miga-base 0.7.26.0 → 1.0.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/miga/_data/aai-intax.blast.tsv.gz +0 -0
- data/lib/miga/_data/aai-intax.diamond.tsv.gz +0 -0
- data/lib/miga/_data/aai-novel.blast.tsv.gz +0 -0
- data/lib/miga/_data/aai-novel.diamond.tsv.gz +0 -0
- data/lib/miga/cli/action/classify_wf.rb +2 -2
- data/lib/miga/cli/action/derep_wf.rb +1 -1
- data/lib/miga/cli/action/doctor.rb +57 -14
- data/lib/miga/cli/action/doctor/base.rb +47 -23
- data/lib/miga/cli/action/init.rb +11 -7
- data/lib/miga/cli/action/init/files_helper.rb +1 -0
- data/lib/miga/cli/action/ncbi_get.rb +3 -3
- data/lib/miga/cli/action/tax_dist.rb +2 -2
- data/lib/miga/cli/action/wf.rb +5 -4
- data/lib/miga/common.rb +1 -0
- data/lib/miga/daemon.rb +11 -4
- data/lib/miga/dataset/result.rb +10 -6
- data/lib/miga/json.rb +5 -4
- data/lib/miga/metadata.rb +5 -1
- data/lib/miga/parallel.rb +36 -0
- data/lib/miga/project.rb +8 -8
- data/lib/miga/project/base.rb +4 -4
- data/lib/miga/project/result.rb +2 -2
- data/lib/miga/sqlite.rb +10 -2
- data/lib/miga/version.rb +23 -9
- data/scripts/aai_distances.bash +16 -18
- data/scripts/ani_distances.bash +16 -17
- data/scripts/assembly.bash +31 -16
- data/scripts/haai_distances.bash +3 -27
- data/scripts/miga.bash +6 -4
- data/scripts/p.bash +1 -1
- data/scripts/read_quality.bash +9 -18
- data/scripts/trimmed_fasta.bash +14 -30
- data/scripts/trimmed_reads.bash +36 -36
- data/test/parallel_test.rb +31 -0
- data/test/project_test.rb +2 -1
- data/test/remote_dataset_test.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/FastAAI +1336 -0
- data/utils/FastAAI/README.md +84 -0
- data/utils/FastAAI/kAAI_v1.0_virus.py +1296 -0
- data/utils/distance/commands.rb +1 -0
- data/utils/distance/database.rb +0 -1
- data/utils/distance/runner.rb +2 -4
- 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 +786 -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 +638 -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 +154 -0
- data/utils/enveomics/Manifest/tasks.json +4 -0
- data/utils/enveomics/Pipelines/assembly.pbs/CONFIG.mock.bash +69 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl +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 +101 -0
- data/utils/enveomics/Scripts/Chao1.pl +97 -0
- data/utils/enveomics/Scripts/CharTable.classify.rb +234 -0
- data/utils/enveomics/Scripts/EBIseq2tax.rb +83 -0
- data/utils/enveomics/Scripts/FastA.N50.pl +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 +419 -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 +63 -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.rb +3 -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/utils.rb +73 -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 +100 -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
- data/utils/requirements.txt +4 -3
- metadata +304 -3
@@ -0,0 +1,161 @@
|
|
1
|
+
{
|
2
|
+
"tasks": [
|
3
|
+
{
|
4
|
+
"task": "TRIBS.test.R",
|
5
|
+
"description": ["Estimates the empirical difference between all the",
|
6
|
+
"distances in a set of objects and a subset, together with its",
|
7
|
+
"statistical significance."],
|
8
|
+
"help_arg": "--help",
|
9
|
+
"requires": [
|
10
|
+
{ "r_package": "optparse" },
|
11
|
+
{ "r_package": "enveomics.R" }
|
12
|
+
],
|
13
|
+
"see_also": ["TRIBS.plot-test.R"],
|
14
|
+
"options": [
|
15
|
+
{
|
16
|
+
"opt": "--dist",
|
17
|
+
"arg": "in_file",
|
18
|
+
"mandatory": true,
|
19
|
+
"description": "A tab-delimited matrix of distances."
|
20
|
+
},
|
21
|
+
{
|
22
|
+
"opt": "--selection",
|
23
|
+
"arg": "in_file",
|
24
|
+
"mandatory": true,
|
25
|
+
"description": "A list of names with the selection to evaluate."
|
26
|
+
},
|
27
|
+
{
|
28
|
+
"opt": "--replicates",
|
29
|
+
"arg": "integer",
|
30
|
+
"default": 1000,
|
31
|
+
"description": "Number of replications per point."
|
32
|
+
},
|
33
|
+
{
|
34
|
+
"opt": "--summary-fx",
|
35
|
+
"arg": "string",
|
36
|
+
"description": ["Function to summarize the distance distributions in",
|
37
|
+
"a given replicate. By default, the median distance is estimated."]
|
38
|
+
},
|
39
|
+
{
|
40
|
+
"opt": "--dist-method",
|
41
|
+
"arg": "string",
|
42
|
+
"default": "euclidean",
|
43
|
+
"description": ["Distance method between random points and samples",
|
44
|
+
"in the transformed space. See the R function 'dist'."]
|
45
|
+
},
|
46
|
+
{
|
47
|
+
"opt": "--dimensions",
|
48
|
+
"arg": "integer",
|
49
|
+
"description": ["Dimensions to use in the NMDS. By default, 5% of",
|
50
|
+
"the selection length."]
|
51
|
+
},
|
52
|
+
{
|
53
|
+
"opt": "--threads",
|
54
|
+
"arg": "integer",
|
55
|
+
"default": 2,
|
56
|
+
"description": "Number of threads to use."
