miga-base 0.7.26.0 → 0.7.26.1
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/FastAAI +1336 -0
- data/utils/FastAAI/README.md +84 -0
- data/utils/FastAAI/kAAI_v1.0_virus.py +1296 -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 +786 -0
- data/utils/enveomics/Manifest/Tasks/distances.json +161 -0
- data/utils/enveomics/Manifest/Tasks/fasta.json +766 -0
- data/utils/enveomics/Manifest/Tasks/fastq.json +243 -0
- data/utils/enveomics/Manifest/Tasks/graphics.json +126 -0
- data/utils/enveomics/Manifest/Tasks/mapping.json +67 -0
- data/utils/enveomics/Manifest/Tasks/ogs.json +382 -0
- data/utils/enveomics/Manifest/Tasks/other.json +829 -0
- data/utils/enveomics/Manifest/Tasks/remote.json +355 -0
- data/utils/enveomics/Manifest/Tasks/sequence-identity.json +501 -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 +156 -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 +163 -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 +56 -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 +92 -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 +83 -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.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.offset.pl +90 -0
- data/utils/enveomics/Scripts/FastQ.split.pl +53 -0
- data/utils/enveomics/Scripts/FastQ.tag.rb +63 -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 +57 -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.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 +418 -0
- data/utils/enveomics/Scripts/ani.rb +362 -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/enveomics.rb +24 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb +253 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/og.rb +182 -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/stat.rb +30 -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.rb +146 -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/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 +50 -0
- data/utils/enveomics/enveomics.R/README.md +80 -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 +17 -0
- data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2-method.Rd +17 -0
- data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2.Peak-method.Rd +17 -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 +32 -0
- data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +91 -0
- data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +57 -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 +39 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +38 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +40 -0
- data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +67 -0
- data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +37 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +122 -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 +68 -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 +41 -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 +40 -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 +41 -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 +43 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.emauto.Rd +37 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.mower.Rd +74 -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 +32 -0
- data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +59 -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 +63 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +38 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +38 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +111 -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
- metadata +277 -4
@@ -0,0 +1,93 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'optparse'
|
4
|
+
|
5
|
+
o = {range: 0.5, perseq: false, length: false}
|
6
|
+
ARGV << '-h' if ARGV.empty?
|
7
|
+
OptionParser.new do |opt|
|
8
|
+
opt.banner = "
|
9
|
+
Estimates the truncated average sequencing depth (TAD) from a BedGraph file.
|
10
|
+
|
11
|
+
IMPORTANT: This script doesn't consider zero-coverage positions if missing
|
12
|
+
from the file. If you produce your BedGraph file with bedtools genomecov and
|
13
|
+
want to consider zero-coverage position, be sure to use -bga (not -bg).
|
14
|
+
|
15
|
+
Usage: #{$0} [options]"
|
16
|
+
opt.separator ''
|
17
|
+
opt.on('-i', '--input PATH',
|
18
|
+
'Input BedGraph file (mandatory).'){ |v| o[:i]=v }
|
19
|
+
opt.on('-r', '--range FLOAT',
|
20
|
+
'Central range to consider, between 0 and 1.',
|
21
|
+
"By default: #{o[:range]} (inter-quartile range)."
|
22
|
+
){ |v| o[:range]=v.to_f }
|
23
|
+
opt.on('-s', '--per-seq',
|
24
|
+
'Calculate averages per reference sequence, not total.',
|
25
|
+
'Assumes a sorted BedGraph file.'
|
26
|
+
){ |v| o[:perseq] = v }
|
27
|
+
opt.on('-l', '--length',
|
28
|
+
'Add sequence length to the output.'){ |v| o[:length] = v }
|
29
|
+
opt.on('-h', '--help', 'Display this screen.') do
|
30
|
+
puts opt
|
31
|
+
exit
|
32
|
+
end
|
33
|
+
opt.separator ''
|
34
|
+
end.parse!
|
35
|
+
abort '-i is mandatory.' if o[:i].nil?
|
36
|
+
|
37
|
+
def pad(d, idx, r)
|
38
|
+
idx.each do |i|
|
39
|
+
next if d[i].nil?
