miga-base 0.3.0.0 → 0.3.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +21 -4
- data/actions/init.rb +258 -0
- data/actions/run_local.rb +1 -2
- data/actions/test_taxonomy.rb +4 -1
- data/bin/miga +8 -1
- data/lib/miga/dataset.rb +4 -4
- data/lib/miga/dataset_result.rb +7 -4
- data/lib/miga/version.rb +2 -2
- data/scripts/_distances_noref_nomulti.bash +3 -1
- data/scripts/clade_finding.bash +1 -1
- data/scripts/init.bash +1 -1
- data/scripts/miga.bash +1 -1
- data/scripts/mytaxa.bash +78 -72
- data/scripts/mytaxa_scan.bash +67 -62
- data/scripts/ogs.bash +1 -1
- data/scripts/trimmed_fasta.bash +4 -3
- 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 +703 -0
- data/utils/enveomics/Manifest/Tasks/distances.json +161 -0
- data/utils/enveomics/Manifest/Tasks/fasta.json +571 -0
- data/utils/enveomics/Manifest/Tasks/fastq.json +208 -0
- data/utils/enveomics/Manifest/Tasks/graphics.json +126 -0
- data/utils/enveomics/Manifest/Tasks/ogs.json +339 -0
- data/utils/enveomics/Manifest/Tasks/other.json +746 -0
- data/utils/enveomics/Manifest/Tasks/remote.json +355 -0
- data/utils/enveomics/Manifest/Tasks/sequence-identity.json +454 -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 +132 -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 +56 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl +60 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl +38 -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 +55 -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 +40 -0
- data/utils/enveomics/Scripts/AAsubs.log2ratio.rb +171 -0
- data/utils/enveomics/Scripts/Aln.cat.rb +162 -0
- data/utils/enveomics/Scripts/Aln.convert.pl +35 -0
- data/utils/enveomics/Scripts/AlphaDiversity.pl +152 -0
- data/utils/enveomics/Scripts/BlastPairwise.AAsubs.pl +102 -0
- data/utils/enveomics/Scripts/BlastTab.addlen.rb +61 -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 +106 -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 +40 -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.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 +87 -0
- data/utils/enveomics/Scripts/FastA.length.pl +38 -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.slider.pl +85 -0
- data/utils/enveomics/Scripts/FastA.split.pl +55 -0
- data/utils/enveomics/Scripts/FastA.subsample.pl +131 -0
- data/utils/enveomics/Scripts/FastA.tag.rb +64 -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.toFastA.awk +24 -0
- data/utils/enveomics/Scripts/GenBank.add_fields.rb +84 -0
- data/utils/enveomics/Scripts/HMM.essential.rb +254 -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 +306 -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/RefSeq.download.bash +48 -0
- data/utils/enveomics/Scripts/SRA.download.bash +50 -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 +30 -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 +373 -0
- data/utils/enveomics/Scripts/ani.rb +362 -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/essential.hmm.gz +0 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +26 -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 +137 -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 +44 -0
- data/utils/enveomics/enveomics.R/DESCRIPTION +31 -0
- data/utils/enveomics/enveomics.R/NAMESPACE +35 -0
- data/utils/enveomics/enveomics.R/R/autoprune.R +121 -0
- data/utils/enveomics/enveomics.R/R/barplot.R +165 -0
- data/utils/enveomics/enveomics.R/R/cliopts.R +119 -0
- data/utils/enveomics/enveomics.R/R/df2dist.R +117 -0
- data/utils/enveomics/enveomics.R/R/growthcurve.R +263 -0
- data/utils/enveomics/enveomics.R/R/recplot.R +320 -0
- data/utils/enveomics/enveomics.R/R/recplot2.R +745 -0
- data/utils/enveomics/enveomics.R/R/tribs.R +423 -0
- data/utils/enveomics/enveomics.R/R/utils.R +16 -0
- data/utils/enveomics/enveomics.R/README.md +52 -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/enve.GrowthCurve-class.Rd +30 -0
- data/utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd +43 -0
- data/utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd +37 -0
- data/utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd +24 -0
- data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd +24 -0
- data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +33 -0
- data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +64 -0
