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 +1,362 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
# @author Luis M. Rodriguez-R
|
4
|
+
# @license Artistic-2.0
|
5
|
+
|
6
|
+
require "optparse"
|
7
|
+
require "tmpdir"
|
8
|
+
has_rest_client = true
|
9
|
+
has_sqlite3 = true
|
10
|
+
begin
|
11
|
+
require "rubygems"
|
12
|
+
require "restclient"
|
13
|
+
rescue LoadError
|
14
|
+
has_rest_client = false
|
15
|
+
end
|
16
|
+
begin
|
17
|
+
require "sqlite3"
|
18
|
+
rescue LoadError
|
19
|
+
has_sqlite3 = false
|
20
|
+
end
|
21
|
+
|
22
|
+
o = {win:1000, step:200, id:70, len:700, correct:true, hits:50, q:false, bin:"",
|
23
|
+
program:"blast+", thr:1, dec:2, auto:false, lookupfirst:false,
|
24
|
+
dbregions:true, dbrbm: true, min_actg:0.95}
|
25
|
+
ARGV << "-h" if ARGV.size==0
|
26
|
+
OptionParser.new do |opts|
|
27
|
+
opts.banner = "
|
28
|
+
Calculates the Average Nucleotide Identity between two genomes.
|
29
|
+
|
30
|
+
Usage: #{$0} [options]"
|
31
|
+
opts.separator ""
|
32
|
+
opts.separator "Mandatory"
|
33
|
+
opts.on("-1", "--seq1 FILE",
|
34
|
+
"Path to the FastA file containing the genome 1."){ |v| o[:seq1] = v }
|
35
|
+
opts.on("-2", "--seq2 FILE",
|
36
|
+
"Path to the FastA file containing the genome 2."){ |v| o[:seq2] = v }
|
37
|
+
if has_rest_client
|
38
|
+
opts.separator " Alternatively, you can supply a NCBI-acc with the " +
|
39
|
+
"format ncbi:CP014272 instead of files."
|
40
|
+
else
|
41
|
+
opts.separator " Install rest-client to enable NCBI-acc support."
|
42
|
+
end
|
43
|
+
opts.separator ""
|
44
|
+
opts.separator "Search Options"
|
45
|
+
opts.on("-w", "--win INT",
|
46
|
+
"Window size in the ANI calculation (in bp). By default: " +
|
47
|
+
"#{o[:win].to_s}."){ |v| o[:win] = v.to_i }
|
48
|
+
opts.on("-s", "--step INT",
|
49
|
+
"Step size in the ANI calculation (in bp). By default: " +
|
50
|
+
"#{o[:step].to_s}."){ |v| o[:step] = v.to_i }
|
51
|
+
opts.on("-l", "--len INT",
|
52
|
+
"Minimum alignment length (in bp). By default: #{o[:len]}."
|
53
|
+
){ |v| o[:len] = v.to_i }
|
54
|
+
opts.on("-i", "--id NUM",
|
55
|
+
"Minimum alignment identity (in %). By default: #{o[:id]}."
|
56
|
+
){ |v| o[:id] = v.to_f }
|
57
|
+
opts.on("-n", "--hits INT",
|
58
|
+
"Minimum number of hits. By default: #{o[:hits]}."
|
59
|
+
){ |v| o[:hits] = v.to_i }
|
60
|
+
opts.on("-N", "--nocorrection",
|
61
|
+
"Report values without post-hoc correction."){ |v| o[:correct] = false }
|
62
|
+
opts.on("--min-actg FLOAT",
|
63
|
+
"Minimum fraction of ACTGN in the sequences before assuming proteins.",
|
64
|
+
"By default: #{o[:min_actg]}."
|
65
|
+
){ |v| o[:min_actg] = v.to_f }
|
66
|
+
opts.separator ""
|
67
|
+
opts.separator "Software Options"
|
68
|
+
opts.on("-b", "--bin DIR",
|
69
|
+
"Path to the directory containing the binaries of the search program."
|
70
|
+
){ |v| o[:bin] = v }
|
71
|
+
opts.on("-p", "--program STR",
|
72
|
+
"Search program to be used. One of: blast+ (default), blast, blat."