|
40
|
+
d[i] -= r
|
41
|
+
break unless d[i] < 0
|
42
|
+
r = -d[i]
|
43
|
+
d[i] = nil
|
44
|
+
end
|
45
|
+
d
|
46
|
+
end
|
47
|
+
|
48
|
+
def report(sq, d, ln, o)
|
49
|
+
# Estimate padding ranges
|
50
|
+
pad = (1.0-o[:range])/2.0
|
51
|
+
r = (pad*ln).round
|
52
|
+
|
53
|
+
# Pad
|
54
|
+
d = pad(d, d.each_index.to_a, r+0)
|
55
|
+
d = pad(d, d.each_index.to_a.reverse, r+0)
|
56
|
+
|
57
|
+
# Average
|
58
|
+
y = [0.0]
|
59
|
+
unless d.compact.empty?
|
60
|
+
s = d.each_with_index.to_a.map{ |v,i| v.nil? ? 0 : i*v }.inject(0,:+)
|
61
|
+
y[0] = s.to_f/d.compact.inject(:+)
|
62
|
+
end
|
63
|
+
|
64
|
+
# Report
|
65
|
+
y.unshift(sq) if o[:perseq]
|
66
|
+
y << ln if o[:length]
|
67
|
+
puts y.join("\t")
|
68
|
+
end
|
69
|
+
|
70
|
+
# Read BedGraph
|
71
|
+
d = []
|
72
|
+
ln = 0
|
73
|
+
pre_sq = nil
|
74
|
+
File.open(o[:i], "r") do |ifh|
|
75
|
+
ifh.each_line do |i|
|
76
|
+
next if i =~ /^#/
|
77
|
+
r = i.chomp.split("\t")
|
78
|
+
sq = r.shift
|
79
|
+
if o[:perseq] and !pre_sq.nil? and pre_sq!=sq
|
80
|
+
report(pre_sq, d, ln, o)
|
81
|
+
d = []
|
82
|
+
ln = 0
|
83
|
+
end
|
84
|
+
r.map! { |j| j.to_i }
|
85
|
+
l = r[1]-r[0]
|
86
|
+
d[ r[2] ] ||= 0
|
87
|
+
d[ r[2] ] += l
|
88
|
+
ln += l
|
89
|
+
pre_sq = sq
|
90
|
+
end
|
91
|
+
end
|
92
|
+
report(pre_sq, d, ln, o)
|
93
|
+
|
@@ -0,0 +1,71 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'optparse'
|
4
|
+
|
5
|
+
o = {win: 1000}
|
6
|
+
ARGV << '-h' if ARGV.empty?
|
7
|
+
OptionParser.new do |opt|
|
8
|
+
opt.banner = "
|
9
|
+
Estimates the sequencing depth per windows from a BedGraph file.
|
10
|
+
|
11
|
+
IMPORTANT: This script doesn't consider zero-coverage positions if missing
|
12
|
+
from the file. If you produce your BedGraph file with bedtools genomecov and
|
13
|
+
want to consider zero-coverage position, be sure to use -bga (not -bg).
|
14
|
+
|
15
|
+
Usage: #{$0} [options]"
|
16
|
+
opt.separator ''
|
17
|
+
opt.on('-i', '--input PATH',
|
18
|
+
'Input BedGraph file (mandatory).'){ |v| o[:i]=v }
|
19
|
+
opt.on('-w', '--win INT',
|
20
|
+
'Window size, in base pairs.', "By default: #{o[:win]}."
|
21
|
+
){ |v| o[:win]=v.to_i }
|
22
|
+
opt.on('-h', '--help', 'Display this screen.') do
|
23
|
+
puts opt
|
24
|
+
exit
|
25
|
+
end
|
26
|
+
opt.separator ''
|
27
|
+
end.parse!
|
28
|
+
abort '-i is mandatory.' if o[:i].nil?
|
29
|
+
|
30
|
+
def report(d, a, b, seqs)
|
31
|
+
# Average
|
32
|
+
y = 0.0
|
33
|
+
unless d.compact.empty?