- data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +37 -0
- data/utils/enveomics/enveomics.R/man/enve.col.alpha.Rd +19 -0
- data/utils/enveomics/enveomics.R/man/enve.col2alpha.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +26 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +25 -0
- data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +26 -0
- data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +49 -0
- data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +28 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +97 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd +40 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +40 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd +24 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__findPeak.Rd +40 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__findPeaks.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd +22 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd +20 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +27 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd +53 -0
- data/utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd +44 -0
- data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +44 -0
- data/utils/enveomics/enveomics.R/man/enve.tribs.test.Rd +21 -0
- data/utils/enveomics/enveomics.R/man/enveomics.R-package.Rd +15 -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 +43 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +29 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +30 -0
- data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +71 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd +18 -0
- data/utils/enveomics/enveomics.R/man/z$-methods.Rd +27 -0
- data/utils/enveomics/globals.mk +8 -0
- data/utils/enveomics/manifest.json +9 -0
- data/utils/index_metadata.rb +0 -0
- data/utils/plot-taxdist.R +0 -0
- data/utils/requirements.txt +19 -19
- metadata +242 -2
@@ -0,0 +1,234 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
#
|
4
|
+
# @author Luis M. Rodriguez-R
|
5
|
+
# @update Jan-13-2016
|
6
|
+
# @license artistic license 2.0
|
7
|
+
#
|
8
|
+
|
9
|
+
require "optparse"
|
10
|
+
|
11
|
+
o = {:q=>false}
|
12
|
+
ARGV << "-h" if ARGV.size==0
|
13
|
+
OptionParser.new do |opts|
|
14
|
+
opts.banner = "
|
15
|
+
Uses a dichotomous key to classify objects parsing a character table.
|
16
|
+
|
17
|
+
Usage: #{$0} [options]"
|
18
|
+
opts.separator ""
|
19
|
+
opts.separator "Input Options (mandatory)"
|
20
|
+
opts.on("-t", "--table FILE",
|
21
|
+
"Input table containing the states (columns) per object (row).",
|
22
|
+
"It must be tab-delimited and with row and column names.",
|
23
|
+
"See Tests/anthrax-cansnp-data.tsv for an example."){ |v| o[:table]=v }
|
24
|
+
opts.on("-k", "--key FILE",
|
25
|
+
"Input table containing the dychotomous key in linked style, defined in",
|
26
|
+
"four columns (can contain #-lead comment lines):",
|
27
|
+
" 1. ID of the step, typically a sequential integer.",
|
28
|
+
" 2. Name of character to evaluate. Must coincide with the -t headers.",
|
29
|
+
" 3. First character decision (see below).",
|
30
|
+
" 4. Second character decision (see below).",
|
31
|
+
"A character decision must be formated as: state (must coincide with the",
|
32
|
+
"values in -t), colon (:), step to follow. If the state is * (star) any",
|
33
|
+
"state triggers the decision (this should be the norm in column 4). The",
|
34
|
+
"step to follow should be a step ID in square brackets, or the name of",
|
35
|
+
"the classification. See Tests/anthrax-cansnp-key.tsv for an example."
|
36
|
+
){ |v| o[:key]=v }
|
37
|
+
opts.separator ""
|
38
|
+
opts.separator "Output Options"
|
39
|
+
opts.on("-c", "--classification FILE",
|
40
|
+
"Two-column table with the classification of the input objects."
|
41
|
+
){ |v| o[:class]=v }
|
42
|
+
opts.on("-n", "--newick FILE",
|
43
|
+
"Tree containing all the classified objects. This only makes sense for",
|
44
|
+
"synoptic keys."){ |v| o[:nwk]=v }
|
45
|
+
opts.separator ""
|
46
|
+
opts.separator "Additional Options"
|
47
|
+
opts.on("-q", "--quiet", "Run quietly (no STDERR output)."){ o[:q] = true }
|
48
|
+
opts.on("-h", "--help", "Display this screen.") do
|
49
|
+
puts opts
|
50
|
+
exit
|
51
|
+
end
|
52
|
+
opts.separator ""
|
53
|
+
end.parse!
