miga-base 1.2.17.0 → 1.2.17.2
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 +2 -2
- 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 +165 -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 +356 -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/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 +138 -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 +67 -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/low-cov.bg.gz +0 -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 +167 -0
- data/utils/enveomics/enveomics.R/R/barplot.R +203 -0
- data/utils/enveomics/enveomics.R/R/cliopts.R +141 -0
- data/utils/enveomics/enveomics.R/R/df2dist.R +192 -0
- data/utils/enveomics/enveomics.R/R/growthcurve.R +349 -0
- data/utils/enveomics/enveomics.R/R/prefscore.R +79 -0
- data/utils/enveomics/enveomics.R/R/recplot.R +419 -0
- data/utils/enveomics/enveomics.R/R/recplot2.R +1698 -0
- data/utils/enveomics/enveomics.R/R/tribs.R +638 -0
- data/utils/enveomics/enveomics.R/R/utils.R +90 -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 +47 -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 +26 -0
- data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd +26 -0
- data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +44 -0
- data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +111 -0
- data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +67 -0
- data/utils/enveomics/enveomics.R/man/enve.col.alpha.Rd +34 -0
- data/utils/enveomics/enveomics.R/man/enve.col2alpha.Rd +25 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +59 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +63 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +46 -0
- data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +78 -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 +147 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd +45 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.ANIr.Rd +27 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +77 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd +28 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd +24 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd +22 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd +22 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.compareIdentities.Rd +52 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.coordinates.Rd +29 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd +21 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +45 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd +34 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_e.Rd +23 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_m.Rd +24 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__emauto_one.Rd +31 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mow_one.Rd +56 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mower.Rd +20 -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 +81 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +49 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +48 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +125 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd +22 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd +22 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd +22 -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 +268 -6
@@ -0,0 +1,790 @@
|
|
1
|
+
{
|
2
|
+
"tasks": [
|
3
|
+
{
|
4
|
+
"task": "BlastTab.addlen.rb",
|
5
|
+
"description": ["Appends an extra column to a tabular BLAST with the",
|
6
|
+
"length of the query or the subject sequence."],
|
7
|
+
"help_arg": "--help",
|
8
|
+
"options": [
|
9
|
+
{
|
10
|
+
"opt": "--fasta",
|
11
|
+
"arg": "in_file",
|
12
|
+
"description": "FastA file of the query or the subject.",
|
13
|
+
"mandatory": true
|
14
|
+
},
|
15
|
+
{
|
16
|
+
"opt": "--subject",
|
17
|
+
"description": ["Use the subject column of the BLAST, by default the",
|
18
|
+
"query column is used."],
|
19
|
+
"note": "If used, the input FastA must contain subject sequences."
|
20
|
+
},
|
21
|
+
{
|
22
|
+
"opt": "--quiet",
|
23
|
+
"description": "Run quietly (no STDERR output)."
|
24
|
+
},
|
25
|
+
"<",
|
26
|
+
{
|
27
|
+
"arg": "in_file",
|
28
|
+
"description": "Input tabular BLAST file.",
|
29
|
+
"mandatory": true
|
30
|
+
},
|
31
|
+
">",
|
32
|
+
{
|
33
|
+
"arg": "out_file",
|
34
|
+
"description": "Output tabular BLAST file with additional column.",
|
35
|
+
"mandatory": true
|
36
|
+
}
|
37
|
+
]
|
38
|
+
},
|
39
|
+
{
|
40
|
+
"task": "BlastTab.advance.bash",
|
41
|
+
"description": ["Calculates the percentage of a partial BLAST result.",
|
42
|
+
"The value produced slightly subestimates the actual advance, due to",
|
43
|
+
"un-flushed output and trailing queries that could be processed but",
|
44
|
+
"generate no results."],
|
45
|
+
"help_arg": "",
|
46
|
+
"requires": [ { "interpreter": "awk" } ],
|
47
|
+
"options": [
|
48
|
+
{
|
49
|
+
"name": "Blast",
|
50
|
+
"arg": "in_file",
|
51
|
+
"description": "Incomplete Tabular BLAST output.",
|
52
|
+
"mandatory": true
|
53
|
+
},
|
54
|
+
{
|
55
|
+
"name": "Query FastA",
|
56
|
+
"arg": "in_file",
|
57
|
+
"description": "FastA file with query sequences.",
|
58
|
+
"mandatory": true
|
59
|
+
}
|
60
|
+
]
|
61
|
+
},
|
62
|
+
{
|
63
|
+
"task": "BlastTab.best_hit_sorted.pl",
|
64
|
+
"description": "Filters a tabular BLAST to retain only the best matches.",
|
65
|
+
"help_arg": "--help",
|
66
|
+
"see_also": ["BlastTab.topHits_sorted.rb"],
|
67
|
+
"options": [
|
68
|
+
{
|
69
|
+
"name": "Sort",
|
70
|
+
"arg": "select",
|
71
|
+
"values": ["sort","cat"],
|
72
|
+
"mandatory": true,
|
73
|
+
"description": ["Use 'sort' if your BLAST is not pre-sorted by the",
|
74
|
+
"first column (or if you're not sure). Use 'cat' otherwise."]