|
34
|
+
s = d.each_with_index.to_a.map{ |v,i| v.nil? ? 0 : i*v }.inject(0,:+)
|
35
|
+
y = s.to_f/d.compact.inject(:+)
|
36
|
+
end
|
37
|
+
|
38
|
+
# Report
|
39
|
+
puts [a, b, y, seqs.keys.join(",")].join("\t")
|
40
|
+
end
|
41
|
+
|
42
|
+
# Read BedGraph
|
43
|
+
d = []
|
44
|
+
ln = 0
|
45
|
+
a = 1
|
46
|
+
seqs = {}
|
47
|
+
b = o[:win]
|
48
|
+
File.open(o[:i], "r") do |ifh|
|
49
|
+
ifh.each_line do |i|
|
50
|
+
next if i =~ /^#/
|
51
|
+
r = i.chomp.split("\t")
|
52
|
+
sq = r.shift
|
53
|
+
seqs[sq] = 1
|
54
|
+
r.map!{ |j| j.to_i }
|
55
|
+
l = r[1]-r[0]
|
56
|
+
d[ r[2] ] ||= 0
|
57
|
+
d[ r[2] ] += l
|
58
|
+
ln += l
|
59
|
+
while ln >= b
|
60
|
+
d[ r[2] ] -= (ln-b)
|
61
|
+
report(d, a, b, seqs)
|
62
|
+
seqs = {}
|
63
|
+
seqs[ sq ] = 1 if ln > b
|
64
|
+
d = []
|
65
|
+
d[ r[2] ] = (ln-b)
|
66
|
+
a = b + 1
|
67
|
+
b = a + o[:win] - 1
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
@@ -0,0 +1,102 @@
|
|
1
|
+
#!/usr/bin/env perl
|
2
|
+
#
|
3
|
+
# @authors Konstantinos Konstantinidis (initial version)
|
4
|
+
# modified to work with the BLASTp 2.2.25+ m0 output by
|
5
|
+
# Despina Tsementzi & Luis M. Rodriguez-R
|
6
|
+
# @updated Dec-21-2015
|
7
|
+
#
|
8
|
+
|
9
|
+
|
10
|
+
$/ = "Lambda ";
|
11
|
+
use strict;
|
12
|
+
my %hash_depth;
|
13
|
+
|
14
|
+
my @query;
|
15
|
+
my @subject;
|
16
|
+
my @similarity;
|
17
|
+
my $length = "0";
|
18
|
+
|
19
|
+
my($cigar_chr, $blast) = @ARGV;
|
20
|
+
|
21
|
+
($cigar_chr and $blast) or die "
|
22
|
+
.Description:
|
23
|
+
Counts the different AA substitutions in the best hit blast alignments, from
|
24
|
+
a BLASTP pairwise format output (-outfmt 0 in BLAST+, -m 0 in legacy BLAST).
|
25
|
+
|
26
|
+
.Usage: $0 cigar_char blast.m0.txt > aa-subs.list
|
27
|
+
|
28
|
+
cigar_char Use '+' for similar substitutions, use '_' for non similar
|
29
|
+
substitutions
|
30
|
+
blast.m0.txt Blast in 'text' format (-outfmt/-m 0).
|
31
|
+
aa-subs.list A tab-delimited raw file with one substitution per row and
|
32
|
+
columns:
|
33
|
+
(1) Name-of-query_Name-of-subject
|
34
|
+
(2) AA-in-subject
|
35
|
+
(3) AA-in-query
|
36
|
+
(4) Total-Align-Length
|
37
|
+
|
38
|
+
";
|
39
|
+
|
40
|
+
# For each blast result (i.e., for each query)
|
41
|
+
open BLAST, "<", $blast or die "Cannot read file: $blast: $!\n";
|
42
|
+
while(my $data=<BLAST>) {
|
43
|
+
$data =~ s/\r//g;
|
44
|
+
my ($data_q, @array_matches) = split(/>/,$data);
|
45
|
+
my ($name_query) = ($data_q =~ /Query\= (\S+?)(?:_GENE|\s)/);
|
46
|
+
my ($length_query) = ($data_q =~ /\(([\d,]+) letters/ );
|
47
|
+
($length_query) = ($data_q =~ /Length=([\d,]+)/) unless $length_query;
|
48
|
+
$length_query =~ tr/,//d;
|
49
|
+
|
50
|
+
# For each alignment (i.e., for each HSP),
|
51
|
+
# note the "last" at the end of the block,
|
52
|
+
# so only the best match is considered
|
53
|
+
foreach my $data_f (@array_matches) {
|
54
|
+
# Capture statistics
|
55
|
+