|
54
|
+
abort "-t is mandatory" if o[:table].nil?
|
55
|
+
abort "-k is mandatory" if o[:key].nil?
|
56
|
+
|
57
|
+
##### Extensions:
|
58
|
+
class String
|
59
|
+
def nwk_sanitize() self.gsub(/[\(\):;,"'\s]/,'_') ; end
|
60
|
+
end
|
61
|
+
|
62
|
+
##### Classes:
|
63
|
+
module Dychotomous
|
64
|
+
class Decision
|
65
|
+
attr_reader :state, :terminal, :conclusion
|
66
|
+
def initialize(string)
|
67
|
+
r = string.split /:/
|
68
|
+
@state = r[0]
|
69
|
+
@terminal = !(r[1] =~ /^\[(.*)\]$/)
|
70
|
+
@conclusion = @terminal ? r[1] : $1
|
71
|
+
end
|
72
|
+
def ==(state)
|
73
|
+
return true if self.state == '*'
|
74
|
+
self.state == state.to_s
|
75
|
+
end
|
76
|
+
end
|
77
|
+
class Character
|
78
|
+
attr_reader :name, :a, :b
|
79
|
+
def initialize(name, a, b)
|
80
|
+
@name = name
|
81
|
+
@a = a
|
82
|
+
@b = b
|
83
|
+
end
|
84
|
+
def eval(object)
|
85
|
+
state = object.state(self.name)
|
86
|
+
return self.a if self.a == state
|
87
|
+
return self.b if self.b == state
|
88
|
+
raise "Impossible to make a decision for #{object.name} based on " +
|
89
|
+
"character #{self.name}. Offending state: #{state.to_s}."
|
90
|
+
end
|
91
|
+
end
|
92
|
+
class Key
|
93
|
+
attr_reader :first
|
94
|
+
def initialize(file)
|
95
|
+
@characters = {}
|
96
|
+
fh = File.open(file, 'r')
|
97
|
+
while ln = fh.gets
|
98
|
+
next if ln=~/^#/ or ln=~/^\s*$/
|
99
|
+
r = ln.chomp.split /\t/
|
100
|
+
@characters[ r[0] ] = Character.new(r[1],
|
101
|
+
Decision.new(r[2]), Decision.new(r[3]))
|
102
|
+
@first = @characters[ r[0] ] if @first.nil?
|
103
|
+
end
|
104
|
+
fh.close
|
105
|
+
end
|
106
|
+
def [](name)
|
107
|
+
raise "Cannot find character #{name} in key." if @characters[name].nil?
|
108
|
+
@characters[name]
|
109
|
+
end
|
110
|
+
end
|
111
|
+
end
|
112
|
+
module CharData
|
113
|
+
class Object
|
114
|
+
attr_reader :name, :states
|
115
|
+
def initialize(name)
|
116
|
+
@name = name
|
117
|
+
@states = {}
|
118
|
+
end
|
119
|
+
def <<(state) @states[state.character] = state ; end
|
120
|
+
def state(name) @states[name] ; end
|
121
|
+
end
|
122
|
+
class State
|
123
|
+
attr_reader :character, :state
|
124
|
+
def initialize(character, state)
|
125
|
+
@character = character
|
126
|
+
@state = state
|
127
|
+
end
|
128
|
+
def to_s() self.state.to_s ; end
|
129
|
+
end
|
130
|
+
class Table
|
131
|
+
attr_reader :objects
|
132
|
+
def initialize(file)
|
133
|
+
@objects = []
|
134
|
+
fh = File.open(file, 'r')
|
135
|
+
header = fh.gets.chomp.split(/\t/)
|
136
|
+
while ln = fh.gets
|
137
|
+
next if ln=~/^#/ or ln=~/^\s*$/
|
138
|
+
r = ln.chomp.split /\t/
|
139
|
+
o = Object.new(r[0])
|
140
|
+
(1 .. r.size).each{ |i| o << State.new(header[i], r[i]) }
|
141
|
+
self << o
|
142
|
+
end
|
143
|
+
fh.close
|
144
|
+
end
|
145
|
+
def <<(object) @objects << object ; end
|
146
|
+
end
|
147
|
+
end
|
148
|
+
module ClassData
|
149
|
+
class Classification
|
150
|
+
attr_reader :key, :object, :result
|
151
|
+
def initialize key, object
|
152
|
+
@key = key
|
153
|
+
@object = object
|
154
|
+
self.classify!