|
57
|
+
},
|
58
|
+
{
|
59
|
+
"opt": "--verbosity",
|
60
|
+
"arg": "integer",
|
61
|
+
"default": 1,
|
62
|
+
"description": ["Verbosity. Use 0 to run quietly, increase for",
|
63
|
+
"additional information."]
|
64
|
+
},
|
65
|
+
{
|
66
|
+
"arg": "out_file",
|
67
|
+
"mandatory": true,
|
68
|
+
"description": "Output file with the TRIBS test R object."
|
69
|
+
},
|
70
|
+
{
|
71
|
+
"name": "Bins",
|
72
|
+
"arg": "integer",
|
73
|
+
"default": 50,
|
74
|
+
"description": "Number of bins to evaluate in the range of distances."
|
75
|
+
}
|
76
|
+
]
|
77
|
+
},
|
78
|
+
{
|
79
|
+
"task": "TRIBS.plot-test.R",
|
80
|
+
"description": "Plots an `enve.TRIBStest` object.",
|
81
|
+
"requires": [
|
82
|
+
{ "r_package": "optparse" },
|
83
|
+
{ "r_package": "enveomics.R" }
|
84
|
+
],
|
85
|
+
"see_also": ["TRIBS.test.R"],
|
86
|
+
"help_arg": "--help",
|
87
|
+
"options": [
|
88
|
+
{
|
89
|
+
"name": "Input TRIBS Test",
|
90
|
+
"opt": "--x",
|
91
|
+
"arg": "in_file",
|
92
|
+
"mandatory": true,
|
93
|
+
"description": "'enve.TRIBStest' object to plot."
|
94
|
+
},
|
95
|
+
{
|
96
|
+
"opt": "--type",
|
97
|
+
"arg": "select",
|
98
|
+
"values": ["overlap","difference"],
|
99
|
+
"default": "overlap",
|
100
|
+
"description": ["What to plot. 'overlap' generates a plot of the two",
|
101
|
+
"contrasting empirical PDFs (to compare against each other),",
|
102
|
+
"'difference' produces a plot of the differences between the",
|
103
|
+
"empirical PDFs (to compare against zero)."]
|
104
|
+
},
|
105
|
+
{
|
106
|
+
"opt": "--col",
|
107
|
+
"arg": "string",
|
108
|
+
"default": "#00000044",
|
109
|
+
"description": "Main color of the plot if type='difference'."
|
110
|
+
},
|
111
|
+
{
|
112
|
+
"opt": "--col1",
|
113
|
+
"arg": "string",
|
114
|
+
"description": ["First color of the plot if 'Type' is overlap. 'Col'",
|
115
|
+
"by default."]
|
116
|
+
},
|
117
|
+
{
|
118
|
+
"opt": "--col2",
|
119
|
+
"arg": "string",
|
120
|
+
"default": "#44001144",
|
121
|
+
"description": "Second color of the plot if 'Type' is overlap."
|
122
|
+
},
|
123
|
+
{
|
124
|
+
"opt": "--ylab",
|
125
|
+
"arg": "string",
|
126
|
+
"default": "Probability",
|
127
|
+
"description": "Y-axis label."
|
128
|
+
},
|
129
|
+
{
|
130
|
+
"opt": "--xlim",
|
131
|
+
"arg": "string",
|
132
|
+
"description": "X-axis limits, separate values by comma."
|
133
|
+
},
|
134
|
+
{
|
135
|
+
"opt": "--ylim",
|
136
|
+
"arg": "string",
|
137
|
+
"description": "Y-axis limits, separate values by comma."
|
138
|
+
},
|
139
|
+
{
|
140
|
+
"arg": "out_file",
|
141
|
+
"mandatory": true,
|
142
|
+
"description": "Output file in PDF format."
|
143
|
+
},
|
144
|
+
{
|
145
|
+
"name": "Width",
|
146
|
+
"arg": "float",
|
147
|
+
"default": 7.0,
|
148
|
+
"mandatory": true,
|
149
|
+
"description": "Width of the plot in inches."
|
150
|
+
},
|
151
|
+
{
|
152
|
+
"name": "Height",
|
153
|
+
"arg": "float",
|
154
|
+
"default": 7.0,
|
155
|
+
"mandatory": true,
|
156
|
+
"description": "Height of the plot in inches."
|
157
|
+
}
|
158
|
+
]
|
159
|
+
}
|
160
|
+
]
|
161
|
+
}
|
@@ -0,0 +1,802 @@
|
|
1
|
+
{
|
2
|
+
"tasks": [
|
3
|
+
{
|
4
|
+
"task": "FastA.N50.pl",
|
5
|
+
"description": ["Calculates the N50 value of a set of sequences.",
|
6
|
+
"Alternatively, it can calculate other N** values. It also calculates",
|
7
|
+
"the total number of sequences, the total added length, and the",
|
8
|
+
"longest sequence length."],
|
9
|
+
"help_arg": "",
|
10
|
+
"see_also": ["FastA.length.pl"],
|
11
|
+
"options": [
|
12
|
+
{
|
13
|
+
"name": "Sequences",
|
14
|
+
"arg": "in_file",
|
15
|
+
"mandatory": true,
|
16
|
+
"description": "A FastA file containing the sequences."