my ($length_match) = ($data_f =~ /Identities = \d+\/(\d+)/);
|
56
|
+
my ($identity_match) = ($data_f =~ /Identities = \d+\/\d+ \((\d+)%/);
|
57
|
+
my ($target_name) = ($data_f =~ /^\s?(\S+)/);
|
58
|
+
|
59
|
+
# If the alignment meets minimum requirements
|
60
|
+
if ($length_query >30 && ($length_match/$length_query > 0.7) && $identity_match > 60) {
|
61
|
+
$data_f =~ tr/ /_/;
|
62
|
+
my @array = split ("\n", $data_f);
|
63
|
+
my $blanks = 0;
|
64
|
+
my $prefix_size = 0;
|
65
|
+
|
66
|
+
# For each line in the alignment
|
67
|
+
for my $data_fff (@array) {
|
68
|
+
if ($data_fff =~ /(Query[:_]_+\d+_+)([^_]+)/){
|
69
|
+
# Query lines
|
70
|
+
$prefix_size = length($1);
|
71
|
+
$length = length($2);
|
72
|
+
@query = split (//, $2);
|
73
|
+
}elsif ($data_fff =~ /^_{11}/){
|
74
|
+
# Cigar lines
|
75
|
+
@similarity = split(//, substr($data_fff, $prefix_size, $length));
|
76
|
+
}elsif ($data_fff =~ /Sbjct[:_]_+\d+_+([^_]+)/){
|
77
|
+
# Subject lines
|
78
|
+
@subject = split(//, $1);
|
79
|
+
# For each alignment column
|
80
|
+
for(my $i=0; $i <= $length; $i++){
|
81
|
+
if ($similarity[$i] eq $cigar_chr) {
|
82
|
+
print "$name_query\_$target_name\t$subject[$i]\t$query[$i]\t$length_match\n";
|
83
|
+
}
|
84
|
+
}
|
85
|
+
undef @query;
|
86
|
+
undef @similarity;
|
87
|
+
undef @subject;
|
88
|
+
}
|
89
|
+
|
90
|
+
# Remove secondary alignments
|
91
|
+
if ($data_fff =~ /^$/){
|
92
|
+
$blanks++;
|
93
|
+
last if $blanks >= 3;
|
94
|
+
}else{
|
95
|
+
$blanks=0;
|
96
|
+
}
|
97
|
+
} # for my $data_fff (@array)
|
98
|
+
} # if ($length_query >30 ...
|
99
|
+
last; # <---- So it takes only the best match!
|
100
|
+
} # foreach my $data_f (@array_matches)
|
101
|
+
} # while(my $data=<>)
|
102
|
+
|
@@ -0,0 +1,63 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
#
|
4
|
+
# @author: Luis M. Rodriguez-R
|
5
|
+
# @license: artistic license 2.0
|
6
|
+
#
|
7
|
+
|
8
|
+
require 'optparse'
|
9
|
+
|
10
|
+
o = { sbj: false, q: false }
|
11
|
+
ARGV << '-h' if ARGV.size == 0
|
12
|
+
OptionParser.new do |opts|
|
13
|
+
opts.banner = "
|
14
|
+
Appends an extra column to a BLAST with the length of the query or the subject
|
15
|
+
sequence. You can pipe two instances to add both:
|
16
|
+
cat input.blast | #{$0} -f queries.fa | #{$0} -f subjects.fa -s > output.blast
|
17
|
+
|
18
|
+
Usage: #{$0} [options] < input.blast > output.blast"
|
19
|
+
opts.separator ''
|
20
|
+
opts.separator 'Mandatory'
|
21
|
+
opts.on('-f', '--fasta FILE', 'Path to the FastA file'){ |v| o[:fasta] = v }
|
22
|
+
opts.separator ''
|
23
|
+
opts.separator 'Options'
|
24
|
+
opts.on('-s', '--subject',
|
25
|
+
'Use the subject column of the BLAST, by default the query column is used'
|
26
|
+
){ o[:sbj] = true }
|
27
|
+
opts.on('-q', '--quiet', 'Run quietly (no STDERR output)'){ o[:q] = true }
|
28
|
+
opts.on('-h', '--help', 'Display this screen') do
|
29
|
+
puts opts
|
30
|
+
exit
|
31
|
+
end
|
32
|
+
opts.separator ''
|
33
|
+
end.parse!
