bio 0.7.0
Sign up to get free protection for your applications and to get access to all the features.
- data/bin/bioruby +107 -0
- data/bin/br_biofetch.rb +59 -0
- data/bin/br_bioflat.rb +294 -0
- data/bin/br_biogetseq.rb +57 -0
- data/bin/br_pmfetch.rb +431 -0
- data/doc/BioRuby.rd.ja +225 -0
- data/doc/Changes-0.7.rd +236 -0
- data/doc/Design.rd.ja +341 -0
- data/doc/KEGG_API.rd +1437 -0
- data/doc/KEGG_API.rd.ja +1399 -0
- data/doc/TODO.rd.ja +138 -0
- data/doc/Tutorial.rd +1138 -0
- data/doc/Tutorial.rd.ja +2110 -0
- data/etc/bioinformatics/seqdatabase.ini +210 -0
- data/lib/bio.rb +256 -0
- data/lib/bio/alignment.rb +1906 -0
- data/lib/bio/appl/bl2seq/report.rb +350 -0
- data/lib/bio/appl/blast.rb +269 -0
- data/lib/bio/appl/blast/format0.rb +1402 -0
- data/lib/bio/appl/blast/format8.rb +95 -0
- data/lib/bio/appl/blast/report.rb +652 -0
- data/lib/bio/appl/blast/rexml.rb +151 -0
- data/lib/bio/appl/blast/wublast.rb +553 -0
- data/lib/bio/appl/blast/xmlparser.rb +222 -0
- data/lib/bio/appl/blat/report.rb +392 -0
- data/lib/bio/appl/clustalw.rb +191 -0
- data/lib/bio/appl/clustalw/report.rb +154 -0
- data/lib/bio/appl/emboss.rb +68 -0
- data/lib/bio/appl/fasta.rb +262 -0
- data/lib/bio/appl/fasta/format10.rb +428 -0
- data/lib/bio/appl/fasta/format6.rb +37 -0
- data/lib/bio/appl/genscan/report.rb +570 -0
- data/lib/bio/appl/hmmer.rb +129 -0
- data/lib/bio/appl/hmmer/report.rb +556 -0
- data/lib/bio/appl/mafft.rb +222 -0
- data/lib/bio/appl/mafft/report.rb +119 -0
- data/lib/bio/appl/psort.rb +555 -0
- data/lib/bio/appl/psort/report.rb +473 -0
- data/lib/bio/appl/sim4.rb +134 -0
- data/lib/bio/appl/sim4/report.rb +501 -0
- data/lib/bio/appl/sosui/report.rb +166 -0
- data/lib/bio/appl/spidey/report.rb +604 -0
- data/lib/bio/appl/targetp/report.rb +283 -0
- data/lib/bio/appl/tmhmm/report.rb +238 -0
- data/lib/bio/command.rb +166 -0
- data/lib/bio/data/aa.rb +354 -0
- data/lib/bio/data/codontable.rb +740 -0
- data/lib/bio/data/na.rb +226 -0
- data/lib/bio/db.rb +340 -0
- data/lib/bio/db/aaindex.rb +280 -0
- data/lib/bio/db/embl/common.rb +332 -0
- data/lib/bio/db/embl/embl.rb +446 -0
- data/lib/bio/db/embl/sptr.rb +954 -0
- data/lib/bio/db/embl/swissprot.rb +32 -0
- data/lib/bio/db/embl/trembl.rb +31 -0
- data/lib/bio/db/embl/uniprot.rb +32 -0
- data/lib/bio/db/fantom.rb +604 -0
- data/lib/bio/db/fasta.rb +869 -0
- data/lib/bio/db/genbank/common.rb +299 -0
- data/lib/bio/db/genbank/ddbj.rb +34 -0
- data/lib/bio/db/genbank/genbank.rb +354 -0
- data/lib/bio/db/genbank/genpept.rb +73 -0
- data/lib/bio/db/genbank/refseq.rb +31 -0
- data/lib/bio/db/gff.rb +106 -0
- data/lib/bio/db/go.rb +497 -0
- data/lib/bio/db/kegg/brite.rb +51 -0
- data/lib/bio/db/kegg/cell.rb +88 -0
- data/lib/bio/db/kegg/compound.rb +130 -0
- data/lib/bio/db/kegg/enzyme.rb +125 -0
- data/lib/bio/db/kegg/expression.rb +173 -0
- data/lib/bio/db/kegg/genes.rb +293 -0
- data/lib/bio/db/kegg/genome.rb +362 -0
- data/lib/bio/db/kegg/glycan.rb +213 -0
- data/lib/bio/db/kegg/keggtab.rb +418 -0
- data/lib/bio/db/kegg/kgml.rb +299 -0
- data/lib/bio/db/kegg/ko.rb +178 -0
- data/lib/bio/db/kegg/reaction.rb +97 -0
- data/lib/bio/db/litdb.rb +131 -0
- data/lib/bio/db/medline.rb +317 -0