|
73
|
+
){ |v| o[:program] = v }
|
74
|
+
opts.on("-t", "--threads INT",
|
75
|
+
"Number of parallel threads to be used. By default: #{o[:thr]}."
|
76
|
+
){ |v| o[:thr] = v.to_i }
|
77
|
+
opts.separator ""
|
78
|
+
opts.separator "SQLite3 Options"
|
79
|
+
opts.on("-S", "--sqlite3 FILE",
|
80
|
+
"Path to the SQLite3 database to create (or update) with the results."
|
81
|
+
){ |v| o[:sqlite3] = v }
|
82
|
+
opts.separator " Install sqlite3 gem to enable database support." unless
|
83
|
+
has_sqlite3
|
84
|
+
opts.on("--name1 STR",
|
85
|
+
"Name of --seq1 to use in --sqlite3. By default determined by filename."
|
86
|
+
){ |v| o[:seq1name] = v }
|
87
|
+
opts.on("--name2 STR",
|
88
|
+
"Name of --seq2 to use in --sqlite3. By default determined by filename."
|
89
|
+
){ |v| o[:seq2name] = v }
|
90
|
+
opts.on("--[no-]save-regions",
|
91
|
+
"Save (or don't save) the fragments in the --sqlite3 database.",
|
92
|
+
"By default: #{o[:dbregions]}."){ |v| o[:dbregions] = !!v }
|
93
|
+
opts.on("--[no-]save-rbm",
|
94
|
+
"Save (or don't save) the reciprocal best matches in the --sqlite3 db.",
|
95
|
+
"By default: #{o[:dbrbm]}."){ |v| o[:dbrbm] = !!v }
|
96
|
+
opts.on("--lookup-first",
|
97
|
+
"Indicates if the ANI should be looked up first in the database.",
|
98
|
+
"Requires --sqlite3, --auto, --name1, and --name2.",
|
99
|
+
"Incompatible with --res, --tab, and --out."){ |v| o[:lookupfirst] = v }
|
100
|
+
opts.separator ""
|
101
|
+
opts.separator "Other Output Options"
|
102
|
+
opts.on("-d", "--dec INT",
|
103
|
+
"Decimal positions to report. By default: #{o[:dec]}"
|
104
|
+
){ |v| o[:dec] = v.to_i }
|
105
|
+
opts.on("-o", "--out FILE",
|
106
|
+
"Saves a file describing the alignments used for two-way ANI."
|
107
|
+
){ |v| o[:out] = v }
|
108
|
+
opts.on("-r", "--res FILE",
|
109
|
+
"Saves a file with the final results."){ |v| o[:res] = v }
|
110
|
+
opts.on("-T", "--tab FILE",
|
111
|
+
"Saves a file with the final two-way results in a tab-delimited form.",
|
112
|
+
"The columns are (in that order):",
|
113
|
+
"ANI, standard deviation, fragments used, fragments in the smallest genome."
|
114
|
+
){ |v| o[:tab]=v }
|
115
|
+
opts.on("-a", "--auto",
|
116
|
+
"ONLY outputs the ANI value in STDOUT (or nothing, if calculation fails)."
|
117
|
+
){ o[:auto] = true }
|
118
|
+
opts.on("-q", "--quiet", "Run quietly (no STDERR output)"){ o[:q] = true }
|
119
|
+
opts.on("-h", "--help", "Display this screen") do
|
120
|
+
puts opts
|
121
|
+
exit
|
122
|
+
end
|
123
|
+
opts.separator ""
|
124
|
+
end.parse!
|
125
|
+
abort "-1 is mandatory" if o[:seq1].nil?
|
126
|
+
abort "-2 is mandatory" if o[:seq2].nil?
|
127
|
+
abort "SQLite3 requested (-S) but sqlite3 not supported. First install gem " +
|
128
|
+
"sqlite3." unless o[:sqlite3].nil? or has_sqlite3
|
129
|
+
abort "Step size must be smaller than window size." if o[:step] > o[:win]
|
130
|
+
o[:bin] = o[:bin]+"/" if o[:bin].size > 0
|
131
|
+
if o[:lookupfirst]
|
132
|
+
abort "--lookup-first needs --sqlite3" if o[:sqlite3].nil?
