ngs-ci 0.0.1.a
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.coveralls.yml +1 -0
- data/.gitignore +15 -0
- data/.rspec +1 -0
- data/.travis.yml +19 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +674 -0
- data/README.md +43 -0
- data/Rakefile +6 -0
- data/TODO.md +31 -0
- data/TODO.org +39 -0
- data/bin/ngs-ci +125 -0
- data/lib/NGSCI/calculator.rb +289 -0
- data/lib/NGSCI/cmd.rb +23 -0
- data/lib/NGSCI/read.rb +31 -0
- data/lib/NGSCI/version.rb +3 -0
- data/lib/NGSCI.rb +31 -0
- data/ngs-ci.gemspec +35 -0
- data/spec/lib/NGSCI_spec.rb +10 -0
- data/spec/lib/bin_spec.rb +51 -0
- data/spec/lib/calculator_spec.rb +316 -0
- data/spec/lib/cmd_spec.rb +17 -0
- data/spec/lib/read_spec.rb +35 -0
- data/spec/spec_helper.rb +11 -0
- data/spec/test_files/empty.bam +0 -0
- data/spec/test_files/test.bam +0 -0
- data/spec/test_files/test.bam.bai +0 -0
- data/spec/test_files/test.fa +2 -0
- metadata +209 -0
@@ -0,0 +1,51 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
testfasta="spec/test_files/test.fa"
|
4
|
+
testbam="spec/test_files/test.bam"
|
5
|
+
|
6
|
+
describe "bin executable" do
|
7
|
+
|
8
|
+
it "runs the --help option" do
|
9
|
+
c=NGSCI::Cmd.new("bundle exec bin/ngs-ci --help")
|
10
|
+
c.run
|
11
|
+
expect(c.stdout).to match /DESCRIPTION/
|
12
|
+
expect(c.status).to be_success
|
13
|
+
end
|
14
|
+
context "non-existent input files" do
|
15
|
+
it "fails on a non-existent bam file" do
|
16
|
+
c=NGSCI::Cmd.new("bundle exec bin/ngs-ci --bam foo.bam --reference #{testfasta}")
|
17
|
+
c.run
|
18
|
+
expect(c.status).to_not be_success
|
19
|
+
end
|
20
|
+
|
21
|
+
it "fails on a non-existent fasta file" do
|
22
|
+
c=NGSCI::Cmd.new("bundle exec bin/ngs-ci --bam #{testbam} --reference foo.fasta")
|
23
|
+
c.run
|
24
|
+
expect(c.status).to_not be_success
|
25
|
+
end
|
26
|
+
end
|
27
|
+
context "improper options" do
|
28
|
+
it "fails on improper strand-specific argument" do
|
29
|
+
c=NGSCI::Cmd.new("bundle exec bin/ngs-ci --bam #{testbam} --reference #{testfasta} --strand G")
|
30
|
+
c.run
|
31
|
+
expect(c.status).to_not be_success
|
32
|
+
end
|
33
|
+
it "fails on improper loglevel argument" do
|
34
|
+
c=NGSCI::Cmd.new("bundle exec bin/ngs-ci --bam #{testbam} --reference #{testfasta} --loglevel foo")
|
35
|
+
c.run
|
36
|
+
expect(c.status).to_not be_success
|
37
|
+
end
|
38
|
+
end
|
39
|
+
it "runs on test data" do
|
40
|
+
c=NGSCI::Cmd.new("bundle exec bin/ngs-ci --bam #{testbam} --reference #{testfasta} --strand F")
|
41
|
+
c.run
|
42
|
+
expect(c.status).to be_success
|
43
|
+
end
|
44
|
+
|
45
|
+
it "produces speed information" do
|
46
|
+
c=NGSCI::Cmd.new("bundle exec bin/ngs-ci --bam #{testbam} --reference #{testfasta} --loglevel debug")
|
47
|
+
c.run
|
48
|
+
expect(c.stdout).to include("Measure Mode:")
|
49
|
+
|
50
|
+
end
|
51
|
+
end
|
@@ -0,0 +1,316 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
require 'bio-samtools'
|
3
|
+
|
4
|
+
testbam="spec/test_files/test.bam"
|
5
|
+
emptybam="spec/test_files/empty.bam"
|
6
|
+
testfasta="spec/test_files/test.fa"
|
7
|
+
testout="spec/test_files/testfile.txt"
|
8
|
+
|
9
|
+
|
10
|
+
|
11
|
+
describe "#run" do
|
12
|
+
context "during a strand specific run" do
|
13
|
+
before(:each) do
|
14