- data/lib/bio/db/nbrf.rb +199 -0
- data/lib/bio/db/pdb.rb +38 -0
- data/lib/bio/db/pdb/atom.rb +60 -0
- data/lib/bio/db/pdb/chain.rb +117 -0
- data/lib/bio/db/pdb/model.rb +106 -0
- data/lib/bio/db/pdb/pdb.rb +1682 -0
- data/lib/bio/db/pdb/residue.rb +122 -0
- data/lib/bio/db/pdb/utils.rb +234 -0
- data/lib/bio/db/prosite.rb +616 -0
- data/lib/bio/db/rebase.rb +417 -0
- data/lib/bio/db/transfac.rb +387 -0
- data/lib/bio/feature.rb +201 -0
- data/lib/bio/io/brdb.rb +103 -0
- data/lib/bio/io/das.rb +471 -0
- data/lib/bio/io/dbget.rb +212 -0
- data/lib/bio/io/ddbjxml.rb +614 -0
- data/lib/bio/io/fastacmd.rb +123 -0
- data/lib/bio/io/fetch.rb +114 -0
- data/lib/bio/io/flatfile.rb +496 -0
- data/lib/bio/io/flatfile/bdb.rb +266 -0
- data/lib/bio/io/flatfile/index.rb +1308 -0
- data/lib/bio/io/flatfile/indexer.rb +778 -0
- data/lib/bio/io/higet.rb +92 -0
- data/lib/bio/io/keggapi.rb +863 -0
- data/lib/bio/io/pubmed.rb +189 -0
- data/lib/bio/io/registry.rb +308 -0
- data/lib/bio/io/soapwsdl.rb +114 -0
- data/lib/bio/io/sql.rb +428 -0
- data/lib/bio/location.rb +650 -0
- data/lib/bio/pathway.rb +991 -0
- data/lib/bio/reference.rb +308 -0
- data/lib/bio/sequence.rb +593 -0
- data/lib/bio/shell.rb +51 -0
- data/lib/bio/shell/core.rb +512 -0
- data/lib/bio/shell/plugin/codon.rb +228 -0
- data/lib/bio/shell/plugin/entry.rb +85 -0
- data/lib/bio/shell/plugin/flatfile.rb +119 -0
- data/lib/bio/shell/plugin/keggapi.rb +187 -0
- data/lib/bio/shell/plugin/midi.rb +448 -0
- data/lib/bio/shell/plugin/obda.rb +63 -0
- data/lib/bio/shell/plugin/seq.rb +238 -0
- data/lib/bio/shell/session.rb +214 -0
- data/lib/bio/util/color_scheme.rb +214 -0
- data/lib/bio/util/color_scheme/buried.rb +78 -0
- data/lib/bio/util/color_scheme/helix.rb +78 -0
- data/lib/bio/util/color_scheme/hydropathy.rb +83 -0
- data/lib/bio/util/color_scheme/nucleotide.rb +50 -0
- data/lib/bio/util/color_scheme/strand.rb +78 -0
- data/lib/bio/util/color_scheme/taylor.rb +69 -0
- data/lib/bio/util/color_scheme/turn.rb +78 -0
- data/lib/bio/util/color_scheme/zappo.rb +69 -0
- data/lib/bio/util/contingency_table.rb +337 -0
- data/lib/bio/util/sirna.rb +306 -0
- data/lib/bioruby.rb +34 -0
- data/sample/biofetch.rb +475 -0
- data/sample/color_scheme_na.rb +99 -0
- data/sample/dbget +37 -0
- data/sample/fasta2tab.rb +99 -0
- data/sample/fsplit.rb +51 -0
- data/sample/gb2fasta.rb +31 -0
- data/sample/gb2tab.rb +325 -0
- data/sample/gbtab2mysql.rb +161 -0
- data/sample/genes2nuc.rb +33 -0
- data/sample/genes2pep.rb +33 -0
- data/sample/genes2tab.rb +81 -0
- data/sample/genome2rb.rb +29 -0
- data/sample/genome2tab.rb +76 -0
- data/sample/goslim.rb +311 -0
- data/sample/gt2fasta.rb +47 -0
- data/sample/pmfetch.rb +42 -0
- data/sample/pmsearch.rb +42 -0
- data/sample/psortplot_html.rb +222 -0
- data/sample/ssearch2tab.rb +96 -0
- data/sample/tdiary.rb +158 -0
- data/sample/tfastx2tab.rb +100 -0
- data/sample/vs-genes.rb +212 -0
- data/test/data/SOSUI/sample.report +11 -0
- data/test/data/TMHMM/sample.report +21 -0
- data/test/data/blast/eco:b0002.faa +15 -0
- data/test/data/blast/eco:b0002.faa.m0 +128 -0
- data/test/data/blast/eco:b0002.faa.m7 +65 -0