|
133
|
+
abort "--lookup-first requires --auto" unless o[:auto]
|
134
|
+
abort "--lookup-first requires --name1" if o[:seq1name].nil?
|
135
|
+
abort "--lookup-first requires --name2" if o[:seq2name].nil?
|
136
|
+
abort "--lookup-first conflicts with --res" unless o[:res].nil?
|
137
|
+
abort "--lookup-first conflicts with --tab" unless o[:tab].nil?
|
138
|
+
abort "--lookup-first conflicts with --out" unless o[:out].nil?
|
139
|
+
end
|
140
|
+
|
141
|
+
# Create SQLite3 file
|
142
|
+
unless o[:sqlite3].nil?
|
143
|
+
$stderr.puts "Accessing SQLite3 file: #{o[:sqlite3]}." unless o[:q]
|
144
|
+
sqlite_db = SQLite3::Database.new o[:sqlite3]
|
145
|
+
sqlite_db.execute "create table if not exists regions( " +
|
146
|
+
"seq varchar(256), id int, source varchar(256), `start` int," +
|
147
|
+
" `end` int )"
|
148
|
+
sqlite_db.execute "create table if not exists rbm( seq1 varchar(256), " +
|
149
|
+
"seq2 varchar(256), id1 int, id2 int, id float, evalue float, " +
|
150
|
+
"bitscore float )"
|
151
|
+
sqlite_db.execute "create table if not exists ani( seq1 varchar(256), " +
|
152
|
+
"seq2 varchar(256), ani float, sd float, n int, omega int )"
|
153
|
+
end
|
154
|
+
|
155
|
+
# Look-up first
|
156
|
+
if o[:lookupfirst]
|
157
|
+
val = sqlite_db.execute "select ani from ani where seq1=? and seq2=?",
|
158
|
+
[o[:seq1name], o[:seq2name]]
|
159
|
+
val = sqlite_db.execute "select ani from ani where seq1=? and seq2=?",
|
160
|
+
[o[:seq2name], o[:seq1name]] if val.empty?
|
161
|
+
unless val.empty?
|
162
|
+
puts val.first.first
|
163
|
+
exit
|
164
|
+
end
|
165
|
+
end
|
166
|
+
|
167
|
+
Dir.mktmpdir do |dir|
|
168
|
+
$stderr.puts "Temporal directory: #{dir}." unless o[:q]
|
169
|
+
|
170
|
+
# Create databases.
|
171
|
+
$stderr.puts "Creating databases." unless o[:q]
|
172
|
+
minfrg = nil
|
173
|
+
seq_names = []
|
174
|
+
seq_len = {}
|
175
|
+
actg_cnt = {}
|
176
|
+
[:seq1, :seq2].each do |seq|
|
177
|
+
abort "GIs are no longer supported by NCBI. Please use NCBI-acc instead" if
|
178
|
+
/^gi:/.match(o[seq])
|
179
|
+
acc = /^ncbi:(\S+)/.match(o[seq])
|
180
|
+
if not acc.nil?
|
181
|
+
abort "NCBI-acc requested but rest-client not supported. First " +
|
182
|
+
"install gem rest-client." unless has_rest_client
|
183
|
+
response = RestClient.get(
|
184
|
+
"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi",
|
185
|
+
{params:{db:"nuccore",rettype:"fasta",id:acc[1],idtype:"acc"}})
|
186
|
+
abort "Unable to reach NCBI EUtils, error code " +
|
187
|
+
response.code.to_s + "." unless response.code == 200
|
188
|
+
o[seq] = "#{dir}/ncbi-#{seq.to_s}.fa"
|
189
|
+
fo = File.open(o[seq], "w")
|
190
|
+
fo.puts response.to_str
|
191
|
+
fo.close
|
192
|
+
seq_names << ( o[ "#{seq}name".to_sym ].nil? ?
|
193
|
+
"ncbi:#{acc[1]}" : o[ "#{seq}name".to_sym ] )
|
194
|
+
else
|
195
|
+
seq_names << ( o[ "#{seq}name".to_sym ].nil? ?
