bio-polyploid-tools 0.10.1 → 1.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/SECURITY.md +16 -0
- data/VERSION +1 -1
- data/bin/polymarker.rb +30 -21
- data/bin/polymarker_capillary.rb +83 -56
- data/bin/{find_homoeologue_variations.rb → polymarker_deletions.rb} +55 -90
- data/bio-polyploid-tools.gemspec +27 -25
- data/lib/bio/BIOExtensions.rb +1 -1
- data/lib/bio/PolyploidTools/ExonContainer.rb +9 -9
- data/lib/bio/PolyploidTools/NoSNPSequence.rb +39 -33
- data/lib/bio/PolyploidTools/SNP.rb +26 -21
- data/lib/bio/db/blast.rb +1 -1
- data/lib/bio/db/primer3.rb +14 -18
- data/test/data/7B_amplicon_test.fa +12 -0
- data/test/data/7B_amplicon_test.fa.fai +1 -0
- data/test/data/7B_amplicon_test_reference.fa +110 -0
- data/test/data/7B_amplicon_test_reference.fa.fai +3 -0
- data/test/data/7B_amplicon_test_reference.fa.ndb +0 -0
- data/test/data/7B_amplicon_test_reference.fa.nhr +0 -0
- data/test/data/7B_amplicon_test_reference.fa.nin +0 -0
- data/test/data/7B_amplicon_test_reference.fa.not +0 -0
- data/test/data/7B_amplicon_test_reference.fa.nsq +0 -0
- data/test/data/7B_amplicon_test_reference.fa.ntf +0 -0
- data/test/data/7B_amplicon_test_reference.fa.nto +0 -0
- metadata +17 -8
- data/README +0 -21
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 9191156e91a48ec245e181a1541d4b636b01c848b03f2b7db5f7729ddfc05421
|
4
|
+
data.tar.gz: '0449ab8d09b268538d3604f20b555d94be53cac35ff8d591a29c792f98df3def'
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 1c23625ac5c1cdfc3b4d34c3a8f416f680bc42a274b983ee64938bc3ba3bd7b685ad3e9cd9c04521a8f1baf8f91b0efae27a4c5d3034a4a18b141ec10209a7ee
|
7
|
+
data.tar.gz: cebf5a46d0a3cce9b63ccd71451f2f2a0d4903ae3e0954d34ba48955cc148b3d232bc5612ed8a528ade86cbfbb6e216c9788126c53b7f8cfa2157785ee00533b
|
data/SECURITY.md
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
# Security Policy
|
2
|
+
|
3
|
+
## Supported Versions
|
4
|
+
|
5
|
+
The following table shows the currently supported version.
|
6
|
+
|
7
|
+
| Version | Supported |
|
8
|
+
| ------- | ------------------ |
|
9
|
+
| 1.1.x | :white_check_mark: |
|
10
|
+
| 1.0.x | :x: |
|
11
|
+
| 0.x.x | :x: |
|
12
|
+
|
13
|
+
|
14
|
+
## Reporting a Vulnerability
|
15
|
+
|
16
|
+
If you find a vulneravility, please submit a comment in the security tab
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
|
1
|
+
1.2.0
|
data/bin/polymarker.rb
CHANGED
@@ -40,8 +40,8 @@ options[:scoring] = :genome_specific
|
|
40
40
|
options[:database] = false
|
41
41
|
options[:filter_best] = false
|
42
42
|
options[:aligner] = :blast
|
43
|
-
|
44
|
-
|
43
|
+
options[:max_hits] = 8
|
44
|
+
options[:max_specific_primers] = 15
|
45
45
|
options[:primer_3_preferences] = {
|
46
46
|
:primer_product_size_range => "50-150" ,
|
47
47
|
:primer_max_size => 25 ,
|
@@ -132,6 +132,15 @@ OptionParser.new do |opts|
|
|
132
132
|
opts.on("-d", "--database PREFIX", "Path to the blast database. Only used if the aligner is blast. The default is the name of the contigs file without extension.") do |o|
|
133
133
|
options[:database] = o
|
134
134
|
end
|
135
|
+
|
136
|
+
opts.on("-H", "--max_hits INT", "Maximum number of hits to the reference. If there are more hits than this value, the marker is ignored") do |o|
|
137
|
+
options[:max_hits] = o.to_i
|
138
|
+
end
|
139
|
+
|
140
|
+
opts.on("-S", "--max_specific_primers INT", "Maximum number of candidate primers to attempt to design. Default: #{options[:max_specific_primers]} ") do |o|
|
141
|
+
options[:max_specific_primers] = o.to_i
|
142
|
+
end
|
143
|
+
|
135
144
|
end.parse!