- data/test/data/blast/eco:b0002.faa.m8 +1 -0
- data/test/data/embl/AB090716.embl +65 -0
- data/test/data/genscan/sample.report +63 -0
- data/test/data/prosite/prosite.dat +2233 -0
- data/test/data/refseq/nm_126355.entret +64 -0
- data/test/data/uniprot/p53_human.uniprot +1456 -0
- data/test/runner.rb +10 -0
- data/test/unit/bio/appl/blast/test_report.rb +427 -0
- data/test/unit/bio/appl/blast/test_xmlparser.rb +400 -0
- data/test/unit/bio/appl/genscan/test_report.rb +195 -0
- data/test/unit/bio/appl/sosui/test_report.rb +94 -0
- data/test/unit/bio/appl/targetp/test_report.rb +159 -0
- data/test/unit/bio/appl/test_blast.rb +159 -0
- data/test/unit/bio/appl/test_fasta.rb +142 -0
- data/test/unit/bio/appl/tmhmm/test_report.rb +139 -0
- data/test/unit/bio/data/test_aa.rb +103 -0
- data/test/unit/bio/data/test_codontable.rb +120 -0
- data/test/unit/bio/data/test_na.rb +89 -0
- data/test/unit/bio/db/embl/test_common.rb +130 -0
- data/test/unit/bio/db/embl/test_embl.rb +227 -0
- data/test/unit/bio/db/embl/test_sptr.rb +268 -0
- data/test/unit/bio/db/embl/test_uniprot.rb +44 -0
- data/test/unit/bio/db/kegg/test_genes.rb +58 -0
- data/test/unit/bio/db/test_fasta.rb +263 -0
- data/test/unit/bio/db/test_gff.rb +140 -0
- data/test/unit/bio/db/test_prosite.rb +1450 -0
- data/test/unit/bio/io/test_ddbjxml.rb +87 -0
- data/test/unit/bio/io/test_soapwsdl.rb +45 -0
- data/test/unit/bio/shell/plugin/test_seq.rb +175 -0
- data/test/unit/bio/test_alignment.rb +1028 -0
- data/test/unit/bio/test_command.rb +71 -0
- data/test/unit/bio/test_db.rb +109 -0
- data/test/unit/bio/test_feature.rb +128 -0
- data/test/unit/bio/test_location.rb +51 -0
- data/test/unit/bio/test_pathway.rb +485 -0
- data/test/unit/bio/test_sequence.rb +386 -0
- data/test/unit/bio/test_shell.rb +31 -0
- data/test/unit/bio/util/test_color_scheme.rb +45 -0
- data/test/unit/bio/util/test_contingency_table.rb +106 -0
- data/test/unit/bio/util/test_sirna.rb +258 -0
- metadata +295 -0
data/sample/tdiary.rb
ADDED
@@ -0,0 +1,158 @@
|
|
1
|
+
#
|
2
|
+
# tDiary : plugin/bio.rb
|
3
|
+
#
|
4
|
+
# Copyright (C) 2003 KATAYAMA Toshiaki <k@bioruby.org>
|
5
|
+
# Mitsuteru C. Nakao <n@bioruby.org>
|
6
|
+
# Itoshi NIKAIDO <itoshi@gsc.riken.go.jp>
|
7
|
+
# Takeya KASUKAWA <kasukawa@gsc.riken.go.jp>
|
8
|
+
#
|
9
|
+
# This library is free software; you can redistribute it and/or
|
10
|
+
# modify it under the terms of the GNU Lesser General Public
|
11
|
+
# License as published by the Free Software Foundation; either
|
12
|
+
# version 2 of the License, or (at your option) any later version.
|
13
|
+
#
|
14
|
+
# This library is distributed in the hope that it will be useful,
|
15
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
16
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
17
|
+
# Lesser General Public License for more details.
|
18
|
+
#
|
19
|
+
# You should have received a copy of the GNU Lesser General Public
|
20
|
+
# License along with this library; if not, write to the Free Software
|
21
|
+
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
22
|
+
#
|
23
|
+
# $Id: tdiary.rb,v 1.3 2003/03/17 04:24:47 k Exp $
|
24
|
+
#
|
25
|
+
|
26
|
+
=begin
|
27
|
+
|
28
|
+
== What's this?
