower.tail}{If \code{FALSE}, it returns windows significantly above the peak in
|
23
|
+
sequencing depth.}
|
24
|
+
|
25
|
+
\item{significance}{Significance threshold (alpha) to select windows.}
|
26
|
+
|
27
|
+
\item{seq.names}{Returns subject sequence names instead of a vector of Booleans. If
|
28
|
+
the recruitment plot was generated with named position bins (e.g, using
|
29
|
+
\code{pos.breaks=0} or a two-column \code{pos.breaks.tsv}), it returns a
|
30
|
+
vector of characters (the sequence identifiers), otherwise it returns a
|
31
|
+
data.frame with a name column and two columns of coordinates.}
|
32
|
+
}
|
33
|
+
\value{
|
34
|
+
Returns a vector of logicals if \code{seq.names = FALSE}.
|
35
|
+
If \code{seq.names = TRUE}, it returns a data.frame with five columns:
|
36
|
+
\code{name.from}, \code{name.to}, \code{pos.from}, \code{pos.to}, and
|
37
|
+
\code{seq.name} (see \code{\link{enve.recplot2.coordinates}}).
|
38
|
+
}
|
39
|
+
\description{
|
40
|
+
Extract windows significantly below (or above) the peak in sequencing
|
41
|
+
depth.
|
42
|
+
}
|
43
|
+
\author{
|
44
|
+
Luis M. Rodriguez-R [aut, cre]
|
45
|
+
}
|
@@ -0,0 +1,36 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.findPeaks}
|
4
|
+
\alias{enve.recplot2.findPeaks}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Peak Finder}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.findPeaks(x, method = "emauto", ...)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{x}{An \code{\link{enve.RecPlot2}} object.}
|
11
|
+
|
12
|
+
\item{method}{Peak-finder method. This should be one of:
|
13
|
+
\itemize{
|
14
|
+
\item \strong{emauto}
|
15
|
+
(Expectation-Maximization with auto-selection of components)
|
16
|
+
\item \strong{em}
|
17
|
+
(Expectation-Maximization)
|
18
|
+
\item \strong{mower}
|
19
|
+
(Custom distribution-mowing method)
|
20
|
+
}}
|
21
|
+
|
22
|
+
\item{...}{Any additional parameters supported by
|
23
|
+
\code{\link{enve.recplot2.findPeaks}}.}
|
24
|
+
}
|
25
|
+
\value{
|
26
|
+
Returns a list of \code{\link{enve.RecPlot2.Peak}} objects.
|
27
|
+
}
|
28
|
+
\description{
|
29
|
+
Identifies peaks in the population histogram potentially indicating
|
30
|
+
sub-population mixtures.
|
31
|
+
}
|
32
|
+
\author{
|
33
|
+
Luis M. Rodriguez-R [aut, cre]
|
34
|
+
|
35
|
+
export
|
36
|
+
}
|
@@ -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.findPeaks.__em_e}
|
4
|
+
\alias{enve.recplot2.findPeaks.__em_e}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) EM Peak Finder - Internal Ancillary Function Expectation}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.findPeaks.__em_e(x, theta)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{x}{Vector of log-transformed sequencing depths}
|
11
|
+
|
12
|
+
\item{theta}{Parameters list}
|
13
|
+
}
|
14
|
+
\description{
|
15
|
+
Internal ancillary function (see \code{\link{enve.recplot2.findPeaks.em}}).
|
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.findPeaks.__em_m}
|
4
|
+
\alias{enve.recplot2.findPeaks.__em_m}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Em Peak Finder - Internal Ancillary Function Maximization}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.findPeaks.__em_m(x, posterior)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{x}{Vector of log-transformed sequencing depths}
|
11
|
+
|
12
|
+
\item{posterior}{Posterior probability}
|
13
|
+
}
|
14
|
+
\description{
|
15
|
+
Internal ancillary function (see \code{\link{enve.recplot2.findPeaks.em}}).