|
17
|
+
},
|
18
|
+
{
|
19
|
+
"name": "Minimum length",
|
20
|
+
"arg": "integer",
|
21
|
+
"description": "Minimum length to take into consideration.",
|
22
|
+
"default": 0
|
23
|
+
},
|
24
|
+
{
|
25
|
+
"name": "NXX",
|
26
|
+
"arg": "integer",
|
27
|
+
"description": "Value NXX to calculate.",
|
28
|
+
"default": 50
|
29
|
+
}
|
30
|
+
]
|
31
|
+
},
|
32
|
+
{
|
33
|
+
"task": "FastA.filter.pl",
|
34
|
+
"description": "Extracts a subset of sequences from a FastA file.",
|
35
|
+
"help_arg": "-h",
|
36
|
+
"see_also": ["FastQ.filter.pl"],
|
37
|
+
"options": [
|
38
|
+
{
|
39
|
+
"opt": "-r",
|
40
|
+
"description": ["Reverse list. Extracts sequences NOT present in the",
|
41
|
+
"list."]
|
42
|
+
},
|
43
|
+
{
|
44
|
+
"opt": "-q",
|
45
|
+
"description": "Runs quietly."
|
46
|
+
},
|
47
|
+
{
|
48
|
+
"name": "List",
|
49
|
+
"arg": "in_file",
|
50
|
+
"mandatory": true,
|
51
|
+
"description": "List of sequences to extract."
|
52
|
+
},
|
53
|
+
{
|
54
|
+
"name": "Sequences",
|
55
|
+
"arg": "in_file",
|
56
|
+
"mandatory": true,
|
57
|
+
"description": "FastA file containing the superset of sequences."
|
58
|
+
},
|
59
|
+
">",
|
60
|
+
{
|
61
|
+
"name": "Subset",
|
62
|
+
"arg": "out_file",
|
63
|
+
"mandatory": true,
|
64
|
+
"description": "FastA file to be created."
|
65
|
+
}
|
66
|
+
]
|
67
|
+
},
|
68
|
+
{
|
69
|
+
"task": "FastA.filterLen.pl",
|
70
|
+
"description": "Filters a multi-FastA file by length.",
|
71
|
+
"requires": [ { "perl_lib": "Bio::SeqIO" } ],
|
72
|
+
"cite": [["Stajich et al, 2002, GRes",
|
73
|
+
"http://dx.doi.org/10.1101/gr.361602"]],
|
74
|
+
"help_arg": "",
|
75
|
+
"options": [
|
76
|
+
{
|
77
|
+
"arg": "in_file",
|
78
|
+
"mandatory": true,
|
79
|
+
"description": "Input FastA file."
|
80
|
+
},
|
81
|
+
{
|
82
|
+
"name": "Minimum length",
|
83
|
+
"arg": "integer",
|
84
|
+
"mandatory": true,
|
85
|
+
"description": "Minimum length to report a sequence."
|
86
|
+
},
|
87
|
+
">",
|
88
|
+
{
|
89
|
+
"arg": "out_file",
|
90
|
+
"mandatory": true,
|
91
|
+
"description": "Filtered FastA file."
|
92
|
+
}
|
93
|
+
]
|
94
|
+
},
|
95
|
+
{
|
96
|
+
"task": "FastA.filterN.pl",
|
97
|
+
"description": ["Filter sequences by N-content and presence of long",
|
98
|
+
"homopolymers."],
|
99
|
+
"help_arg": "",
|
100
|
+
"options": [
|
101
|
+
{
|
102
|
+
"name": "Sequences",
|
103
|
+
"arg": "in_file",
|
104
|
+
"mandatory": true,
|
105
|
+
"description": "Input file in FastA format."
|
106
|
+
},
|
107
|
+
{
|
108
|
+
"name": "Content",
|
109
|
+
"arg": "float",
|
110
|
+
"default": 0.5,
|
111
|
+
"mandatory": true,
|
112
|
+
"description": ["A number between 0 and 1 indicating the maximum",
|
113
|
+
"proportion of Ns (1 to turn off, 0.5 by default)."]
|
114
|
+
},
|
115
|
+
{
|
116
|
+
"name": "Stretch",
|
117
|
+
"arg": "integer",
|
118
|
+
"default": 100,
|
119
|
+
"description": ["A number indicating the maximum number of",
|
120
|
+
"consecutive identical nucleotides allowed (0 to turn off, 100 by",
|
121
|
+
"default)."]
|
122
|
+
},
|
123
|
+
">",
|
124
|
+
{
|
125
|
+
"name": "Filtered",
|
126
|
+
"arg": "out_file",
|
127
|
+
"mandatory": true,
|
128
|
+
"description": "Filtered set of sequences."
|
129
|
+
}
|
130
|
+
]
|
131
|
+
},
|
132
|
+
{
|
133
|
+
"task": "FastA.gc.pl",
|
134
|
+
"description": "Estimates the G+C content of sequences.",
|
135
|
+
"help_arg": "",
|
136
|
+
"options": [
|
137
|
+
{
|
138
|
+
"name": "seqs.fa",
|
139
|
+
"arg": "in_file",
|
140
|
+
"multiple_sep": " ",
|
141
|
+
"mandatory": true,
|
142
|
+
"description": "One or more FastA files."
|
143
|
+
},
|
144
|
+
">",
|
145
|
+
{
|
146
|
+
"name": "gc.txt",
|
147
|
+
"arg": "out_file",
|
148
|
+
"mandatory": true,
|
149
|
+
"description": "A table with the G+C content of the sequences."