|
155
|
+
end
|
156
|
+
def classify!
|
157
|
+
@result = self.key.first.eval(object)
|
158
|
+
while ! self.result.terminal
|
159
|
+
@result = self.key[ self.result.conclusion ].eval(object)
|
160
|
+
end
|
161
|
+
end
|
162
|
+
end
|
163
|
+
class Collection
|
164
|
+
attr_reader :key, :table, :classifications
|
165
|
+
def initialize(key, table)
|
166
|
+
@key = key
|
167
|
+
@table = table
|
168
|
+
@classifications = []
|
169
|
+
self.classify!
|
170
|
+
end
|
171
|
+
def classify!
|
172
|
+
table.objects.each do |object|
|
173
|
+
@classifications << Classification.new(key, object)
|
174
|
+
end
|
175
|
+
end
|
176
|
+
def classified_as(conclusion)
|
177
|
+
self.classifications.select{ |c|
|
178
|
+
c.result.conclusion==conclusion }.map{ |c| c.object }
|
179
|
+
end
|
180
|
+
def to_nwk
|
181
|
+
self.to_nwk_node(self.key.first) + ";"
|
182
|
+
end
|
183
|
+
def to_nwk_node(node)
|
184
|
+
if node.is_a? Dychotomous::Character
|
185
|
+
a = self.to_nwk_node(node.a)
|
186
|
+
b = self.to_nwk_node(node.b)
|
187
|
+
return "" if (a + b)==""
|
188
|
+
return "(" + a + b + ")#{node.name.nwk_sanitize}" if a=="" or b==""
|
189
|
+
return "(" + self.to_nwk_node(node.a) + "," +
|
190
|
+
self.to_nwk_node(node.b) + ")#{node.name.nwk_sanitize}"
|
191
|
+
end
|
192
|
+
if node.is_a? Dychotomous::Decision and node.terminal
|
193
|
+
objects = self.classified_as(node.conclusion)
|
194
|
+
return '' if objects.empty?
|
195
|
+
return objects[0].name.nwk_sanitize if objects.size==1
|
196
|
+
return "(" + objects.map{|o| o.name.nwk_sanitize}.join(",") + ")"
|
197
|
+
end
|
198
|
+
return self.to_nwk_node( self.key[node.conclusion] ) if
|
199
|
+
node.is_a? Dychotomous::Decision
|
200
|
+
raise "Unsupported class: to_nwk_node: #{node}."
|
201
|
+
end
|
202
|
+
end
|
203
|
+
end
|
204
|
+
|
205
|
+
##### MAIN:
|
206
|
+
begin
|
207
|
+
$stderr.puts "Reading dychotomous key." unless o[:q]
|
208
|
+
key = Dychotomous::Key.new(o[:key])
|
209
|
+
$stderr.puts "Reading character table." unless o[:q]
|
210
|
+
table = CharData::Table.new(o[:table])
|
211
|
+
$stderr.puts "Classifying objects." unless o[:q]
|
212
|
+
classif = ClassData::Collection.new(key, table)
|
213
|
+
|
214
|
+
unless o[:class].nil?
|
215
|
+
$stderr.puts "Generating classification table." unless o[:q]
|
216
|
+
fh = File.open(o[:class], 'w')
|
217
|
+
classif.classifications.each do |c|
|
218
|
+
fh.puts c.object.name + "\t" + c.result.conclusion
|
219
|
+
end
|
220
|
+
fh.close
|
221
|
+
end
|
222
|
+
|
223
|
+
unless o[:nwk].nil?