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta,strand:"FR")
|
15
|
+
@testchrom=@calc.chroms.keys[0]
|
16
|
+
end
|
17
|
+
it "returns a hash" do
|
18
|
+
expect(@calc.run(runtime: false)).to be_instance_of Hash
|
19
|
+
end
|
20
|
+
it "returns the hash with keys of the chromosomes names" do
|
21
|
+
expect(@calc.run.keys).to eq(@calc.chroms.keys)
|
22
|
+
end
|
23
|
+
it "returns the hash with keys for each strand" do
|
24
|
+
expect(@calc.run[@testchrom].keys).to eq(%w(+ -))
|
25
|
+
end
|
26
|
+
it "returns NGSCI for each base of the genome" do
|
27
|
+
expect(@calc.run[@testchrom]["+"].size).to eq(@calc.chroms[@testchrom])
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
context "during an unstranded run" do
|
32
|
+
before(:each) do
|
33
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
34
|
+
@testchrom=@calc.chroms.keys[0]
|
35
|
+
end
|
36
|
+
it "returns the hash with keys of the chromosomes names" do
|
37
|
+
expect(@calc.run.keys).to eq(@calc.chroms.keys)
|
38
|
+
end
|
39
|
+
it "returns the hash with a nil strand key" do
|
40
|
+
expect(@calc.run[@testchrom].keys[0]).to be nil
|
41
|
+
end
|
42
|
+
it "returns NGSCI for each base of the genome" do
|
43
|
+
expect(@calc.run[@testchrom][nil].size).to eq(@calc.chroms[@testchrom])
|
44
|
+
end
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
describe "#readblock" do
|
49
|
+
context "when reading the first block" do
|
50
|
+
it "returns a hash with an array of length @block_size" do
|
51
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
52
|
+
results=@calc.readblock(@calc.chroms.keys[0],0)
|
53
|
+
result_length=results[results.keys[0]].size
|
54
|
+
expect(result_length).to eq(@calc.block_size)
|
55
|
+
end
|
56
|
+
end
|
57
|
+
context "when reading any other block" do
|
58
|
+
it "returns a hash with and array of length @block_size" do
|
59
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
60
|
+
results=@calc.readblock(@calc.chroms.keys[0],1)
|
61
|
+
result_length=results[results.keys[0]].size
|
62
|
+
expect(result_length).to eq(@calc.block_size)
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
describe "#sci" do
|
68
|
+
context "when passed an array of read objects" do
|
69
|
+
before(:each) do
|
70
|
+
@calc = NGSCI::Calculator.new(testbam,testfasta)
|
71
|
+
@bam = Bio::DB::Sam.new(:bam=>testbam,:fasta=>testfasta)
|
72
|
+
@bam.open
|
73
|
+
@reads = []
|
74
|
+
@bam.fetch("NC_001988.2",75,75){|x| read = @calc.convert(x); @reads << read unless read.nil?}
|
75
|
+
@reads = @reads.uniq{|r|r.start}
|
76
|
+
end
|
77
|
+
it "returns an array" do
|
78
|
+
expect(@calc.sci(@reads)).to be_kind_of(Array)
|
79
|
+
end
|
80
|
+
it "returns the sequencing complexity index" do
|
81
|
+
expect(@calc.sci(@reads)[-1]).to eq(0.0)
|
82
|
+
end
|
83
|
+
end
|
84
|
+
context "when passed an empty array" do
|
85
|
+
it "returns nil" do
|
86
|
+
@calc = NGSCI::Calculator.new(testbam,testfasta)
|
87
|
+
empty_sci = @calc.sci([])[-1]
|
88
|
+
expect(empty_sci).to be_zero
|
89
|
+
end
|
90
|
+
end
|
91
|
+
end
|
92
|
+
|
93
|
+
describe "#read_length" do
|
94
|
+
it "calculates the read length" do
|
95
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
96
|
+
expect(@calc.buffer).to eq(76)
|
97
|
+
end
|
98
|
+
it "fails on an empty bam file" do
|
99
|
+