|
16
|
+
}
|
17
|
+
\author{
|
18
|
+
Luis M. Rodriguez-R [aut, cre]
|
19
|
+
}
|
@@ -0,0 +1,27 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.findPeaks.__emauto_one}
|
4
|
+
\alias{enve.recplot2.findPeaks.__emauto_one}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) EMauto Peak Finder - Internal Ancillary Function}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.findPeaks.__emauto_one(x, comp, do_crit, best, verbose, ...)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{x}{\code{\link{enve.RecPlot2}} object}
|
11
|
+
|
12
|
+
\item{comp}{Components}
|
13
|
+
|
14
|
+
\item{do_crit}{Function estimating the criterion}
|
15
|
+
|
16
|
+
\item{best}{Best solution thus far}
|
17
|
+
|
18
|
+
\item{verbose}{If verbose}
|
19
|
+
|
20
|
+
\item{...}{Additional parameters for \code{\link{enve.recplot2.findPeaks.em}}}
|
21
|
+
}
|
22
|
+
\description{
|
23
|
+
Internal ancillary function (see \code{\link{enve.recplot2.findPeaks.emauto}}).
|
24
|
+
}
|
25
|
+
\author{
|
26
|
+
Luis M. Rodriguez-R [aut, cre]
|
27
|
+
}
|
@@ -0,0 +1,52 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.findPeaks.__mow_one}
|
4
|
+
\alias{enve.recplot2.findPeaks.__mow_one}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Mowing Peak Finder - Internal Ancillary Function 1}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.findPeaks.__mow_one(
|
8
|
+
lsd1,
|
9
|
+
min.points,
|
10
|
+
quant.est,
|
11
|
+
mlv.opts,
|
12
|
+
fitdist.opts,
|
13
|
+
with.skewness,
|
14
|
+
optim.rounds,
|
15
|
+
optim.epsilon,
|
16
|
+
n.total,
|
17
|
+
merge.logdist,
|
18
|
+
verbose,
|
19
|
+
log
|
20
|
+
)
|
21
|
+
}
|
22
|
+
\arguments{
|
23
|
+
\item{lsd1}{Vector of log-transformed sequencing depths}
|
24
|
+
|
25
|
+
\item{min.points}{Minimum number of points}
|
26
|
+
|
27
|
+
\item{quant.est}{Quantile estimate}
|
28
|
+
|
29
|
+
\item{mlv.opts}{List of options for \code{mlv}}
|
30
|
+
|
31
|
+
\item{fitdist.opts}{List of options for \code{fitdist}}
|
32
|
+
|
33
|
+
\item{with.skewness}{If skewed-normal should be used}
|
34
|
+
|
35
|
+
\item{optim.rounds}{Maximum number of optimization rounds}
|
36
|
+
|
37
|
+
\item{optim.epsilon}{Minimum difference considered negligible}
|
38
|
+
|
39
|
+
\item{n.total}{Global number of windows}
|
40
|
+
|
41
|
+
\item{merge.logdist}{Attempted \code{merge.logdist} parameter}
|
42
|
+
|
43
|
+
\item{verbose}{If verbose}
|
44
|
+
|
45
|
+
\item{log}{If log-transformed depths}
|
46
|
+
}
|
47
|
+
\description{
|
48
|
+
Internall ancillary function (see \code{\link{enve.recplot2.findPeaks.mower}}).
|
49
|
+
}
|
50
|
+
\author{
|
51
|
+
Luis M. Rodriguez-R [aut, cre]
|
52
|
+
}
|
@@ -0,0 +1,17 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.findPeaks.__mower}
|
4
|
+
\alias{enve.recplot2.findPeaks.__mower}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Mowing Peak Finder - Internal Ancillary Function 2}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.findPeaks.__mower(peaks.opts)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{peaks.opts}{List of options for \code{\link{enve.recplot2.findPeaks.__mow_one}}}
|
11
|
+
}
|
12
|
+
\description{
|
13
|
+
Internal ancillary function (see \code{\link{enve.recplot2.findPeaks.mower}}).