|
136
145
|
|
137
146
|
|
@@ -233,8 +242,8 @@ File.open(test_file) do | f |
|
|
233
242
|
region = fasta_reference_db.index.region_for_entry(snp.gene).get_full_region
|
234
243
|
snp.template_sequence = fasta_reference_db.fetch_sequence(region)
|
235
244
|
else
|
236
|
-
|
237
|
-
|
245
|
+
write_status "WARN: Unable to find entry for #{snp.gene}"
|
246
|
+
end
|
238
247
|
elsif options[:mutant_list] and options[:reference] #List and fasta file
|
239
248
|
snp = Bio::PolyploidTools::SNPMutant.parse(line)
|
240
249
|
entry = fasta_reference_db.index.region_for_entry(snp.contig)
|
@@ -242,21 +251,21 @@ File.open(test_file) do | f |
|
|
242
251
|
region = fasta_reference_db.index.region_for_entry(snp.contig).get_full_region
|
243
252
|
snp.full_sequence = fasta_reference_db.fetch_sequence(region)
|
244
253
|
else
|
245
|
-
|
246
|
-
end
|
247
|
-
else
|
248
|
-
raise Bio::DB::Exonerate::ExonerateException.new "Wrong number of arguments. "
|
249
|
-
end
|
250
|
-
raise Bio::DB::Exonerate::ExonerateException.new "No SNP for line '#{line}'" if snp == nil
|
251
|
-
|
252
|
-
snp.genomes_count = options[:genomes_count]
|
253
|
-
snp.snp_in = snp_in
|
254
|
-
snp.original_name = original_name
|
255
|
-
if snp.position
|
256
|
-
snps << snp
|
257
|
-
else
|
258
|
-
$stderr.puts "ERROR: #{snp.gene} doesn't contain a SNP"
|
254
|
+
write_status "WARN: Unable to find entry for #{snp.gene}"
|
259
255
|
end
|
256
|
+
else
|
257
|
+
raise Bio::DB::Exonerate::ExonerateException.new "Wrong number of arguments. "
|
258
|
+
end
|
259
|
+
raise Bio::DB::Exonerate::ExonerateException.new "No SNP for line '#{line}'" if snp == nil
|
260
|
+
snp.max_hits = options[:max_hits]
|
261
|
+
snp.genomes_count = options[:genomes_count]
|
262
|
+
snp.snp_in = snp_in
|
263
|
+
snp.original_name = original_name
|
264
|
+
if snp.position
|
265
|
+
snps << snp
|
266
|
+
else
|
267
|
+
$stderr.puts "ERROR: #{snp.gene} doesn't contain a SNP"
|
268
|
+
end
|
260
269
|
end
|
261
270
|
end
|
262
271
|
|
@@ -307,7 +316,7 @@ def do_align(aln, exo_f, found_contigs, min_identity,fasta_file,options)
|
|
307
316
|
|
308
317
|
end
|
309
318
|
|
310
|
-
Bio::DB::Blast.align({:query=>temp_fasta_query, :target=>options[:database], :model=>model}) do |aln|
|
319
|
+
Bio::DB::Blast.align({:query=>temp_fasta_query, :target=>options[:database], :model=>model, :max_hits=>options[:max_hits]}) do |aln|
|
311
320
|
do_align(aln, exo_f, found_contigs,min_identity, fasta_file,options)
|
312
321
|
end if options[:aligner] == :blast
|
313
322
|
|
@@ -334,7 +343,7 @@ container.gene_models(temp_fasta_query)
|
|
334
343
|
container.chromosomes(target)
|
335
344
|
container.add_parental({:name=>snp_in})
|
336
345
|
container.add_parental({:name=>original_name})
|
337
|
-
|
346
|
+
container.max_hits = options[:max_hits]
|
338
347
|
snps.each do |snp|
|
339
348
|
snp.container = container
|
340
349
|
snp.flanking_size = container.flanking_size
|
@@ -358,7 +367,7 @@ write_status "Running primer3"
|
|
358
367
|
file = File.open(primer_3_input, "w")
|
359
368
|
|
360
369
|
Bio::DB::Primer3.prepare_input_file(file, options[:primer_3_preferences])
|
361
|
-
added_exons = container.print_primer_3_exons(file, nil, snp_in)
|
370
|
+
added_exons = container.print_primer_3_exons(file, nil, snp_in, max_specific_primers: options[:max_specific_primers] )
|
362
371
|
file.close
|
363
372
|
|
364
373
|
Bio::DB::Primer3.run({:in=>primer_3_input, :out=>primer_3_output}) if added_exons > 0
|
data/bin/polymarker_capillary.rb
CHANGED
@@ -35,15 +35,21 @@ options[:primer_3_preferences] = {