|
75
|
+
},
|
76
|
+
{
|
77
|
+
"name": "Input BLAST",
|
78
|
+
"arg": "in_file",
|
79
|
+
"multiple_sep": " ",
|
80
|
+
"mandatory": true,
|
81
|
+
"description": "Tabular BLAST file to filter."
|
82
|
+
},
|
83
|
+
"|",
|
84
|
+
{ "arg": "task" },
|
85
|
+
">",
|
86
|
+
{
|
87
|
+
"name": "Output BLAST",
|
88
|
+
"arg": "out_file",
|
89
|
+
"mandatory": true,
|
90
|
+
"description": "Filetered tabular BLAST output."
|
91
|
+
}
|
92
|
+
]
|
93
|
+
},
|
94
|
+
{
|
95
|
+
"task": "BlastTab.catsbj.pl",
|
96
|
+
"description": ["Generates a list of hits from a BLAST result",
|
97
|
+
"concatenating the subject sequences. This can be used, e.g., to",
|
98
|
+
"analyze BLAST results against draft genomes. This script creates two",
|
99
|
+
"files using <map.bls> as prefix with extensions .rec (for the",
|
100
|
+
"recruitment plot) and .lim (for the limits of the different sequences",
|
101
|
+
"in <seq.fa>)."],
|
102
|
+
"see_also": ["BlastTab.recplot2.R", "GFF.catsbj.pl"],
|
103
|
+
"help_arg": "-h",
|
104
|
+
"options": [
|
105
|
+
{
|
106
|
+
"opt": "-i",
|
107
|
+
"name": "Identity",
|
108
|
+
"description": "Minimum identity (in %) to report a result.",
|
109
|
+
"arg": "float",
|
110
|
+
"default": 70.0
|
111
|
+
},
|
112
|
+
{
|
113
|
+
"opt": "-l",
|
114
|
+
"name": "Length",
|
115
|
+
"description": "Minimum alignment length to report a result.",
|
116
|
+
"default": 60.0,
|
117
|
+
"arg": "float"
|
118
|
+
},
|
119
|
+
{
|
120
|
+
"opt": "-s",
|
121
|
+
"name": "Subset",
|
122
|
+
"description": ["The FastA provided is to be treated as a subset of",
|
123
|
+
"the subject. By default, it expects all the BLAST subjects to be",
|
124
|
+
"present in the FastA."]
|
125
|
+
},
|
126
|
+
{
|
127
|
+
"opt": "-q",
|
128
|
+
"name": "Quiet",
|
129
|
+
"description": "Run quietly."
|
130
|
+
},
|
131
|
+
{
|
132
|
+
"name": "seq.fa",
|
133
|
+
"description": "Subject sequences (ref) in FastA format.",
|
134
|
+
"mandatory": true,
|
135
|
+
"arg": "in_file"
|
136
|
+
},
|
137
|
+
{
|
138
|
+
"name": "map.bls",
|
139
|
+
"description": ["Mapping of the reads to the reference in Tabular",
|
140
|
+
"BLAST format."],
|
141
|
+
"mandatory": true,
|
142
|
+
"arg": "in_file"
|
143
|
+
}
|
144
|
+
]
|
145
|
+
},
|
146
|
+
{
|
147
|
+
"task": "BlastTab.cogCat.rb",
|
148
|
+
"description": ["Replaces the COG gene IDs in a BLAST for the COG",
|
149
|
+
"category."],
|
150
|
+
"help_arg": "--help",
|
151
|
+
"options": [
|
152
|
+
{
|
153
|
+
"opt": "--whog",
|
154
|
+
"arg": "in_file",
|
155
|
+
"mandatory": true,
|
156
|
+
"description": "COG's 'whog' file."
|
157
|
+
},
|
158
|
+
{
|
159
|
+
"opt": "--blast",
|
160
|
+
"arg": "in_file",
|
161
|
+
"mandatory": true,
|
162
|
+
"description": "Tabular BLAST file with COG IDs as subject."
|
163
|
+
},
|
164
|
+
{
|
165
|
+
"opt": "--cog",
|
166
|
+
"description": "If set, returns the COG ID, not the COG category."
|
167
|
+
},
|
168
|
+
{
|
169
|
+
"opt": "--desc",
|
170
|
+
"description": "Includes COG description (requires --cog)."
|
171
|
+
},
|
172
|
+
{
|
173
|
+
"opt": "--noverbose",
|
174
|
+
"description": "Run quietly, but show warnings."
|
175
|
+
},
|
176
|
+
{
|
177
|
+
"opt": "--quiet",
|
178
|
+
"description": "Run quietly."