|
14
|
+
}
|
15
|
+
\author{
|
16
|
+
Luis M. Rodriguez-R [aut, cre]
|
17
|
+
}
|
@@ -0,0 +1,51 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.findPeaks.em}
|
4
|
+
\alias{enve.recplot2.findPeaks.em}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Em Peak Finder}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.findPeaks.em(
|
8
|
+
x,
|
9
|
+
max.iter = 1000,
|
10
|
+
ll.diff.res = 1e-08,
|
11
|
+
components = 2,
|
12
|
+
rm.top = 0.05,
|
13
|
+
verbose = FALSE,
|
14
|
+
init,
|
15
|
+
log = TRUE
|
16
|
+
)
|
17
|
+
}
|
18
|
+
\arguments{
|
19
|
+
\item{x}{An \code{\link{enve.RecPlot2}} object.}
|
20
|
+
|
21
|
+
\item{max.iter}{Maximum number of EM iterations.}
|
22
|
+
|
23
|
+
\item{ll.diff.res}{Maximum Log-Likelihood difference to be considered as convergent.}
|
24
|
+
|
25
|
+
\item{components}{Number of distributions assumed in the mixture.}
|
26
|
+
|
27
|
+
\item{rm.top}{Top-values to remove before finding peaks, as a quantile probability.
|
28
|
+
This step is useful to remove highly conserved regions, but can be
|
29
|
+
turned off by setting \code{rm.top=0}. The quantile is determined
|
30
|
+
\strong{after} removing zero-coverage windows.}
|
31
|
+
|
32
|
+
\item{verbose}{Display (mostly debugging) information.}
|
33
|
+
|
34
|
+
\item{init}{Initialization parameters. By default, these are derived from k-means
|
35
|
+
clustering. A named list with vectors for \code{mu}, \code{sd}, and
|
36
|
+
\code{alpha}, each of length \code{components}.}
|
37
|
+
|
38
|
+
\item{log}{Logical value indicating if the estimations should be performed in
|
39
|
+
natural logarithm units. Do not change unless you know what you're
|
40
|
+
doing.}
|
41
|
+
}
|
42
|
+
\value{
|
43
|
+
Returns a list of \code{\link{enve.RecPlot2.Peak}} objects.
|
44
|
+
}
|
45
|
+
\description{
|
46
|
+
Identifies peaks in the population histogram using a Gaussian Mixture
|
47
|
+
Model Expectation Maximization (GMM-EM) method.
|
48
|
+
}
|
49
|
+
\author{
|
50
|
+
Luis M. Rodriguez-R [aut, cre]
|
51
|
+
}
|
@@ -0,0 +1,43 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.findPeaks.emauto}
|
4
|
+
\alias{enve.recplot2.findPeaks.emauto}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Emauto Peak Finder}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.findPeaks.emauto(
|
8
|
+
x,
|
9
|
+
components = seq(1, 5),
|
10
|
+
criterion = "aic",
|
11
|
+
merge.tol = 2L,
|
12
|
+
verbose = FALSE,
|
13
|
+
...
|
14
|
+
)
|
15
|
+
}
|
16
|
+
\arguments{
|
17
|
+
\item{x}{An \code{\link{enve.RecPlot2}} object.}
|
18
|
+
|
19
|
+
\item{components}{A vector of number of components to evaluate.}
|
20
|
+
|
21
|
+
\item{criterion}{Criterion to use for components selection. Must be one of:
|
22
|
+
\code{aic} (Akaike Information Criterion), \code{bic} or \code{sbc}
|
23
|
+
(Bayesian Information Criterion or Schwarz Criterion).}
|
24
|
+
|
25
|
+
\item{merge.tol}{When attempting to merge peaks with very similar sequencing depth, use
|
26
|
+
this number of significant digits (in log-scale).}
|
27
|
+
|
28
|
+
\item{verbose}{Display (mostly debugging) information.}
|
29
|
+
|
30
|
+
\item{...}{Any additional parameters supported by
|
31
|
+
\code{\link{enve.recplot2.findPeaks.em}}.}
|
32
|
+
}
|
33
|
+
\value{
|
34
|
+
Returns a list of \code{\link{enve.RecPlot2.Peak}} objects.