|
|
35
35
|
}
|
36
36
|
options[:genomes_count] = 3
|
37
37
|
options[:allow_non_specific] = false
|
38
|
+
options[:aligner] = :blast
|
39
|
+
options[:arm_selection]
|
40
|
+
model="ungapped"
|
41
|
+
options[:arm_selection] = Bio::PolyploidTools::ChromosomeArm.getArmSelection("nrgene")
|
42
|
+
options[:database] = false
|
38
43
|
|
39
44
|
OptionParser.new do |opts|
|
40
|
-
opts.banner = "Usage:
|
45
|
+
opts.banner = "Usage: polymarker_deletions.rb [options]"
|
41
46
|
|
42
47
|
opts.on("-r", "--reference FILE", "Fasta file with the assembly") do |o|
|
43
48
|
options[:reference] = o
|
44
49
|
end
|
45
50
|
|
46
|
-
opts.on("-m", "--sequences FILE", "Fasta file with the sequences to amplify. the format must be Chromosome:start-end. Chromosome
|
51
|
+
opts.on("-m", "--sequences FILE", "Fasta file with the sequences to amplify. the format must be Chromosome:start-end. Chromosome
|
52
|
+
should match the names to the entries in the fasta files as it is used as main target") do |o|
|
47
53
|
options[:markers] = o
|
48
54
|
end
|
49
55
|
|
@@ -53,10 +59,19 @@ OptionParser.new do |opts|
|
|
53
59
|
opts.on("-g", "--genomes_count INT", "Number of genomes (default 3, for hexaploid)") do |o|
|
54
60
|
options[:genomes_count] = o.to_i
|
55
61
|
end
|
56
|
-
opts.on("-
|
62
|
+
opts.on("-A", "--allow_non_specific", "If used, semi-specific and non-specific primers will be produced") do |o|
|
57
63
|
options[:allow_non_specific] = true
|
58
64
|
end
|
59
65
|
|
66
|
+
opts.on("-d", "--database PREFIX", "Path to the blast database. Only used if the aligner is blast. The default is the name of the contigs file without extension.") do |o|
|
67
|
+
options[:database] = o
|
68
|
+
end
|
69
|
+
|
70
|
+
|
71
|
+
opts.on("-a", "--arm_selection #{Bio::PolyploidTools::ChromosomeArm.getValidFunctions.join('|')}", "Function to decide the chromome arm") do |o|
|
72
|
+
options[:arm_selection] = Bio::PolyploidTools::ChromosomeArm.getArmSelection(o)
|
73
|
+
end
|
74
|
+
|
60
75
|
end.parse!
|
61
76
|
|
62
77
|
|
@@ -65,23 +80,33 @@ reference = options[:reference]
|
|
65
80
|
markers = options[:markers]
|
66
81
|
output_folder = options[:output_folder]
|
67
82
|
allow_non_specific = options[:allow_non_specific]
|
83
|
+
|
84
|
+
options[:database] = options[:reference] unless options[:database]
|
85
|
+
temp_fasta_query="#{output_folder}/to_align.fa"
|
68
86
|
log "Output folder: #{output_folder}"
|
69
87
|
exonerate_file="#{output_folder}/exonerate_tmp.tab"
|
70
88
|
Dir.mkdir(output_folder)
|
89
|
+
arm_selection = options[:arm_selection]
|
71
90
|
|
72
91
|
module Bio::PolyploidTools
|
73
|
-
|
74
|
-
|
75
92
|
|
76
93
|
class SequenceToAmplify < SNP
|
77
94
|
|
78
|
-
def self.select_chromosome(
|
79
|
-
|
80
|
-
|
81
|
-
ret =
|
82
|
-
|
83
|
-
|
84
|
-
|
95
|
+
def self.select_chromosome(gene_name, arm_selection)
|
96
|
+
#m=/##INFO=<ID=(.+),Number=(.+),Type=(.+),Description="(.+)">/.match(gene_name)
|
97
|
+
#m=/TraesCS(\d{1})(\w{1})(\d{2})G(\d+)/.match(gene_name)
|
98
|
+
#ret = {:group : m[1],
|
99
|
+
# :genome : m[2],:version=>m[3],:chr_id=>m[4]}
|
100
|
+
|
101
|
+
|
102
|
+
#arr = contig_name.split('_')
|
103
|
+
#ret = "U"
|
104
|
+
#ret = arr[2][0,2] if arr.size >= 3
|
105
|
+
#ret = "3B" if arr.size == 2 and arr[0] == "v443"
|
106
|
+
#ret = arr[0][0,2] if arr.size == 1
|
107
|
+
#ret = "#{m[1]}#{m[2]}"
|
108
|
+
#puts ret
|
109
|
+
ret = arm_selection.call(gene_name)
|
85
110
|
return ret
|
86
111
|
end
|
87
112
|
|
@@ -92,18 +117,18 @@ module Bio::PolyploidTools