|
196
|
+
File.basename(o[seq], ".fna") : o[ "#{seq}name".to_sym ] )
|
197
|
+
end
|
198
|
+
$stderr.puts " Reading FastA file: #{o[seq]}" unless o[:q]
|
199
|
+
sqlite_db.execute("delete from regions where seq=?",
|
200
|
+
[seq_names.last]) unless o[:sqlite3].nil?
|
201
|
+
buffer = ""
|
202
|
+
frgs = 0
|
203
|
+
seq_len[seq] = 0
|
204
|
+
actg_cnt[seq] = 0
|
205
|
+
seqs = 0
|
206
|
+
disc = 0
|
207
|
+
seqn = ""
|
208
|
+
from = 1
|
209
|
+
fi = File.open(o[seq], "r")
|
210
|
+
fo = File.open("#{dir}/#{seq.to_s}.fa", "w")
|
211
|
+
fi.each_line do |ln|
|
212
|
+
if ln =~ /^>(\S+)/
|
213
|
+
seqs += 1
|
214
|
+
disc += buffer.size
|
215
|
+
buffer = ""
|
216
|
+
seqn = $1
|
217
|
+
from = 1
|
218
|
+
else
|
219
|
+
ln.gsub!(/[^A-Za-z]/, '')
|
220
|
+
seq_len[seq] += ln.length
|
221
|
+
actg_cnt[seq] += ln.gsub(/[^ACTGN]/,"").length
|
222
|
+
buffer = buffer + ln
|
223
|
+
while buffer.size > o[:win]
|
224
|
+
seq_i = buffer[0, o[:win]]
|
225
|
+
if seq_i =~ /^N+$/
|
226
|
+
disc += seq_i.size
|
227
|
+
else
|
228
|
+
frgs += 1
|
229
|
+
fo.puts ">#{frgs}"
|
230
|
+
fo.puts seq_i
|
231
|
+
sqlite_db.execute("insert into regions values(?,?,?,?,?)",
|
232
|
+
[seq_names.last, frgs, seqn, from, from+o[:win]]) if
|
233
|
+
not o[:sqlite3].nil? and o[:dbregions]
|
234
|
+
end
|
235
|
+
buffer = buffer[o[:step] .. -1]
|
236
|
+
from += o[:win]
|
237
|
+
end
|
238
|
+
end
|
239
|
+
end
|
240
|
+
fi.close
|
241
|
+
fo.close
|
242
|
+
actg_frx = actg_cnt[seq].to_f/seq_len[seq].to_f
|
243
|
+
abort "Input sequences appear to be proteins " +
|
244
|
+
"(ACTGN fraction: %.2f%%)." % (actg_frx*100) if actg_frx < o[:min_actg]
|
245
|
+
$stderr.puts " Created #{frgs} fragments from #{seqs} sequences, " +
|
246
|
+
"discarded #{disc} bp." unless o[:q]
|
247
|
+
minfrg ||= frgs
|
248
|
+
minfrg = frgs if minfrg > frgs
|
249
|
+
case o[:program].downcase
|
250
|
+
when "blast"
|
251
|
+
`"#{o[:bin]}formatdb" -i "#{dir}/#{seq.to_s}.fa" -p F`
|
252
|
+
when "blast+"
|
253
|
+
`"#{o[:bin]}makeblastdb" -in "#{dir}/#{seq.to_s}.fa" -dbtype nucl`
|
254
|
+
when "blat"
|
255
|
+
# Nothing to do
|
256
|
+
else
|
257
|
+
abort "Unsupported program: #{o[:program]}."
|
258
|
+
end
|
259
|
+
end # [:seq1, :seq2].each
|
260
|
+
|
261
|
+
# Best-hits.
|
262
|
+
$stderr.puts "Running one-way comparisons." unless o[:q]
|
263
|
+
rbh = []
|
264
|
+
id2 = 0
|
265
|
+
sq2 = 0
|
266
|
+
n2 = 0
|
267
|
+
unless o[:sqlite3].nil?
|
268
|
+
sqlite_db.execute "delete from rbm where seq1=? and seq2=?", seq_names
|
269
|
+
sqlite_db.execute "delete from ani where seq1=? and seq2=?", seq_names
|
270
|
+
end
|
271
|
+
unless o[:out].nil?
