miga-base 1.2.17.0 → 1.2.17.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/miga/version.rb +1 -1
- data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Archaea_SCG.hmm +41964 -0
- data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Bacteria_SCG.hmm +32439 -0
- data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Complete_SCG_DB.hmm +62056 -0
- data/utils/FastAAI/FastAAI +3659 -0
- data/utils/FastAAI/FastAAI-legacy/FastAAI +1336 -0
- data/utils/FastAAI/FastAAI-legacy/kAAI_v1.0_virus.py +1296 -0
- data/utils/FastAAI/README.md +84 -0
- data/utils/enveomics/Docs/recplot2.md +244 -0
- data/utils/enveomics/Examples/aai-matrix.bash +66 -0
- data/utils/enveomics/Examples/ani-matrix.bash +66 -0
- data/utils/enveomics/Examples/essential-phylogeny.bash +105 -0
- data/utils/enveomics/Examples/unus-genome-phylogeny.bash +100 -0
- data/utils/enveomics/LICENSE.txt +73 -0
- data/utils/enveomics/Makefile +52 -0
- data/utils/enveomics/Manifest/Tasks/aasubs.json +103 -0
- data/utils/enveomics/Manifest/Tasks/blasttab.json +790 -0
- data/utils/enveomics/Manifest/Tasks/distances.json +161 -0
- data/utils/enveomics/Manifest/Tasks/fasta.json +802 -0
- data/utils/enveomics/Manifest/Tasks/fastq.json +291 -0
- data/utils/enveomics/Manifest/Tasks/graphics.json +126 -0
- data/utils/enveomics/Manifest/Tasks/mapping.json +137 -0
- data/utils/enveomics/Manifest/Tasks/ogs.json +382 -0
- data/utils/enveomics/Manifest/Tasks/other.json +906 -0
- data/utils/enveomics/Manifest/Tasks/remote.json +355 -0
- data/utils/enveomics/Manifest/Tasks/sequence-identity.json +650 -0
- data/utils/enveomics/Manifest/Tasks/tables.json +308 -0
- data/utils/enveomics/Manifest/Tasks/trees.json +68 -0
- data/utils/enveomics/Manifest/Tasks/variants.json +111 -0
- data/utils/enveomics/Manifest/categories.json +165 -0
- data/utils/enveomics/Manifest/examples.json +162 -0
- data/utils/enveomics/Manifest/tasks.json +4 -0
- data/utils/enveomics/Pipelines/assembly.pbs/CONFIG.mock.bash +69 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl +1 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl +1 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl +1 -0
- data/utils/enveomics/Pipelines/assembly.pbs/README.md +189 -0
- data/utils/enveomics/Pipelines/assembly.pbs/RUNME-2.bash +112 -0
- data/utils/enveomics/Pipelines/assembly.pbs/RUNME-3.bash +23 -0
- data/utils/enveomics/Pipelines/assembly.pbs/RUNME-4.bash +44 -0
- data/utils/enveomics/Pipelines/assembly.pbs/RUNME.bash +50 -0
- data/utils/enveomics/Pipelines/assembly.pbs/kSelector.R +37 -0
- data/utils/enveomics/Pipelines/assembly.pbs/newbler.pbs +68 -0
- data/utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl +49 -0
- data/utils/enveomics/Pipelines/assembly.pbs/soap.pbs +80 -0
- data/utils/enveomics/Pipelines/assembly.pbs/stats.pbs +57 -0
- data/utils/enveomics/Pipelines/assembly.pbs/velvet.pbs +63 -0
- data/utils/enveomics/Pipelines/blast.pbs/01.pbs.bash +38 -0
- data/utils/enveomics/Pipelines/blast.pbs/02.pbs.bash +73 -0
- data/utils/enveomics/Pipelines/blast.pbs/03.pbs.bash +21 -0
- data/utils/enveomics/Pipelines/blast.pbs/BlastTab.recover_job.pl +72 -0
- data/utils/enveomics/Pipelines/blast.pbs/CONFIG.mock.bash +98 -0
- data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl +1 -0
- data/utils/enveomics/Pipelines/blast.pbs/README.md +127 -0
- data/utils/enveomics/Pipelines/blast.pbs/RUNME.bash +109 -0
- data/utils/enveomics/Pipelines/blast.pbs/TASK.check.bash +128 -0
- data/utils/enveomics/Pipelines/blast.pbs/TASK.dry.bash +16 -0
- data/utils/enveomics/Pipelines/blast.pbs/TASK.eo.bash +22 -0
- data/utils/enveomics/Pipelines/blast.pbs/TASK.pause.bash +26 -0
- data/utils/enveomics/Pipelines/blast.pbs/TASK.run.bash +89 -0
- data/utils/enveomics/Pipelines/blast.pbs/sentinel.pbs.bash +29 -0
- data/utils/enveomics/Pipelines/idba.pbs/README.md +49 -0
- data/utils/enveomics/Pipelines/idba.pbs/RUNME.bash +95 -0
- data/utils/enveomics/Pipelines/idba.pbs/run.pbs +56 -0
- data/utils/enveomics/Pipelines/trim.pbs/README.md +54 -0
- data/utils/enveomics/Pipelines/trim.pbs/RUNME.bash +70 -0
- data/utils/enveomics/Pipelines/trim.pbs/run.pbs +130 -0
- data/utils/enveomics/README.md +42 -0
- data/utils/enveomics/Scripts/AAsubs.log2ratio.rb +171 -0
- data/utils/enveomics/Scripts/Aln.cat.rb +221 -0
- data/utils/enveomics/Scripts/Aln.convert.pl +35 -0
- data/utils/enveomics/Scripts/AlphaDiversity.pl +152 -0
- data/utils/enveomics/Scripts/BedGraph.tad.rb +93 -0
- data/utils/enveomics/Scripts/BedGraph.window.rb +71 -0
- data/utils/enveomics/Scripts/BlastPairwise.AAsubs.pl +102 -0
- data/utils/enveomics/Scripts/BlastTab.addlen.rb +63 -0
- data/utils/enveomics/Scripts/BlastTab.advance.bash +48 -0
- data/utils/enveomics/Scripts/BlastTab.best_hit_sorted.pl +55 -0
- data/utils/enveomics/Scripts/BlastTab.catsbj.pl +104 -0
- data/utils/enveomics/Scripts/BlastTab.cogCat.rb +76 -0
- data/utils/enveomics/Scripts/BlastTab.filter.pl +47 -0
- data/utils/enveomics/Scripts/BlastTab.kegg_pep2path_rest.pl +194 -0
- data/utils/enveomics/Scripts/BlastTab.metaxaPrep.pl +104 -0
- data/utils/enveomics/Scripts/BlastTab.pairedHits.rb +157 -0
- data/utils/enveomics/Scripts/BlastTab.recplot2.R +48 -0
- data/utils/enveomics/Scripts/BlastTab.seqdepth.pl +86 -0
- data/utils/enveomics/Scripts/BlastTab.seqdepth_ZIP.pl +119 -0
- data/utils/enveomics/Scripts/BlastTab.seqdepth_nomedian.pl +86 -0
- data/utils/enveomics/Scripts/BlastTab.subsample.pl +47 -0
- data/utils/enveomics/Scripts/BlastTab.sumPerHit.pl +114 -0
- data/utils/enveomics/Scripts/BlastTab.taxid2taxrank.pl +90 -0
- data/utils/enveomics/Scripts/BlastTab.topHits_sorted.rb +123 -0
- data/utils/enveomics/Scripts/Chao1.pl +97 -0
- data/utils/enveomics/Scripts/CharTable.classify.rb +234 -0
- data/utils/enveomics/Scripts/EBIseq2tax.rb +83 -0
- data/utils/enveomics/Scripts/FastA.N50.pl +60 -0
- data/utils/enveomics/Scripts/FastA.extract.rb +152 -0
- data/utils/enveomics/Scripts/FastA.filter.pl +52 -0
- data/utils/enveomics/Scripts/FastA.filterLen.pl +28 -0