|
|
92
117
|
#Format:
|
93
118
|
#A fasta entry with the id: contig:start-end
|
94
119
|
#The sequence can be prodcued with samtools faidx
|
95
|
-
def self.parse(fasta_entry)
|
96
|
-
|
120
|
+
def self.parse(fasta_entry, arm_selection)
|
121
|
+
#puts fasta_entry.definition
|
97
122
|
snp = SequenceToAmplify.new
|
98
123
|
match_data = /(?<rname>\w*):(?<rstart>\w*)-(?<rend>\w*)/.match(fasta_entry.definition)
|
99
|
-
|
124
|
+
#puts match_data.inspect
|
100
125
|
rName = Regexp.last_match(:rname)
|
101
126
|
rStart = Regexp.last_match(:rstart).to_i
|
102
127
|
rEnd = Regexp.last_match(:rend).to_i
|
103
128
|
snp.gene = fasta_entry.definition
|
104
129
|
#snp.chromosome=rName
|
105
|
-
|
106
|
-
snp.chromosome=select_chromosome(
|
130
|
+
#puts "Gene: #{snp.gene}"
|
131
|
+
snp.chromosome=select_chromosome(fasta_entry.definition, arm_selection)
|
107
132
|
#puts "#{rName}: #{snp.chromosome}"
|
108
133
|
snp.sequence_original = fasta_entry.seq
|
109
134
|
snp.template_sequence = fasta_entry.seq.upcase
|
@@ -111,7 +136,7 @@ module Bio::PolyploidTools
|
|
111
136
|
snp.rstart = rStart
|
112
137
|
snp.rend = rEnd
|
113
138
|
|
114
|
-
snp.position =
|
139
|
+
snp.position = snp.sequence_original.size / 2
|
115
140
|
snp.original = snp.sequence_original[snp.position]
|
116
141
|
|
117
142
|
tmp = Bio::Sequence::NA.new(snp.original)
|
@@ -121,7 +146,7 @@ module Bio::PolyploidTools
|
|
121
146
|
snp
|
122
147
|
end
|
123
148
|
|
124
|
-
def primer_3_all_strings(target_chromosome, parental)
|
149
|
+
def primer_3_all_strings(target_chromosome, parental, max_specific_primers: 20, flanking_size:500)
|
125
150
|
#puts target_chromosome
|
126
151
|
#puts parental
|
127
152
|
#puts aligned_sequences.to_fasta
|
@@ -130,8 +155,11 @@ module Bio::PolyploidTools
|
|
130
155
|
|
131
156
|
seq_original = String.new(pr.sequence)
|
132
157
|
#puts seq_original.size.to_s << "-" << primer_3_min_seq_length.to_s
|
158
|
+
#puts "___"
|
159
|
+
#puts pr.inspect
|
133
160
|
return primer_3_propertes if seq_original.size < primer_3_min_seq_length
|
134
|
-
|
161
|
+
#puts "((("
|
162
|
+
return primer_3_propertes unless pr.snp_pos == flanking_size
|
135
163
|
#puts "Sequence origina: #{ self.original}"
|
136
164
|
#puts pr.to_fasta
|
137
165
|
#puts "Postion: #{pr.snp_pos}"
|
@@ -232,10 +260,13 @@ file = Bio::FastaFormat.open(markers)
|
|
232
260
|
file.each do |entry|
|
233
261
|
|
234
262
|
begin
|
235
|
-
|
263
|
+
#puts entry.inspect
|
264
|
+
tmp = Bio::PolyploidTools::SequenceToAmplify.parse(entry, arm_selection)
|
236
265
|
snps << tmp if tmp
|
237
|
-
rescue
|
266
|
+
rescue Exception => e
|
267
|
+
log "ERROR\t#{e.message}"
|
238
268
|
$stderr.puts "Unable to generate the marker for: #{entry.definition}"
|
269
|
+
$stderr.puts e.backtrace
|
239
270
|
end
|
240
271
|
|
241
272
|
end
|
@@ -246,45 +277,38 @@ file.close
|
|
246
277
|
exo_f = File.open(exonerate_file, "w")
|
247
278
|
target=reference
|
248
279
|
|
249
|
-
fasta_file = Bio::DB::Fasta::FastaFile.new(
|
280
|
+
fasta_file = Bio::DB::Fasta::FastaFile.new(fasta: target)
|
250
281
|
fasta_file.load_fai_entries
|
251
|
-
min_identity =
|
282
|
+
min_identity = 90
|
252
283
|
found_contigs = Set.new
|
253
284
|
|
254
|
-
|
285
|
+
|
286
|
+
def do_align(aln, exo_f, found_contigs, min_identity,fasta_file,options)
|
255
287
|
if aln.identity > min_identity
|
256
288
|
exo_f.puts aln.line
|
257
|
-
#puts aln.line
|
258
289
|
unless found_contigs.include?(aln.target_id) #We only add once each contig. Should reduce the size of the output file.