|
179
|
+
},
|
180
|
+
">",
|
181
|
+
{
|
182
|
+
"arg": "out_file",
|
183
|
+
"name": "COG Blast",
|
184
|
+
"mandatory": true,
|
185
|
+
"description": "Tabular BLAST with COG ID's or categories as subject."
|
186
|
+
}
|
187
|
+
]
|
188
|
+
},
|
189
|
+
{
|
190
|
+
"task": "BlastTab.filter.pl",
|
191
|
+
"description": ["Extracts a subset of hits (queries or subjects) from a",
|
192
|
+
"tabular BLAST."],
|
193
|
+
"help_arg": "",
|
194
|
+
"see_also": "BlastTab.subsample.pl",
|
195
|
+
"options": [
|
196
|
+
{
|
197
|
+
"name": "Subject",
|
198
|
+
"opt": "-s",
|
199
|
+
"description": ["If set, assumes that list.txt contains subject IDs.",
|
200
|
+
"By default: assumes query IDs."]
|
201
|
+
},
|
202
|
+
{
|
203
|
+
"name": "Inverse",
|
204
|
+
"opt": "-i",
|
205
|
+
"description": ["If set, reports the inverse of the list (i.e.,",
|
206
|
+
"reports only hits absent in the list)."]
|
207
|
+
},
|
208
|
+
{
|
209
|
+
"name": "list.txt",
|
210
|
+
"arg": "in_file",
|
211
|
+
"mandatory": true,
|
212
|
+
"description": "List of IDs to extract."
|
213
|
+
},
|
214
|
+
{
|
215
|
+
"name": "blast.txt",
|
216
|
+
"arg": "in_file",
|
217
|
+
"mandatory": true,
|
218
|
+
"description": "Tabular BLAST file containing the superset of hits."
|
219
|
+
},
|
220
|
+
">",
|
221
|
+
{
|
222
|
+
"name": "subset.txt",
|
223
|
+
"arg": "out_file",
|
224
|
+
"mandatory": true,
|
225
|
+
"description": "Tabulat BLAST file to be created."
|
226
|
+
}
|
227
|
+
]
|
228
|
+
},
|
229
|
+
{
|
230
|
+
"task": "BlastTab.pairedHits.rb",
|
231
|
+
"description": "Identifies the best hits of paired-reads.",
|
232
|
+
"help_arg": "--help",
|
233
|
+
"options": [
|
234
|
+
{
|
235
|
+
"opt": "--blast",
|
236
|
+
"arg": "in_file",
|
237
|
+
"mandatory": true,
|
238
|
+
"description": "Input Tabular BLAST file.",
|
239
|
+
"note": ["This script assumes that paired hits are next to each",
|
240
|
+
"other. If this is not the case (e.g., because the blast was",
|
241
|
+
"concatenated), you must sort the input before running this",
|
242
|
+
"script."]
|
243
|
+
},
|
244
|
+
{
|
245
|
+
"name": "Min score",
|
246
|
+
"opt": "--minscore",
|
247
|
+
"arg": "float",
|
248
|
+
"default": 0.0,
|
249
|
+
"description": "Minimum (summed) Bit-Score to consider a pair-match."
|
250
|
+
},
|
251
|
+
{
|
252
|
+
"name": "Best hits",
|
253
|
+
"opt": "--besthits",
|
254
|
+
"arg": "integer",
|
255
|
+
"default": 0,
|
256
|
+
"description": ["Outputs top best-hits only (use 0 to output all the",
|
257
|
+
"paired hits)."]
|
258
|
+
},
|
259
|
+
{
|
260
|
+
"name": "Orientation",
|
261
|
+
"opt": "--orient",
|
262
|
+
"arg": "select",
|
263
|
+
"values": [0,1,2,3,4],
|
264
|
+
"default": 0,
|
265
|
+
"description": ["Checks the orientation of the hit. Values are: 0,",
|
266
|
+
"no checking; 1, same direction; 2, inwards; 3, outwards; 4,",
|
267
|
+
"different direction (i.e., 2 or 3)."]
|
268
|
+
},
|
269
|
+
{
|
270
|
+
"name": "Sister prefix",
|
271
|
+
"opt": "--sisprefix",
|
272
|
+
"arg": "string",
|
273
|
+
"default": "_",
|
274
|
+
"description": ["Sister read number prefix in the name of the reads.",
|
275
|
+
"Escape characters as dots (\\.), parenthesis (\\(, \\), \\[,",
|
276
|
+
"\\]), other characters with special meaning in regular",
|
277
|
+
"expressions (\\*, \\+, \\^, \\$, \\|). This prefix allows regular",
|
278
|
+
"expressions (for example, use ':|\\.' to use any of colon or",
|
279
|
+
"dot). Note that the prefix will not be included in the base name",
|
280
|
+
"reported in the output."]