|
29
|
+
|
30
|
+
This is a plugin for the ((<tDiary|URL:http://www.tdiary.org/>)) to create
|
31
|
+
various links for biological resources from your diary.
|
32
|
+
|
33
|
+
tDiary is an extensible web diary application written in Ruby.
|
34
|
+
|
35
|
+
== How to install
|
36
|
+
|
37
|
+
Just copy this file under the tDiary's plugin directory as bio.rb.
|
38
|
+
|
39
|
+
== Usage
|
40
|
+
|
41
|
+
--- pubmed(pmid, comment = nil)
|
42
|
+
|
43
|
+
Create a link to NCBI Entrez reference database by using PubMed ID.
|
44
|
+
See ((<URL:http://www.ncbi.nlm.nih.gov/entrez/query.fcgi>)) for more
|
45
|
+
information.
|
46
|
+
|
47
|
+
* tDiary style
|
48
|
+
* <%= pubmed 12345 %>
|
49
|
+
* <%= pubmed 12345, 'hogehoge' %>
|
50
|
+
* RD style
|
51
|
+
* ((% pubmed 12345 %))
|
52
|
+
* ((% pubmed 12345, 'hogehoge' %))
|
53
|
+
|
54
|
+
--- biofetch(db, entry_id)
|
55
|
+
|
56
|
+
Create a link to the BioFetch detabase entry retrieval system.
|
57
|
+
See ((<URL:http://biofetch.bioruby.org/>)) for more information.
|
58
|
+
|
59
|
+
* tDiary style
|
60
|
+
* <%= biofetch 'genbank', 'AA2CG' %>
|
61
|
+
* RD style
|
62
|
+
* ((% biofetch 'genbank', 'AA2CG' %))
|
63
|
+
|
64
|
+
--- amigo(go_id, comment = nil)
|
65
|
+
|
66
|
+
Create a link to the AmiGO GO term browser by using GO ID.
|
67
|
+
See ((<URL:http://www.godatabase.org/cgi-bin/go.cgi>)) for more
|
68
|
+
information.
|
69
|
+
|
70
|
+
* tDiary style
|
71
|
+
* <%= amigo '0003673' %>
|
72
|
+
* <%= amigo '0003673', 'The root of GO' %>
|
73
|
+
* RD style
|
74
|
+
* ((% amigo 0003673 %))
|
75
|
+
* ((% amigo 0003673, 'The root of GO' %))
|
76
|
+
|
77
|
+
--- fantom(id, comment = nil)
|
78
|
+
|
79
|
+
Create a link to FANTOM database by using Clone ID.
|
80
|
+
You can use RIKEN clone ID, Rearray ID, Seq ID and Accession Number.
|
81
|
+
See ((<URL:http://fantom2.gsc.riken.go.jp/db/>)) for more information.
|
82
|
+
|
83
|
+
* tDiary style
|
84
|
+
* <%= fantom 12345 %>
|
85
|
+
* <%= fantom 12345, 'hogehoge' %>
|
86
|
+
* RD style
|
87
|
+
* ((% fantom 12345 %))
|
88
|
+
* ((% fantom 12345, 'hogehoge' %))
|
89
|
+
|
90
|
+
--- rtps(id, comment = nil)
|
91
|
+
|
92
|
+
Create a link to FANTOM RTPS database by using Clone ID.
|
93
|
+
You can use only RTPS ID.
|
94
|
+
See ((<URL:http://fantom2.gsc.riken.go.jp/RTPS/>)) for more information.
