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$-methods.Rd +27 -0
- data/utils/enveomics/globals.mk +8 -0
- data/utils/enveomics/manifest.json +9 -0
- data/utils/index_metadata.rb +0 -0
- data/utils/plot-taxdist.R +0 -0
- data/utils/requirements.txt +19 -19
- metadata +242 -2
@@ -0,0 +1,60 @@
|
|
1
|
+
#!/usr/bin/env perl
|
2
|
+
#
|
3
|
+
# @author Luis M. Rodriguez-R
|
4
|
+
# @update Oct-07-2015
|
5
|
+
# @license artistic license 2.0
|
6
|
+
#
|
7
|
+
|
8
|
+
use warnings;
|
9
|
+
use strict;
|
10
|
+
|
11
|
+
my($file, $content, $stretch) = @ARGV;
|
12
|
+
$file or die <<HELP
|
13
|
+
|
14
|
+
Description:
|
15
|
+
Filter sequences by N-content and presence of long homopolymers.
|
16
|
+
Usage:
|
17
|
+
$0 sequences.fa [content [stretch]] > filtered.fa
|
18
|
+
Where:
|
19
|
+
sequences.fa Input file in FastA format
|
20
|
+
content A number between 0 and 1 indicating the maximum proportion of Ns
|
21
|
+
(1 to turn off, 0.5 by default)
|
22
|
+
stretch A number indicating the maximum number of consecutive identical
|
23
|
+
nucleotides allowed (0 to turn off, 100 by default)
|
24
|
+
filtered.fa Filtered set of sequences.
|
25
|
+
|
26
|
+
HELP
|
27
|
+
;
|
28
|
+
($content ||= 0.5)+=0;
|
29
|
+
($stretch ||= 100)+=0;
|
30
|
+
|
31
|
+
my $good = 0;
|
32
|
+
my $N = 0;
|
33
|
+
|
34
|
+
FASTA: {
|
35
|
+
local $/ = "\n>";
|
36
|
+
open FILE, "<", $file or die "I can not open the file: $file: $!\n";
|
37
|
+
SEQ: while(<FILE>){
|
38
|
+
$N++;
|
39
|
+
s/^;.*//gm;
|
40
|
+
s/>//g;
|
41
|
+
my($n,$s) = split /\n/, $_, 2;
|
42
|
+
(my $clean = $s) =~ s/[^ACTGN]//g;
|
43
|
+
if($content < 1){
|
44
|
+
(my $Ns = $clean) =~ s/[^N]//g;
|
45
|
+
next SEQ if length($Ns)>length($clean)*$content;
|
46
|
+
}
|
47
|
+
if($stretch > 0){
|
48
|
+
for my $nuc (qw(A C T G N)){
|
49
|
+
next SEQ if $clean =~ m/[$nuc]{$stretch}/;
|
50
|
+
}
|
51
|
+
}
|
52
|
+
print ">$n\n$s\n";
|
53
|
+
$good++;
|
54
|
+
}
|
55
|
+
close FILE;
|
56
|
+
print STDERR "Total sequences: $N\nAfter filtering: $good\n";
|
57
|
+
}
|
58
|
+
|
59
|
+
|
60
|
+
|
@@ -0,0 +1,92 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
# @author Luis M. Rodriguez-R
|
4
|
+
# @license artistic license 2.0
|
5
|
+
|
6
|
+
$:.push File.expand_path("../lib", __FILE__)
|
7
|
+
require "enveomics_rb/enveomics"
|
8
|
+
require "enveomics_rb/stat"
|
9
|
+
|
10
|
+
o = {q:false, completeness:nil, minlen:500, shuffle:true}
|
11
|
+
OptionParser.new do |opts|
|
12
|
+
opts.banner = "
|
13
|
+
Simulates incomplete (fragmented) drafts from complete genomes.