- data/utils/enveomics/Scripts/FastA.filterN.pl +60 -0
- data/utils/enveomics/Scripts/FastA.fragment.rb +100 -0
- data/utils/enveomics/Scripts/FastA.gc.pl +42 -0
- data/utils/enveomics/Scripts/FastA.interpose.pl +93 -0
- data/utils/enveomics/Scripts/FastA.length.pl +38 -0
- data/utils/enveomics/Scripts/FastA.mask.rb +89 -0
- data/utils/enveomics/Scripts/FastA.per_file.pl +36 -0
- data/utils/enveomics/Scripts/FastA.qlen.pl +57 -0
- data/utils/enveomics/Scripts/FastA.rename.pl +65 -0
- data/utils/enveomics/Scripts/FastA.revcom.pl +23 -0
- data/utils/enveomics/Scripts/FastA.sample.rb +98 -0
- data/utils/enveomics/Scripts/FastA.slider.pl +85 -0
- data/utils/enveomics/Scripts/FastA.split.pl +55 -0
- data/utils/enveomics/Scripts/FastA.split.rb +79 -0
- data/utils/enveomics/Scripts/FastA.subsample.pl +131 -0
- data/utils/enveomics/Scripts/FastA.tag.rb +65 -0
- data/utils/enveomics/Scripts/FastA.toFastQ.rb +69 -0
- data/utils/enveomics/Scripts/FastA.wrap.rb +48 -0
- data/utils/enveomics/Scripts/FastQ.filter.pl +54 -0
- data/utils/enveomics/Scripts/FastQ.interpose.pl +90 -0
- data/utils/enveomics/Scripts/FastQ.maskQual.rb +89 -0
- data/utils/enveomics/Scripts/FastQ.offset.pl +90 -0
- data/utils/enveomics/Scripts/FastQ.split.pl +53 -0
- data/utils/enveomics/Scripts/FastQ.tag.rb +70 -0
- data/utils/enveomics/Scripts/FastQ.test-error.rb +81 -0
- data/utils/enveomics/Scripts/FastQ.toFastA.awk +24 -0
- data/utils/enveomics/Scripts/GFF.catsbj.pl +127 -0
- data/utils/enveomics/Scripts/GenBank.add_fields.rb +84 -0
- data/utils/enveomics/Scripts/HMM.essential.rb +351 -0
- data/utils/enveomics/Scripts/HMM.haai.rb +168 -0
- data/utils/enveomics/Scripts/HMMsearch.extractIds.rb +83 -0
- data/utils/enveomics/Scripts/JPlace.distances.rb +88 -0
- data/utils/enveomics/Scripts/JPlace.to_iToL.rb +320 -0
- data/utils/enveomics/Scripts/M5nr.getSequences.rb +81 -0
- data/utils/enveomics/Scripts/MeTaxa.distribution.pl +198 -0
- data/utils/enveomics/Scripts/MyTaxa.fragsByTax.pl +35 -0
- data/utils/enveomics/Scripts/MyTaxa.seq-taxrank.rb +49 -0
- data/utils/enveomics/Scripts/NCBIacc2tax.rb +92 -0
- data/utils/enveomics/Scripts/Newick.autoprune.R +27 -0
- data/utils/enveomics/Scripts/RAxML-EPA.to_iToL.pl +228 -0
- data/utils/enveomics/Scripts/RecPlot2.compareIdentities.R +32 -0
- data/utils/enveomics/Scripts/RefSeq.download.bash +48 -0
- data/utils/enveomics/Scripts/SRA.download.bash +55 -0
- data/utils/enveomics/Scripts/TRIBS.plot-test.R +36 -0
- data/utils/enveomics/Scripts/TRIBS.test.R +39 -0
- data/utils/enveomics/Scripts/Table.barplot.R +31 -0
- data/utils/enveomics/Scripts/Table.df2dist.R +30 -0
- data/utils/enveomics/Scripts/Table.filter.pl +61 -0
- data/utils/enveomics/Scripts/Table.merge.pl +77 -0
- data/utils/enveomics/Scripts/Table.prefScore.R +60 -0
- data/utils/enveomics/Scripts/Table.replace.rb +69 -0
- data/utils/enveomics/Scripts/Table.round.rb +63 -0
- data/utils/enveomics/Scripts/Table.split.pl +57 -0
- data/utils/enveomics/Scripts/Taxonomy.silva2ncbi.rb +227 -0
- data/utils/enveomics/Scripts/VCF.KaKs.rb +147 -0
- data/utils/enveomics/Scripts/VCF.SNPs.rb +88 -0
- data/utils/enveomics/Scripts/aai.rb +421 -0
- data/utils/enveomics/Scripts/ani.rb +362 -0
- data/utils/enveomics/Scripts/anir.rb +137 -0
- data/utils/enveomics/Scripts/clust.rand.rb +102 -0
- data/utils/enveomics/Scripts/gi2tax.rb +103 -0
- data/utils/enveomics/Scripts/in_silico_GA_GI.pl +96 -0
- data/utils/enveomics/Scripts/lib/data/dupont_2012_essential.hmm.gz +0 -0
- data/utils/enveomics/Scripts/lib/data/lee_2019_essential.hmm.gz +0 -0
- data/utils/enveomics/Scripts/lib/enveomics.R +1 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/anir.rb +293 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/bm_set.rb +175 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +24 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/errors.rb +17 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/gmm_em.rb +30 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb +253 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/match.rb +88 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/og.rb +182 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/rbm.rb +49 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb +74 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb +237 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/stats/rand.rb +31 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/stats/sample.rb +152 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/stats.rb +3 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/utils.rb +74 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb +135 -0
- data/utils/enveomics/Scripts/ogs.annotate.rb +88 -0
- data/utils/enveomics/Scripts/ogs.core-pan.rb +160 -0
- data/utils/enveomics/Scripts/ogs.extract.rb +125 -0
- data/utils/enveomics/Scripts/ogs.mcl.rb +186 -0
- data/utils/enveomics/Scripts/ogs.rb +104 -0
- data/utils/enveomics/Scripts/ogs.stats.rb +131 -0
- data/utils/enveomics/Scripts/rbm-legacy.rb +172 -0
- data/utils/enveomics/Scripts/rbm.rb +108 -0
- data/utils/enveomics/Scripts/sam.filter.rb +148 -0
- data/utils/enveomics/Tests/Makefile +10 -0
- data/utils/enveomics/Tests/Mgen_M2288.faa +3189 -0
- data/utils/enveomics/Tests/Mgen_M2288.fna +8282 -0
- data/utils/enveomics/Tests/Mgen_M2321.fna +8288 -0
- data/utils/enveomics/Tests/Nequ_Kin4M.faa +2970 -0
- data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.tribs.Rdata +0 -0
- data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.txt +7 -0
- data/utils/enveomics/Tests/Xanthomonas_oryzae.aai-mat.tsv +17 -0
- data/utils/enveomics/Tests/Xanthomonas_oryzae.aai.tsv +137 -0
- data/utils/enveomics/Tests/a_mg.cds-go.blast.tsv +123 -0
- data/utils/enveomics/Tests/a_mg.reads-cds.blast.tsv +200 -0
- data/utils/enveomics/Tests/a_mg.reads-cds.counts.tsv +55 -0
- data/utils/enveomics/Tests/alkB.nwk +1 -0
- data/utils/enveomics/Tests/anthrax-cansnp-data.tsv +13 -0
- data/utils/enveomics/Tests/anthrax-cansnp-key.tsv +17 -0