|
95
|
+
|
96
|
+
* tDiary style
|
97
|
+
* <%= rtps 12345 %>
|
98
|
+
* <%= rtps 12345, 'hogehoge' %>
|
99
|
+
* RD style
|
100
|
+
* ((% rtps 12345 %))
|
101
|
+
* ((% rtps 12345, 'hogehoge' %))
|
102
|
+
|
103
|
+
== References
|
104
|
+
|
105
|
+
* Analysis of the mouse transcriptome based on functional annotation of
|
106
|
+
60,770 full-length cDNAs, The FANTOM Consortium and the RIKEN Genome
|
107
|
+
Exploration Research Group Phase I & II Team, Nature 420:563-573, 2002
|
108
|
+
|
109
|
+
* Functional annotation of a full-length mouse cDNA collection,
|
110
|
+
The RIKEN Genome Exploration Research Group Phase II Team and
|
111
|
+
the FANTOM Consortium, Nature 409:685-690, 2001
|
112
|
+
|
113
|
+
=end
|
114
|
+
|
115
|
+
def pubmed(pmid, comment = nil)
|
116
|
+
pmid = pmid.to_s.strip
|
117
|
+
url = "http://www.ncbi.nlm.nih.gov/entrez/query.fcgi"
|
118
|
+
url << "?cmd=Retrieve&db=PubMed&dopt=Abstract&list_uids=#{pmid}"
|
119
|
+
if comment
|
120
|
+
%Q[<a href="#{url}">#{comment.to_s.strip}</a>]
|
121
|
+
else
|
122
|
+
%Q[<a href="#{url}">PMID:#{pmid}</a>]
|
123
|
+
end
|
124
|
+
end
|
125
|
+
|
126
|
+
def biofetch(db, entry_id)
|
127
|
+
url = "http://biofetch.bioruby.org/"
|
128
|
+
%Q[<a href="#{url}?db=#{db};id=#{entry_id};style=raw">#{db}:#{entry_id}</a>]
|
129
|
+
end
|
130
|
+
|
131
|
+
def amigo(go_id = '0003673', comment = nil)
|
132
|
+
go_id = go_id.to_s.strip
|
133
|
+
url = "http://www.godatabase.org/cgi-bin/go.cgi?query=#{go_id};view=query;action=query;search_constraint=terms"
|
134
|
+
comment = "AmiGO:#{go_id}" unless comment
|
135
|
+
%Q[<a href="#{url}">#{comment}</a>]
|
136
|
+
end
|
137
|
+
|
138
|
+
def fantom(id, comment = nil)
|
139
|
+
id = id.to_s.strip
|
140
|
+
url = "http://fantom2.gsc.riken.go.jp/db/link/id.cgi"
|
141
|
+
url << "?id=#{id}"
|
142
|
+
if comment
|
143
|
+
%Q[<a href="#{url}">#{comment.to_s.strip}</a>]
|
144
|
+
else
|
145
|
+
%Q[<a href="#{url}">FANTOM DB:#{id}</a>]
|
146
|
+
end
|
147
|
+
end
|
148
|
+
|
149
|
+
def rtps(id, comment = nil)
|
150
|
+
id = id.to_s.strip
|
151
|
+
url = "http://fantom2.gsc.riken.go.jp/RTPS/link/id.cgi"
|
152
|
+
url << "?id=#{id}"
|
153
|
+
if comment
|
154
|
+
%Q[<a href="#{url}">#{comment.to_s.strip}</a>]
|
155
|
+
else
|
156
|
+
%Q[<a href="#{url}">FANTOM RTPS DB:#{id}</a>]