|
259
290
|
found_contigs.add(aln.target_id)
|
260
291
|
entry = fasta_file.index.region_for_entry(aln.target_id)
|
261
|
-
raise
|
292
|
+
raise ExonerateException.new, "Entry not found! #{aln.target_id}. Make sure that the #{target_id}.fai was generated properly." if entry == nil
|
293
|
+
if options[:extract_found_contigs]
|
294
|
+
region = entry.get_full_region
|
295
|
+
seq = fasta_file.fetch_sequence(region)
|
296
|
+
contigs_f.puts(">#{aln.target_id}\n#{seq}")
|
297
|
+
end
|
262
298
|
end
|
263
299
|
end
|
264
|
-
end
|
265
|
-
exo_f.close
|
266
|
-
|
267
|
-
arm_selection_functions = Hash.new
|
268
300
|
|
269
|
-
arm_selection_functions[:full_scaffold] = lambda do | contig_name |
|
270
|
-
return contig_name
|
271
301
|
end
|
272
302
|
|
273
|
-
|
274
|
-
|
275
|
-
|
276
|
-
#And with the cases when 3B is named with the prefix: v443
|
277
|
-
arm_selection_functions[:arm_selection_embl] = lambda do | contig_name|
|
278
|
-
|
279
|
-
arr = contig_name.split('_')
|
280
|
-
ret = "U"
|
281
|
-
ret = arr[2][0,2] if arr.size >= 3
|
282
|
-
ret = "3B" if arr.size == 2 and arr[0] == "v443"
|
283
|
-
ret = arr[0][0,2] if arr.size == 1
|
284
|
-
return ret
|
285
|
-
end
|
303
|
+
Bio::DB::Blast.align({:query=>markers, :target=>options[:database], :model=>model, :max_hits=>options[:max_hits]}) do |aln|
|
304
|
+
do_align(aln, exo_f, found_contigs,min_identity, fasta_file,options)
|
305
|
+
end if options[:aligner] == :blast
|
286
306
|
|
307
|
+
Bio::DB::Exonerate.align({:query=>markers, :target=>target, :model=>model}) do |aln|
|
308
|
+
do_align(aln, exo_f, found_contigs, min_identity,fasta_file,options)
|
309
|
+
end if options[:aligner] == :exonerate
|
287
310
|
|
311
|
+
exo_f.close
|
288
312
|
|
289
313
|
container= Bio::PolyploidTools::ExonContainer.new
|
290
314
|
container.flanking_size=500
|
@@ -292,6 +316,7 @@ container.gene_models(markers)
|
|
292
316
|
container.chromosomes(target)
|
293
317
|
container.add_parental({:name=>"A"})
|
294
318
|
container.add_parental({:name=>"B"})
|
319
|
+
#puts "SNPs size: #{snps.size}"
|
295
320
|
snps.each do |snp|
|
296
321
|
snp.snp_in = "B"
|
297
322
|
snp.container = container
|
@@ -300,8 +325,10 @@ snps.each do |snp|
|
|
300
325
|
snp.includeNoSpecific = allow_non_specific
|
301
326
|
container.add_snp(snp)
|
302
327
|
end
|
303
|
-
container.add_alignments({:exonerate_file=>exonerate_file, :arm_selection=>arm_selection_functions[:arm_selection_embl] , :min_identity=>min_identity})
|
304
328
|
|
329
|
+
container.add_alignments({:exonerate_file=>exonerate_file,
|
330
|
+
:arm_selection=> arm_selection,
|
331
|
+
:min_identity=>min_identity})
|
305
332
|
|
306
333
|
|
307
334
|
exons_filename="#{output_folder}/localAlignment.fa"
|
@@ -329,12 +356,15 @@ output_file = "#{output_folder}/primers.csv"
|
|
329
356
|
file = File.open(masks_output, "w")
|
330
357
|
out = File.open(output_file, "w")
|
331
358
|
|
359
|
+
out.puts ["Id","specificity","inside","type","target","orientation","product_size",
|
360
|
+
"left_position","left_tm","left_sequence",
|
361
|
+
"right_position","right_tm","right_sequence"].join ","
|
332
362
|
class Bio::DB::Primer3::Primer3Record
|
333
363
|
attr_accessor :primerPairs
|
334
364
|
end
|
335
365
|
|
336
366
|
printed_counts = Hash.new(0)
|
337
|
-
Bio::DB::Primer3::Primer3Record.parse_file(primer_3_output) do | primer3record |
|
367
|
+
Bio::DB::Primer3::Primer3Record.parse_file(primer_3_output ) do | primer3record |
|
338
368
|
#puts primer3record.inspect
|
339
369
|
next if primer3record.primer_left_num_returned.to_i == 0
|
340
370
|
|
@@ -358,10 +388,7 @@ Bio::DB::Primer3::Primer3Record.parse_file(primer_3_output) do | primer3record |
|
|
358
388
|
|
359
389
|
file.puts ">#{seq_id}\n#{sequence_template}"
|
360
390
|
file.puts ">#{seq_id}:mask\n#{sequence_mask}"
|
361
|
-
|
362
|
-
|
363
|
-
#puts primer3record.primerPairs
|
364
|
-
|
391
|
+
|
365
392
|