|
35
|
+
}
|
36
|
+
\description{
|
37
|
+
Identifies peaks in the population histogram using a Gaussian Mixture
|
38
|
+
Model Expectation Maximization (GMM-EM) method with number of components
|
39
|
+
automatically detected.
|
40
|
+
}
|
41
|
+
\author{
|
42
|
+
Luis M. Rodriguez-R [aut, cre]
|
43
|
+
}
|
@@ -0,0 +1,82 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.findPeaks.mower}
|
4
|
+
\alias{enve.recplot2.findPeaks.mower}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Mowing Peak Finder}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.findPeaks.mower(
|
8
|
+
x,
|
9
|
+
min.points = 10,
|
10
|
+
quant.est = c(0.002, 0.998),
|
11
|
+
mlv.opts = list(method = "parzen"),
|
12
|
+
fitdist.opts.sn = list(distr = "sn", method = "qme", probs = c(0.1, 0.5, 0.8), start =
|
13
|
+
list(omega = 1, alpha = -1), lower = c(0, -Inf, -Inf)),
|
14
|
+
fitdist.opts.norm = list(distr = "norm", method = "qme", probs = c(0.4, 0.6), start =
|
15
|
+
list(sd = 1), lower = c(0, -Inf)),
|
16
|
+
rm.top = 0.05,
|
17
|
+
with.skewness = TRUE,
|
18
|
+
optim.rounds = 200,
|
19
|
+
optim.epsilon = 1e-04,
|
20
|
+
merge.logdist = log(1.75),
|
21
|
+
verbose = FALSE,
|
22
|
+
log = TRUE
|
23
|
+
)
|
24
|
+
}
|
25
|
+
\arguments{
|
26
|
+
\item{x}{An \code{\link{enve.RecPlot2}} object.}
|
27
|
+
|
28
|
+
\item{min.points}{Minimum number of points in the quantile-estimation-range
|
29
|
+
\code{(quant.est)} to estimate a peak.}
|
30
|
+
|
31
|
+
\item{quant.est}{Range of quantiles to be used in the estimation of a peak's
|
32
|
+
parameters.}
|
33
|
+
|
34
|
+
\item{mlv.opts}{Ignored. For backwards compatibility.}
|
35
|
+
|
36
|
+
\item{fitdist.opts.sn}{Options passed to \code{fitdist} to estimate the standard deviation if
|
37
|
+
\code{with.skewness=TRUE}. Note that the \code{start} parameter will be
|
38
|
+
ammended with \code{xi=estimated} mode for each peak.}
|
39
|
+
|
40
|
+
\item{fitdist.opts.norm}{Options passed to \code{fitdist} to estimate the standard deviation if
|
41
|
+
\code{with.skewness=FALSE}. Note that the \code{start} parameter will be
|
42
|
+
ammended with \code{mean=estimated} mode for each peak.}
|
43
|
+
|
44
|
+
\item{rm.top}{Top-values to remove before finding peaks, as a quantile probability.
|
45
|
+
This step is useful to remove highly conserved regions, but can be
|
46
|
+
turned off by setting \code{rm.top=0}. The quantile is determined
|
47
|
+
\strong{after} removing zero-coverage windows.}
|
48
|
+
|
49
|
+
\item{with.skewness}{Allow skewness correction of the peaks. Typically, the
|
50
|
+
sequencing-depth distribution for a single peak is left-skewed, due
|
51
|
+
partly (but not exclusively) to fragmentation and mapping sensitivity.