|
34
|
+
abort '-f is mandatory' if o[:fasta].nil?
|
35
|
+
|
36
|
+
len = {}
|
37
|
+
id = ''
|
38
|
+
$stderr.puts "Reading FastA file: #{o[:fasta]}" unless o[:q]
|
39
|
+
fh = File.open(o[:fasta], 'r')
|
40
|
+
fh.each_line do |ln|
|
41
|
+
defline = /^>(\S+)/.match(ln)
|
42
|
+
if defline.nil?
|
43
|
+
ln.gsub! /[^A-Za-z]/, ''
|
44
|
+
abort 'Error: Unsupported format, expecting FastA' if len[id].nil?
|
45
|
+
len[id] = len[id] + ln.size
|
46
|
+
else
|
47
|
+
id = defline[1]
|
48
|
+
len[id] = 0
|
49
|
+
end
|
50
|
+
end
|
51
|
+
fh.close
|
52
|
+
|
53
|
+
unless o[:q]
|
54
|
+
$stderr.puts 'Appending %s length column' % (o[:sbj] ? 'subject' : 'query')
|
55
|
+
end
|
56
|
+
ARGF.each_line do |ln|
|
57
|
+
ln.chomp!
|
58
|
+
row = ln.split /\t/
|
59
|
+
id = o[:sbj] ? row[1] : row[0]
|
60
|
+
abort "Impossible to find sequence of #{id}" if len[id].nil?
|
61
|
+
puts "#{ln}\t#{len[id]}"
|
62
|
+
end
|
63
|
+
|
@@ -0,0 +1,48 @@
|
|
1
|
+
#!/bin/bash
|
2
|
+
|
3
|
+
#
|
4
|
+
# @author Luis M. Rodriguez-R
|
5
|
+
# @update Mar-23-2016
|
6
|
+
# @license artistic license 2.0
|
7
|
+
#
|
8
|
+
|
9
|
+
if [[ ! $2 ]] ; then
|
10
|
+
echo "
|
11
|
+
.DESCRIPTION
|
12
|
+
Calculates the percentage of a partial BLAST result. The
|
13
|
+
value produced slightly subestimates the actual advance,
|
14
|
+
due to un-flushed output and trailing queries that could
|
15
|
+
be processed but generate no results.
|
16
|
+
|
17
|
+
.USAGE
|
18
|
+
$0 blast.txt qry.fasta
|
19
|
+
|
20
|
+
blast.txt Incomplete Tabular BLAST output.
|
21
|
+
qry.fasta FastA file with query sequences.
|
22
|
+
";
|
23
|
+
exit 1;
|
24
|
+
fi
|
25
|
+
|
26
|
+
if [[ ! -r $1 ]]; then
|
27
|
+
echo "Cannot open file: $1";
|
28
|
+
exit 1;
|
29
|
+
fi
|
30
|
+
|
31
|
+
if [[ ! -r $2 ]]; then
|
32
|
+
echo "Cannot open file: $2";
|
33
|
+
exit 1;
|
34
|
+
fi
|
35
|
+
|
36
|
+
LAST_Q=`tail -n 2 $1 | head -n 1 | awk '{print $1}'`
|
37
|
+
LAST_Q_NO=`grep -n "^>$LAST_Q\\( \\|$\\)" $2 | sed -e 's/:.*//'`
|
38
|
+
if [[ ! $LAST_Q_NO ]]; then
|
39
|
+
echo "Cannot find sequence: $LAST_Q";
|
40
|
+
echo "Make sure you are providing the right query file.";
|
41
|
+
exit 1;
|
42
|
+
fi
|
43
|
+
TOTAL_Q_NO=`cat $2 | wc -l | sed -e 's/ *//'`
|
44
|
+
let PERC=100*$LAST_Q_NO/$TOTAL_Q_NO
|
45
|
+
|
46
|
+
echo "$PERC%: $LAST_Q_NO / $TOTAL_Q_NO"
|
47
|
+
exit 0;
|
48
|
+
|
@@ -0,0 +1,55 @@
|
|
1
|
+
#!/usr/bin/env perl
|
2
|
+
|
3
|
+
#
|
4
|
+
# @author: Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
|
5
|
+
# @license: artistic license 2.0
|
6
|
+
# @last_update: Mar-23-2015
|
7
|
+
#
|
8
|
+
|
9
|
+
use strict;
|
10
|
+
use warnings;
|
11
|
+
|
12
|
+
die "
|
13
|
+
Usage:
|
14
|
+
sort blast.txt ... | $0 > blast.bh.txt
|
15
|
+
$0 blast_sorted.txt ... > blast.bh.txt
|
16
|
+
$0 -h|--help|-?