|
150
|
+
}
|
151
|
+
]
|
152
|
+
},
|
153
|
+
{
|
154
|
+
"task": "FastA.interpose.pl",
|
155
|
+
"description": ["Interpose sequences in FastA format from two files into",
|
156
|
+
"one output file. If more than two files are provided, the script will",
|
157
|
+
"interpose all the input files."],
|
158
|
+
"see_also": ["FastA.split.rb","FastQ.interpose.pl"],
|
159
|
+
"warn": ["Please note that this script will check for the consistency of",
|
160
|
+
"the names (assuming a pair of related reads contains the same name",
|
161
|
+
"varying only in a trailing slash (/) followed by a digit. If you want",
|
162
|
+
"to turn this feature off just set the checking period to zero. If",
|
163
|
+
"you want to decrease the sampling period (to speed the script up) or",
|
164
|
+
"increase it (to make it more sensitive to errors) just change the ",
|
165
|
+
"checking period accordingly."],
|
166
|
+
"help_arg": "",
|
167
|
+
"options": [
|
168
|
+
{
|
169
|
+
"name": "Checking period",
|
170
|
+
"opt": "-T",
|
171
|
+
"arg": "integer",
|
172
|
+
"default": 1000,
|
173
|
+
"description": "Sampling period for names evaluation."
|
174
|
+
},
|
175
|
+
{
|
176
|
+
"arg": "out_file",
|
177
|
+
"mandatory": true,
|
178
|
+
"description": "Output FastA file."
|
179
|
+
},
|
180
|
+
{
|
181
|
+
"name": "Input FastA 1",
|
182
|
+
"arg": "in_file",
|
183
|
+
"mandatory": true,
|
184
|
+
"description": "First FastA file."
|
185
|
+
},
|
186
|
+
{
|
187
|
+
"name": "Input FastA 2",
|
188
|
+
"arg": "in_file",
|
189
|
+
"mandatory": true,
|
190
|
+
"description": "Second FastA file."
|
191
|
+
},
|
192
|
+
{
|
193
|
+
"name": "Additional FastA",
|
194
|
+
"arg": "in_file",
|
195
|
+
"multiple_sep": " ",
|
196
|
+
"description": "Any additional FastA files (or none)."
|
197
|
+
}
|
198
|
+
]
|
199
|
+
},
|
200
|
+
{
|
201
|
+
"task": "FastA.length.pl",
|
202
|
+
"description": "Returns the length of sequences in (multi-)FastA.",
|
203
|
+
"see_also": ["FastA.N50.pl"],
|
204
|
+
"help_arg": "",
|
205
|
+
"options": [
|
206
|
+
{
|
207
|
+
"arg": "in_file",
|
208
|
+
"multiple_sep": " ",
|
209
|
+
"mandatory": true,
|
210
|
+
"description": "One or more FastA files."
|
211
|
+
},
|
212
|
+
">",
|
213
|
+
{
|
214
|
+
"arg": "out_file",
|
215
|
+
"mandatory": true,
|
216
|
+
"description": "A table with the lengths of the sequences."
|
217
|
+
}
|
218
|
+
]
|
219
|
+
},
|
220
|
+
{
|
221
|
+
"task": "FastA.mask.rb",
|
222
|
+
"description": "Mask sequence region(s) in a FastA file.",
|
223
|
+
"help_arg": "--help",
|
224
|
+
"options": [
|
225
|
+
{
|
226
|
+
"opt": "--in",
|
227
|
+
"arg": "in_file",
|
228
|
+
"mandatory": true,
|
229
|
+
"description": "Input FastA file."
|
230
|
+
},
|
231
|
+
{
|
232
|
+
"opt": "--out",
|
233
|
+
"arg": "out_file",
|
234
|
+
"mandatory": true,
|
235
|
+
"description": "Output FastA file."
|
236
|
+
},
|
237
|
+
{
|
238
|
+
"opt": "--regions",
|
239
|
+
"arg": "string",
|
240
|
+
"mandatory": true,
|
241
|
+
"description": ["Regions to mask separated by commas.",
|
242
|
+
"Each region must be in the format \"sequence_id:from..to\"."]
|
243
|
+
},
|
244
|
+
{
|
245
|
+
"opt": "--symbol",
|
246
|
+
"arg": "string",
|
247
|
+
"default": "N",
|
248
|
+
"description": "Character used to mask the region(s)."
|
249
|
+
},
|
250
|
+
{
|
251
|
+
"opt": "--trim",
|
252
|
+
"description": ["Trim masked regions extending to the edge of a",
|
253
|
+
"sequence."]
|
254
|
+
},
|
255
|
+
{
|
256
|
+
"opt": "--wrap",
|
257
|
+
"arg": "integer",
|
258
|
+
"default": 70,
|
259
|
+
"description": ["Line length to wrap sequences. Use 0 to generate",
|
260
|
+
"1-line sequences."]
|
261
|
+
}
|
262
|
+
]
|
263
|
+
},
|
264
|
+
{
|
265
|
+
"task": "FastA.qlen.pl",
|
266
|
+
"description": ["Calculates the quartiles of the length in a set of",
|
267
|
+
"sequences. The Q2 is also known as the median. Q0 is the minimum",
|
268
|
+
"length, and Q4 is the maximum length. It also calculates TOTAL, the",
|
269
|
+
"added length of the sequences in the file, and AVG, the average",
|
270
|
+
"length."],
|
271
|
+
"help_arg": "",
|
272
|
+
"options": [
|
273
|
+
{
|
274
|
+
"name": "Sequences",
|
275
|
+
"arg": "in_file",
|
276
|
+
"mandatory": true,
|
277
|
+
"description": "A FastA file containing the sequences."
|
278
|
+
},
|
279
|
+
{
|
280
|
+
"name": "Minimum Length",
|
281
|
+
"arg": "integer",
|
282
|
+
"default": 0,
|
283
|
+
"description": "The minimum length to take into consideration."