- data/utils/enveomics/Tests/hiv1.faa +59 -0
- data/utils/enveomics/Tests/hiv1.fna +134 -0
- data/utils/enveomics/Tests/hiv2.faa +70 -0
- data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv +233 -0
- data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.lim +1 -0
- data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.rec +233 -0
- data/utils/enveomics/Tests/phyla_counts.tsv +10 -0
- data/utils/enveomics/Tests/primate_lentivirus.ogs +11 -0
- data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv1.rbm +9 -0
- data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv2.rbm +8 -0
- data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-siv.rbm +6 -0
- data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-hiv2.rbm +9 -0
- data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-siv.rbm +6 -0
- data/utils/enveomics/Tests/primate_lentivirus.rbm/siv-siv.rbm +6 -0
- data/utils/enveomics/build_enveomics_r.bash +45 -0
- data/utils/enveomics/enveomics.R/DESCRIPTION +31 -0
- data/utils/enveomics/enveomics.R/NAMESPACE +39 -0
- data/utils/enveomics/enveomics.R/R/autoprune.R +155 -0
- data/utils/enveomics/enveomics.R/R/barplot.R +184 -0
- data/utils/enveomics/enveomics.R/R/cliopts.R +135 -0
- data/utils/enveomics/enveomics.R/R/df2dist.R +154 -0
- data/utils/enveomics/enveomics.R/R/growthcurve.R +331 -0
- data/utils/enveomics/enveomics.R/R/prefscore.R +79 -0
- data/utils/enveomics/enveomics.R/R/recplot.R +354 -0
- data/utils/enveomics/enveomics.R/R/recplot2.R +1631 -0
- data/utils/enveomics/enveomics.R/R/tribs.R +583 -0
- data/utils/enveomics/enveomics.R/R/utils.R +80 -0
- data/utils/enveomics/enveomics.R/README.md +81 -0
- data/utils/enveomics/enveomics.R/data/growth.curves.rda +0 -0
- data/utils/enveomics/enveomics.R/data/phyla.counts.rda +0 -0
- data/utils/enveomics/enveomics.R/man/cash-enve.GrowthCurve-method.Rd +16 -0
- data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2-method.Rd +16 -0
- data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2.Peak-method.Rd +16 -0
- data/utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd +25 -0
- data/utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd +46 -0
- data/utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd +23 -0
- data/utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd +47 -0
- data/utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd +23 -0
- data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd +23 -0
- data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +40 -0
- data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +103 -0
- data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +67 -0
- data/utils/enveomics/enveomics.R/man/enve.col.alpha.Rd +24 -0
- data/utils/enveomics/enveomics.R/man/enve.col2alpha.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +45 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +44 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +47 -0
- data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +75 -0
- data/utils/enveomics/enveomics.R/man/enve.prefscore.Rd +50 -0
- data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +44 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +139 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd +45 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.ANIr.Rd +24 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +77 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd +25 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd +21 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.compareIdentities.Rd +47 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.coordinates.Rd +29 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +45 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd +36 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_e.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_m.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__emauto_one.Rd +27 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mow_one.Rd +52 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mower.Rd +17 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.em.Rd +51 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.emauto.Rd +43 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.mower.Rd +82 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd +59 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.seqdepth.Rd +27 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.windowDepthThreshold.Rd +36 -0
- data/utils/enveomics/enveomics.R/man/enve.selvector.Rd +23 -0
- data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +68 -0
- data/utils/enveomics/enveomics.R/man/enve.tribs.test.Rd +28 -0
- data/utils/enveomics/enveomics.R/man/enve.truncate.Rd +27 -0
- data/utils/enveomics/enveomics.R/man/growth.curves.Rd +14 -0
- data/utils/enveomics/enveomics.R/man/phyla.counts.Rd +13 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd +78 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +46 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +45 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +125 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd +19 -0
- data/utils/enveomics/globals.mk +8 -0
- data/utils/enveomics/manifest.json +9 -0
- data/utils/multitrim/Multitrim How-To.pdf +0 -0
- data/utils/multitrim/README.md +67 -0
- data/utils/multitrim/multitrim.py +1555 -0
- data/utils/multitrim/multitrim.yml +13 -0
- metadata +301 -5
@@ -0,0 +1,131 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
#
|
4
|
+
# @author: Luis M. Rodriguez-R
|
5
|
+
# @license: Artistic-2.0
|
6
|
+
#
|
7
|
+
|
8
|
+
$:.push File.expand_path(File.dirname(__FILE__) + '/lib')
|
9
|
+
require 'enveomics_rb/og'
|
10
|
+
require 'optparse'
|
11
|
+
require 'json'
|
12
|
+
|
13
|
+
o = {q:false, a:false}
|
14
|
+
ARGV << '-h' if ARGV.size==0
|
15
|
+
OptionParser.new do |opts|
|
16
|
+
opts.banner = "
|
17
|
+
Estimates some descriptive statistics on a set of Orthology Groups (OGs).