|
281
|
+
},
|
282
|
+
">",
|
283
|
+
{
|
284
|
+
"arg": "out_file",
|
285
|
+
"mandatory": true,
|
286
|
+
"description": ["Tab-delimited flat file, with the following",
|
287
|
+
"columns: (1) Query ID (without the \"sister\" identifier). (2)",
|
288
|
+
"Subject ID. (3) Bit score (summed from both sister reads). (4/5)",
|
289
|
+
"From/To (subject) coordinates for read 1. (6/7) From/To (subject)",
|
290
|
+
"coordinates for read 2. (8) Reads orientation (1: same direction,",
|
291
|
+
"2: inwards, 3: outwards). (9) Estimated insert size."]
|
292
|
+
}
|
293
|
+
]
|
294
|
+
},
|
295
|
+
{
|
296
|
+
"task": "BlastTab.seqdepth.pl",
|
297
|
+
"description": "Estimates the sequencing depth of subject sequences.",
|
298
|
+
"help_arg": "",
|
299
|
+
"see_also": ["BlastTab.seqdepth_ZIP.pl", "BlastTab.seqdepth_nomedian.pl",
|
300
|
+
"BedGraph.tad.rb"],
|
301
|
+
"options": [
|
302
|
+
"cat",
|
303
|
+
{
|
304
|
+
"arg": "in_file",
|
305
|
+
"multiple_sep": " ",
|
306
|
+
"mandatory": true,
|
307
|
+
"description": ["One or more Tabular BLAST files of reads vs genes",
|
308
|
+
"(or contigs)."]
|
309
|
+
},
|
310
|
+
"|",
|
311
|
+
{ "arg": "task" },
|
312
|
+
{
|
313
|
+
"name": "genes_or_ctgs.fna",
|
314
|
+
"arg": "in_file",
|
315
|
+
"mandatory": true,
|
316
|
+
"description": ["A FastA file containing the genes or the contigs",
|
317
|
+
"(db)."]
|
318
|
+
},
|
319
|
+
">",
|
320
|
+
{
|
321
|
+
"name": "genes_or_ctgs.cov",
|
322
|
+
"arg": "out_file",
|
323
|
+
"mandatory": true,
|
324
|
+
"description": ["A tab-delimited file with the following columns:",
|
325
|
+
"(1) Subject ID. (2) Average sequencing depth. (3) Median",
|
326
|
+
"sequencing depth. (4) Number of mapped reads. (5) Length of the",
|
327
|
+
"subject sequence."]
|
328
|
+
}
|
329
|
+
]
|
330
|
+
},
|
331
|
+
{
|
332
|
+
"task": "BlastTab.seqdepth_ZIP.pl",
|
333
|
+
"description": ["Estimates the average sequencing depth of subject",
|
334
|
+
"sequences (genes or contigs) assuming a Zero-Inflated Poisson",
|
335
|
+
"distribution (ZIP) to correct for non-covered positions. It uses the",
|
336
|
+
"corrected method of moments estimators (CMMEs) as described by",
|
337
|
+
"Beckett et al [1]. Note that [1] has a mistake in eq. (2.4), that",
|
338
|
+
"should be: pi-hat-MM = 1 - (X-bar / lambda-hat-MM). Also note that a",
|
339
|
+
"more elaborated mixture distribution can arise from coverage",
|
340
|
+
"histograms (e.g., see [2] for an additional correction called 'tail",
|
341
|
+
"distribution' and mixtures involving negative binomial) so take these",
|
342
|
+
"results cum grano salis.\n [1]",
|
343
|
+
"http://anisette.ucs.louisiana.edu/Academic/Sciences/MATH/stage/stat2012.pdf\n",
|
344
|
+
"[2] Lindner et al, Bioinformatics, 2013."],
|
345
|
+
"help_arg": "",
|
346
|
+
"see_also": ["BlastTab.seqdepth.pl", "BlastTab.seqdepth_nomedian.pl",
|
347
|
+
"BedGraph.tad.rb"],
|
348
|
+
"options": [
|
349
|
+
"cat",
|
350
|
+
{
|
351
|
+
"name": "blast",
|
352
|
+
"arg": "in_file",
|
353
|
+
"multiple_sep": " ",
|
354
|
+
"mandatory": true,
|
355
|
+
"description": ["One or more Tabular BLAST files of reads vs genes",
|
356
|
+
"(or contigs)."]
|
357
|
+
},
|
358
|
+
"|",
|
359
|
+
{ "arg": "task" },
|
360
|
+
{
|
361
|
+
"name": "genes_or_ctgs.fna",
|
362
|
+
"arg": "in_file",
|
363
|
+
"mandatory": true,
|
364
|
+
"description": ["A FastA file containing the genes or the contigs",
|
365
|
+
"(db)."]