|
284
|
+
}
|
285
|
+
]
|
286
|
+
},
|
287
|
+
{
|
288
|
+
"task": "FastA.rename.pl",
|
289
|
+
"description": "Renames a set of sequences in FastA format.",
|
290
|
+
"help_arg": "-h",
|
291
|
+
"options": [
|
292
|
+
{
|
293
|
+
"name": "Filter list",
|
294
|
+
"opt": "-f",
|
295
|
+
"description": "Ignore sequences NOT present in the list."
|
296
|
+
},
|
297
|
+
{
|
298
|
+
"name": "Quiet",
|
299
|
+
"opt": "-q",
|
300
|
+
"description": "Runs quietly."
|
301
|
+
},
|
302
|
+
{
|
303
|
+
"name": "List.txt",
|
304
|
+
"arg": "in_file",
|
305
|
+
"mandatory": true,
|
306
|
+
"description": ["Tab-delimited list of sequences, with the original",
|
307
|
+
"ID in the first column and the ID to use in the second."]
|
308
|
+
},
|
309
|
+
{
|
310
|
+
"name": "Seqs.fa",
|
311
|
+
"arg": "in_file",
|
312
|
+
"mandatory": true,
|
313
|
+
"description": "FastA file containing the superset of sequences."
|
314
|
+
},
|
315
|
+
">",
|
316
|
+
{
|
317
|
+
"name": "Renamed.fa",
|
318
|
+
"arg": "out_file",
|
319
|
+
"mandatory": true,
|
320
|
+
"description": "FastA file to be created."
|
321
|
+
}
|
322
|
+
]
|
323
|
+
},
|
324
|
+
{
|
325
|
+
"task": "FastA.revcom.pl",
|
326
|
+
"description": "Reverse-complement sequences in FastA format.",
|
327
|
+
"requires": [ { "perl_lib": "Bio::SeqIO" } ],
|
328
|
+
"cite": [["Stajich et al, 2002, GRes",
|
329
|
+
"http://dx.doi.org/10.1101/gr.361602"]],
|
330
|
+
"help_arg": "--help",
|
331
|
+
"options": [
|
332
|
+
"<",
|
333
|
+
{
|
334
|
+
"arg": "in_file",
|
335
|
+
"mandatory": true,
|
336
|
+
"description": "Input file in FastA format."
|
337
|
+
},
|
338
|
+
">",
|
339
|
+
{
|
340
|
+
"arg": "out_file",
|
341
|
+
"mandatory": true,
|
342
|
+
"description": "Output file in FastA format."
|
343
|
+
}
|
344
|
+
]
|
345
|
+
},
|
346
|
+
{
|
347
|
+
"task": "FastA.sample.rb",
|
348
|
+
"description": ["Samples a random set of sequences from a multi-FastA",
|
349
|
+
"file."],
|
350
|
+
"help_arg": "--help",
|
351
|
+
"see_also": "FastA.subsample.pl",
|
352
|
+
"options": [
|
353
|
+
{
|
354
|
+
"name": "Input File",
|
355
|
+
"opt": "--in",
|
356
|
+
"arg": "in_file",
|
357
|
+
"mandatory": true,
|
358
|
+
"description": "Input FastA file (supports .gz compression)."
|
359
|
+
},
|
360
|
+
{
|
361
|
+
"name": "Output file",
|
362
|
+
"opt": "--out",
|
363
|
+
"arg": "out_file",
|
364
|
+
"mandatory": true,
|
365
|
+
"description": "Output FastA file (supports .gz compression)."
|
366
|
+
},
|
367
|
+
{
|
368
|
+
"opt": "--fraction",
|
369
|
+
"arg": "float",
|
370
|
+
"description": ["Fraction of sequences to sample [0-1].",
|
371
|
+
"Mandatory unless Number is provided."]
|
372
|
+
},
|
373
|
+
{
|
374
|
+
"opt": "--number",
|
375
|
+
"arg": "integer",
|
376
|
+
"description": ["Number of sequences to sample.",
|
377
|
+
"Mandatory unless -f is provided."]
|
378
|
+
},
|
379
|
+
{
|
380
|
+
"opt": "--replacement",
|
381
|
+
"description": "Sample with replacement."
|
382
|
+
},
|
383
|
+
{
|
384
|
+
"opt": "--quiet",
|
385
|
+
"description": "Run quietly (no STDERR output)."
|
386
|
+
}
|
387
|
+
]
|
388
|
+
},
|
389
|
+
{
|
390
|
+
"task": "FastA.slider.pl",
|
391
|
+
"description": "Slices sequences in fixed- or variable-length windows.",
|
392
|
+
"help_arg": "-help",
|
393
|
+
"options": [
|
394
|
+
{
|
395
|
+
"opt": "-seq",
|
396
|
+
"arg": "in_file",
|
397
|
+
"mandatory": true,
|
398
|
+
"description": "Input file in FastA format."
|
399
|
+
},
|
400
|
+
{
|
401
|
+
"opt": "-out",
|
402
|
+
"arg": "out_file",
|
403
|
+
"mandatory": true,
|
404
|
+
"description": "Output file in FastA format."
|
405
|
+
},
|
406
|
+
{
|
407
|
+
"opt": "-win",
|
408
|
+
"arg": "integer",
|
409
|
+
"default": 18,
|
410
|
+
"description": "Window size."
|
411
|
+
},
|
412
|
+
{
|
413
|
+
"opt": "-step",
|
414
|
+
"arg": "integer",
|
415
|
+
"default": 1,
|
416
|
+
"description": "Step size."