|
14
|
+
|
15
|
+
Usage: #{$0} [options]"
|
16
|
+
opts.separator ""
|
17
|
+
opts.separator "Mandatory"
|
18
|
+
opts.on("-i", "--in FILE",
|
19
|
+
"Path to the FastA file containing the complete sequences."
|
20
|
+
){ |v| o[:in] = v }
|
21
|
+
opts.on("-o", "--out FILE", "Path to the FastA to create."){ |v| o[:out] = v }
|
22
|
+
opts.on("-c", "--completeness FLOAT",
|
23
|
+
"Fraction of genome completeness to simulate from 0 to 1."
|
24
|
+
){ |v| o[:completeness] = v.to_f }
|
25
|
+
opts.separator ""
|
26
|
+
opts.separator "Options"
|
27
|
+
opts.on("-m", "--minlen INT",
|
28
|
+
"Minimum fragment length to report. By default: #{o[:minlen]}."
|
29
|
+
){ |v| o[:minlen] = v.to_i }
|
30
|
+
opts.on("-s", "--sorted", "Keep fragments sorted as in the input file. ",
|
31
|
+
"By default, fragments are shuffled."){ |v| o[:shuffle] = !v }
|
32
|
+
opts.on("-q", "--quiet", "Run quietly (no STDERR output)"){ o[:q] = true }
|
33
|
+
opts.on("-h", "--help", "Display this screen") do
|
34
|
+
puts opts
|
35
|
+
exit
|
36
|
+
end
|
37
|
+
opts.separator ""
|
38
|
+
end.parse!
|
39
|
+
abort "-i is mandatory" if o[:in].nil?
|
40
|
+
abort "-o is mandatory" if o[:out].nil?
|
41
|
+
abort "-c is mandatory" if o[:completeness].nil?
|
42
|
+
|
43
|
+
begin
|
44
|
+
# Read input sequences
|
45
|
+
g_id = []
|
46
|
+
g_seq = []
|
47
|
+
File.open(o[:in], "r") do |ifh|
|
48
|
+
id = ""
|
49
|
+
ifh.each_line do |ln|
|
50
|
+
if ln =~ /^>(\S*)/
|
51
|
+
g_id << $1
|
52
|
+
g_seq << ""
|
53
|
+
else
|
54
|
+
g_seq[g_seq.size-1] += ln.gsub(/[^A-Za-z]/,"")
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
# Fragment genomes
|
60
|
+
f = {}
|
61
|
+
binlen = [1, (o[:minlen].to_f/(1.5**2)).ceil].max
|
62
|
+
p = [0.001, [1.0, 1.0 - (o[:completeness]/1.25 + 0.1)].min].max
|
63
|
+
while not g_seq.empty?
|
64
|
+
id = g_id.shift
|
65
|
+
seq = g_seq.shift
|
66
|
+
gL = seq.length
|
67
|
+
while not seq.empty?
|
68
|
+
fL = [0, ((Enve::Stat.r_geom(p).to_f +
|
69
|
+
Enve::Stat.r_unif(-0.5,0.5))*binlen).round].max
|
70
|
+
f["#{f.size+1}_#{id}"] = seq[0,fL] if fL >= o[:minlen]
|
71
|
+
seq = seq[(fL+1) .. -1]
|
72
|
+
seq = "" if seq.nil?
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
# Save output
|
77
|
+
k = f.keys
|
78
|
+
k.shuffle! if o[:shuffle]
|
79
|
+
File.open(o[:out], "w") do |ofh|
|
80
|
+
k.each do |id|
|
81
|
+
ofh.puts ">#{id}"
|
82
|
+
ofh.puts f[id].gsub(/(\S{50})/, "\\1\n")
|
83
|
+
end
|
84
|
+
end
|
85
|
+
|
86
|
+
rescue => err
|
87
|
+
$stderr.puts "Exception: #{err}\n\n"
|
88
|
+
err.backtrace.each { |l| $stderr.puts l + "\n" }
|
89
|
+
err
|
90
|
+
end
|
91
|
+
|
92
|
+
|
@@ -0,0 +1,42 @@
|
|
1
|
+
#!/usr/bin/env perl
|
2
|
+
#
|
3
|
+
# @author Luis M Rodriguez-R
|
4
|
+
# @update Mar-23-2016
|
5
|
+
# @license artistic license 2.0
|
6
|
+
#
|
7
|
+
|
8
|
+
use warnings;
|
9
|
+
use strict;
|
10
|
+
|
11
|
+
$#ARGV>=0 or die "
|
12
|
+
Usage:
|
13
|
+
$0 seqs.fa... > gc.txt
|
14
|
+
|
15
|
+
seqs.fa One or more FastA files.