|
17
|
+
|
18
|
+
blast.txt ... One or more files in Tabular BLAST format.
|
19
|
+
blast_sorted.txt ... One or more files in Tabular BLAST format pre-sorted.
|
20
|
+
blast.bh.txt Output file in BLAST format containing best-hits only.
|
21
|
+
-h|--help|-? Any of these flags trigger this help message and exits.
|
22
|
+
|
23
|
+
NOTE: This script assumes that the BLAST is sorted. Because it can read
|
24
|
+
from the STDIN, calling this script without arguments cause it to still until
|
25
|
+
killed or until an EOF (^D) is presented.
|
26
|
+
|
27
|
+
" if exists $ARGV[0] and $ARGV[0] =~ /^\-?\-(h(elp)?|\?)/i;
|
28
|
+
|
29
|
+
my $last_qry = '';
|
30
|
+
my @best_res;
|
31
|
+
|
32
|
+
sub best_result($$){
|
33
|
+
my($r1, $r2)=@_;
|
34
|
+
return $r1 unless $r2;
|
35
|
+
return $r1->[11] > $r2->[11] ? @$r1 : @$r2;
|
36
|
+
}
|
37
|
+
|
38
|
+
my $i=0;
|
39
|
+
while(<>){
|
40
|
+
chomp;
|
41
|
+
#print STDERR " Reading entry $i... \r" unless $i%1000;
|
42
|
+
my @res = split /\t/;
|
43
|
+
die "\nCannot parse BLAST line $.: $_\n" unless exists $res[1];
|
44
|
+
if($last_qry eq $res[0]){
|
45
|
+
@best_res = &best_result(\@res, \@best_res);
|
46
|
+
}else{
|
47
|
+
print join("\t", @best_res), "\n" if $#best_res>0;
|
48
|
+
@best_res = @res;
|
49
|
+
$last_qry = $res[0];
|
50
|
+
}
|
51
|
+
}
|
52
|
+
print join("\t", @best_res), "\n" if @best_res;
|
53
|
+
|
54
|
+
|
55
|
+
|
@@ -0,0 +1,104 @@
|
|
1
|
+
#!/usr/bin/env perl
|
2
|
+
|
3
|
+
# @author: Luis M. Rodriguez-R
|
4
|
+
# @license: Artistic-2.0
|
5
|
+
|
6
|
+
use warnings;
|
7
|
+
use strict;
|
8
|
+
use List::Util qw/min max/;
|
9
|
+
use Getopt::Std;
|
10
|
+
|
11
|
+
sub HELP_MESSAGE { die "
|
12
|
+
|
13
|
+
Description:
|
14
|
+
Generates a list of hits from a BLAST result concatenating the subject
|
15
|
+
sequences. This can be used, e.g., to analyze BLAST results against
|
16
|
+
draft genomes.
|
17
|
+
|
18
|
+
Usage:
|
19
|
+
$0 [options] seq.fa map.bls
|
20
|
+
|
21
|
+
seq.fa Subject sequences (ref) in FastA format.
|
22
|
+
map.bls Mapping of the reads to the reference in BLAST Tabular
|
23
|
+
format.
|
24
|
+
|
25
|
+
Options:
|
26
|
+
-i <float> Minimum identity to report a result. By default: 70.
|
27
|
+
-l <int> Minimum alignment length to report a result. By default: 60.
|
28
|
+
-s The FastA provided is to be treated as a subset of the subject.