|
417
|
+
},
|
418
|
+
{
|
419
|
+
"name": "Length error",
|
420
|
+
"opt": "-lerr",
|
421
|
+
"arg": "integer",
|
422
|
+
"default": 2,
|
423
|
+
"description": "Expected error in chunks length."
|
424
|
+
},
|
425
|
+
{
|
426
|
+
"opt": "-comm",
|
427
|
+
"arg": "select",
|
428
|
+
"values": [0,1],
|
429
|
+
"default": 0,
|
430
|
+
"description": ["Generate FastA comments (leaded by semi-colon) to",
|
431
|
+
"separate input sequences. Set to 0 for no-comments, to 1 for",
|
432
|
+
"comments."]
|
433
|
+
},
|
434
|
+
{
|
435
|
+
"opt": "-short",
|
436
|
+
"arg": "select",
|
437
|
+
"values": [0,1],
|
438
|
+
"default": 0,
|
439
|
+
"description": ["Use chunks shorter than the window size 'as is'.",
|
440
|
+
"Set to 0 to discard those chunks, to 1 to use them."]
|
441
|
+
}
|
442
|
+
]
|
443
|
+
},
|
444
|
+
{
|
445
|
+
"task": "FastA.split.rb",
|
446
|
+
"description": ["Evenly splits a multi-FastA file into multiple",
|
447
|
+
"multi-FastA files."],
|
448
|
+
"see_also": ["FastA.interpose.pl","FastQ.split.pl"],
|
449
|
+
"help_arg": "--help",
|
450
|
+
"options": [
|
451
|
+
{
|
452
|
+
"opt": "--input",
|
453
|
+
"arg": "in_file",
|
454
|
+
"mandatory": true,
|
455
|
+
"description": "Input FastA file."
|
456
|
+
},
|
457
|
+
{
|
458
|
+
"opt": "--prefix",
|
459
|
+
"arg": "out_file",
|
460
|
+
"mandatory": true,
|
461
|
+
"description": "Prefix of output FastA files."
|
462
|
+
},
|
463
|
+
{
|
464
|
+
"opt": "--number",
|
465
|
+
"arg": "integer",
|
466
|
+
"default": 12,
|
467
|
+
"description": "Number of output files to produce."
|
468
|
+
},
|
469
|
+
{
|
470
|
+
"opt": "--zero-padded",
|
471
|
+
"description": "Use zero-padded numbers as output index."
|
472
|
+
},
|
473
|
+
{
|
474
|
+
"opt": "--lowercase-letters",
|
475
|
+
"description": "Use lowercase letters as output index."
|
476
|
+
},
|
477
|
+
{
|
478
|
+
"name": "Output format",
|
479
|
+
"opt": "--out",
|
480
|
+
"arg": "string",
|
481
|
+
"default": "%s.%s.fa",
|
482
|
+
"description": ["Format of output filenames, where %s are replaced",
|
483
|
+
"by prefix and index."]
|
484
|
+
},
|
485
|
+
{
|
486
|
+
"opt": "--quiet",
|
487
|
+
"description": "Run quietly (no STDERR output)."
|
488
|
+
}
|
489
|
+
]
|
490
|
+
},
|
491
|
+
{
|
492
|
+
"task": "FastA.split.pl",
|
493
|
+
"description": "Splits a FastA file into two or more files.",
|
494
|
+
"warn": "Deprecated in favor of FastA.split.rb.",
|
495
|
+
"see_also": ["FastA.split.rb","FastA.interpose.pl","FastQ.split.pl"],
|
496
|
+
"help_arg": "",
|
497
|
+
"options": [
|
498
|
+
{
|
499
|
+
"arg": "in_file",
|
500
|
+
"mandatory": true,
|
501
|
+
"description": "Input file in FastA format."
|
502
|
+
},
|
503
|
+
{
|
504
|
+
"name": "Out base",
|
505
|
+
"arg": "out_file",
|
506
|
+
"mandatory": true,
|
507
|
+
"description": ["Prefix for the name of the output files. It will be",
|
508
|
+
"appended with .<i>.fa, where <i> is a consecutive number starting",
|
509
|
+
"in 1."]
|
510
|
+
},
|
511
|
+
{
|
512
|
+
"name": "Number of files",
|
513
|
+
"arg": "integer",
|
514
|
+
"default": 12,
|
515
|
+
"description": "Number of files to generate."
|
516
|
+
}
|
517
|
+
]
|
518
|
+
},
|
519
|
+
{
|
520
|
+
"task": "FastA.subsample.pl",
|
521
|
+
"description": "Subsamples a set of sequences.",
|
522
|
+
"help_arg": "-h",
|
523
|
+
"see_also": "FastA.sample.rb",
|
524
|
+
"options": [
|
525
|
+
{
|
526
|
+
"name": "Fraction",
|
527
|
+
"opt": "-f",
|
528
|
+
"arg": "string",
|
529
|
+
"default": "10",
|
530
|
+
"description": ["Fraction of the library to be sampled (as",
|
531
|
+
"percentage). It can include several values (separated by comma),",
|
532
|
+
"as well as ranges of values in the form 'from-to/by'. For",
|
533
|
+
"example, the -f value 1-5/1,10-50/10,75,99 will produce 12",
|
534
|
+
"subsamples with expected fractions 1%, 2%, 3%, 4%, 5%, 10%, 20%,",
|
535
|
+
"30%, 40%, 50%, 75%, and 99%."]
|
536
|
+
},
|
537
|
+
{
|
538
|
+
"name": "Replicates",
|
539
|
+
"opt": "-r",
|
540
|
+
"arg": "integer",
|
541
|
+
"default": 1,
|
542
|
+
"description": "Number of replicates per fraction."