|
52
|
+
See \emph{Lindner et al 2013, Bioinformatics 29(10):1260-7} for an
|
53
|
+
alternative solution for the first problem (fragmentation) called
|
54
|
+
"tail distribution".}
|
55
|
+
|
56
|
+
\item{optim.rounds}{Maximum rounds of peak optimization.}
|
57
|
+
|
58
|
+
\item{optim.epsilon}{Trace change at which optimization stops (unless \code{optim.rounds} is
|
59
|
+
reached first). The trace change is estimated as the sum of square
|
60
|
+
differences between parameters in one round and those from two rounds
|
61
|
+
earlier (to avoid infinite loops from approximation).}
|
62
|
+
|
63
|
+
\item{merge.logdist}{Maximum value of \code{|log-ratio|} between centrality parameters in peaks
|
64
|
+
to attempt merging. The default of ~0.22 corresponds to a maximum
|
65
|
+
difference of 25\%.}
|
66
|
+
|
67
|
+
\item{verbose}{Display (mostly debugging) information.}
|
68
|
+
|
69
|
+
\item{log}{Logical value indicating if the estimations should be performed in
|
70
|
+
natural logarithm units. Do not change unless you know what you're
|
71
|
+
doing.}
|
72
|
+
}
|
73
|
+
\value{
|
74
|
+
Returns a list of \code{\link{enve.RecPlot2.Peak}} objects.
|
75
|
+
}
|
76
|
+
\description{
|
77
|
+
Identifies peaks in the population histogram potentially indicating
|
78
|
+
sub-population mixtures, using a custom distribution-mowing method.
|
79
|
+
}
|
80
|
+
\author{
|
81
|
+
Luis M. Rodriguez-R [aut, cre]
|
82
|
+
}
|
@@ -0,0 +1,59 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\docType{class}
|
4
|
+
\name{enve.RecPlot2.Peak-class}
|
5
|
+
\alias{enve.RecPlot2.Peak-class}
|
6
|
+
\alias{enve.RecPlot2.Peak}
|
7
|
+
\title{Enveomics: Recruitment Plot (2) Peak - S4 Class}
|
8
|
+
\description{
|
9
|
+
Enve-omics representation of a peak in the sequencing depth histogram
|
10
|
+
of a Recruitment plot (see \code{\link{enve.recplot2.findPeaks}}).
|
11
|
+
}
|
12
|
+
\section{Slots}{
|
13
|
+
|
14
|
+
\describe{
|
15
|
+
\item{\code{dist}}{\code{(character)}
|
16
|
+
Distribution of the peak. Currently supported: \code{norm} (normal) and \code{sn}
|
17
|
+
(skew-normal).}
|
18
|
+
|
19
|
+
\item{\code{values}}{\code{(numeric)}
|
20
|
+
Sequencing depth values predicted to conform the peak.}
|
21
|
+
|
22
|
+
\item{\code{values.res}}{\code{(numeric)}
|
23
|
+
Sequencing depth values not explained by this or previously identified
|
24
|
+
peaks.}
|
25
|
+
|
26
|
+
\item{\code{mode}}{\code{(numeric)}
|
27
|
+
Seed-value of mode anchoring the peak.}
|
28
|
+
|
29
|
+
\item{\code{param.hat}}{\code{(list)}
|
30
|
+
Parameters of the distribution. A list of two values if dist=\code{norm} (sd
|
31
|
+
and mean), or three values if dist=\code{sn}(omega=scale, alpha=shape, and
|
32
|
+
xi=location). Note that the "dispersion" parameter is always first and
|
33
|
+
the "location" parameter is always last.}
|
34
|
+
|
35
|
+
\item{\code{n.hat}}{\code{(numeric)}
|
36
|
+
Number of bins estimated to be explained by this peak. This should
|
37
|
+
ideally be equal to the length of \code{values}, but it's not an integer.}
|
38
|
+
|
39
|
+
\item{\code{n.total}}{\code{(numeric)}
|
40
|
+