|
272
|
+
fo = File.open(o[:out], "w")
|
273
|
+
fo.puts %w(identity aln.len mismatch gap.open evalue bitscore).join("\t")
|
274
|
+
end
|
275
|
+
res = File.open(o[:res], "w") unless o[:res].nil?
|
276
|
+
[1,2].each do |i|
|
277
|
+
qry_seen = []
|
278
|
+
q = "#{dir}/seq#{i}.fa"
|
279
|
+
s = "#{dir}/seq#{i==1?2:1}.fa"
|
280
|
+
case o[:program].downcase
|
281
|
+
when "blast"
|
282
|
+
`"#{o[:bin]}blastall" -p blastn -d "#{s}" -i "#{q}" \
|
283
|
+
-F F -v 1 -b 1 -a #{o[:thr]} -m 8 -o "#{dir}/#{i}.tab"`
|
284
|
+
when "blast+"
|
285
|
+
`"#{o[:bin]}blastn" -db "#{s}" -query "#{q}" \
|
286
|
+
-dust no -max_target_seqs 1 \
|
287
|
+
-num_threads #{o[:thr]} -outfmt 6 -out "#{dir}/#{i}.tab"`
|
288
|
+
when "blat"
|
289
|
+
`#{o[:bin]}blat "#{s}" "#{q}" -out=blast8 "#{dir}/#{i}.tab"`
|
290
|
+
else
|
291
|
+
abort "Unsupported program: #{o[:program]}."
|
292
|
+
end
|
293
|
+
fh = File.open("#{dir}/#{i}.tab", "r")
|
294
|
+
id = 0
|
295
|
+
sq = 0
|
296
|
+
n = 0
|
297
|
+
fh.each_line do |ln|
|
298
|
+
ln.chomp!
|
299
|
+
row = ln.split(/\t/)
|
300
|
+
if qry_seen[ row[0].to_i ].nil? and row[3].to_i >= o[:len] and
|
301
|
+
row[2].to_f >= o[:id]
|
302
|
+
qry_seen[ row[0].to_i ] = 1
|
303
|
+
identity_corr = 100 - (100-row[2].to_f)/(o[:correct] ? 0.8621 : 1.0)
|
304
|
+
id += identity_corr
|
305
|
+
sq += identity_corr ** 2
|
306
|
+
n += 1
|
307
|
+
if i==1
|
308
|
+
rbh[ row[0].to_i ] = row[1].to_i
|
309
|
+
else
|
310
|
+
if !rbh[ row[1].to_i ].nil? and rbh[ row[1].to_i ]==row[0].to_i
|
311
|
+
id2 += identity_corr
|
312
|
+
sq2 += identity_corr ** 2
|
313
|
+
n2 += 1
|
314
|
+
fo.puts [identity_corr,row[3..5],
|
315
|
+
row[10..11]].join("\t") unless o[:out].nil?
|
316
|
+
sqlite_db.execute("insert into rbm values(?,?,?,?,?,?,?)",
|
317
|
+
seq_names + [row[1], row[0], row[2], row[10], row[11]]
|
318
|
+
) if not o[:sqlite3].nil? and o[:dbrbm]
|
319
|
+
end
|
320
|
+
end
|
321
|
+
end
|
322
|
+
end
|
323
|
+
fh.close
|
324
|
+
if n < o[:hits]
|
325
|
+
puts "Insuffient hits to estimate one-way ANI: #{n}." unless o[:auto]
|
326
|
+
res.puts "Insufficient hits to estimate one-way ANI: #{n}" unless
|
327
|
+
o[:res].nil?
|
328
|
+
else
|
329
|
+
printf "! One-way ANI %d: %.#{o[:dec]}f%% (SD: %.#{o[:dec]}f%%), " +
|
330
|
+
"from %i fragments.\n", i, id/n, (sq/n - (id/n)**2)**0.5, n unless
|
331
|
+
o[:auto]
|
332
|
+
res.puts sprintf "<b>One-way ANI %d:</b> %.#{o[:dec]}f%% " +
|
333
|
+
"(SD: %.#{o[:dec]}f%%), from %i fragments.<br/>", i, id/n,
|
334
|
+
(sq/n - (id/n)**2)**0.5, n unless o[:res].nil?