|
366
|
+
},
|
367
|
+
">",
|
368
|
+
{
|
369
|
+
"name": "genes_or_ctgs.cov",
|
370
|
+
"arg": "out_file",
|
371
|
+
"mandatory": true,
|
372
|
+
"description": ["Output file with the following columns:",
|
373
|
+
"(1) Subject ID.",
|
374
|
+
"(2) Estimated average sequencing depth (CMME lambda).",
|
375
|
+
"(3) Zero-inflation (CMME pi).",
|
376
|
+
"(4) Observed average sequencing depth.",
|
377
|
+
"(5) Observed median sequencing depth.",
|
378
|
+
"(6) Observed median sequencing depth excluding zeroes.",
|
379
|
+
"(7) Number of mapped reads.",
|
380
|
+
"(8) Length of the subject sequence."]
|
381
|
+
}
|
382
|
+
]
|
383
|
+
},
|
384
|
+
{
|
385
|
+
"task": "BlastTab.seqdepth_nomedian.pl",
|
386
|
+
"description": ["Estimates the sequencing depth of subject",
|
387
|
+
"sequences. The values reported by this script may differ from those",
|
388
|
+
"of BlastTab.seqdepth.pl, because this script uses the aligned length",
|
389
|
+
"of the read while BlastTab.seqdepth.pl uses the aligned length of the",
|
390
|
+
"subject sequence."],
|
391
|
+
"help_arg": "",
|
392
|
+
"see_also": ["BlastTab.seqdepth.pl", "BlastTab.seqdepth_ZIP.pl"],
|
393
|
+
"options": [
|
394
|
+
"cat",
|
395
|
+
{
|
396
|
+
"arg": "in_file",
|
397
|
+
"multiple_sep": " ",
|
398
|
+
"mandatory": true,
|
399
|
+
"description": ["One or more Tabular BLAST files of reads vs genes",
|
400
|
+
"(or contigs)."]
|
401
|
+
},
|
402
|
+
"|",
|
403
|
+
{ "arg": "task" },
|
404
|
+
{
|
405
|
+
"name": "genes_or_ctgs.fna",
|
406
|
+
"arg": "in_file",
|
407
|
+
"mandatory": true,
|
408
|
+
"description": ["A FastA file containing the genes or the contigs",
|
409
|
+
"(db)."]
|
410
|
+
},
|
411
|
+
">",
|
412
|
+
{
|
413
|
+
"name": "genes_or_ctgs.cov",
|
414
|
+
"arg": "out_file",
|
415
|
+
"mandatory": true,
|
416
|
+
"description": ["A tab-delimited file with the following columns:",
|
417
|
+
"(1) Subject ID. (2) Average sequencing depth. (3) Number of",
|
418
|
+
"mapped reads. (4) Length of the subject sequence."]
|
419
|
+
}
|
420
|
+
]
|
421
|
+
},
|
422
|
+
{
|
423
|
+
"task": "BlastTab.subsample.pl",
|
424
|
+
"description": ["Filters a BLAST output including only the hits produced",
|
425
|
+
"by any of the given sequences as query."],
|
426
|
+
"help_arg": "",
|
427
|
+
"see_also": "BlastTab.filter.pl",
|
428
|
+
"options": [
|
429
|
+
{
|
430
|
+
"name": "blast.tab",
|
431
|
+
"mandatory": true,
|
432
|
+
"arg": "in_file",
|
433
|
+
"description": "BLAST output to be filtered (tabular format)."
|
434
|
+
},
|
435
|
+
{
|
436
|
+
"name": "sample.fa",
|
437
|
+
"mandatory": true,
|
438
|
+
"arg": "in_file",
|
439
|
+
"description": "Sequences to use as query (FastA format)."
|
440
|
+
},
|
441
|
+
">",
|
442
|
+
{
|
443
|
+
"arg": "out_file",
|
444
|
+
"mandatory": true,
|
445
|
+
"description": "The filtered BLAST output (tabular format)."
|
446
|
+
}
|
447
|
+
]
|
448
|
+
},
|
449
|
+
{
|
450
|
+
"task": "BlastTab.sumPerHit.pl",
|
451
|
+
"description": ["Sums the weights of all the queries hitting each",
|
452
|
+
"subject. Often (but not necessarily) the BLAST files contain only",
|
453
|
+
"best matches. The weights can be any number, but a common use of this",
|
454
|
+
"Script is to add up counts (weights are integers). For example, in a",
|
455
|
+
"BLAST of predicted genes vs some annotation source, the weights could",
|
456
|
+
"be the number of reads recruited by each gene."],
|
457
|
+
"help_arg": "-h",
|
458
|
+
"options": [
|
459
|
+
{
|
460
|
+
"name": "Weights file",
|
461
|
+
"opt": "-w",
|
462
|
+
"arg": "in_file",
|
463
|
+
"description": ["A two-columns tab-delimited file containing the",
|
464
|
+
"the name (column 1) and the weight (column 2) of each query."]