|
157
|
+
end
|
158
|
+
end
|
@@ -0,0 +1,100 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
#
|
3
|
+
# tfastx2tab.rb - convert TFASTX (-m 6) output into tab delimited data for MySQL
|
4
|
+
#
|
5
|
+
# Usage:
|
6
|
+
#
|
7
|
+
# % tfastx2tab.rb TFASTX-output-file[s] > tfastx_results.tab
|
8
|
+
# % mysql < tfastx_results.sql (use sample at the end of this file)
|
9
|
+
#
|
10
|
+
# Format accepted:
|
11
|
+
#
|
12
|
+
# % tfastx3[3][_t] -Q -H -m 6 query.f target.f ktup > TFASTX-output-file
|
13
|
+
#
|
14
|
+
# Copyright (C) 2001 KATAYAMA Toshiaki <k@bioruby.org>
|
15
|
+
#
|
16
|
+
# This program is free software; you can redistribute it and/or modify
|
17
|
+
# it under the terms of the GNU General Public License as published by
|
18
|
+
# the Free Software Foundation; either version 2 of the License, or
|
19
|
+
# (at your option) any later version.
|
20
|
+
#
|
21
|
+
# This program is distributed in the hope that it will be useful,
|
22
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
23
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
24
|
+
# GNU General Public License for more details.
|
25
|
+
#
|
26
|
+
# $Id: tfastx2tab.rb,v 0.1 2001/06/21 08:26:14 katayama Exp $
|
27
|
+
#
|
28
|
+
|
29
|
+
while gets
|
30
|
+
|
31
|
+
# query
|
32
|
+
if /^\S+: (\d+) aa$/
|
33
|
+
q_len = $1
|
34
|
+
end
|
35
|
+
|
36
|
+
# each hit
|
37
|
+
if /^>>([^>]\S+).*\((\d+) aa\)$/
|
38
|
+
target = $1
|
39
|
+
t_len = $2
|
40
|
+
|
41
|
+
# d = dummy variable
|
42
|
+
d, frame, d, initn, d, init1, d, opt, d, zscore, d, bits, d, evalue =
|
43
|
+
gets.split(/\s+/)
|
44
|
+
d, d, sw, ident, d, ugident, d, d, overlap, d, d, lap =
|
45
|
+
gets.split(/\s+/)
|
46
|
+
|
47
|
+
# query-hit pair
|
48
|
+
print "#{$FILENAME}\t#{q_len}\t#{target}\t#{t_len}"
|
49
|
+
|
50
|
+
# pick up values
|
51
|
+
ary = [
|
52
|
+
initn,
|
53
|
+
init1,
|
54
|
+
opt,
|
55
|
+
zscore,
|
56
|
+
bits,
|
57
|
+
evalue,
|
58
|
+
sw,
|
59
|
+
ident,
|
60
|
+
ugident,
|
61
|
+
overlap,
|
62
|
+
lap
|
63
|
+
]
|
64
|
+
|
65
|
+
# print values
|
66
|
+
for i in ary
|
67
|
+
i.tr!('^0-9.:e\-','')
|
68
|
+
print "\t#{i}"
|
69
|
+
end
|
70
|
+
|
71
|
+
print "\t#{frame}\n"
|
72
|
+
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
=begin MySQL tfastx_results.sql sample
|
77
|
+
|
78
|
+
CREATE DATABASE IF NOT EXISTS db_name;
|
79
|
+
CREATE TABLE IF NOT EXISTS db_name.table_name (
|
80
|
+
query varchar(25) not NULL,
|
81
|
+
q_len integer unsigned default 0,
|
82
|
+
target varchar(25) not NULL,
|
83
|
+
t_len integer unsigned default 0,
|
84
|
+
initn integer unsigned default 0,
|
85
|
+
init1 integer unsigned default 0,
|
86
|
+
opt integer unsigned default 0,
|
87
|
+
zscore float default 0.0,
|
88
|
+
bits float default 0.0,
|
89
|
+
evalue float default 0.0,
|
90
|
+
sw integer unsigned default 0,
|
91
|
+
ident float default 0.0,
|
92
|
+
ugident float default 0.0,
|
93
|
+
overlap integer unsigned default 0,
|
94
|
+
lap_at varchar(25) default NULL,
|
95
|
+
frame varchar(5) default NULL
|
96
|
+
);
|
97
|
+
LOAD DATA LOCAL INFILE 'tfastx_results.tab' INTO TABLE db_name.table_name;