|
335
|
+
end
|
336
|
+
end # [1,2].each
|
337
|
+
if n2 < o[:hits]
|
338
|
+
puts "Insufficient hits to estimate two-way ANI: #{n2}" unless o[:auto]
|
339
|
+
res.puts "Insufficient hits to estimate two-way ANI: #{n2}" unless
|
340
|
+
o[:res].nil?
|
341
|
+
else
|
342
|
+
ani = id2/n2
|
343
|
+
ani_sd = (sq2/n2 - (id2/n2)**2)**0.5
|
344
|
+
printf "! Two-way ANI : %.#{o[:dec]}f%% (SD: %.#{o[:dec]}f%%), " +
|
345
|
+
"from %i fragments.\n", ani, ani_sd, n2 unless o[:auto]
|
346
|
+
res.puts sprintf "<b>Two-way ANI:</b> %.#{o[:dec]}f%% " +
|
347
|
+
"(SD: %.#{o[:dec]}f%%), from %i fragments.<br/>",
|
348
|
+
ani, ani_sd, n2 unless o[:res].nil?
|
349
|
+
unless o[:tab].nil?
|
350
|
+
tab = File.open(o[:tab], "w")
|
351
|
+
tab.printf "%.#{o[:dec]}f\t%.#{o[:dec]}f\t%i\t%i\n",
|
352
|
+
ani, ani_sd, n2, minfrg
|
353
|
+
tab.close
|
354
|
+
end
|
355
|
+
sqlite_db.execute("insert into ani values(?,?,?,?,?,?)",
|
356
|
+
seq_names + [ani, ani_sd, n2, minfrg]) unless o[:sqlite3].nil?
|
357
|
+
puts ani if o[:auto]
|
358
|
+
end
|
359
|
+
res.close unless o[:res].nil?
|
360
|
+
fo.close unless o[:out].nil?
|
361
|
+
end
|
362
|
+
|
@@ -0,0 +1,103 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
#
|
4
|
+
# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
|
5
|
+
# @license artistic license 2.0
|
6
|
+
#
|
7
|
+
|
8
|
+
$:.push File.expand_path(File.dirname(__FILE__) + "/lib")
|
9
|
+
require "enveomics_rb/remote_data"
|
10
|
+
use "nokogiri"
|
11
|
+
|
12
|
+
#================================[ Options parsing ]
|
13
|
+
o = {
|
14
|
+
:q=>false, :gis=>[], :dbfrom=>"nuccore", :header=>true,
|
15
|
+
:exact_gi=>false, :no_nil=>false, :ret=>"ScientificName",
|
16
|
+
:ranks=>%w(superkingdom phylum class order family genus species)}
|
17
|
+
OptionParser.new do |opt|
|
18
|
+
opt.banner = "
|
19
|
+
Maps a list of NCBI GIs to their corresponding taxonomy using the NCBI
|
20
|
+
EUtilities. Avoid using this script on millions of entries at a time, since
|
21
|
+
each entry elicits two requests to NCBI's servers.
|
22
|
+
|
23
|
+
*IMPORTANT NOTE*: NCBI is phasing out support for GIs. Please use acc.ver
|
24
|
+
instead with NCBIacc2tax.rb.
|
25
|
+
|
26
|
+
Usage: #{$0} [options]".gsub(/^ +/,"")
|
27
|
+
opt.separator ""
|
28
|
+
opt.on("-g", "--gis GI1,GI2,...", Array,
|
29
|
+
"Comma-separated list of GIs. Required unless -i is passed."
|
30
|
+
){ |v| o[:gis]=v }
|
31
|
+
opt.on("-i", "--infile FILE",
|
32
|
+
"Raw text file containing the list of GIs, one per line.",
|
33
|
+
"Required unless -g is passed."){ |v| o[:infile]=v }
|
34
|
+
opt.on("-p", "--protein",
|
35
|
+
"Use if the GIs are proteins. Otherwise, GIs are assumed to be from " +
|
36
|
+
"the Nuccore Database."){ o[:dbfrom]="protein" }
|
37
|
+
opt.on("-r", "--ranks RANK1,RANK2,...", Array,
|
38
|
+
"Taxonomic ranks to report. By default: #{o[:ranks].join(",")}."