|
543
|
+
},
|
544
|
+
{
|
545
|
+
"name": "Out base",
|
546
|
+
"opt": "-o",
|
547
|
+
"arg": "out_file",
|
548
|
+
"description": ["Prefix of the output files to be created. The",
|
549
|
+
"output files will have a suffix of the form",
|
550
|
+
"'.fraction-replicate.fa', where 'fraction' is the percentage",
|
551
|
+
"sampled and 'replicate' is an increasing integer for replicates",
|
552
|
+
"of the same fraction. By default: Path to the input file."]
|
553
|
+
},
|
554
|
+
{
|
555
|
+
"name": "Force",
|
556
|
+
"opt": "-F",
|
557
|
+
"description": "Force overwriting output file(s)."
|
558
|
+
},
|
559
|
+
{
|
560
|
+
"name": "Zeroes",
|
561
|
+
"opt": "-z",
|
562
|
+
"description": ["Include leading zeroes in the numeric parts of the",
|
563
|
+
"output files (e.g., file.002.50-01.fa instead of file.2.50-1.fa),",
|
564
|
+
"so that alphabetic sorting of files reflects the sampled",
|
565
|
+
"fraction."]
|
566
|
+
},
|
567
|
+
{
|
568
|
+
"name": "Quiet",
|
569
|
+
"opt": "-q",
|
570
|
+
"description": "Run quietly."
|
571
|
+
},
|
572
|
+
{
|
573
|
+
"arg": "in_file",
|
574
|
+
"mandatory": true,
|
575
|
+
"multiple_sep": " ",
|
576
|
+
"description": "Input multi-FastA file(s)."
|
577
|
+
}
|
578
|
+
]
|
579
|
+
},
|
580
|
+
{
|
581
|
+
"task": "FastA.tag.rb",
|
582
|
+
"description": "Generates easy-to-parse tagged reads from FastA files.",
|
583
|
+
"see_also": ["FastQ.tag.rb"],
|
584
|
+
"help_arg": "--help",
|
585
|
+
"options": [
|
586
|
+
{
|
587
|
+
"name": "Input file",
|
588
|
+
"opt": "--in",
|
589
|
+
"arg": "in_file",
|
590
|
+
"mandatory": true,
|
591
|
+
"description": "FastA file containing the sequences."
|
592
|
+
},
|
593
|
+
{
|
594
|
+
"name": "Output file",
|
595
|
+
"opt": "--out",
|
596
|
+
"arg": "out_file",
|
597
|
+
"mandatory": true,
|
598
|
+
"description": "FastA file to create."
|
599
|
+
},
|
600
|
+
{
|
601
|
+
"opt": "--prefix",
|
602
|
+
"arg": "string",
|
603
|
+
"description": "Prefix to use in all IDs."
|
604
|
+
},
|
605
|
+
{
|
606
|
+
"opt": "--suffix",
|
607
|
+
"arg": "string",
|
608
|
+
"description": "Suffix to use in all IDs."
|
609
|
+
},
|
610
|
+
{
|
611
|
+
"opt": "--defline",
|
612
|
+
"description": "Keep the original defline after a space."
|
613
|
+
},
|
614
|
+
{
|
615
|
+
"opt": "--list",
|
616
|
+
"arg": "in_file",
|
617
|
+
"description": "Reads a list of IDS."
|
618
|
+
},
|
619
|
+
{
|
620
|
+
"opt": "--quiet",
|
621
|
+
"description": "Run quietly (no STDERR output)."
|
622
|
+
}
|
623
|
+
]
|
624
|
+
},
|
625
|
+
{
|
626
|
+
"task": "FastA.per_file.pl",
|
627
|
+
"description": ["Extracts all the sequences in a multi-FastA into",
|
628
|
+
"multiple single-FastA files."],
|
629
|
+
"see_also": "FastA.split.rb",
|
630
|
+
"help_arg": "",
|
631
|
+
"options": [
|
632
|
+
{
|
633
|
+
"arg": "out_dir",
|
634
|
+
"mandatory": true,
|
635
|
+
"description": "Output directory for the individual files."
|
636
|
+
},
|
637
|
+
{
|
638
|
+
"arg": "in_file",
|
639
|
+
"mandatory": true,
|
640
|
+
"multiple_sep": " ",
|
641
|
+
"description": "Input multi-FastA file(s)."
|
642
|
+
}
|
643
|
+
]
|
644
|
+
},
|
645
|
+
{
|
646
|
+
"task": "FastA.extract.rb",
|
647
|
+
"description": ["Extracts a list of sequences and/or coordinates from",
|
648
|
+
"multi-FastA files."],
|
649
|
+
"help_arg": "--help",
|
650
|
+
"options": [
|
651
|
+
{
|
652
|
+
"name": "Input file",
|
653
|
+
"opt": "--in",
|
654
|
+
"arg": "in_file",
|
655
|
+
"mandatory": true,
|
656
|
+
"description": "Input FastA file."
|
657
|
+
},
|
658
|
+
{
|
659
|
+
"name": "Output file",
|
660
|
+
"opt": "--out",
|
661
|
+
"arg": "out_file",
|
662
|
+
"mandatory": true,
|
663
|
+
"description": "Output FastA file."
|
664
|
+
},
|
665
|
+
{
|
666
|
+
"name": "Coordinates",
|
667
|
+
"opt": "--coords",
|
668
|
+
"arg": "string",
|
669
|
+
"description": ["Comma-delimited list of coordinates (mandatory",
|
670
|
+
"unless -C is passed).",
|
671
|
+
"The format of the coordinates is SEQ:FROM..TO or SEQ:FROM~LEN:",
|
672
|
+
"SEQ: Sequence ID, or * (asterisk) to extract range from all",
|
673
|
+
"sequences",
|
674
|
+
"FROM: Integer, position of the first base to include (can be",
|
675
|
+
"negative)",
|
676
|
+
"TO: Integer, last base to include (can be negative)",
|
677
|
+
"LEN: Length of the range to extract."]