|
224
|
+
$stderr.puts "Generating classification tree." unless o[:q]
|
225
|
+
fh = File.open(o[:nwk], 'w')
|
226
|
+
fh.puts classif.to_nwk
|
227
|
+
fh.close
|
228
|
+
end
|
229
|
+
|
230
|
+
rescue => err
|
231
|
+
$stderr.puts "Exception: #{err}\n\n"
|
232
|
+
err.backtrace.each { |l| $stderr.puts l + "\n" }
|
233
|
+
err
|
234
|
+
end
|
@@ -0,0 +1,83 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
#
|
4
|
+
# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
|
5
|
+
# @update Oct-13-2015
|
6
|
+
# @license Artistic License 2.0
|
7
|
+
#
|
8
|
+
|
9
|
+
$:.push File.expand_path(File.dirname(__FILE__) + "/lib")
|
10
|
+
require "enveomics_rb/remote_data"
|
11
|
+
use "nokogiri"
|
12
|
+
|
13
|
+
#================================[ Options parsing ]
|
14
|
+
$o = {
|
15
|
+
q: false, ids: [], dbfrom: "uniprotkb", header: true,
|
16
|
+
ret: "ScientificName",
|
17
|
+
ranks: %w(superkingdom phylum class order family genus species)}
|
18
|
+
|
19
|
+
OptionParser.new do |opt|
|
20
|
+
opt.banner = "
|
21
|
+
Maps a list of EBI-supported IDs to their corresponding NCBI taxonomy using
|
22
|
+
EBI RESTful API. Avoid using this script on millions of entries at a time,
|
23
|
+
since each entry elicits requests to EBI and NCBI servers.
|
24
|
+
|
25
|
+
Usage: #{$0} [options]".gsub(/^ +/,"")
|
26
|
+
opt.separator ""
|
27
|
+
opt.on("-i", "--ids ID1,ID2,...", Array,
|
28
|
+
"Comma-separated list of EBI IDs. Required unless -I is passed."
|
29
|
+
){ |v| $o[:ids]=v }
|
30
|
+
opt.on("-I", "--infile FILE",
|
31
|
+
"Raw text file containing the list of EBI IDs, one per line.",
|
32
|
+
"Required unless -i is passed."){ |v| $o[:infile]=v }
|
33
|
+
opt.on("-d", "--database DB",
|
34
|
+
"EBI database defining the EBI IDs. By default: " + $o[:dbfrom].to_s + "."
|
35
|
+
){ |v| $o[:dbfrom]=v }
|
36
|
+
opt.on("-r", "--ranks RANK1,RANK2,...", Array,
|
37
|
+
"Taxonomic ranks to report. By default:",
|
38
|
+
$o[:ranks].join(",") + "."){ |v| $o[:ranks]=v }
|
39
|
+
opt.on("-n", "--noheader",
|
40
|
+
"Do not includ a header in the output."){ $o[:header]=false }
|
41
|
+
opt.on("-t", "--taxids",
|
42
|
+
"Return Taxonomy IDs instead of scientific names."){ $o[:ret]="TaxId" }
|
43
|
+
opt.on("-q", "--quiet", "Run quietly."){ |v| $o[:q]=true }
|
44
|
+
opt.on("-h", "--help","Display this screen") do
|
45
|
+
puts opt
|
46
|
+
exit
|
47
|
+
end
|
48
|
+
opt.separator ""
|
49
|
+
end.parse!
|
50
|
+
|
51
|
+
#================================[ Main ]
|
52
|
+
begin
|
53
|
+
$o[:ids] += File.readlines($o[:infile]).map{ |l| l.chomp } unless
|
54
|
+
$o[:infile].nil?
|
55
|
+
$o[:ranks].map!{ |r| r.downcase }
|
56
|
+
puts (["ID", "TaxId"] + $o[:ranks].map{ |r| r.capitalize }).join("\t") if
|
57
|
+
$o[:header]
|
58
|
+
$o[:ids].each do |id|
|
59
|
+
id = $1 if id =~ /^[a-z]+\|\S+\|(\S+)/
|
60
|
+
taxid = RemoteData.ebiseq2taxid(id, $o[:dbfrom])
|
61
|
+
if taxid.nil?