|
18
|
+
|
19
|
+
Usage: #{$0} [options]"
|
20
|
+
opts.separator ""
|
21
|
+
opts.separator "Mandatory"
|
22
|
+
opts.on("-o", "--ogs FILE",
|
23
|
+
"Input file containing the precomputed OGs."){ |v| o[:ogs]=v }
|
24
|
+
opts.separator ""
|
25
|
+
opts.separator "Other Options"
|
26
|
+
opts.on("-j", "--json FILE", "Output file in JSON format."){ |v| o[:json]=v }
|
27
|
+
opts.on("-t", "--tab FILE","Output file in tabular format."){ |v| o[:tab]=v }
|
28
|
+
opts.on("-T", "--transposed-tab FILE",
|
29
|
+
"Output file in transposed tabular format."){ |v| o[:ttab]=v }
|
30
|
+
opts.on("-a", "--auto", "Run completely quietly (no STDERR or STDOUT)") do
|
31
|
+
o[:q] = true
|
32
|
+
o[:a] = true
|
33
|
+
end
|
34
|
+
opts.on("-q", "--quiet", "Run quietly (no STDERR output)."){ o[:q] = true }
|
35
|
+
opts.on("-h", "--help", "Display this screen.") do
|
36
|
+
puts opts
|
37
|
+
exit
|
38
|
+
end
|
39
|
+
opts.separator ""
|
40
|
+
end.parse!
|
41
|
+
abort "-o is mandatory" if o[:ogs].nil?
|
42
|
+
|
43
|
+
##### MAIN:
|
44
|
+
begin
|
45
|
+
# Initialize the collection of OGs.
|
46
|
+
collection = OGCollection.new
|
47
|
+
|
48
|
+
# Read the pre-computed OGs
|
49
|
+
$stderr.puts "Reading pre-computed OGs in '#{o[:ogs]}'." unless o[:q]
|
50
|
+
f = File.open(o[:ogs], "r")
|
51
|
+
h = f.gets.chomp.split /\t/
|
52
|
+
while ln = f.gets
|
53
|
+
collection << OG.new(h, ln.chomp.split(/\t/))
|
54
|
+
end
|
55
|
+
f.close
|
56
|
+
$stderr.puts " Loaded OGs: #{collection.ogs.length}." unless o[:q]
|
57
|
+
|
58
|
+
# Estimate descriptive stats
|
59
|
+
stat_name = {
|
60
|
+
genomes: "Number of genomes",
|
61
|
+
pan: "Pangenome (OGs)",
|
62
|
+
core: "Core genome (OGs)",
|
63
|
+
core90pc: "OGs in 90% of the genomes",
|
64
|
+
core80pc: "OGs in 80% of the genomes",
|
65
|
+
unus: "Unus genome, core genome discarding paralogs (OGs)",
|
66
|
+
avg: "Average number of OGs in a genome",
|
67
|
+
avg_pan: "Average genome (OGs) / Pangenome (OGs)",
|
68
|
+
core_avg: "Core genome (OGs) / Average genome (OGs)",
|
69
|
+
core_pan: "Core genome (OGs) / Pangenome (OGs)",
|
70
|
+
ogs_shannon: "Entropy of the OG frequencies (bits)"
|
71
|
+
}
|
72
|
+
stats = {}
|
73
|
+
stats[:genomes] = Gene.genomes.length
|
74
|
+
stats[:pan] = collection.ogs.length
|
75
|
+
stats[:core] = collection.ogs.map do |og|
|
76
|
+
(og.genomes.length == Gene.genomes.length) ? 1 : 0
|
77
|
+
end.inject(0,:+)
|
78
|
+
stats[:core90pc] = collection.ogs.map do |og|
|
79
|
+
(og.genomes.length >= 0.9*Gene.genomes.length) ? 1 : 0
|
80
|
+
end.inject(0,:+)
|
81
|
+
stats[:core80pc] = collection.ogs.map do |og|
|
82
|
+
(og.genomes.length >= 0.8*Gene.genomes.length) ? 1 : 0
|
83
|
+
end.inject(0,:+)
|
84
|
+
stats[:unus] = collection.ogs.map do |og|
|
85
|
+
(og.genomes.length != Gene.genomes.length) ? 0 :
|
86
|
+
(og.genes.all?{ |i| i.size==1 }) ? 1 : 0
|
87
|
+
end.inject(0,:+)
|
88
|
+
og_genomes = collection.ogs.map{ |og| og.genomes.length }.inject(0,:+)
|
89
|
+
stats[:avg] = og_genomes.to_f/Gene.genomes.length
|
90
|
+
stats[:avg_pan] = stats[:avg]/stats[:pan]
|
91
|
+
stats[:core_avg] = stats[:core].to_f/stats[:avg]
|
92
|
+
stats[:core_pan] = stats[:core].to_f/stats[:pan]
|
93
|
+
stats[:ogs_shannon] = -1 * collection.ogs.map do |og|
|
94
|
+
pi = og.genomes.length.to_f/Gene.genomes.length
|
95
|
+
pi * Math.log(pi)
|
96
|
+
end.inject(0.0,:+)
|
97
|
+
|
98
|
+
# Show result
|
99
|
+
$stderr.puts "Generating reports." unless o[:q]
|
100
|
+
stats.each_pair{ |k,v| puts " #{stat_name[k]}: #{v}" } unless o[:a]
|
101
|
+
|
102
|
+
# Save results in JSON
|
103
|
+
unless o[:json].nil?
