bio-vcf 0.0.2 → 0.0.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (29) hide show
  1. checksums.yaml +4 -4
  2. data/Gemfile +1 -0
  3. data/Gemfile.lock +8 -0
  4. data/README.md +376 -11
  5. data/VERSION +1 -1
  6. data/bin/bio-vcf +172 -39
  7. data/bio-vcf.gemspec +18 -3
  8. data/features/cli.feature +32 -0
  9. data/features/multisample.feature +28 -10
  10. data/features/step_definitions/cli-feature.rb +12 -0
  11. data/features/step_definitions/multisample.rb +64 -18
  12. data/features/support/env.rb +5 -0
  13. data/lib/bio-vcf.rb +2 -0
  14. data/lib/bio-vcf/utils.rb +23 -0
  15. data/lib/bio-vcf/vcfgenotypefield.rb +73 -28
  16. data/lib/bio-vcf/vcfheader.rb +8 -0
  17. data/lib/bio-vcf/vcfline.rb +1 -0
  18. data/lib/bio-vcf/vcfrecord.rb +142 -14
  19. data/lib/bio-vcf/vcfsample.rb +88 -0
  20. data/test/data/input/dbsnp.vcf +200 -0
  21. data/test/data/input/multisample.vcf +2 -2
  22. data/test/data/regression/eval_r.info.dp.ref +150 -0
  23. data/test/data/regression/r.info.dp.ref +147 -0
  24. data/test/data/regression/rewrite.info.sample.ref +150 -0
  25. data/test/data/regression/s.dp.ref +145 -0
  26. data/test/data/regression/seval_s.dp.ref +36 -0
  27. data/test/data/regression/sfilter001.ref +145 -0
  28. data/test/performance/metrics.md +98 -0
  29. metadata +28 -2
data/test/performance/metrics.md ADDED
@@ -0,0 +1,98 @@
1
+ Round of testing with
2
+
3
+ ruby -v
4
+ ruby 2.1.0p0 (2013-12-25 revision 44422) [x86_64-linux]
5
+
6
+ wc test/tmp/test.vcf
7
+ 12469 137065 2053314 test/tmp/test.vcf
8
+
9
+ time ./bin/bio-vcf -i --filter 'r.info.dp>20' --sfilter 's.dp>10' < test/tmp/test.vcf > /dev/null
10
+ vcf 0.0.3-pre4 (biogem Ruby 2.1.0) by Pjotr Prins 2014
11
+ Options: {:show_help=>false, :ignore_missing=>true, :filter=>"r.info.dp>20", :sfilter=>"s.dp>10"}
12
+ real 0m1.215s
13
+ user 0m1.208s
14
+ sys 0m0.004s
15
+
16
+ Reload
17
+
18
+ time ./bin/bio-vcf -i --filter 'r.info.dp>20' --sfilter 's.dp>10' < test/tmp/test.vcf > /dev/null
19
+ vcf 0.0.3-pre4 (biogem Ruby 2.1.0) by Pjotr Prins 2014
20
+ Options: {:show_help=>false, :ignore_missing=>true, :filter=>"r.info.dp>20", :sfilter=>"s.dp>10"}
21
+ real 0m1.194s
22
+ user 0m1.172s
23
+ sys 0m0.016s
24
+
25
+ Introduced method caching
26
+
27
+ real 0m1.190s
28
+ user 0m1.180s
29
+ sys 0m0.004s
30
+
31
+ Introduce !!Float test
32
+
33
+ real 0m1.187s
34
+ user 0m1.180s
35
+ sys 0m0.004s
36
+
37
+ Cache sample index
38
+
39
+ real 0m1.156s
40
+ user 0m1.148s
41
+ sys 0m0.004s
42
+
43
+ Run the profiler
44
+
45
+ ruby -rprofile ./bin/bio-vcf -i --filter 'r.info.dp>20' --sfilter 's.dp>10' < test/tmp/test.vcf > /dev/null
46
+ vcf 0.0.3-pre4 (biogem Ruby 2.1.0) by Pjotr Prins 2014
47
+ Options: {:show_help=>false, :ignore_missing=>true, :filter=>"r.info.dp>20", :sfilter=>"s.dp>10"}
48
+ % cumulative self self total
49
+ time seconds seconds calls ms/call ms/call name
50
+ 9.45 2.19 2.19 34968 0.06 0.76 Object#parse_line
51
+ 7.25 3.87 1.68 75031 0.02 0.03 BioVcf::VcfRecordInfo#[]=
52
+ 7.12 5.52 1.65 34968 0.05 0.29 Kernel.eval
53
+ 6.86 7.11 1.59 87481 0.02 0.10 BioVcf::VcfRecordInfo#initialize
54
+ 5.57 8.40 1.29 35994 0.04 0.47 Array#each
55
+ 4.14 9.36 0.96 34253 0.03 0.65 BioVcf::VcfRecord#each_sample