|
16
|
+
gc.txt A table with the G+C content of the sequences.
|
17
|
+
|
18
|
+
";
|
19
|
+
|
20
|
+
for my $fa (@ARGV){
|
21
|
+
open FA, "<", $fa or die "Cannot open file: $fa: $!\n";
|
22
|
+
my $def = "";
|
23
|
+
my $len = 0;
|
24
|
+
my $gc = 0;
|
25
|
+
while(<FA>){
|
26
|
+
next if /^;/;
|
27
|
+
if(m/^>(\S*)/){
|
28
|
+
print "$def\t".($gc/$len)."\n" if $len;
|
29
|
+
$def = $1;
|
30
|
+
$len = 0;
|
31
|
+
$gc = 0;
|
32
|
+
}else{
|
33
|
+
s/[^ACTGactg]//g;
|
34
|
+
$len += length $_;
|
35
|
+
s/[^GC]//g;
|
36
|
+
$gc += length $_;
|
37
|
+
}
|
38
|
+
}
|
39
|
+
print "$def\t".($gc/$len)."\n" if $len;
|
40
|
+
close FA;
|
41
|
+
}
|
42
|
+
|
@@ -0,0 +1,87 @@
|
|
1
|
+
#!/usr/bin/env perl
|
2
|
+
|
3
|
+
# Interpose sequences in FastA format from two files into one output file. If more than two files are
|
4
|
+
# provided, the script will interpose all the input files.
|
5
|
+
# Please note that this script will check for the consistency of the names (assuming a pair of related reads
|
6
|
+
# contains the same name varying only in a trailing slash (/) followed by a digit. If you want to turn this
|
7
|
+
# feature off just set the $eval_T variable to zero. If you want to decrease the sampling period (to speed
|
8
|
+
# the script up) or increase it (to make it more sensitive to errors) just change $eval_T accordingly.
|
9
|
+
#
|
10
|
+
# @author Luis M. Rodriguez-R
|
11
|
+
# @version 1.0
|
12
|
+
# @created Nov-27-2012
|
13
|
+
# @update Mar-23-2015
|
14
|
+
# @license artistic license 2.0
|
15
|
+
#
|
16
|
+
# Usage: FastQ.interpose.pl <output_fastq> <input_fastq_1> <input_fastq_2> [additional input files...]
|
17
|
+
|
18
|
+
use strict;
|
19
|
+
use warnings;
|
20
|
+
use Symbol;
|
21
|
+
|
22
|
+
my $HELP = <<HELP
|
23
|
+
Usage:
|
24
|
+
$0 <output_fasta> <input_fasta_1> <input_fasta_2> [additional input files...]
|
25
|
+
|
26
|
+
Where,
|
27
|
+
output_fasta : Output file
|
28
|
+
input_fasta_1 : First FastA file
|
29
|
+
input_fasta_2 : Second FastA file
|
30
|
+
... : Any additional FastA files (or none)
|
31
|
+
|
32
|
+
HELP
|
33
|
+
;
|
34
|
+
my $eval_T = 1000; # Period (in number of entries) of evaluation for consistency of the names.