expect{NGSCI::Calculator.new(emptybam,testfasta)}.to raise_error(NGSCI::NGSCIIOError)
|
100
|
+
`rm #{emptybam}.bai`
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
describe "#summed_overlaps" do
|
105
|
+
it "returns an int" do
|
106
|
+
@bam=Bio::DB::Sam.new(:bam=>testbam,:fasta=>testfasta)
|
107
|
+
@bam.open
|
108
|
+
@reads = []
|
109
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
110
|
+
@bam.fetch("NC_001988.2",8,75) {|x| read=@calc.convert(x); @reads << read if read}
|
111
|
+
@reads = @reads.uniq{|r| r.start}
|
112
|
+
expect(@calc.summed_overlaps(@reads)).to be_an(Integer)
|
113
|
+
end
|
114
|
+
context "when passed an array of read objects" do
|
115
|
+
before(:each) do
|
116
|
+
@bam=Bio::DB::Sam.new(:bam=>testbam,:fasta=>testfasta)
|
117
|
+
@bam.open
|
118
|
+
@reads = []
|
119
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
120
|
+
@bam.fetch("NC_001988.2",8,75) {|x| read=@calc.convert(x); @reads << read if read}
|
121
|
+
@reads = @reads.uniq{|r| r.start}
|
122
|
+
end
|
123
|
+
it "returns the #overlap of two reads" do
|
124
|
+
summed_overlap = 2*@calc.overlap(@reads[0],@reads[1])
|
125
|
+
expect(@calc.summed_overlaps(@reads[0..1])).to eq(summed_overlap)
|
126
|
+
end
|
127
|
+
|
128
|
+
it "calculates the average overlap between a group of reads" do
|
129
|
+
expect(@calc.summed_overlaps(@reads[0..7]).round(4)).to eq(380.0)
|
130
|
+
end
|
131
|
+
end
|
132
|
+
context "when passed an array with a single read object" do
|
133
|
+
it "returns zero" do
|
134
|
+
@bam=Bio::DB::Sam.new(:bam=>testbam,:fasta=>testfasta)
|
135
|
+
@bam.open
|
136
|
+
@reads=[]
|
137
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
138
|
+
@bam.fetch("NC_001988.2",8,75) {|x| read=@calc.convert(x); @reads << read if read}
|
139
|
+
expect(@calc.summed_overlaps([@reads[0]])).to be_zero
|
140
|
+
end
|
141
|
+
end
|
142
|
+
context "when passed an empty array" do
|
143
|
+
it "returns zero" do
|
144
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
145
|
+
expect(@calc.summed_overlaps([])).to be_zero
|
146
|
+
end
|
147
|
+
end
|
148
|
+
end
|
149
|
+
|
150
|
+
describe "#overlap" do
|
151
|
+
before(:each) do
|
152
|
+
@bam=Bio::DB::Sam.new(:bam=>testbam,:fasta=>testfasta)
|
153
|
+
@bam.open
|
154
|
+
@reads=[]
|
155
|
+
@bam.fetch("NC_001988.2",0,200) {|x| @reads << x}
|
156
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
157
|
+
@read1=@calc.convert(@reads[2])
|
158
|
+
@read2=@calc.convert(@reads[3])
|
159
|
+
end
|
160
|
+
it "calculates the overlap between two reads" do
|
161
|
+
expect(@calc.overlap(@read1,@read2)).to eq(14)
|
162
|
+
end
|
163
|
+
|
164
|
+
it "calculates the overlap regardless of order" do
|
165
|
+
expect(@calc.overlap(@read2,@read1)).to eq(14)
|
166
|
+
end
|
167
|
+
end
|
168
|
+
|
169
|
+
describe '#reference_sequences' do
|
170
|
+
before(:each) do
|
171
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
172
|
+
end
|
173
|
+
|
174
|
+
it "retrieves reference sequences" do
|
175
|
+
expect(@calc.reference_sequences(testfasta).keys).to include "NC_001988.2"
|
176
|
+
end
|
177
|
+
end
|
178
|
+
|
179
|
+
describe '#newread' do
|
180
|
+
before(:each) do
|
181
|
+
@bam=Bio::DB::Sam.new(:bam=>testbam,:fasta=>testfasta)
|
182
|
+
@bam.open
|
183
|
+
@reads=[]
|