primer3record.primerPairs.each do |p|
|
366
393
|
#puts p.inspect
|
367
394
|
printed += 1
|
@@ -381,10 +408,10 @@ Bio::DB::Primer3::Primer3Record.parse_file(primer_3_output) do | primer3record |
|
|
381
408
|
toPrint << p.right.sequence
|
382
409
|
|
383
410
|
middle = 501
|
384
|
-
toPrint << lArr[0]
|
385
|
-
toPrint << rArr[0]
|
386
|
-
toPrint << middle - lArr[0]
|
387
|
-
toPrint << rArr[0] - middle
|
411
|
+
#toPrint << lArr[0]
|
412
|
+
#toPrint << rArr[0]
|
413
|
+
#toPrint << middle - lArr[0]
|
414
|
+
#toPrint << rArr[0] - middle
|
388
415
|
#Start End LeftDistance RightDistance
|
389
416
|
|
390
417
|
out.puts toPrint.join(",")
|
@@ -53,14 +53,12 @@ class Bio::PolyploidTools::ExonContainer
|
|
53
53
|
end
|
54
54
|
|
55
55
|
class Bio::DB::Primer3::SNP
|
56
|
-
|
57
56
|
def to_s
|
58
57
|
"#{gene}:#{snp_from.chromosome}"
|
59
58
|
end
|
60
|
-
|
61
59
|
end
|
62
|
-
class Bio::DB::Primer3::Primer3Record
|
63
60
|
|
61
|
+
class Bio::DB::Primer3::Primer3Record
|
64
62
|
|
65
63
|
def best_pair
|
66
64
|
return @best_pair if @best_pair
|
@@ -82,7 +80,7 @@ class Bio::DB::Primer3::Primer3Record
|
|
82
80
|
@total_caps = capital_count
|
83
81
|
end
|
84
82
|
end
|
85
|
-
|
83
|
+
|
86
84
|
@best_pair
|
87
85
|
end
|
88
86
|
|
@@ -107,12 +105,13 @@ class Bio::DB::Primer3::Primer3Record
|
|
107
105
|
|
108
106
|
def score
|
109
107
|
best_pair
|
108
|
+
total_caps = "#{best_pair.left.sequence}#{best_pair.right.sequence}".scan(/[A-Z]/).length
|
110
109
|
# puts "score"
|
111
110
|
# puts self.inspect
|
112
111
|
ret = 0
|
113
112
|
ret += @scores[type]
|
114
113
|
ret += @scores[:exon] if exon?
|
115
|
-
ret -=
|
114
|
+
ret -= total_caps * 10
|
116
115
|
ret -= product_length
|
117
116
|
ret
|
118
117
|
end
|
@@ -123,71 +122,21 @@ class Bio::DB::Primer3::Primer3Record
|
|
123
122
|
|
124
123
|
def left_primer_snp(snp)
|
125
124
|
tmp_primer = String.new(left_primer)
|
126
|
-
#if self.orientation == :forward
|
127
|
-
# base_original = snp.original
|
128
|
-
# base_snp = snp.snp
|
129
|
-
#elsif self.orientation == :reverse
|
130
|
-
# base_original = reverse_complement_string(snp.original )
|
131
|
-
# base_snp = reverse_complement_string(snp.snp)
|
132
|
-
#else
|
133
|
-
# raise Primer3Exception.new "#{self.orientation} is not a valid orientation"
|
134
|
-
#end
|
135
|
-
|
136
|
-
# puts "#{snp.to_s} #{self.orientation} #{tmp_primer[-1] } #{base_original} #{base_snp}"
|
137
|
-
#if tmp_primer[-1] == base_original
|
138
|
-
# tmp_primer[-1] = base_snp
|
139
|
-
#elsif tmp_primer[-1] == base_snp
|
140
|
-
# tmp_primer[-1] = base_original
|
141
|
-
#else
|
142
|
-
# raise Primer3Exception.new "#{tmp_primer} doesnt end in a base in the SNP #{snp.to_s}"
|
143
|
-
#end
|
144
|
-
#puts "tmp_primer: #{tmp_primer}"
|
145
125
|
return tmp_primer
|
146
126
|
end
|
147
127
|
|
148
128
|
end
|
149
129
|
|
150
|
-
arm_selection_functions = Hash.new;
|
151
|
-
|
152
|
-
|
153
|
-
arm_selection_functions[:arm_selection_first_two] = lambda do | contig_name |
|
154
|
-
ret = contig_name[0,2]
|
155
|
-
return ret
|
156
|
-
end
|
157
|
-
|
158
|
-
#Function to parse stuff like: "IWGSC_CSS_1AL_scaff_110"
|
159
|
-
#Or the first two characters in the contig name, to deal with
|
160
|
-
#pseudomolecules that start with headers like: "1A"
|
161
|
-
#And with the cases when 3B is named with the prefix: v443
|
162
|
-
arm_selection_functions[:arm_selection_embl] = lambda do | contig_name|
|
163
|
-
|
164
|
-
arr = contig_name.split('_')
|
165
|
-
ret = "U"
|
166
|
-
ret = arr[2][0,2] if arr.size >= 3
|
167
|
-
ret = "3B" if arr.size == 2 and arr[0] == "v443"
|
168
|
-
ret = arr[0][0,2] if arr.size == 1
|
169
|
-
return ret
|
170
|
-
end
|
171
|
-
|
172
|
-
arm_selection_functions[:arm_selection_morex] = lambda do | contig_name |
|
173
|
-
ret = contig_name.split(':')[0].split("_")[1];
|
174
|
-
return ret
|
175
|
-
end
|
176
|
-
|
177
|
-
arm_selection_functions[:scaffold] = lambda do | contig_name |