|
35
|
+
# To turn off evaluation set to 0 (zero).
|
36
|
+
my $out = shift @ARGV;
|
37
|
+
my @in = @ARGV;
|
38
|
+
$/ = "\n>";
|
39
|
+
|
40
|
+
|
41
|
+
die $HELP unless $out and $#in >= 1;
|
42
|
+
open OUT, ">", $out or die "Unable to write on $out: $!\n";
|
43
|
+
print "Output file: $out\n";
|
44
|
+
|
45
|
+
my @in_fh = ();
|
46
|
+
|
47
|
+
for my $k (0 .. $#in) {
|
48
|
+
$in_fh[$k] = gensym;
|
49
|
+
open $in_fh[$k], "<", $in[$k] or die "Unable to read $in[$k]: $!\n";
|
50
|
+
print "Input file: $in[$k]\n";
|
51
|
+
}
|
52
|
+
|
53
|
+
my $i = 0;
|
54
|
+
my $frl;
|
55
|
+
LINE: while(1){
|
56
|
+
my $name = "";
|
57
|
+
print STDERR "\rEntry: $i " unless $i % 1000;
|
58
|
+
FILE: for my $k (0 .. $#in_fh){
|
59
|
+
my $ln = readline($in_fh[$k]);
|
60
|
+
last LINE if $k==0 and not defined $ln;
|
61
|
+
defined $ln or die "Impossible to read next entry ($.) from $in[$k]: $!\n";
|
62
|
+
$ln =~ s/^\>?/>/;
|
63
|
+
$ln =~ s/\>$//;
|
64
|
+
$ln =~ s/^;.*//gm;
|
65
|
+
if($eval_T and not $i % $eval_T){
|
66
|
+
unless($name){
|
67
|
+
$ln =~ m/^>(.*?)[\/ \\_]\d+/ or die "Impossible to evaluate names!\n offending entry:\n$ln\n";
|
68
|
+
$name = $1;
|
69
|
+
}
|
70
|
+
die "Inconsistent name!\n base name is $name\n offending entry is:\n$ln\n" unless $ln =~ /^>$name/;
|
71
|
+
}
|
72
|
+
unless($frl){
|
73
|
+
$ln =~ m/^>.*?\n(.*?)\n/ or die "Unexpected format!\n offending entry:\n$ln\n";
|
74
|
+
my $i = $ln;
|
75
|
+
$i =~ s/^>.*?\n//;
|
76
|
+
$i =~ s/\n//g;
|
77
|
+
$frl = length $i;
|
78
|
+
}
|
79
|
+
print OUT $ln;
|
80
|
+
}
|
81
|
+
$i++;
|
82
|
+
}
|
83
|
+
print "\rNumber of entries: $i \nFirst read length: $frl\n";
|
84
|
+
close OUT;
|
85
|
+
|
86
|
+
for my $k(0..$#in_fh){print "ALERT: The file $in[$k] contains trailing entries\n" if defined readline($in_fh[$k])}
|
87
|
+
|
@@ -0,0 +1,38 @@
|
|
1
|
+
#!/usr/bin/env perl
|
2
|
+
#
|
3
|
+
# @author Luis M Rodriguez-R
|
4
|
+
# @update Oct-07-2015
|
5
|
+
# @license artistic license 2.0
|
6
|
+
#
|
7
|
+
|
8
|
+
use warnings;
|
9
|
+
use strict;
|
10
|
+
|
11
|
+
$#ARGV>=0 or die "
|
12
|
+
Usage:
|
13
|
+
$0 seqs.fa... > length.txt
|
14
|
+
|
15
|
+
seqs.fa One or more FastA files.
|
16
|
+
length.txt A table with the lengths of the sequences.