|
104
|
+
ohf = File.open(o[:json], "w")
|
105
|
+
ohf.puts JSON.pretty_generate(stats)
|
106
|
+
ohf.close
|
107
|
+
end
|
108
|
+
|
109
|
+
# Save results in tab
|
110
|
+
unless o[:tab].nil?
|
111
|
+
ohf = File.open(o[:tab], "w")
|
112
|
+
stats.each_pair{ |k,v| ohf.puts "#{k}\t#{v}" }
|
113
|
+
ohf.close
|
114
|
+
end
|
115
|
+
|
116
|
+
# Save results in T(tab)
|
117
|
+
unless o[:ttab].nil?
|
118
|
+
ohf = File.open(o[:ttab], "w")
|
119
|
+
ohf.puts stats.keys.join("\t")
|
120
|
+
ohf.puts stats.values.join("\t")
|
121
|
+
ohf.close
|
122
|
+
end
|
123
|
+
|
124
|
+
$stderr.puts "Done.\n" unless o[:q]
|
125
|
+
rescue => err
|
126
|
+
$stderr.puts "Exception: #{err}\n\n"
|
127
|
+
err.backtrace.each { |l| $stderr.puts l + "\n" }
|
128
|
+
err
|
129
|
+
end
|
130
|
+
|
131
|
+
|
@@ -0,0 +1,172 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
# frozen_string_literal: true
|
4
|
+
|
5
|
+
$VERSION = 0.1
|
6
|
+
$:.push File.expand_path('../lib', __FILE__)
|
7
|
+
require 'enveomics_rb/enveomics'
|
8
|
+
require 'tmpdir'
|
9
|
+
|
10
|
+
o = {
|
11
|
+
q: false, thr: 1,
|
12
|
+
len: 0, id: 0.0, fract: 0.0, score: 0.0,
|
13
|
+
bin: '', program: :'blast+', nucl: false
|
14
|
+
}
|
15
|
+
|
16
|
+
OptionParser.new do |opts|
|
17
|
+
cmd = File.basename($0)
|
18
|
+
opts.banner = <<~BANNER
|
19
|
+
|
20
|
+
[Enveomics Collection: #{cmd} v#{$VERSION}]
|
21
|
+
|
22
|
+
[DEPRECATED: Please use rbm.rb instead]
|
23
|
+
|
24
|
+
Finds the reciprocal best matches between two sets of sequences
|
25
|
+
|
26
|
+
Usage: #{cmd} [options]
|
27
|
+
|
28
|
+
BANNER
|
29
|
+
|
30
|
+
opts.separator 'Mandatory'
|
31
|
+
opts.on(
|
32
|
+
'-1', '--seq1 FILE',
|
33
|
+
'Path to the FastA file containing the set 1'
|
34
|
+
) { |v| o[:seq1] = v }
|
35
|
+
opts.on(
|
36
|
+
'-2', '--seq2 FILE',
|
37
|
+
'Path to the FastA file containing the set 2'
|
38
|
+
) { |v| o[:seq2] = v }
|
39
|
+
opts.separator ''
|
40
|
+
opts.separator 'Search Options'
|
41
|
+
opts.on(
|
42
|
+
'-n', '--nucl',
|
43
|
+
'Sequences are assumed to be nucleotides (proteins by default)',
|
44
|
+
'Incompatible with -p diamond'
|
45
|
+
) { |v| o[:nucl] = true }
|
46
|
+
opts.on(
|
47
|
+
'-l', '--len INT', Integer,
|
48
|
+
'Minimum alignment length (in residues)',
|
49
|
+
"By default: #{o[:len]}"
|
50
|
+
) { |v| o[:len] = v }
|
51
|
+
opts.on(
|
52
|
+
'-f', '--fract FLOAT', Float,
|
53
|
+
'Minimum alignment length (as a fraction of the query)',
|
54
|
+
'If set, requires BLAST+ or Diamond (see -p)',
|
55
|
+
"By default: #{o[:fract]}"
|
56
|
+
) { |v| o[:fract] = v }
|
57
|
+
opts.on(
|
58
|
+
'-i', '--id NUM', Float,
|
59
|
+
'Minimum alignment identity (in %)',
|
60
|
+
"By default: #{o[:id]}"
|
61
|
+
){ |v| o[:id] = v }
|
62
|
+
opts.on(
|
63
|
+
'-s', '--score NUM', Float,
|
64
|
+
'Minimum alignment score (in bits)',
|
65
|
+
"By default: #{o[:score]}"
|
66
|
+
) { |v| o[:score] = v }
|
67
|
+
opts.separator ''
|
68
|
+
opts.separator 'Software Options'
|
69
|
+
opts.on(
|
70
|
+
'-b', '--bin DIR',
|
71
|
+
'Path to the directory containing the binaries of the search program'
|
72
|
+
) { |v| o[:bin] = v }
|
73
|
+
opts.on(
|
74
|
+
'-p', '--program STR',
|
75
|
+
'Search program to be used. One of: blast+ (default), blast, diamond'
|
76
|
+
) { |v| o[:program] = v.downcase.to_sym }
|
77
|
+
opts.on(
|
78
|
+
'-t', '--threads INT', Integer,
|
79
|
+
'Number of parallel threads to be used',
|
80
|
+
"By default: #{o[:thr]}"
|
81
|
+
) { |v| o[:thr] = v }
|
82
|
+
opts.separator ''
|
83
|
+
opts.separator 'Other Options'
|
84
|
+
opts.on('-q', '--quiet', 'Run quietly (no STDERR output)') { o[:q] = true }
|
85
|
+
opts.on('-h', '--help', 'Display this screen') { puts opts ; exit }
|
86
|
+
opts.separator ''
|
87
|
+
end.parse!