56
+ 3.93 10.27 0.91 93880 0.01 0.03 BioVcf::VcfRecordParser.get_format
57
+ 3.88 11.17 0.90 145920 0.01 0.01 String#split
58
+
59
+ Late parsing of info field without split:
60
+
61
+ real 0m1.124s
62
+ user 0m1.120s
63
+ sys 0m0.008s
64
+
65
+ Global sample info caching
66
+
67
+ real 0m1.032s
68
+ user 0m1.020s
69
+ sys 0m0.008s
70
+
71
+ Assign some repeated Hash queries
72
+
73
+ real 0m1.028s
74
+ user 0m1.024s
75
+ sys 0m0.000s
76
+
77
+ Profiler now picking out eval for further optimization
78
+
79
+ % cumulative self self total
80
+ time seconds seconds calls ms/call ms/call name
81
+ 10.45 1.80 1.80 34968 0.05 0.59 Object#parse_line
82
+ 7.89 3.16 1.36 34968 0.04 0.17 Kernel.eval
83
+ 5.69 4.14 0.98 34253 0.03 0.57 BioVcf::VcfRecord#each_sample
84
+ 4.93 4.99 0.85 12497 0.07 1.37 nil#
85
+
86
+ Compiling sample eval
87
+
88
+ real 0m0.820s
89
+ user 0m0.812s
90
+ sys 0m0.004s
91
+
92
+ Compiling record eval
93
+
94
+ real 0m0.647s
95
+ user 0m0.644s
96
+ sys 0m0.000s
97
+
98
+
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: bio-vcf
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.0.2
4
+ version: 0.0.3
5
5
  platform: ruby
6
6
  authors:
7
7
  - Pjotr Prins
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2014-03-05 00:00:00.000000000 Z
11
+ date: 2014-05-24 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: rspec
@@ -52,6 +52,20 @@ dependencies:
52
52
  - - ">="
53
53
  - !ruby/object:Gem::Version
54
54
  version: '0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: regressiontest
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - ">="
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - ">="
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
55
69
  description: Smart parser for VCF format
56
70
  email: pjotr.public01@thebird.nl
57
71
  executables:
@@ -70,15 +84,18 @@ files:
70
84
  - VERSION
71
85
  - bin/bio-vcf
72
86
  - bio-vcf.gemspec
87
+ - features/cli.feature
73
88
  - features/diff_count.feature
74
89
  - features/multisample.feature
75
90
  - features/somaticsniper.feature
76
91
  - features/step_definitions/bio-vcf_steps.rb
92
+ - features/step_definitions/cli-feature.rb
77
93
  - features/step_definitions/diff_count.rb
78
94
  - features/step_definitions/multisample.rb
79
95
  - features/step_definitions/somaticsniper.rb
80
96
  - features/support/env.rb
81
97
  - lib/bio-vcf.rb
98
+ - lib/bio-vcf/utils.rb
82
99
  - lib/bio-vcf/variant.rb
83
100
  - lib/bio-vcf/vcf.rb
84
101
  - lib/bio-vcf/vcfgenotypefield.rb
@@ -86,8 +103,17 @@ files:
86
103
  - lib/bio-vcf/vcfline.rb
87
104
  - lib/bio-vcf/vcfrdf.rb
88
105
  - lib/bio-vcf/vcfrecord.rb
106
+ - lib/bio-vcf/vcfsample.rb
107
+ - test/data/input/dbsnp.vcf
89
108
  - test/data/input/multisample.vcf
90
109
  - test/data/input/somaticsniper.vcf
110
+ - test/data/regression/eval_r.info.dp.ref
111
+ - test/data/regression/r.info.dp.ref
112
+ - test/data/regression/rewrite.info.sample.ref
113
+ - test/data/regression/s.dp.ref
114
+ - test/data/regression/seval_s.dp.ref
115
+ - test/data/regression/sfilter001.ref
116
+ - test/performance/metrics.md
91
117
  homepage: http://github.com/pjotrp/bioruby-vcf
92
118
  licenses:
93
119
  - MIT