|
98
|
+
|
99
|
+
=end
|
100
|
+
|
data/sample/vs-genes.rb
ADDED
@@ -0,0 +1,212 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
#
|
3
|
+
# vs-genes.rb - homology/motif search wrapper
|
4
|
+
#
|
5
|
+
# FASTA/BLAST/Pfam interface for the multiple query in the FASTA format
|
6
|
+
#
|
7
|
+
# Copyright (C) 2001 KATAYAMA Toshiaki <k@bioruby.org>
|
8
|
+
#
|
9
|
+
# This program is free software; you can redistribute it and/or modify
|
10
|
+
# it under the terms of the GNU General Public License as published by
|
11
|
+
# the Free Software Foundation; either version 2 of the License, or
|
12
|
+
# (at your option) any later version.
|
13
|
+
#
|
14
|
+
# This program is distributed in the hope that it will be useful,
|
15
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
16
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
17
|
+
# GNU General Public License for more details.
|
18
|
+
#
|
19
|
+
# $Id: vs-genes.rb,v 0.1 2001/06/21 08:26:31 katayama Exp $
|
20
|
+
#
|
21
|
+
|
22
|
+
def usage(cpu, ktup, skip, resultdir, verbose)
|
23
|
+
print <<-END
|
24
|
+
|
25
|
+
Usage:
|
26
|
+
|
27
|
+
% #{$0} -p PROG -q QUERY -t TARGET [-c #] [-k #] [-s #] [-d DIR] [-v on]
|
28
|
+
|
29
|
+
options
|
30
|
+
-p PROG : (fasta3|ssearch3|tfasta3|fastx3|tfastx3)[3]
|
31
|
+
or
|
32
|
+
(blastp|blastn|blastx|tblastn|tblastx)
|
33
|
+
or
|
34
|
+
(hmmpfam|hmmpfam_n)
|
35
|
+
-q QUERY : query nucleotide or peptide sequences in the FASTA format
|
36
|
+
-t TARGET : target DB (FASTA or BLAST2 formatdb or Pfam format)
|
37
|
+
|
38
|
+
optional arguments
|
39
|
+
-c num : number of CPUs (for the SMP machines, default is #{cpu})
|
40
|
+
-k num : FASTA ktup value (2 for pep, 6 for nuc, default is #{ktup})
|
41
|
+
-s num : skip query (for the resume session, default is #{skip})
|
42
|
+
-d DIR : result output directory (default is "#{resultdir}")
|
43
|
+
-v on/off : verbose output of processing if on (default is "#{verbose}")
|
44
|
+
|
45
|
+
END
|
46
|
+
|
47
|
+
exit 1
|
48
|
+
end
|
49
|
+
|
50
|
+
|
51
|
+
### initialize
|
52
|
+
|
53
|
+
def init
|
54
|
+
arg = {}
|
55
|
+
|
56
|
+
# default values
|
57
|
+
arg['c'] = 1 # num of CPUs
|
58
|
+
arg['k'] = 2 # ktup value for FASTA
|
59
|
+
arg['s'] = 0 # skip query
|
60
|
+
arg['d'] = "./result" # result directory
|
61
|
+
arg['v'] = 'off' # verbose mode
|
62
|
+
|
63
|
+
# parse options
|
64
|
+
ARGV.join(' ').scan(/-(\w) (\S+)/).each do |key, val|
|
65
|
+
arg[key] = val
|
66
|
+
end
|
67
|
+
|
68
|
+
# check program, query, target or print usage
|
69
|
+
unless arg['p'] and arg['q'] and arg['t']
|
70
|
+
usage(arg['c'], arg['k'], arg['s'], arg['d'], arg['v'])
|
71
|
+
end
|
72
|
+
|
73
|
+
# create result output directory
|
74
|
+
unless test(?d, "#{arg['d']}")
|
75
|
+
Dir.mkdir("#{arg['d']}", 0755)
|
76
|
+
end
|
77
|
+
|
78
|
+
# print status
|
79
|
+
if arg['v'] != 'off'
|
80
|
+
puts "PROG : #{arg['p']}"
|
81
|
+
puts " ktup : #{arg['k']}" if arg['p'] =~ /fast/
|
82
|
+
puts "QUERY : #{arg['q']}"
|
83
|
+
puts " skip : #{arg['s']}"
|
84
|
+
puts "TARGET : #{arg['t']}"
|
85
|
+
puts "RESULT : #{arg['d']}"
|
86
|
+
end
|
87
|
+
|
88
|
+
return arg
|
89
|
+
end
|
90
|
+
|
91
|
+
|
92
|
+
### generate command line
|
93
|
+
|
94
|
+
def cmd_line(arg, orf)
|
95
|
+
# program with default command line options # query -> target DB
|
96
|
+
opt = {
|
97
|
+
# FASTA : "-b n" for best n scores, "-d n" for best n alignment
|
98
|
+
'fasta3' => "fasta3 -Q -H -m 6", # pep -> pep or nuc -> nuc
|
99
|
+
'ssearch3' => "ssearch3 -Q -H -m 6", # pep -> pep or nuc -> nuc
|
100
|
+
'tfasta3' => "tfasta3 -Q -H -m 6", # pep -> nuc
|
101
|
+
'fastx3' => "fastx3 -Q -H -m 6", # nuc -> pep
|
102
|
+
'tfastx3' => "tfastx3 -Q -H -m 6", # pep -> nuc (with frameshifts)
|
103
|
+
|
104
|
+
'fasta33' => "fasta33 -Q -H -m 6", # pep -> pep or nuc -> nuc
|
105
|
+
'ssearch33' => "ssearch33 -Q -H -m 6", # pep -> pep or nuc -> nuc
|
106
|
+
'tfasta33' => "tfasta33 -Q -H -m 6", # pep -> nuc
|
107
|
+
'fastx33' => "fastx33 -Q -H -m 6", # nuc -> pep
|
108
|
+
'tfastx33' => "tfastx33 -Q -H -m 6", # pep -> nuc (with frameshifts)
|
109
|
+
|
110
|
+
# BLAST : outputs XML
|
111
|
+
'blastp' => "blastall -m 7 -p blastp -d", # pep -> pep
|
112
|
+
'blastn' => "blastall -m 7 -p blastn -d", # nuc -> nuc
|
113
|
+
'blastx' => "blastall -m 7 -p blastx -d", # nuc -> pep
|
114
|
+
'tblastn' => "blastall -m 7 -p tblastn -d", # pep -> nuc
|
115
|
+
'tblastx' => "blastall -m 7 -p tblastx -d", # nuc -> nuc (by trans)