|
88
|
+
|
89
|
+
abort '-1 is mandatory' if o[:seq1].nil?
|
90
|
+
abort '-2 is mandatory' if o[:seq2].nil?
|
91
|
+
if o[:program] == :diamond && o[:nucl]
|
92
|
+
abort '-p diamond is incompatible with -n'
|
93
|
+
end
|
94
|
+
if o[:fract] > 0.0 && o[:program] == :blast
|
95
|
+
abort 'Argument -f/--fract requires -p blast+ or -p diamond'
|
96
|
+
end
|
97
|
+
o[:bin] = o[:bin] + '/' if o[:bin].size > 0
|
98
|
+
$quiet = o[:q]
|
99
|
+
|
100
|
+
Dir.mktmpdir do |dir|
|
101
|
+
say('Temporal directory: ', dir)
|
102
|
+
|
103
|
+
# Create databases
|
104
|
+
say 'Creating databases'
|
105
|
+
[:seq1, :seq2].each do |seq|
|
106
|
+
case o[:program]
|
107
|
+
when :blast
|
108
|
+
`"#{o[:bin]}formatdb" -i "#{o[seq]}" -n "#{dir}/#{seq}" \
|
109
|
+
-p #{o[:nucl] ? 'F' : 'T'}`
|
110
|
+
when :'blast+'
|
111
|
+
`"#{o[:bin]}makeblastdb" -in "#{o[seq]}" -out "#{dir}/#{seq}" \
|
112
|
+
-dbtype #{o[:nucl] ? 'nucl' : 'prot'}`
|
113
|
+
when :diamond
|
114
|
+
`"#{o[:bin]}diamond" makedb --in "#{o[seq]}" \
|
115
|
+
--db "#{dir}/#{seq}.dmnd" --threads "#{o[:thr]}"`
|
116
|
+
else
|
117
|
+
abort "Unsupported program: #{o[:program]}"
|
118
|
+
end
|
119
|
+
end
|
120
|
+
|
121
|
+
# Best-hits
|
122
|
+
rbh = {}
|
123
|
+
n2 = 0
|
124
|
+
say ' Running comparisons'
|
125
|
+
[2, 1].each do |i|
|
126
|
+
qry_seen = {}
|
127
|
+
q = o[:"seq#{i}"]
|
128
|
+
s = "#{dir}/seq#{i == 1 ? 2 : 1}"
|
129
|
+
say(' Query: ', q)
|
130
|
+
case o[:program]
|
131
|
+
when :blast
|
132
|
+
`"#{o[:bin]}blastall" -p #{o[:nucl] ? 'blastn' : 'blastp'} -d "#{s}" \
|
133
|
+
-i "#{q}" -v 1 -b 1 -a #{o[:thr]} -m 8 -o "#{dir}/#{i}.tab"`
|
134
|
+
when :'blast+'
|
135
|
+
`"#{o[:bin]}#{o[:nucl] ? 'blastn' : 'blastp'}" -db "#{s}" -query "#{q}" \
|
136
|
+
-max_target_seqs 1 -num_threads #{o[:thr]} -out "#{dir}/#{i}.tab" \
|
137
|
+
-outfmt "6 qseqid sseqid pident length mismatch gapopen qstart qend \
|
138
|
+
sstart send evalue bitscore qlen slen"`
|
139
|
+
when :diamond
|
140
|
+
`"#{o[:bin]}diamond" blastp --threads "#{o[:thr]}" --db "#{s}.dmnd" \
|
141
|
+
--query "#{q}" --sensitive --daa "#{dir}/#{i}.daa" --quiet \
|
142
|
+
&& "#{o[:bin]}diamond" view --daa "#{dir}/#{i}.daa" --outfmt \
|
143
|
+
6 qseqid sseqid pident length mismatch gapopen qstart qend sstart \
|
144
|
+
send evalue bitscore qlen slen --out "#{dir}/#{i}.tab" --quiet`
|
145
|
+
else
|
146
|
+
abort "Unsupported program: #{o[:program]}"
|
147
|
+
end
|
148
|
+
|
149
|
+
n = 0
|
150
|
+
File.open("#{dir}/#{i}.tab", 'r') do |fh|
|
151
|
+
fh.each do |ln|
|
152
|
+
ln.chomp!