184
|
+
@bam.fetch("NC_001988.2",0,200) {|x| @reads << x}
|
185
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
186
|
+
end
|
187
|
+
|
188
|
+
it "converts an alignment object to a read object" do
|
189
|
+
expect(@calc.newread(@reads[0])).to be_instance_of NGSCI::Read
|
190
|
+
end
|
191
|
+
end
|
192
|
+
|
193
|
+
describe "#fr" do
|
194
|
+
before(:each) do
|
195
|
+
@bam=Bio::DB::Sam.new(:bam=>testbam,:fasta=>testfasta)
|
196
|
+
@bam.open
|
197
|
+
@reads=[]
|
198
|
+
@bam.fetch("NC_001988.2",0,200) {|x| @reads << x}
|
199
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
200
|
+
@testpair=[@reads[5],@reads[10]]
|
201
|
+
end
|
202
|
+
|
203
|
+
it "converts the first read with FR chemistry" do
|
204
|
+
first=@calc.fr(@testpair[0])
|
205
|
+
expect(first.strand).to eq("+")
|
206
|
+
end
|
207
|
+
it "converts the second read with FR chemistry" do
|
208
|
+
second=@calc.fr(@testpair[1])
|
209
|
+
expect(second.strand).to eq("+")
|
210
|
+
end
|
211
|
+
end
|
212
|
+
|
213
|
+
describe "#rf" do
|
214
|
+
before(:each) do
|
215
|
+
@bam=Bio::DB::Sam.new(:bam=>testbam,:fasta=>testfasta)
|
216
|
+
@bam.open
|
217
|
+
@reads=[]
|
218
|
+
@bam.fetch("NC_001988.2",0,200) {|x| @reads << x}
|
219
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
220
|
+
@testpair=[@reads[5],@reads[10]]
|
221
|
+
end
|
222
|
+
it "converts the first read with RF chemistry" do
|
223
|
+
first=@calc.rf(@testpair[0])
|
224
|
+
expect(first.strand).to eq("-")
|
225
|
+
end
|
226
|
+
|
227
|
+
it "converts the second read with RF chemistry" do
|
228
|
+
second=@calc.rf(@testpair[1])
|
229
|
+
expect(second.strand).to eq("-")
|
230
|
+
end
|
231
|
+
end
|
232
|
+
|
233
|
+
describe "#f" do
|
234
|
+
before(:each) do
|
235
|
+
@bam=Bio::DB::Sam.new(:bam=>testbam,:fasta=>testfasta)
|
236
|
+
@bam.open
|
237
|
+
@reads=[]
|
238
|
+
@bam.fetch("NC_001988.2",0,200) {|x| @reads << x}
|
239
|
+
@calc=NGSCI::Calculator.new(testbam,testfasta)
|
240
|
+
@testpair=[@reads[5],@reads[10]]
|
241
|
+
end
|
242
|
+
it "converts a read with F chemistry on the + strand" do
|
243
|
+
first=@calc.f(@testpair[0])
|
244
|
+
expect(first.strand).to eq("-")
|
245
|
+
end
|
246
|
+
it "converts a read with F chemistry on the - strand" do
|
247
|
+
second=@calc.f(@testpair[1])
|
248
|
+
expect(second.strand).to eq("+")
|
249
|
+
end
|
250
|
+
|
251
|
+
end
|
252
|
+
|
253
|
+
describe '#convert' do
|
254
|
+
before(:each) do
|
255
|
+
@bam=Bio::DB::Sam.new(:bam=>testbam,:fasta=>testfasta)
|
256
|
+
@bam.open
|
257
|
+
@reads=[]
|
258
|
+
@bam.fetch("NC_001988.2",0,200) {|x| @reads << x}
|
259
|
+
end
|
260
|
+
it "converts an alignment object to a read object" do
|
261
|
+
calc=NGSCI::Calculator.new(testbam,testfasta)
|
262
|
+
expect(calc.convert(@reads[2])).to be_instance_of NGSCI::Read
|
263
|
+
end
|
264
|
+
|
265
|
+
it "returns nil for an unmapped read" do
|
266
|
+
calc=NGSCI::Calculator.new(testbam,testfasta)
|
267
|
+
expect(calc.convert(@reads[1])).to be_nil
|
268
|
+
end
|
269
|
+
|
270
|
+
it "converts the first read in FR chemistry aligned to the + strand" do
|
271
|
+
calc=NGSCI::Calculator.new(testbam,testfasta,strand:"FR")
|
272
|
+
testpair=[@reads[5],@reads[10]]
|
273
|
+
first=calc.convert(testpair[1])
|
274
|
+
expect(first.strand).to eq("+")