|
178
|
-
ret = contig_name;
|
179
|
-
return ret
|
180
|
-
end
|
181
|
-
|
182
130
|
markers = nil
|
183
131
|
|
184
132
|
options = {}
|
133
|
+
options[:aligner] = :blast
|
185
134
|
options[:model] = "est2genome"
|
186
135
|
options[:min_identity] = 90
|
187
|
-
options[:extract_found_contigs] =
|
188
|
-
options[:arm_selection] =
|
136
|
+
options[:extract_found_contigs] = true
|
137
|
+
options[:arm_selection] = Bio::PolyploidTools::ChromosomeArm.getArmSelection("nrgene")
|
189
138
|
options[:genomes_count] = 3
|
190
|
-
|
139
|
+
options[:variation_free_region] =0
|
191
140
|
|
192
141
|
options[:primer_3_preferences] = {
|
193
142
|
:primer_product_size_range => "50-150" ,
|
@@ -200,11 +149,14 @@ options[:primer_3_preferences] = {
|
|
200
149
|
}
|
201
150
|
|
202
151
|
|
152
|
+
options[:database] = false
|
153
|
+
|
154
|
+
|
203
155
|
OptionParser.new do |opts|
|
204
156
|
|
205
|
-
opts.banner = "Usage:
|
157
|
+
opts.banner = "Usage: polymarker_deletions.rb [options]"
|
206
158
|
|
207
|
-
opts.on("-
|
159
|
+
opts.on("-m", "--sequences FASTA", "Sequence of the region to search") do |o|
|
208
160
|
options[:sequences] = o
|
209
161
|
end
|
210
162
|
opts.on("-r", "--reference FASTA", "reference with the contigs") do |o|
|
@@ -221,6 +173,14 @@ OptionParser.new do |opts|
|
|
221
173
|
opts.on("-x", "--extract_found_contigs", "If present, save in a separate file the contigs with matches. Useful to debug.") do |o|
|
222
174
|
options[:extract_found_contigs] = true
|
223
175
|
end
|
176
|
+
|
177
|
+
opts.on("-d", "--database PREFIX", "Path to the blast database. Only used if the aligner is blast. The default is the name of the contigs file without extension.") do |o|
|
178
|
+
options[:database] = o
|
179
|
+
end
|
180
|
+
|
181
|
+
opts.on("-a", "--arm_selection #{Bio::PolyploidTools::ChromosomeArm.getValidFunctions.join('|')}", "Function to decide the chromome arm") do |o|
|
182
|
+
options[:arm_selection] = Bio::PolyploidTools::ChromosomeArm.getArmSelection(o)
|
183
|
+
end
|
224
184
|
|
225
185
|
end.parse!
|
226
186
|
#reference="/Users/ramirezr/Documents/TGAC/references/Triticum_aestivum.IWGSP1.21.dna_rm.genome.fa"
|
@@ -231,11 +191,14 @@ throw raise Exception.new(), "Fasta file with sequences has to be provided" unle
|
|
231
191
|
output_folder = options[:output] if options[:output]
|
232
192
|
throw raise Exception.new(), "An output directory has to be provided" unless output_folder
|
233
193
|
model=options[:model]
|
194
|
+
|
195
|
+
options[:database] = options[:reference] unless options[:database]
|
196
|
+
|
234
197
|
Dir.mkdir(output_folder)
|
235
198
|
min_identity= options[:min_identity]
|
236
199
|
|
237
200
|
exonerate_file="#{output_folder}/exonerate_tmp.tab"
|
238
|
-
|
201
|
+
|
239
202
|
primer_3_input="#{output_folder}/primer_3_input_temp"
|
240
203
|
primer_3_output="#{output_folder}/primer_3_output_temp"
|
241
204
|
exons_filename="#{output_folder}/exons_genes_and_contigs.fa"
|
@@ -248,14 +211,8 @@ fasta_file.load_fai_entries
|
|
248
211
|
original_name="A"
|
249
212
|
snp_in="B"
|
250
213
|
|
251
|
-
|
214
|
+
arm_selection = options[:arm_selection]
|
252
215
|
|
253
|
-
unless arm_selection
|
254
|
-
arm_selection = lambda do | contig_name |
|
255
|
-
ret = contig_name[0,3]
|
256
|
-
return ret
|
257
|
-
end
|
258
|
-
end
|
259
216
|
begin
|
260
217
|
log "Reading exons"
|
261
218
|
exons = Array.new
|
@@ -279,22 +236,28 @@ end
|
|
279
236
|
log "Searching markers in genome"
|
280
237
|
found_contigs = Set.new
|
281
238
|
exo_f = File.open(exonerate_file, "w")
|
282
|
-
|
283
|
-
|
284
|
-
|
239
|
+
|
240
|
+
def do_align(aln, exo_f, found_contigs, min_identity,fasta_file,options)
|
241
|
+
if aln.identity > min_identity
|
285
242
|
exo_f.puts aln.line
|
286
243
|
unless found_contigs.include?(aln.target_id) #We only add once each contig. Should reduce the size of the output file.