|
153
|
+
row = ln.split(/\t/)
|
154
|
+
row[12] = '1' unless [:'blast+', :diamond].include? o[:program]
|
155
|
+
next unless qry_seen[row[0]].nil? &&
|
156
|
+
row[3].to_i >= o[:len] && row[2].to_f >= o[:id] &&
|
157
|
+
row[11].to_f >= o[:score] && row[3].to_f / row[12].to_i >= o[:fract]
|
158
|
+
|
159
|
+
qry_seen[row[0]] = 1
|
160
|
+
n += 1
|
161
|
+
if i == 2
|
162
|
+
rbh[row[0]] = row[1]
|
163
|
+
elsif !rbh[row[1]].nil? && rbh[row[1]] == row[0]
|
164
|
+
puts ln
|
165
|
+
n2 += 1
|
166
|
+
end
|
167
|
+
end
|
168
|
+
end
|
169
|
+
say " #{n} sequences with hit"
|
170
|
+
end
|
171
|
+
say " #{n2} RBMs"
|
172
|
+
end
|
@@ -0,0 +1,108 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
# frozen_string_literal: true
|
4
|
+
|
5
|
+
$VERSION = 1.01
|
6
|
+
$:.push File.expand_path('../lib', __FILE__)
|
7
|
+
require 'enveomics_rb/rbm'
|
8
|
+
require 'tmpdir'
|
9
|
+
|
10
|
+
bms_dummy = Enveomics::RBM.new('1', '2').bms1
|
11
|
+
o = { q: false, out: '-' }
|
12
|
+
%i[thr len id fract score bin program nucl].each do |k|
|
13
|
+
o[k] = bms_dummy.opt(k)
|
14
|
+
end
|
15
|
+
|
16
|
+
OptionParser.new do |opts|
|
17
|
+
opts.version = $VERSION
|
18
|
+
cmd = File.basename($0)
|
19
|
+
opts.banner = <<~BANNER
|
20
|
+
|
21
|
+
[Enveomics Collection: #{cmd} v#{$VERSION}]
|
22
|
+
|
23
|
+
Finds the reciprocal best matches between two sets of sequences
|
24
|
+
|
25
|
+
Usage: #{cmd} [options]
|
26
|
+
|
27
|
+
BANNER
|
28
|
+
|
29
|
+
opts.separator 'Mandatory'
|
30
|
+
opts.on(
|
31
|
+
'-1', '--seq1 FILE',
|
32
|
+
'Path to the FastA file containing the set 1'
|
33
|
+
) { |v| o[:seq1] = v }
|
34
|
+
opts.on(
|
35
|
+
'-2', '--seq2 FILE',
|
36
|
+
'Path to the FastA file containing the set 2'
|
37
|
+
) { |v| o[:seq2] = v }
|
38
|
+
opts.on(
|
39
|
+
'-o', '--out FILE',
|
40
|
+
'Reciprocal Best Matches in BLAST tabular format.',
|
41
|
+
'Supports compression with .gz extension, use - for STDOUT (default)'
|
42
|
+
) { |v| o[:out] = v }
|
43
|
+
opts.separator ''
|
44
|
+
opts.separator 'Search Options'
|
45
|
+
opts.on(
|
46
|
+
'-n', '--nucl',
|
47
|
+
'Sequences are assumed to be nucleotides (proteins by default)',
|
48
|
+
'Incompatible with -p diamond'
|
49
|
+
) { |v| o[:nucl] = true }
|
50
|
+
opts.on(
|
51
|
+
'-l', '--len INT', Integer,
|
52
|
+
'Minimum alignment length (in residues)',
|
53
|
+
"By default: #{o[:len]}"
|
54
|
+
) { |v| o[:len] = v }
|
55
|
+
opts.on(
|
56
|
+
'-f', '--fract FLOAT', Float,
|
57
|
+
'Minimum alignment length (as a fraction of the query)',
|
58
|
+
'If set, requires BLAST+ or Diamond (see -p)',
|
59
|
+
"By default: #{o[:fract]}"
|
60
|
+
) { |v| o[:fract] = v }
|
61
|
+
opts.on(
|
62
|
+
'-i', '--id NUM', Float,
|
63
|
+
'Minimum alignment identity (in %)',
|
64
|
+
"By default: #{o[:id]}"
|
65
|
+
){ |v| o[:id] = v }
|
66
|
+
opts.on(
|
67
|
+
'-s', '--score NUM', Float,
|
68
|
+
'Minimum alignment score (in bits)',
|
69
|
+
"By default: #{o[:score]}"
|
70
|
+
) { |v| o[:score] = v }
|
71
|
+
opts.separator ''
|
72
|
+
opts.separator 'Software Options'
|
73
|
+
opts.on(
|
74
|
+
'-b', '--bin DIR',
|
75
|
+
'Path to the directory containing the binaries of the search program'
|
76
|
+
) { |v| o[:bin] = v }
|
77
|
+
opts.on(
|
78
|
+
'-p', '--program STR',
|
79
|
+
'Search program to be used',
|
80
|
+
'One of: blast+ (default), blast, diamond, blat'
|
81
|
+
) { |v| o[:program] = v.downcase.to_sym }
|
82
|
+
opts.on(
|
83
|
+
'-t', '--threads INT', Integer,
|
84
|
+
'Number of parallel threads to be used',
|
85
|
+
"By default: #{o[:thr]}"
|
86
|
+
) { |v| o[:thr] = v }
|
87
|
+
opts.separator ''
|
88
|
+
opts.separator 'Other Options'
|
89
|
+
opts.on('-q', '--quiet', 'Run quietly (no STDERR output)') { $QUIET = true }
|
90
|
+
opts.on('-h', '--help', 'Display this screen') { puts opts ; exit }
|
91
|
+
opts.separator ''
|
92
|
+
end.parse!
|
93
|
+
|
94
|
+
raise Enveomics::OptionError.new('-1 is mandatory') if o[:seq1].nil?
|
95
|
+
raise Enveomics::OptionError.new('-2 is mandatory') if o[:seq2].nil?
|
96
|
+
raise Enveomics::OptionError.new(
|
97
|
+
'Argument -f/--fract requires -p blast+ or -p diamond'
|
98
|
+
) if o[:fract] > 0.0 && !%i[blast+ diamond].include?(o[:program])
|
99
|
+
|
100
|
+
rbm = Enveomics::RBM.new(o[:seq1], o[:seq2], o)
|
101
|
+
ofh = writer(o[:out])
|
102
|
+
rbm.each { |bm| ofh.puts bm.to_s }
|
103
|
+
ofh.close
|
104
|
+
|
105
|
+
say('Forward Best Matches: ', rbm.bms1.count)
|
106
|
+
say('Reverse Best Matches: ', rbm.bms2.count)
|
107
|
+
say('Reciprocal Best Matches: ', rbm.count)
|
108
|
+
|
@@ -0,0 +1,148 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
# frozen_string_literal: true
|
4
|
+
|
5
|
+
$VERSION = 1.0
|
6
|
+
$:.push File.expand_path('../lib', __FILE__)
|
7
|
+
require 'enveomics_rb/enveomics'
|
8
|
+