Total number of bins from which the peak was extracted. I.e., total
|
41
|
+
number of position bins with non-zero sequencing depth in the recruitment
|
42
|
+
plot (regardless of peak count).}
|
43
|
+
|
44
|
+
\item{\code{err.res}}{\code{(numeric)}
|
45
|
+
Error left after adding the peak (mower) or log-likelihood (em or emauto).}
|
46
|
+
|
47
|
+
\item{\code{merge.logdist}}{\code{(numeric)}
|
48
|
+
Attempted \code{merge.logdist} parameter.}
|
49
|
+
|
50
|
+
\item{\code{seq.depth}}{\code{(numeric)}
|
51
|
+
Best estimate available for the sequencing depth of the peak (centrality).}
|
52
|
+
|
53
|
+
\item{\code{log}}{\code{(logical)}
|
54
|
+
Indicates if the estimation was performed in natural logarithm space.}
|
55
|
+
}}
|
56
|
+
|
57
|
+
\author{
|
58
|
+
Luis M. Rodriguez-R [aut, cre]
|
59
|
+
}
|
@@ -0,0 +1,27 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.seqdepth}
|
4
|
+
\alias{enve.recplot2.seqdepth}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Sequencing Depth}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.seqdepth(x, sel, low.identity = FALSE)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{x}{\code{\link{enve.RecPlot2}} object.}
|
11
|
+
|
12
|
+
\item{sel}{Window(s) for which the sequencing depth is to be calculated. If not
|
13
|
+
passed, it returns the sequencing depth of all windows.}
|
14
|
+
|
15
|
+
\item{low.identity}{A logical indicating if the sequencing depth is to be estimated only
|
16
|
+
with low-identity matches. By default, only high-identity matches are
|
17
|
+
used.}
|
18
|
+
}
|
19
|
+
\value{
|
20
|
+
Returns a numeric vector of sequencing depths (in bp/bp).
|
21
|
+
}
|
22
|
+
\description{
|
23
|
+
Calculate the sequencing depth of the given window(s).
|
24
|
+
}
|
25
|
+
\author{
|
26
|
+
Luis M. Rodriguez-R [aut, cre]
|
27
|
+
}
|
@@ -0,0 +1,36 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/recplot2.R
|
3
|
+
\name{enve.recplot2.windowDepthThreshold}
|
4
|
+
\alias{enve.recplot2.windowDepthThreshold}
|
5
|
+
\title{Enveomics: Recruitment Plot (2) Window Depth Threshold}
|
6
|
+
\usage{
|
7
|
+
enve.recplot2.windowDepthThreshold(
|
8
|
+
rp,
|
9
|
+
peak,
|
10
|
+
lower.tail = TRUE,
|
11
|
+
significance = 0.05
|
12
|
+
)
|
13
|
+
}
|
14
|
+
\arguments{
|
15
|
+
\item{rp}{Recruitment plot, an \code{\link{enve.RecPlot2}} object.}
|
16
|
+
|
17
|
+
\item{peak}{Peak, an \code{\link{enve.RecPlot2.Peak}} object. If list, it is assumed to be a
|
18
|
+
list of \code{\link{enve.RecPlot2.Peak}} objects, in which case the core peak is
|
19
|
+
used (see \code{\link{enve.recplot2.corePeak}}).}
|
20
|
+
|
21
|
+
\item{lower.tail}{If \code{FALSE}, it returns windows significantly above the peak in
|
22
|
+
sequencing depth.}
|
23
|
+
|
24
|
+
\item{significance}{Significance threshold (alpha) to select windows.}
|
25
|
+
}
|
26
|
+
\value{
|
27
|
+
Returns a float. The units are depth if the peaks were estimated in
|
28
|
+
linear scale, or log-depth otherwise (\code{peak$log}).
|
29
|
+
}
|
30
|
+
\description{
|
31
|
+
Identifies the threshold below which windows should be identified as
|
32
|
+
variable or absent.