|
287
244
|
found_contigs.add(aln.target_id)
|
288
245
|
entry = fasta_file.index.region_for_entry(aln.target_id)
|
289
246
|
raise ExonerateException.new, "Entry not found! #{aln.target_id}. Make sure that the #{target_id}.fai was generated properly." if entry == nil
|
290
|
-
|
291
|
-
seq = fasta_file.fetch_sequence(region)
|
292
|
-
contigs_f.puts(">#{aln.target_id}\n#{seq}") if options[:extract_found_contigs]
|
247
|
+
|
293
248
|
end
|
294
249
|
end
|
295
250
|
end
|
251
|
+
|
252
|
+
Bio::DB::Blast.align({:query=>sequences, :target=>options[:database], :model=>model, :max_hits=>options[:max_hits]}) do |aln|
|
253
|
+
do_align(aln, exo_f, found_contigs,min_identity, fasta_file,options)
|
254
|
+
end if options[:aligner] == :blast
|
255
|
+
|
256
|
+
Bio::DB::Exonerate.align({:query=>sequences, :target=>target, :model=>model}) do |aln|
|
257
|
+
do_align(aln, exo_f, found_contigs, min_identity,fasta_file,options)
|
258
|
+
end if options[:aligner] == :exonerate
|
259
|
+
|
296
260
|
exo_f.close()
|
297
|
-
contigs_f.close() if options[:extract_found_contigs]
|
298
261
|
|
299
262
|
|
300
263
|
|
@@ -303,18 +266,24 @@ log "Reading best alignment on each chromosome"
|
|
303
266
|
container= Bio::PolyploidTools::ExonContainer.new
|
304
267
|
container.flanking_size=options[:flanking_size]
|
305
268
|
container.gene_models(sequences)
|
306
|
-
container.chromosomes(
|
269
|
+
container.chromosomes(reference)
|
307
270
|
container.add_parental({:name=>"A"})
|
308
271
|
container.add_parental({:name=>"B"})
|
309
272
|
exons.each do |exon|
|
310
273
|
exon.container = container
|
311
|
-
exon.flanking_size =
|
274
|
+
exon.flanking_size = 200
|
312
275
|
exon.variation_free_region = options[:variation_free_region]
|
313
|
-
#
|
276
|
+
#puts exon.inspect
|
314
277
|
container.add_snp(exon)
|
315
278
|
|
316
279
|
end
|
317
|
-
container.add_alignments(
|
280
|
+
container.add_alignments(
|
281
|
+
{:exonerate_file=>exonerate_file,
|
282
|
+
:arm_selection=>options[:arm_selection] ,
|
283
|
+
:min_identity=>min_identity})
|
284
|
+
|
285
|
+
|
286
|
+
|
318
287
|
|
319
288
|
#4.1 generating primer3 file
|
320
289
|
log "Running primer3"
|
@@ -348,18 +317,14 @@ exons.each do |snp|
|
|
348
317
|
end
|
349
318
|
|
350
319
|
kasp_container.add_primers_file(primer_3_output) if added_exons > 0
|
351
|
-
header = "Marker,SNP,RegionSize,chromosome,total_contigs,contig_regions,SNP_type,#{original_name},#{snp_in},common,primer_type,orientation,#{original_name}_TM,#{snp_in}_TM,common_TM,selected_from,product_size,errors"
|
320
|
+
header = "Marker,SNP,RegionSize,chromosome,total_contigs,contig_regions,SNP_type,#{original_name},#{snp_in},common,primer_type,orientation,#{original_name}_TM,#{snp_in}_TM,common_TM,selected_from,product_size,errors,repetitive,blast_hits"
|
352
321
|
File.open(output_primers, 'w') { |f| f.write("#{header}\n#{kasp_container.print_primers}") }
|
353
322
|
|
354
|
-
|
355
|
-
|
356
|
-
|
357
|
-
|
358
|
-
|
359
|
-
out_fasta_products = "#{output_folder}/#{name}.fa"
|
360
|
-
File.open(out_fasta_products, 'w') { |f| f.write(kaspSNP.realigned_primers_fasta) }
|
361
|
-
|
362
|
-
|
323
|
+
out_fasta_products = "#{output_folder}/products.fa"
|
324
|
+
File.open(out_fasta_products, 'w') do |f|
|
325
|
+
kasp_container.snp_hash.each_pair do |name, kaspSNP|
|
326
|
+
f.write(kaspSNP.realigned_primers_fasta)
|
327
|
+
end
|
363
328
|
end
|
364
329
|
|
365
330
|
File.open(output_to_order, "w") { |io| io.write(kasp_container.print_primers_with_tails()) }
|