use 'shellwords'
|
9
|
+
|
10
|
+
o = {
|
11
|
+
q: false, threads: 2, m_format: :sam, g_format: :fasta, identity: 95.0,
|
12
|
+
o: '-', header: true
|
13
|
+
}
|
14
|
+
|
15
|
+
OptionParser.new do |opt|
|
16
|
+
Enveomics.opt_banner(
|
17
|
+
opt, 'Filters a SAM or BAM file by target sequences and/or identity',
|
18
|
+
"#{File.basename($0)} -m map.sam -o filtered_map.sam [options]"
|
19
|
+
)
|
20
|
+
|
21
|
+
opt.separator 'Input/Output'
|
22
|
+
opt.on(
|
23
|
+
'-g', '--genome PATH',
|
24
|
+
'Genome assembly',
|
25
|
+
'Supports compression with .gz extension, use - for STDIN'
|
26
|
+
) { |v| o[:g] = v }
|
27
|
+
opt.on(
|
28
|
+
'-m', '--mapping PATH',
|
29
|
+
'Mapping file',
|
30
|
+
'Supports compression with .gz extension, use - for STDIN'
|
31
|
+
) { |v| o[:m] = v }
|
32
|
+
opt.on(
|
33
|
+
'-o', '--out-sam PATH',
|
34
|
+
'Output filtered file in SAM format',
|
35
|
+
'Supports compression with .gz extension, use - for STDOUT (default)'
|
36
|
+
) { |v| o[:o] = v }
|
37
|
+
opt.separator ''
|
38
|
+
|
39
|
+
opt.separator 'Formats'
|
40
|
+
opt.on(
|
41
|
+
'--g-format STRING',
|
42
|
+
'Genome assembly format: fasta (default) or list'
|
43
|
+
) { |v| o[:g_format] = v.downcase.to_sym }
|
44
|
+
opt.on(
|
45
|
+
'--m-format STRING',
|
46
|
+
'Mapping file format: sam (default) or bam',
|
47
|
+
'sam supports compression with .gz file extension'
|
48
|
+
) { |v| o[:m_format] = v.downcase.to_sym }
|
49
|
+
opt.separator ''
|
50
|
+
|
51
|
+
opt.separator 'General'
|
52
|
+
opt.on(
|
53
|
+
'-i', '--identity FLOAT', Float,
|
54
|
+
"Set a fixed threshold of percent identity (default: #{o[:identity]})"
|
55
|
+
) { |v| o[:identity] = v }
|
56
|
+
opt.on('--no-header', 'Do not include the headers') { |v| o[:header] = v }
|
57
|
+
opt.separator ''
|
58
|
+
opt.on(
|
59
|
+
'-t', '--threads INT', Integer, "Threads to use (default: #{o[:threads]})"
|
60
|
+
) { |v| o[:threads] = v }
|
61
|
+
opt.on('-l', '--log PATH', 'Log file to save output') { |v| o[:log] = v }
|
62
|
+
opt.on('-q', '--quiet', 'Run quietly') { |v| o[:q] = v }
|
63
|
+
opt.on('-h', '--help', 'Display this screen') do
|
64
|
+
puts opt
|
65
|
+
exit
|
66
|
+
end
|
67
|
+
opt.separator ''
|
68
|
+
end.parse!
|
69
|
+
|
70
|
+
$QUIET = o[:q]
|
71
|
+
|
72
|
+
# Functions
|
73
|
+
|
74
|
+
##
|
75
|
+
# Parses one line +ln+ in SAM format and outputs filtered lines to +ofh+
|
76
|
+
# Filters by minimum +identity+ and +target+ sequences, and prints
|
77
|
+
# the headers if +header+
|
78
|
+
def parse_sam_line(ln, identity, target, header, ofh)
|
79
|
+
if ln =~ /^@/ || ln =~ /^\s*$/
|
80
|
+
ofh.puts ln if header
|
81
|
+
return
|
82
|
+
end
|
83
|
+
|
84
|
+
# No match
|
85
|
+
row = ln.chomp.split("\t")
|
86
|
+
return if row[2] == '*'
|
87
|
+
|
88
|
+
# Filter by target
|
89
|
+
return if !target.nil? && !target.include?(row[2])
|
90
|
+
|
91
|
+
# Exclude unless concordant or unaligned
|
92
|
+
length = row[9].size
|
93
|
+
row.shift(11) # Discard non-flag columns
|
94
|
+
flags = Hash[row.map { |i| i.sub(/:.:/, ':').split(':', 2) }]
|
95
|
+
return if flags['YT'] && !%w[CP UU].include?(flags['YT'])
|
96
|
+
|
97
|
+
# Filter by identity
|
98
|
+
unless flags['MD']
|
99
|
+
raise Enveomics::ParseError.new(
|
100
|
+
"SAM line missing MD flag:\n#{ln}\nFlags: #{flags}"
|
101
|
+
)
|
102
|
+
end
|
103
|
+
mismatches = flags['MD'].scan(/[^\d]/).count
|
104
|
+
id = 100.0 * (length - mismatches) / length
|
105
|
+
ofh.puts ln if id >= identity
|
106
|
+
end
|
107
|
+
|
108
|
+
# Reading targets
|
109
|
+
if o[:g]
|
110
|
+
say 'Loading target sequences to filter'
|
111
|
+
reader = reader(o[:g])
|
112
|
+
target =
|
113
|
+
case o[:g_format]
|
114
|
+
when :fasta
|
115
|
+
reader.each.map { |ln| $1 if ln =~ /^>(\S+)/ }.compact
|
116
|
+
when :list
|
117
|
+
reader.each.map(&:chomp)
|
118
|
+
else
|
119
|
+
raise Enveomics::OptionError.new(
|
120
|
+
"Unsupported target sequences format: #{o[:g_format]}"
|
121
|
+
)
|
122
|
+
end
|
123
|
+
reader.close
|
124
|
+
else
|
125
|
+
target = nil
|
126
|
+
end
|
127
|
+
|
128
|
+
# Reading and filtering mapping
|
129
|
+
say 'Reading mapping file'
|
130
|
+
ofh = writer(o[:o])
|
131
|
+
case o[:m_format]
|
132
|
+
when :sam
|
133
|
+
reader = reader(o[:m])
|
134
|
+
reader.each { |ln| parse_sam_line(ln, o[:identity], target, o[:header], ofh) }
|
135
|
+
reader.close
|
136
|
+
when :bam
|
137
|
+
cmd = ['samtools', 'view', o[:m], '-@', o[:threads]]
|
138
|
+
cmd << '-h' if o[:header]
|
139
|
+
IO.popen(cmd.shelljoin) do |fh|
|
140
|
+
fh.each { |ln| parse_sam_line(ln, o[:identity], target, o[:header], ofh) }
|
141
|
+
end
|
142
|
+
else
|
143
|
+
raise Enveomics::OptionError.new(
|
144
|
+
"Unsupported mapping format: #{o[:m_format]}"
|
145
|
+
)
|
146
|
+
end
|
147
|
+
ofh.close
|
148
|
+
|