|
465
|
+
},
|
466
|
+
{
|
467
|
+
"name": "Minimum score",
|
468
|
+
"opt": "-s",
|
469
|
+
"arg": "float",
|
470
|
+
"default": 0.0
|
471
|
+
},
|
472
|
+
{
|
473
|
+
"name": "Minimum identity (%)",
|
474
|
+
"opt": "-i",
|
475
|
+
"arg": "float",
|
476
|
+
"default": 0.0
|
477
|
+
},
|
478
|
+
{
|
479
|
+
"name": "Queries",
|
480
|
+
"opt": "-m",
|
481
|
+
"arg": "integer",
|
482
|
+
"default": 0,
|
483
|
+
"description": "Maximum number of queries. Set to 0 for all."
|
484
|
+
},
|
485
|
+
{
|
486
|
+
"name": "Normalize",
|
487
|
+
"opt": "-n",
|
488
|
+
"description": "Normalize weights by the number of hits per query."
|
489
|
+
},
|
490
|
+
{
|
491
|
+
"name": "Include zeroes",
|
492
|
+
"opt": "-z",
|
493
|
+
"description": ["Add zero when weight is not found (by default:",
|
494
|
+
"doesn't list them)."]
|
495
|
+
},
|
496
|
+
{
|
497
|
+
"name": "Run quietly",
|
498
|
+
"opt": "-q"
|
499
|
+
},
|
500
|
+
{
|
501
|
+
"name": "blast",
|
502
|
+
"arg": "in_file",
|
503
|
+
"multiple_sep": " ",
|
504
|
+
"mandatory": true,
|
505
|
+
"description": "One or more BLAST files."
|
506
|
+
},
|
507
|
+
">",
|
508
|
+
{
|
509
|
+
"arg": "out_file",
|
510
|
+
"mandatory": true,
|
511
|
+
"description": ["A two-columns tab-delimited file containing the",
|
512
|
+
"summed weights per hit."]
|
513
|
+
}
|
514
|
+
]
|
515
|
+
},
|
516
|
+
{
|
517
|
+
"task": "BlastTab.taxid2taxrank.pl",
|
518
|
+
"description": ["Takes a BLAST with NCBI Taxonomy IDs as subjects and",
|
519
|
+
"replaces them by names at a given taxonomic rank."],
|
520
|
+
"help_arg": "",
|
521
|
+
"options": [
|
522
|
+
{
|
523
|
+
"name": "tax_blast.txt",
|
524
|
+
"mandatory": true,
|
525
|
+
"arg": "in_file",
|
526
|
+
"description": ["BLAST output, where subject IDs are NCBI Taxonomy",
|
527
|
+
"IDs."]
|
528
|
+
},
|
529
|
+
{
|
530
|
+
"name": "nodes.dmp",
|
531
|
+
"mandatory": true,
|
532
|
+
"arg": "in_file",
|
533
|
+
"description": "Nodes file from NCBI Taxonomy.",
|
534
|
+
"source_url": "ftp://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz"
|
535
|
+
},
|
536
|
+
{
|
537
|
+
"name": "names.dmp",
|
538
|
+
"mandatory": true,
|
539
|
+
"arg": "in_file",
|
540
|
+
"description": "Names file from NCBI Taxonomy.",
|
541
|
+
"source_url": "ftp://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz"
|
542
|
+
},
|
543
|
+
{
|
544
|
+
"name": "rank",
|
545
|
+
"arg": "string",
|
546
|
+
"mandatory": true,
|
547
|
+
"default": "genus",
|
548
|
+
"description": ["The rank to be reported. All the reported nodes",
|
549
|
+
"will have the same rank. To see supported values, run:\n",
|
550
|
+
"`cut -f 5 nodes.dmp | sort -u`."]
|
551
|
+
},
|
552
|
+
{
|
553
|
+
"name": "Best-hit",
|
554
|
+
"arg": "select",
|
555
|
+
"values": ["yes", "no"],
|
556
|
+
"default": "yes",
|
557
|
+
"description": ["Should it take into account the best hit per query",
|
558
|
+
"only? This is: should it filter by best-hit?"]
|
559
|
+
},
|
560
|
+
">",
|
561
|
+
{
|
562
|
+
"name": "taxrank_list.txt",
|
563
|
+
"arg": "out_file",
|
564
|
+
"mandatory": true,
|
565
|
+
"description": ["BLAST-like output, where subject IDs are Taxonomy",
|
566
|
+
"names."]
|
567
|
+
}
|
568
|
+
]
|
569
|
+
},
|
570
|
+
{
|
571
|
+
"task": "BlastTab.topHits_sorted.rb",
|
572
|
+
"description": "Reports the top-N best hits of a BLAST.",
|
573
|
+
"help_arg": "--help",
|
574
|
+
"see_also": "BlastTab.best_hit_sorted.pl",
|
575
|
+
"options": [
|
576
|
+
{
|
577
|
+
"name": "Sort",
|
578
|
+
"arg": "select",
|
579
|
+
"values": ["sort","cat"],
|
580
|
+
"mandatory": true,
|
581
|
+
"description": ["Use 'sort' if your BLAST is not pre-sorted by the",
|
582
|
+
"first column (or if you're not sure). Use 'cat' otherwise."]