|
62
|
+
warn "Cannot find link to taxonomy: #{id}"
|
63
|
+
next
|
64
|
+
end
|
65
|
+
taxonomy = {}
|
66
|
+
unless taxid.nil?
|
67
|
+
doc = Nokogiri::XML( RemoteData.efetch({db: "taxonomy", id: taxid}) )
|
68
|
+
taxonomy[ doc.at_xpath("/TaxaSet/Taxon/Rank").content ] =
|
69
|
+
doc.at_xpath("/TaxaSet/Taxon/#{$o[:ret]}").content
|
70
|
+
doc.xpath("/TaxaSet/Taxon/LineageEx/Taxon").each do |taxon|
|
71
|
+
taxonomy[ taxon.at_xpath("./Rank").content ] =
|
72
|
+
taxon.at_xpath("./#{$o[:ret]}").content
|
73
|
+
end
|
74
|
+
end
|
75
|
+
puts ([id, taxid] +
|
76
|
+
$o[:ranks].map{ |rank| taxonomy[ rank ] ||= "" }).join("\t")
|
77
|
+
end # $o[:ids].each
|
78
|
+
rescue => err
|
79
|
+
$stderr.puts "Exception: #{err}\n\n"
|
80
|
+
err.backtrace.each { |l| $stderr.puts l + "\n" }
|
81
|
+
err
|
82
|
+
end
|
83
|
+
|
@@ -0,0 +1,56 @@
|
|
1
|
+
#!/usr/bin/env perl
|
2
|
+
#
|
3
|
+
# @author: Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
|
4
|
+
# @update: Oct 07 2015
|
5
|
+
# @license: artistic license 2.0
|
6
|
+
#
|
7
|
+
use strict;
|
8
|
+
use warnings;
|
9
|
+
use List::Util qw/sum min max/;
|
10
|
+
|
11
|
+
my ($seqs, $minlen, $n__) = @ARGV;
|
12
|
+
$seqs or die "
|
13
|
+
Description:
|
14
|
+
Calculates the N50 value of a set of sequences. Alternatively, it
|
15
|
+
can calculate other N** values. It also calculates the total number
|
16
|
+
of sequences and the total added length.
|
17
|
+
|
18
|
+
Usage:
|
19
|
+
$0 seqs.fa[ minlen[ **]]
|
20
|
+
|
21
|
+
seqs.fa A FastA file containing the sequences.
|
22
|
+
minlen (optional) The minimum length to take into consideration.
|
23
|
+
By default: 0.
|
24
|
+
** Value N** to calculate. By default: 50 (N50).
|
25
|
+
";
|
26
|
+
$minlen ||= 0;
|
27
|
+
$n__ ||= 50;
|
28
|
+
|
29
|
+
my @len = ();
|
30
|
+
open SEQ, "<", $seqs or die "Cannot open file: $seqs: $!\n";
|
31
|
+
while(<SEQ>){
|
32
|
+
if(/^>/){
|
33
|
+
push @len, 0;
|
34
|
+
}else{
|
35
|
+
next if /^;/;
|
36
|
+
chomp;
|
37
|
+
s/\W//g;
|
38
|
+
$len[-1]+=length $_;
|
39
|
+
}
|
40
|
+
}
|
41
|
+
close SEQ;
|
42
|
+
@len = sort { $a <=> $b } map { $_>=$minlen?$_:() } @len;
|
43
|
+
my $tot = (sum(@len) || 0);
|
44
|
+
|
45
|
+
my $thr = $n__*$tot/100;
|
46
|
+
my $pos = 0;
|
47
|
+
for(@len){
|
48
|
+
$pos+= $_;
|
49
|
+
if($pos>=$thr){
|
50
|
+
print "N$n__: $_\n";
|
51
|
+
last;
|
52
|
+
}
|
53
|
+
}
|
54
|
+
print "Sequences: ".scalar(@len)."\n";
|
55
|
+
print "Total length: $tot\n";
|
56
|
+
|
@@ -0,0 +1,52 @@
|
|
1
|
+
#!/usr/bin/env perl
|
2
|
+
#
|
3
|
+
# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
|
4
|
+
# @update Oct-07-2015
|
5
|
+
# @license artistic license 2.0
|
6
|
+
#
|
7
|
+
|
8
|
+
use warnings;
|
9
|
+
use strict;
|
10
|
+
use Getopt::Std;
|
11
|
+
|
12
|
+
sub HELP_MESSAGE { die "
|
13
|
+
.Description:
|
14
|
+
Extracts a subset of sequences from a FastA file.