|
29
|
+
By default, it expects all the BLAST subjects to be present in
|
30
|
+
the FastA.
|
31
|
+
-q Run quietly.
|
32
|
+
-h Display this message and exit.
|
33
|
+
|
34
|
+
This script creates two files using <map.bls> as prefix with extensions
|
35
|
+
.rec (for the recruitment plot) and .lim (for the limits of the different
|
36
|
+
sequences in <seq.fa>).
|
37
|
+
|
38
|
+
";}
|
39
|
+
|
40
|
+
my %o;
|
41
|
+
getopts('i:l:sqh', \%o);
|
42
|
+
my($fa, $map) = @ARGV;
|
43
|
+
($fa and $map) or &HELP_MESSAGE;
|
44
|
+
$o{h} and &HELP_MESSAGE;
|
45
|
+
$o{i} ||= 70;
|
46
|
+
$o{l} ||= 60;
|
47
|
+
|
48
|
+
my %seq = ();
|
49
|
+
my @seq = ();
|
50
|
+
my $tot = 0;
|
51
|
+
|
52
|
+
SEQ: {
|
53
|
+
print STDERR "== Reading reference sequences\n" unless $o{q};
|
54
|
+
open FA, "<", $fa or die "Cannot read the file: $fa: $!\n";
|
55
|
+
my $cur_seq = '';
|
56
|
+
while(<FA>){
|
57
|
+
chomp;
|
58
|
+
if(m/^>(\S+)/){
|
59
|
+
my $c = $1;
|
60
|
+
$seq{$c} = exists $seq{$cur_seq} ? $seq{$cur_seq}+1 : 1;
|
61
|
+
push @seq, $c;
|
62
|
+
$cur_seq = $c;
|
63
|
+
}else{
|
64
|
+
s/[^A-Za-z]//g;
|
65
|
+
$seq{$cur_seq} += length $_;
|
66
|
+
}
|
67
|
+
}
|
68
|
+
close FA;
|
69
|
+
print STDERR " Found ".(scalar @seq)." sequences.\n" unless $o{q};
|
70
|
+
}
|
71
|
+
|
72
|
+
open LIM, ">", "$map.lim" or die "Cannot create the file: $map.lim: $!\n";
|
73
|
+
my $l = 0;
|
74
|
+
for my $s (@seq){
|
75
|
+
print LIM "$s\t".(++$l)."\t$seq{$s}\n";
|
76
|
+
($l, $seq{$s}) = ($seq{$s}, $l);
|
77
|
+
}
|
78
|
+
close LIM;
|
79
|
+
|
80
|
+
MAP: {
|
81
|
+
print STDERR "== Reading mapping\n" unless $o{q};
|
82
|
+
open BLS, "<", $map or die "Cannot read the file: $map: $!\n";
|
83
|
+
open REC, ">", "$map.rec" or die "Cannot create the file: $map.rec: $!\n";
|
84
|
+
RESULT: while(<BLS>){
|
85
|
+
chomp;
|
86
|
+
my @ln = split /\t/;
|
87
|
+
$ln[11] or die "Cannot parse line $map:$.: $_\n";
|
88
|
+
next unless $ln[3]>=$o{l};
|
89
|
+
next unless $ln[2]>=$o{i};
|
90
|
+
unless(exists $seq{$ln[1]}){
|
91
|
+
die "Cannot find the subject sequence: $ln[1]\n" unless $o{s};
|
92
|
+
next RESULT;
|
93
|
+
}
|
94
|
+
my $start = $seq{$ln[1]}+min($ln[8], $ln[9]);
|
95
|
+
my $end = $seq{$ln[1]}+max($ln[8], $ln[9]);
|
96
|
+
print REC "$start\t$end\t$ln[2]\t$ln[11]\t$ln[0]",
|
97
|
+
(exists($ln[13])?"\t".($ln[2]*$ln[3]/min($ln[12],$ln[13]))."\t":
|
98
|
+
exists($ln[12])?"\t".($ln[2]*$ln[3]/$ln[12])."\t":""),"\n";
|
99
|
+
}
|
100
|
+
close BLS;
|
101
|
+
close REC;
|
102
|
+
print STDERR " done.\n" unless $o{q};
|
103
|
+
}
|
104
|
+
|