|
275
|
+
end
|
276
|
+
it "converts the second read in FR chemistry aligned to the - strand" do
|
277
|
+
calc=NGSCI::Calculator.new(testbam,testfasta,strand:"FR")
|
278
|
+
testpair=[@reads[5],@reads[10]]
|
279
|
+
second=calc.convert(testpair[0])
|
280
|
+
expect(second.strand).to eq("+")
|
281
|
+
end
|
282
|
+
it "converts the first read in RF chemistry aligned to the + strand" do
|
283
|
+
calc=NGSCI::Calculator.new(testbam,testfasta,strand:"RF")
|
284
|
+
testpair=[@reads[5],@reads[10]]
|
285
|
+
first=calc.convert(testpair[1])
|
286
|
+
expect(first.strand).to eq("-")
|
287
|
+
end
|
288
|
+
it "converts the second read in FR chemistry aligned to the - strand" do
|
289
|
+
calc=NGSCI::Calculator.new(testbam,testfasta,strand:"RF")
|
290
|
+
testpair=[@reads[5],@reads[10]]
|
291
|
+
second=calc.convert(testpair[0])
|
292
|
+
expect(second.strand).to eq("-")
|
293
|
+
end
|
294
|
+
|
295
|
+
end
|
296
|
+
|
297
|
+
describe "#export" do
|
298
|
+
context "calculator has not run" do
|
299
|
+
it "returns nil" do
|
300
|
+
calc=NGSCI::Calculator.new(testbam,testfasta)
|
301
|
+
expect(calc.export(testout)).to be nil
|
302
|
+
end
|
303
|
+
end
|
304
|
+
context "calculator has run" do
|
305
|
+
after(:all) do
|
306
|
+
`rm #{testout}`
|
307
|
+
end
|
308
|
+
it "returns outfile" do
|
309
|
+
calc=NGSCI::Calculator.new(testbam,testfasta)
|
310
|
+
calc.run
|
311
|
+
expect(calc.export(testout)).to eq(testout)
|
312
|
+
end
|
313
|
+
end
|
314
|
+
end
|
315
|
+
|
316
|
+
|
@@ -0,0 +1,17 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
|
4
|
+
describe "command" do
|
5
|
+
|
6
|
+
it "runs commands" do
|
7
|
+
c=NGSCI::Cmd.new("echo success")
|
8
|
+
c.run
|
9
|
+
expect(c.stdout.chomp).to eq("success")
|
10
|
+
end
|
11
|
+
|
12
|
+
it "receives commands" do
|
13
|
+
c=NGSCI::Cmd.new("echo success")
|
14
|
+
expect(c.to_s).to eq("echo success")
|
15
|
+
end
|
16
|
+
|
17
|
+
end
|
@@ -0,0 +1,35 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
|
4
|
+
describe "reads" do
|
5
|
+
|
6
|
+
it "fails to instantiate on a string start site" do
|
7
|
+
expect{NGSCI::Read.new("foo",3)}.to raise_error(NGSCI::NGSCIError)
|
8
|
+
end
|
9
|
+
|
10
|
+
it "fails to instantiate on a string stop site" do
|
11
|
+
expect{NGSCI::Read.new(1,"foo")}.to raise_error(NGSCI::NGSCIError)
|
12
|
+
end
|
13
|
+
|
14
|
+
it "fails to instantiate when the stop site is greater than the start site" do
|
15
|
+
expect{NGSCI::Read.new(3,1)}.to raise_error(NGSCI::NGSCIError)
|
16
|
+
end
|
17
|
+
|
18
|
+
it "fails to instantiate on an improper strand argument" do
|
19
|
+
expect{NGSCI::Read.new(1,3,strand:"foo")}.to raise_error(NGSCI::NGSCIError)
|
20
|
+
end
|
21
|
+
|
22
|
+
it "fails to instantiate without the three necessary arguments" do
|
23
|
+
expect{NGSCI::Read.new(1)}.to raise_error(ArgumentError)
|
24
|
+
end
|
25
|
+
|
26
|
+
it "instantiates a new read with proper unstranded arguments" do
|
27
|
+
expect{NGSCI::Read.new(1,3)}.to_not raise_error
|
28
|
+
end
|
29
|
+
|
30
|
+
it "instantiates a new read with proper stranded arguments" do
|
31
|
+
expect{NGSCI::Read.new(1,3,strand:"+")}.to_not raise_error
|
32
|
+
end
|
33
|
+
|
34
|
+
|
35
|
+
end
|
data/spec/spec_helper.rb
ADDED
Binary file
|
Binary file
|
Binary file
|