|
17
|
+
|
18
|
+
";
|
19
|
+
|
20
|
+
for my $fa (@ARGV){
|
21
|
+
open FA, "<", $fa or die "Cannot open file: $fa: $!\n";
|
22
|
+
my $def = '';
|
23
|
+
my $len = 0;
|
24
|
+
while(<FA>){
|
25
|
+
next if /^;/;
|
26
|
+
if(m/^>(\S+)\s?/){
|
27
|
+
print "$def\t$len\n" if $def;
|
28
|
+
$def = $1;
|
29
|
+
$len = 0;
|
30
|
+
}else{
|
31
|
+
s/[^A-Za-z]//g;
|
32
|
+
$len+= length $_;
|
33
|
+
}
|
34
|
+
}
|
35
|
+
print "$def\t$len\n" if $def;
|
36
|
+
close FA;
|
37
|
+
}
|
38
|
+
|
@@ -0,0 +1,36 @@
|
|
1
|
+
#!/usr/bin/env perl
|
2
|
+
#
|
3
|
+
# @author Luis M Rodriguez-R
|
4
|
+
# @update Mar-17-2016
|
5
|
+
# @license artistic license 2.0
|
6
|
+
#
|
7
|
+
|
8
|
+
use warnings;
|
9
|
+
use strict;
|
10
|
+
|
11
|
+
$#ARGV>=1 or die "
|
12
|
+
Usage:
|
13
|
+
$0 outdir seqs.fa...
|
14
|
+
|
15
|
+
outdir Output directory for the individual files.
|
16
|
+
seqs.fa One or more FastA files.
|
17
|
+
|
18
|
+
";
|
19
|
+
|
20
|
+
my $dir = shift @ARGV;
|
21
|
+
|
22
|
+
for my $fa (@ARGV){
|
23
|
+
open FA, "<", $fa or die "Cannot open file: $fa: $!\n";
|
24
|
+
my $file = '';
|
25
|
+
while(<FA>){
|
26
|
+
next if /^;/;
|
27
|
+
if(m/^>(\S+)\s?/){
|
28
|
+
close ONE if $file;
|
29
|
+
$file = $dir."/".$1.".fasta";
|
30
|
+
open ONE, ">", $file or die "Cannot open file: $file: $!\n";
|
31
|
+
}
|
32
|
+
print ONE $_ if $file;
|
33
|
+
}
|
34
|
+
close ONE if $file;
|
35
|
+
}
|
36
|
+
|
@@ -0,0 +1,57 @@
|
|
1
|
+
#!/usr/bin/env perl
|
2
|
+
#
|
3
|
+
# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
|
4
|
+
# @update Dec-22-2015
|
5
|
+
# @license artistic license 2.0
|
6
|
+
#
|
7
|
+
use strict;
|
8
|
+
use warnings;
|
9
|
+
use List::Util qw/sum min max/;
|
10
|
+
|
11
|
+
my ($seqs, $minlen) = @ARGV;
|
12
|
+
$seqs or die "
|
13
|
+
Description:
|
14
|
+
Calculates the quartiles of the length in a set of sequences. The Q2 is
|
15
|
+
also known as the median. Q0 is the minimum length, and Q4 is the maximum
|
16
|
+
length. It also calculates TOTAL, the added length of the sequences in
|
17
|
+
the file, and AVG, the average length.
|
18
|
+
|
19
|
+
Usage:
|
20
|
+
$0 seqs.fa[ minlen]
|
21
|
+
|
22
|
+
seqs.fa A FastA file containing the sequences.
|
23
|
+
minlen (optional) The minimum length to take into consideration.
|
24
|
+
By default: 0.