|
15
|
+
|
16
|
+
.Usage: $0 [options] list.txt seqs.fa > subset.fa
|
17
|
+
|
18
|
+
[options]
|
19
|
+
-r Reverse list. Extracts sequences NOT present in the list.
|
20
|
+
-q Runs quietly.
|
21
|
+
-h Prints this message and exits.
|
22
|
+
|
23
|
+
[mandatory]
|
24
|
+
list.txt List of sequences to extract.
|
25
|
+
seqs.fa FastA file containing the superset of sequences.
|
26
|
+
subset.fa FastA file to be created.
|
27
|
+
|
28
|
+
" }
|
29
|
+
|
30
|
+
my %o=();
|
31
|
+
getopts('rhq', \%o);
|
32
|
+
my($list, $fa) = @ARGV;
|
33
|
+
($list and $fa) or &HELP_MESSAGE;
|
34
|
+
$o{h} and &HELP_MESSAGE;
|
35
|
+
|
36
|
+
print STDERR "Reading list.\n" unless $o{q};
|
37
|
+
open LI, "<", $list or die "Cannot read file: $list: $!\n";
|
38
|
+
my %li = map { chomp; $_ => 1 } <LI>;
|
39
|
+
close LI;
|
40
|
+
|
41
|
+
print STDERR "Filtering FastA.\n" unless $o{q};
|
42
|
+
open FA, "<", $fa or die "Cannot read file: $fa: $!\n";
|
43
|
+
my $good = 0;
|
44
|
+
while(my $ln = <FA>){
|
45
|
+
next if $ln =~ /^;/;
|
46
|
+
chomp $ln;
|
47
|
+
if($ln =~ m/^>((\S+).*)/){ $good = (exists $li{$1} or exists $li{">$1"} or exists $li{$2} or exists $li{$ln}) }
|
48
|
+
elsif($ln =~ m/^>/){ $good=$o{r}; print STDERR "Warning: Non-cannonical defline, line $.: $ln\n" }
|
49
|
+
print "$ln\n" if (($good and not $o{r}) or ($o{r} and not $good));
|
50
|
+
}
|
51
|
+
close FA;
|
52
|
+
|
@@ -0,0 +1,28 @@
|
|
1
|
+
#!/usr/bin/env perl
|
2
|
+
|
3
|
+
use warnings;
|
4
|
+
use strict;
|
5
|
+
use Bio::SeqIO;
|
6
|
+
|
7
|
+
my $file = $ARGV[0];
|
8
|
+
my $min = $ARGV[1];
|
9
|
+
($file and $min) or die <<HELP
|
10
|
+
|
11
|
+
This script will filter a multi fastA file by length
|
12
|
+
|
13
|
+
Usage "perl $0 fastafile minlenght "
|
14
|
+
HELP
|
15
|
+
;
|
16
|
+
my $seq_in = Bio::SeqIO->new( -format => 'fasta',-file => $file);
|
17
|
+
|
18
|
+
while( my $seq1 = $seq_in->next_seq() ) {
|
19
|
+
|
20
|
+
my $id = $seq1->primary_id;
|
21
|
+
chomp $id;
|
22
|
+
my $seq = $seq1->seq;
|
23
|
+
chomp $seq;
|
24
|
+
my $lseq = length($seq);
|
25
|
+
if($lseq>=$min){
|
26
|
+
print ">$id","\n",$seq,"\n";
|
27
|
+
}
|
28
|
+
}
|