|
583
|
+
},
|
584
|
+
{
|
585
|
+
"arg": "in_file",
|
586
|
+
"mandatory": true,
|
587
|
+
"description": "Tabular BLAST file."
|
588
|
+
},
|
589
|
+
"|",
|
590
|
+
{ "arg": "task" },
|
591
|
+
"--blast",
|
592
|
+
"-",
|
593
|
+
{
|
594
|
+
"name": "Output",
|
595
|
+
"opt": "--out",
|
596
|
+
"arg": "out_file",
|
597
|
+
"mandatory": true,
|
598
|
+
"description": [
|
599
|
+
"Output filtered BLAST file.",
|
600
|
+
"Supports compression with .gz extension."
|
601
|
+
]
|
602
|
+
},
|
603
|
+
{
|
604
|
+
"opt": "--top",
|
605
|
+
"arg": "integer",
|
606
|
+
"default": 5,
|
607
|
+
"description": "Maximum number of hits to report for each query."
|
608
|
+
},
|
609
|
+
{
|
610
|
+
"opt": "--sort-by",
|
611
|
+
"arg": "select",
|
612
|
+
"values": ["bitscore", "evalue", "identity", "length", "no"],
|
613
|
+
"default": "bitscore",
|
614
|
+
"description": "Parameter used to detect the 'best' hits."
|
615
|
+
},
|
616
|
+
{
|
617
|
+
"opt": "--quiet",
|
618
|
+
"description": "Run quietly."
|
619
|
+
}
|
620
|
+
]
|
621
|
+
},
|
622
|
+
{
|
623
|
+
"task": "BlastTab.recplot2.R",
|
624
|
+
"description": ["Produce recruitment plot objects provided that",
|
625
|
+
"BlastTab.catsbj.pl has been previously executed."],
|
626
|
+
"help_arg": "--help",
|
627
|
+
"requires": [
|
628
|
+
{ "r_package": "optparse" },
|
629
|
+
{ "r_package": "enveomics.R" }
|
630
|
+
],
|
631
|
+
"see_also": ["BlastTab.catsbj.pl", "GFF.catsbj.pl",
|
632
|
+
"RecPlot2.compareIdentities.R"],
|
633
|
+
"options": [
|
634
|
+
{
|
635
|
+
"opt": "--prefix",
|
636
|
+
"arg": "in_file",
|
637
|
+
"mandatory": true,
|
638
|
+
"description": ["Path to the prefix of the BlastTab.catsbj.pl output",
|
639
|
+
"files. At least the files .rec and .lim must exist with this",
|
640
|
+
"prefix."]
|
641
|
+
},
|
642
|
+
{
|
643
|
+
"opt": "--pos-breaks",
|
644
|
+
"arg": "integer",
|
645
|
+
"default": 1000,
|
646
|
+
"description": "Breaks in the positions histogram."
|
647
|
+
},
|
648
|
+
{
|
649
|
+
"opt": "--pos-breaks-tsv",
|
650
|
+
"arg": "in_file",
|
651
|
+
"description": ["File with (absolute) coordinates of breaks in the",
|
652
|
+
"position histogram."]
|
653
|
+
},
|
654
|
+
{
|
655
|
+
"opt": "--id-breaks",
|
656
|
+
"arg": "integer",
|
657
|
+
"default": 300,
|
658
|
+
"description": ["Breaks in the identity histogram."]
|
659
|
+
},
|
660
|
+
{
|
661
|
+
"opt": "--id-free-range",
|
662
|
+
"description": ["Indicates that the range should be freely set from",
|
663
|
+
"the observed values. Otherwise, 70-100% is included in the",
|
664
|
+
"identity histogram (default)."]
|
665
|
+
},
|
666
|
+
{
|
667
|
+
"opt": "--id-metric",
|
668
|
+
"arg": "select",
|
669
|
+
"values": ["identity", "corrected identity", "bit score"],
|
670
|
+
"default": "identity",
|
671
|
+
"description": ["Metric of identity to be used (Y-axis). Corrected",
|
672
|
+
"identity is only supported if the original BLAST file included",
|
673
|
+
"sequence lengths."]
|
674
|
+
},
|
675
|
+
{
|
676
|
+
"opt": "--id-summary",
|
677
|
+
"arg": "string",
|
678
|
+
"default": "sum",
|
679
|
+
"description": "Function summarizing the identity bins."
|
680
|
+
},
|
681
|
+
{
|
682
|
+
"opt": "--id-cutoff",
|
683
|
+
"arg": "float",
|
684
|
+
"default": 95.0,
|
685
|
+
"description": ["Cutoff of identity metric above which the hits are",
|
686
|
+
"considered 'in-group'. The 95% identity corresponds to the",
|
687
|
+
"expectation of ANI<95% within species."]