|
116
|
+
|
117
|
+
# Pfam : "-A n" for best n alignment, "-E n" for E value cutoff etc.
|
118
|
+
'hmmpfam' => "hmmpfam", # pep -> Pfam DB
|
119
|
+
'hmmpfam_n' => "hmmpfam -n", # nuc -> Pfam DB
|
120
|
+
}
|
121
|
+
|
122
|
+
# arguments used in the command line
|
123
|
+
cpu = arg['c'].to_i
|
124
|
+
ktup = arg['k']
|
125
|
+
target = arg['t']
|
126
|
+
query = arg['d'] + "/query." + orf
|
127
|
+
result = arg['d'] + "/" + orf
|
128
|
+
|
129
|
+
prog = opt[arg['p']]
|
130
|
+
|
131
|
+
if cpu > 1 # use multiple CPUs
|
132
|
+
case arg['p']
|
133
|
+
when /(fast|ssearch)/
|
134
|
+
prog += " -T #{cpu}"
|
135
|
+
prog.sub!(' ', '_t ') # rename program with "_t"
|
136
|
+
when /pfam/
|
137
|
+
prog += " --cpu #{cpu}"
|
138
|
+
end
|
139
|
+
end
|
140
|
+
|
141
|
+
# generate complete command line to execute
|
142
|
+
case arg['p']
|
143
|
+
when /fast/
|
144
|
+
command = "#{prog} #{query} #{target} #{ktup} > #{result}"
|
145
|
+
when /ssearch/
|
146
|
+
command = "#{prog} #{query} #{target} > #{result}"
|
147
|
+
when /blast/
|
148
|
+
command = "#{prog} #{target} -i #{query} > #{result}"
|
149
|
+
when /pfam/
|
150
|
+
command = "#{prog} #{target} #{query} > #{result}"
|
151
|
+
end
|
152
|
+
|
153
|
+
return command
|
154
|
+
end
|
155
|
+
|
156
|
+
|
157
|
+
### main
|
158
|
+
|
159
|
+
begin
|
160
|
+
arg = init
|
161
|
+
count = 0
|
162
|
+
|
163
|
+
open(arg['q'], "r") do |f|
|
164
|
+
while seq = f.gets("\n>")
|
165
|
+
count += 1
|
166
|
+
|
167
|
+
# skip (-s option)
|
168
|
+
next unless count > arg['s'].to_i
|
169
|
+
|
170
|
+
# clean up
|
171
|
+
seq.sub!(/^>?[ \t]*/, '') # delete '>' and SPACEs or TABs at the head
|
172
|
+
seq.sub!(/>$/, '') # delete '>' at the tail (separator)
|
173
|
+
|
174
|
+
# get ORF name
|
175
|
+
if seq[/^$/] # no definition (e.g. ">\nSEQ>" or ">\n>")
|
176
|
+
next # -> useless for the multiple query
|
177
|
+
else
|
178
|
+
orf = seq[/^\S+/] # the first word in the definition line
|
179
|
+
end
|
180
|
+
|
181
|
+
# KEGG uses ">DB:ENTRY" format in the definition line
|
182
|
+
if orf =~ /:/
|
183
|
+
db,orf = orf.split(/:/)
|
184
|
+
end
|
185
|
+
|
186
|
+
# add time if the same ORF name was already used
|
187
|
+
if test(?f, "#{arg['d']}/#{orf}")
|
188
|
+
orf = "#{orf}.#{Time.now.to_f.to_s}"
|
189
|
+
end
|
190
|
+
|
191
|
+
# create temporal file of the query
|
192
|
+
open("#{arg['d']}/query.#{orf}", "w+") do |tmp|
|
193
|
+
tmp.print(">#{seq}")
|
194
|
+
end
|
195
|
+
|
196
|
+
command = cmd_line(arg, orf)
|
197
|
+
|
198
|
+
# print status
|
199
|
+
if arg['v'] != 'off'
|
200
|
+
puts "#{count} : #{orf} ..."
|
201
|
+
puts " #{command}"
|
202
|
+
end
|
203
|
+
|
204
|
+
# execute
|
205
|
+
system("#{command}")
|
206
|
+
|
207
|
+
# remove temporal file
|
208
|
+
File.delete("#{arg['d']}/query.#{orf}")
|
209
|
+
end
|
210
|
+
end
|
211
|
+
end
|
212
|
+
|