|
39
|
+
){ |v| o[:ranks]=v }
|
40
|
+
opt.on("-n", "--noheader",
|
41
|
+
"Do not include a header in the output."){ o[:header]=false }
|
42
|
+
opt.on("-t", "--taxids",
|
43
|
+
"Return Taxonomy IDs instead of scientific names."){ o[:ret]="TaxId" }
|
44
|
+
opt.on("--exact-gi",
|
45
|
+
"Returns only taxonomy associated with the exact GI passed.",
|
46
|
+
"By default, it attempts to update accession versions if possible."
|
47
|
+
){ |v| o[:exact_gi]=v }
|
48
|
+
opt.on("--ignore-missing",
|
49
|
+
"Does not report missing GIs in the output file.",
|
50
|
+
"By default, it reports GI and empty values for all other columns."
|
51
|
+
){ |v| o[:no_nil]=v }
|
52
|
+
opt.on("-q", "--quiet", "Run quietly."){ |v| o[:q]=true }
|
53
|
+
opt.on("-h", "--help","Display this screen") do
|
54
|
+
puts opt
|
55
|
+
exit
|
56
|
+
end
|
57
|
+
opt.separator ""
|
58
|
+
end.parse!
|
59
|
+
|
60
|
+
#================================[ Functions ]
|
61
|
+
def gi2taxid(db, gi)
|
62
|
+
doc = Nokogiri::XML( RemoteData.elink({:dbfrom=>db,
|
63
|
+
:db=>"taxonomy", :id=>gi}) )
|
64
|
+
doc.at_xpath("/eLinkResult/LinkSet/LinkSetDb/Link/Id")
|
65
|
+
end
|
66
|
+
#================================[ Main ]
|
67
|
+
begin
|
68
|
+
o[:gis] += File.readlines(o[:infile]).map{ |l| l.chomp } unless
|
69
|
+
o[:infile].nil?
|
70
|
+
o[:ranks].map!{ |r| r.downcase }
|
71
|
+
puts (["GI", "TaxId"] + o[:ranks].map{ |r| r.capitalize }).join("\t") if
|
72
|
+
o[:header]
|
73
|
+
o[:gis].each do |gi|
|
74
|
+
taxid = gi2taxid(o[:dbfrom], gi)
|
75
|
+
status = ""
|
76
|
+
if taxid.nil? and not o[:exact_gi]
|
77
|
+
new_gi, status = RemoteData.update_gi(o[:dbfrom], gi)
|
78
|
+
taxid = gi2taxid(o[:dbfrom], new_gi) unless new_gi.nil?
|
79
|
+
end
|
80
|
+
if taxid.nil?
|
81
|
+
warn "Cannot find link to taxonomy: #{gi} #{status}"
|
82
|
+
puts ([gi, ""] + o[:ranks].map{ |i| "" }).join("\t") unless o[:no_nil]
|
83
|
+
next
|
84
|
+
end
|
85
|
+
taxonomy = {}
|
86
|
+
unless taxid.nil?
|
87
|
+
doc = Nokogiri::XML( RemoteData.efetch({:db=>"taxonomy",
|
88
|
+
:id=>taxid.content}) )
|
89
|
+
taxonomy[ doc.at_xpath("/TaxaSet/Taxon/Rank").content ] =
|
90
|
+
doc.at_xpath("/TaxaSet/Taxon/#{o[:ret]}").content
|
91
|
+
doc.xpath("/TaxaSet/Taxon/LineageEx/Taxon").each do |taxon|
|
92
|
+
taxonomy[ taxon.at_xpath("./Rank").content ] =
|
93
|
+
taxon.at_xpath("./#{o[:ret]}").content
|
94
|
+
end
|
95
|
+
end
|
96
|
+
puts ([gi, taxid.content] +
|
97
|
+
o[:ranks].map{ |rank| taxonomy[ rank ] ||= "" }).join("\t")
|
98
|
+
end
|
99
|
+
rescue => err
|
100
|
+
$stderr.puts "Exception: #{err}\n\n"
|
101
|
+
err.backtrace.each { |l| $stderr.puts l + "\n" }
|
102
|
+
err
|
103
|
+
end
|