|
688
|
+
},
|
689
|
+
{
|
690
|
+
"opt": "--threads",
|
691
|
+
"arg": "integer",
|
692
|
+
"default": 2,
|
693
|
+
"description": "Number of threads to use."
|
694
|
+
},
|
695
|
+
{
|
696
|
+
"opt": "--no-verbose",
|
697
|
+
"description": "Indicates if the function should report the advance."
|
698
|
+
},
|
699
|
+
{
|
700
|
+
"opt": "--peaks-col",
|
701
|
+
"arg": "string",
|
702
|
+
"default": "NA",
|
703
|
+
"description": ["Color of peaks, mandatory for peak-finding (e.g.,",
|
704
|
+
"darkred)."]
|
705
|
+
},
|
706
|
+
{
|
707
|
+
"opt": "--peaks-method",
|
708
|
+
"arg": "select",
|
709
|
+
"values": ["emauto","em","mower"],
|
710
|
+
"default": "emauto",
|
711
|
+
"description": "Method to detect peaks."
|
712
|
+
},
|
713
|
+
{
|
714
|
+
"name": "R Object Output",
|
715
|
+
"arg": "out_file",
|
716
|
+
"mandatory": true,
|
717
|
+
"description": ["Recplo2 object that can be re-plotted using",
|
718
|
+
"R function plot."]
|
719
|
+
},
|
720
|
+
{
|
721
|
+
"name": "Graphical Output",
|
722
|
+
"arg": "out_file",
|
723
|
+
"description": "Recruitment plot in PDF."
|
724
|
+
},
|
725
|
+
{
|
726
|
+
"name": "Width",
|
727
|
+
"arg": "float",
|
728
|
+
"description": "Width of the plot in inches (7 by default)."
|
729
|
+
},
|
730
|
+
{
|
731
|
+
"name": "Height",
|
732
|
+
"arg": "float",
|
733
|
+
"description": "Height of the plot in inches (7 by default)."
|
734
|
+
}
|
735
|
+
]
|
736
|
+
},
|
737
|
+
{
|
738
|
+
"task": "RecPlot2.compareIdentities.R",
|
739
|
+
"description": ["Calculates the difference between identity",
|
740
|
+
"distributions of two recruitment plots."],
|
741
|
+
"help_arg": "--help",
|
742
|
+
"requires": [
|
743
|
+
{ "r_package": "optparse" },
|
744
|
+
{ "r_package": "enveomics.R" }
|
745
|
+
],
|
746
|
+
"see_also": [ "BlastTab.recplot2.R" ],
|
747
|
+
"options": [
|
748
|
+
{
|
749
|
+
"opt": "--method",
|
750
|
+
"arg": "string",
|
751
|
+
"default": "hellinger",
|
752
|
+
"description": ["Distance method to use. This should be (an",
|
753
|
+
"unambiguous abbreviation of) one of:",
|
754
|
+
"'hellinger' (Hellinger, 1090, doi:10.1515/crll.1909.136.210),",
|
755
|
+
"'bhattacharyya' (Bhattacharyya, 1943, Bull. Calcutta Math. Soc.",
|
756
|
+
"35), 'kl' or 'kullback–leibler' (Kullback & Leibler, 1951,",
|
757
|
+
"doi:10.1214/aoms/1177729694), or 'euclidean'."]
|
758
|
+
},
|
759
|
+
{
|
760
|
+
"opt": "--pseudocounts",
|
761
|
+
"arg": "float",
|
762
|
+
"default": 0.0,
|
763
|
+
"description": ["Smoothing parameter for Laplace smoothing. Use 0",
|
764
|
+
"for no smoothing, or 1 for add-one smoothing."]
|
765
|
+
},
|
766
|
+
{
|
767
|
+
"opt": "--max-deviation",
|
768
|
+
"arg": "float",
|
769
|
+
"description": ["Maximum mean deviation between identity breaks",
|
770
|
+
"tolerated (as percent identity). Difference in number of",
|
771
|
+
"id.breaks is never tolerated."]
|
772
|
+
},
|
773
|
+
{
|
774
|
+
"arg": "in_file",
|
775
|
+
"name": "RecPlot A",
|
776
|
+
"mandatory": true,
|
777
|
+
"description": ["File containing the R object `rp` for the first",
|
778
|
+
"recruitment plot."]
|
779
|
+
},
|
780
|
+
{
|
781
|
+
"arg": "in_file",
|
782
|
+
"name": "RecPlot B",
|
783
|
+
"mandatory": true,
|
784
|
+
"description": ["File containing the R object `rp` for the second",
|
785
|
+
"recruitment plot."]
|
786
|
+
}
|
787
|
+
]
|
788
|
+
}
|
789
|
+
]
|
790
|
+
}
|