|
33
|
+
}
|
34
|
+
\author{
|
35
|
+
Luis M. Rodriguez-R [aut, cre]
|
36
|
+
}
|
@@ -0,0 +1,23 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/utils.R
|
3
|
+
\name{enve.selvector}
|
4
|
+
\alias{enve.selvector}
|
5
|
+
\title{Enveomics: Selection vector}
|
6
|
+
\usage{
|
7
|
+
enve.selvector(sel, dim.names)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{sel}{A vector of numbers, characters, or booleans.}
|
11
|
+
|
12
|
+
\item{dim.names}{A vector of names from which to select.}
|
13
|
+
}
|
14
|
+
\value{
|
15
|
+
Returns a logical vector with the same length as \code{dim.name}.
|
16
|
+
}
|
17
|
+
\description{
|
18
|
+
Normalizes a selection vector \code{sel} to a logical vector with indexes
|
19
|
+
from \code{dim.names}.
|
20
|
+
}
|
21
|
+
\author{
|
22
|
+
Luis M. Rodriguez-R [aut, cre]
|
23
|
+
}
|
@@ -0,0 +1,68 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/tribs.R
|
3
|
+
\name{enve.tribs}
|
4
|
+
\alias{enve.tribs}
|
5
|
+
\title{Enveomics: TRIBS}
|
6
|
+
\usage{
|
7
|
+
enve.tribs(
|
8
|
+
dist,
|
9
|
+
selection = labels(dist),
|
10
|
+
replicates = 1000,
|
11
|
+
summary.fx = median,
|
12
|
+
dist.method = "euclidean",
|
13
|
+
subsamples = seq(0, 1, by = 0.01),
|
14
|
+
dimensions = ceiling(length(selection) * 0.05),
|
15
|
+
metaMDS.opts = list(),
|
16
|
+
threads = 2,
|
17
|
+
verbosity = 1,
|
18
|
+
points,
|
19
|
+
pre.tribs
|
20
|
+
)
|
21
|
+
}
|
22
|
+
\arguments{
|
23
|
+
\item{dist}{Distances as a \code{dist} object.}
|
24
|
+
|
25
|
+
\item{selection}{Objects to include in the subsample. By default, all objects are
|
26
|
+
selected.}
|
27
|
+
|
28
|
+
\item{replicates}{Number of replications per point.}
|
29
|
+
|
30
|
+
\item{summary.fx}{Function to summarize the distance distributions in a given replicate. By
|
31
|
+
default, the median distance is estimated.}
|
32
|
+
|
33
|
+
\item{dist.method}{Distance method between random points and samples in the transformed
|
34
|
+
space. See \code{dist}.}
|
35
|
+
|
36
|
+
\item{subsamples}{Subsampling fractions.}
|
37
|
+
|
38
|
+
\item{dimensions}{Dimensions to use in the NMDS. By default, 5\% of the selection length.}
|
39
|
+
|
40
|
+
\item{metaMDS.opts}{Any additional options to pass to metaMDS, as \code{list}.}
|
41
|
+
|
42
|
+
\item{threads}{Number of threads to use.}
|
43
|
+
|
44
|
+
\item{verbosity}{Verbosity. Use 0 to run quietly, increase for additional information.}
|
45
|
+
|
46
|
+
\item{points}{Optional. If passed, the MDS step is skipped and this object is used
|
47
|
+
instead. It can be the \code{$points} slot of class \code{metaMDS}
|
48
|
+
(from \code{vegan}).
|
49
|
+
It must be a matrix or matrix-coercible object, with samples as rows and
|
50
|
+
dimensions as columns.}
|
51
|
+
|
52
|
+
\item{pre.tribs}{Optional. If passed, the points are recovered from this object (except if
|
53
|
+
\code{points} is also passed. This should be an \code{\link{enve.TRIBS}} object
|
54
|
+
estimated on the same objects (the selection is unimportant).}
|
55
|
+
}
|
56
|
+
\value{
|
57
|
+
Returns an \code{\link{enve.TRIBS}} object.