|
25
|
+
|
26
|
+
";
|
27
|
+
$minlen ||= 0;
|
28
|
+
|
29
|
+
# Read files
|
30
|
+
my @len = ();
|
31
|
+
open FA, "<", $seqs or die "Cannot open file: $seqs: $!\n";
|
32
|
+
my $def = '';
|
33
|
+
my $len = 0;
|
34
|
+
while(<FA>){
|
35
|
+
next if /^;/;
|
36
|
+
if(m/^>(\S+)\s?/){
|
37
|
+
push(@len, int($len)) if $def and not $len<$minlen;
|
38
|
+
$def = $1;
|
39
|
+
$len = 0;
|
40
|
+
}else{
|
41
|
+
s/[^A-Za-z]//g;
|
42
|
+
$len+= length $_;
|
43
|
+
}
|
44
|
+
}
|
45
|
+
push(@len, int($len)) if $def and not $len<$minlen;
|
46
|
+
close FA;
|
47
|
+
|
48
|
+
# Sort and estimates quantiles
|
49
|
+
@len = sort { $a <=> $b } @len;
|
50
|
+
for my $q (0 .. 4){
|
51
|
+
my $ii = int(my $i = $#len*$q/4);
|
52
|
+
print "Q$q: ".($i==$ii ? $len[$i] : ($len[$ii]+$len[$ii+1])/2 )."\n";
|
53
|
+
}
|
54
|
+
my $sum = sum @len;
|
55
|
+
print "N: ".scalar(@len)."\n";
|
56
|
+
print "TOTAL: $sum\n";
|
57
|
+
print "AVG: ".($sum/scalar(@len))."\n";
|
@@ -0,0 +1,65 @@
|
|
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
|
+
Renames a set of sequences in FastA format.
|
15
|
+
|
16
|
+
.Usage: $0 [options] list.txt seqs.fa > renamed.fa
|
17
|
+
|
18
|
+
[options]
|
19
|
+
-f Filter list. Ignores sequences NOT present in the list.
|
20
|
+
-q Runs quietly.
|
21
|
+
-h Prints this message and exits.
|
22
|
+
|
23
|
+
[mandatory]
|
24
|
+
list.txt Tab-delimited list of sequences, with the original ID in the
|
25
|
+
first column and the ID to use in the second.
|
26
|
+
seqs.fa FastA file containing the superset of sequences.
|
27
|
+
renamed.fa FastA file to be created.
|
28
|
+
|
29
|
+
" }
|
30
|
+
|
31
|
+
my %o=();
|
32
|
+
getopts('fhq', \%o);
|
33
|
+
my($list, $fa) = @ARGV;
|
34
|
+
($list and $fa) or &HELP_MESSAGE;
|
35
|
+
$o{h} and &HELP_MESSAGE;
|
36
|
+
|
37
|
+
print STDERR "Reading list.\n" unless $o{q};
|
38
|
+
open LI, "<", $list or die "Cannot read file: $list: $!\n";
|
39
|
+
my %li = map { my $l=$_; chomp $l; my @r=split(/\t/,$l); $r[0] => $r[1] } <LI>;
|
40
|
+
close LI;
|
41
|
+
|
42
|
+
print STDERR "Renaming FastA.\n" unless $o{q};
|
43
|
+
open FA, "<", $fa or die "Cannot read file: $fa: $!\n";
|
44
|
+
my $good = 0;
|
45
|
+
while(my $ln = <FA>){
|
46
|
+
next if $ln =~ /^;/;
|
47
|
+
chomp $ln;
|
48
|
+
if($ln =~ m/^>((\S+).*)/){
|
49
|
+
my $rep=0;
|
50
|
+
$rep = ">".$li{$ln} if exists $li{$ln};
|
51
|
+
$rep = ">".$li{$1} if exists $li{$1} and not $rep;
|
52
|
+
$rep = ">".$li{">$1"} if exists $li{">$1"} and not $rep;
|
53
|
+
$rep = ">".$li{$2} if exists $li{$2} and not $rep;
|
54
|
+
if($rep){
|
55
|
+
$ln = $rep;
|
56
|
+
$good = 1;
|
57
|
+
}
|
58
|
+
}elsif($ln =~ m/^>/){
|
59
|
+
$good=0;
|
60
|
+
print STDERR "Warning: Non-cannonical defline, line $.: $ln\n";
|
61
|
+
}
|
62
|
+
print "$ln\n" if $good or not $o{f};
|
63
|
+
}
|
64
|
+
close FA;
|
65
|
+
|