|
678
|
+
},
|
679
|
+
{
|
680
|
+
"name": "Coordinates file",
|
681
|
+
"opt": "--coords-file",
|
682
|
+
"arg": "in_file",
|
683
|
+
"description": ["File containing the coordinates, one per line.",
|
684
|
+
"Each line must follow the format described for Coordinates."]
|
685
|
+
},
|
686
|
+
{
|
687
|
+
"opt": "--quiet",
|
688
|
+
"description": "Run quietly (no STDERR output)."
|
689
|
+
}
|
690
|
+
]
|
691
|
+
},
|
692
|
+
{
|
693
|
+
"task": "FastA.fragment.rb",
|
694
|
+
"description": ["Simulates incomplete (fragmented) drafts from complete",
|
695
|
+
"genomes."],
|
696
|
+
"help_arg": "--help",
|
697
|
+
"options": [
|
698
|
+
{
|
699
|
+
"name": "Input file",
|
700
|
+
"opt": "--in",
|
701
|
+
"arg": "in_file",
|
702
|
+
"mandatory": true,
|
703
|
+
"description": "FastA file containing the complete sequences."
|
704
|
+
},
|
705
|
+
{
|
706
|
+
"name": "Output file",
|
707
|
+
"opt": "--out",
|
708
|
+
"arg": "out_file",
|
709
|
+
"mandatory": true,
|
710
|
+
"description": "FastA to create."
|
711
|
+
},
|
712
|
+
{
|
713
|
+
"opt": "--completeness",
|
714
|
+
"arg": "float",
|
715
|
+
"mandatory": true,
|
716
|
+
"description": ["Fraction of genome completeness to simulate from 0",
|
717
|
+
"to 1."]
|
718
|
+
},
|
719
|
+
{
|
720
|
+
"name": "Minimum length",
|
721
|
+
"opt": "--minlen",
|
722
|
+
"arg": "integer",
|
723
|
+
"description": "Minimum fragment length to report.",
|
724
|
+
"default": 500
|
725
|
+
},
|
726
|
+
{
|
727
|
+
"opt": "--sorted",
|
728
|
+
"description": ["Keep fragments sorted as in the input file. By",
|
729
|
+
"default, fragments are shuffled."]
|
730
|
+
},
|
731
|
+
{
|
732
|
+
"opt": "--quiet",
|
733
|
+
"description": "Run quietly (no STDERR output)."
|
734
|
+
}
|
735
|
+
]
|
736
|
+
},
|
737
|
+
{
|
738
|
+
"task": "FastA.toFastQ.rb",
|
739
|
+
"description": "Creates a FastQ-compliant file from a FastA file.",
|
740
|
+
"see_also": "FastQ.toFastA.awk",
|
741
|
+
"help_arg": "--help",
|
742
|
+
"options": [
|
743
|
+
{
|
744
|
+
"name": "Input FastA",
|
745
|
+
"opt": "--in",
|
746
|
+
"arg": "in_file",
|
747
|
+
"mandatory": true,
|
748
|
+
"description": "Input FastA file (supports .gz compression)."
|
749
|
+
},
|
750
|
+
{
|
751
|
+
"name": "Output FastQ",
|
752
|
+
"opt": "--out",
|
753
|
+
"arg": "out_file",
|
754
|
+
"mandatory": true,
|
755
|
+
"description": "Output FastQ file (supports .gz compression)."
|
756
|
+
},
|
757
|
+
{
|
758
|
+
"opt": "--quality",
|
759
|
+
"arg": "integer",
|
760
|
+
"default": 31,
|
761
|
+
"description": ["PHRED quality score to use (fixed), in the range",
|
762
|
+
"[-5, 41]."]
|
763
|
+
},
|
764
|
+
{
|
765
|
+
"opt": "--encoding",
|
766
|
+
"arg": "integer",
|
767
|
+
"default": 33,
|
768
|
+
"description": "Base encoding (33 or 64)."
|
769
|
+
}
|
770
|
+
]
|
771
|
+
},
|
772
|
+
{
|
773
|
+
"task": "FastA.wrap.rb",
|
774
|
+
"description": "Wraps sequences in a FastA to a given line length.",
|
775
|
+
"help_arg": "--help",
|
776
|
+
"options": [
|
777
|
+
{
|
778
|
+
"name": "Input FastA",
|
779
|
+
"opt": "--in",
|
780
|
+
"arg": "in_file",
|
781
|
+
"mandatory": true,
|
782
|
+
"description": "Input FastA file."
|
783
|
+
},
|
784
|
+
{
|
785
|
+
"name": "Output FastA",
|
786
|
+
"opt": "--out",
|
787
|
+
"arg": "out_file",
|
788
|
+
"mandatory": true,
|
789
|
+
"description": "Output FastA file."
|
790
|
+
},
|
791
|
+
{
|
792
|
+
"name": "Wrap length",
|
793
|
+
"opt": "--wrap",
|
794
|
+
"arg": "integer",
|
795
|
+
"description": ["Line length to wrap sequences. Use 0 to generate",
|
796
|
+
"1-line sequences."],
|
797
|
+
"default": 70
|
798
|
+
}
|
799
|
+
]
|
800
|
+
}
|
801
|
+
]
|
802
|
+
}
|