|
58
|
+
}
|
59
|
+
\description{
|
60
|
+
Subsample any objects in "distance space" to reduce the effect of
|
61
|
+
sample-clustering. This function was originally designed to subsample
|
62
|
+
genomes in "phylogenetic distance space", a clear case of strong
|
63
|
+
clustering bias in sampling, by Luis M. Rodriguez-R and Michael R
|
64
|
+
Weigand.
|
65
|
+
}
|
66
|
+
\author{
|
67
|
+
Luis M. Rodriguez-R [aut, cre]
|
68
|
+
}
|
@@ -0,0 +1,28 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/tribs.R
|
3
|
+
\name{enve.tribs.test}
|
4
|
+
\alias{enve.tribs.test}
|
5
|
+
\title{Enveomics: TRIBS Test}
|
6
|
+
\usage{
|
7
|
+
enve.tribs.test(dist, selection, bins = 50, ...)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{dist}{Distances as \code{dist} object.}
|
11
|
+
|
12
|
+
\item{selection}{Selection defining the subset.}
|
13
|
+
|
14
|
+
\item{bins}{Number of bins to evaluate in the range of distances.}
|
15
|
+
|
16
|
+
\item{...}{Any other parameters supported by \code{\link{enve.tribs}},
|
17
|
+
except \code{subsamples}.}
|
18
|
+
}
|
19
|
+
\value{
|
20
|
+
Returns an \code{\link{enve.TRIBStest}} object.
|
21
|
+
}
|
22
|
+
\description{
|
23
|
+
Estimates the empirical difference between all the distances in a set of
|
24
|
+
objects and a subset, together with its statistical significance.
|
25
|
+
}
|
26
|
+
\author{
|
27
|
+
Luis M. Rodriguez-R [aut, cre]
|
28
|
+
}
|
@@ -0,0 +1,27 @@
|
|
1
|
+
% Generated by roxygen2: do not edit by hand
|
2
|
+
% Please edit documentation in R/utils.R
|
3
|
+
\name{enve.truncate}
|
4
|
+
\alias{enve.truncate}
|
5
|
+
\title{Enveomics: Truncate}
|
6
|
+
\usage{
|
7
|
+
enve.truncate(x, f = 0.95, FUN = mean)
|
8
|
+
}
|
9
|
+
\arguments{
|
10
|
+
\item{x}{A vector of numbers.}
|
11
|
+
|
12
|
+
\item{f}{The fraction of values to retain.}
|
13
|
+
|
14
|
+
\item{FUN}{Summary function to apply to the vectors. To obtain the
|
15
|
+
truncated vector itself, use \code{c}.}
|
16
|
+
}
|
17
|
+
\value{
|
18
|
+
Returns the summary \code{(FUN)} of the truncated vector.
|
19
|
+
}
|
20
|
+
\description{
|
21
|
+
Removes the \code{n} highest and lowest values from a vector, and applies
|
22
|
+
summary function. The value of \code{n} is determined such that the central
|
23
|
+
range is used, corresponding to the \code{f} fraction of values.
|
24
|
+
}
|
25
|
+
\author{
|
26
|
+
Luis M. Rodriguez-R [aut, cre]
|
27
|
+
}
|
@@ -0,0 +1,14 @@
|
|
1
|
+
|
2
|
+
\name{growth.curves}
|
3
|
+
\docType{data}
|
4
|
+
\alias{growth.curves}
|
5
|
+
\title{Bacterial growth curves for three Escherichia coli mutants}
|
6
|
+
\description{
|
7
|
+
This data set provides time (first column) and three triplicated growth
|
8
|
+
curves as optical density at 600nm (OD_600nm) for different mutants of E.
|
9
|
+
coli.
|
10
|
+
}
|
11
|
+
\usage{growth.curves}
|
12
|
+
\format{A data frame with 16 rows (times) and 10 rows (times and OD_600nm).}
|
13
|
+
\keyword{datasets}
|
14
|
+
|