bioinform 0.1.17 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile +3 -3
- data/LICENSE +0 -1
- data/README.md +1 -1
- data/TODO.txt +23 -30
- data/bin/convert_motif +4 -0
- data/bin/pcm2pwm +1 -1
- data/bin/split_motifs +1 -1
- data/bioinform.gemspec +0 -2
- data/lib/bioinform.rb +54 -16
- data/lib/bioinform/alphabet.rb +85 -0
- data/lib/bioinform/background.rb +90 -0
- data/lib/bioinform/cli.rb +1 -2
- data/lib/bioinform/cli/convert_motif.rb +52 -17
- data/lib/bioinform/cli/pcm2pwm.rb +32 -26
- data/lib/bioinform/cli/split_motifs.rb +31 -30
- data/lib/bioinform/conversion_algorithms.rb +6 -0
- data/lib/bioinform/conversion_algorithms/pcm2ppm_converter.rb +13 -11
- data/lib/bioinform/conversion_algorithms/pcm2pwm_converter.rb +39 -11
- data/lib/bioinform/conversion_algorithms/pcm2pwm_mara_converter.rb +26 -0
- data/lib/bioinform/conversion_algorithms/ppm2pcm_converter.rb +30 -0
- data/lib/bioinform/conversion_algorithms/pwm2iupac_pwm_converter.rb +23 -0
- data/lib/bioinform/conversion_algorithms/pwm2pcm_converter.rb +85 -0
- data/lib/bioinform/data_models.rb +1 -7
- data/lib/bioinform/data_models/named_model.rb +38 -0
- data/lib/bioinform/data_models/pcm.rb +18 -28
- data/lib/bioinform/data_models/pm.rb +73 -170
- data/lib/bioinform/data_models/ppm.rb +11 -24
- data/lib/bioinform/data_models/pwm.rb +30 -56
- data/lib/bioinform/errors.rb +17 -0
- data/lib/bioinform/formatters.rb +4 -2
- data/lib/bioinform/formatters/consensus_formatter.rb +35 -0
- data/lib/bioinform/formatters/motif_formatter.rb +69 -0
- data/lib/bioinform/formatters/pretty_matrix_formatter.rb +36 -0
- data/lib/bioinform/formatters/transfac_formatter.rb +29 -37
- data/lib/bioinform/parsers.rb +1 -8
- data/lib/bioinform/parsers/matrix_parser.rb +44 -36
- data/lib/bioinform/parsers/motif_splitter.rb +45 -0
- data/lib/bioinform/support.rb +46 -14
- data/lib/bioinform/support/strip_doc.rb +1 -1
- data/lib/bioinform/version.rb +1 -1
- data/spec/alphabet_spec.rb +79 -0
- data/spec/background_spec.rb +57 -0
- data/spec/cli/cli_spec.rb +6 -6
- data/spec/cli/convert_motif_spec.rb +88 -88
- data/spec/cli/data/pcm2pwm/KLF4_f2.pwm.result +9 -9
- data/spec/cli/data/pcm2pwm/SP1_f1.pwm.result +11 -11
- data/spec/cli/pcm2pwm_spec.rb +22 -23
- data/spec/cli/shared_examples/convert_motif/motif_list_empty.rb +1 -1
- data/spec/cli/shared_examples/convert_motif/several_motifs_specified.rb +1 -1
- data/spec/cli/shared_examples/convert_motif/single_motif_specified.rb +5 -5
- data/spec/cli/shared_examples/convert_motif/yield_help_string.rb +2 -2
- data/spec/cli/shared_examples/convert_motif/yield_motif_conversion_error.rb +3 -3
- data/spec/cli/split_motifs_spec.rb +6 -21
- data/spec/converters/pcm2ppm_converter_spec.rb +32 -0
- data/spec/converters/pcm2pwm_converter_spec.rb +71 -0
- data/spec/converters/ppm2pcm_converter_spec.rb +32 -0
- data/spec/converters/pwm2iupac_pwm_converter_spec.rb +65 -0
- data/spec/converters/pwm2pcm_converter_spec.rb +57 -0
- data/spec/data_models/named_model_spec.rb +41 -0
- data/spec/data_models/pcm_spec.rb +114 -45
- data/spec/data_models/pm_spec.rb +132 -333
- data/spec/data_models/ppm_spec.rb +47 -44
- data/spec/data_models/pwm_spec.rb +85 -77
- data/spec/fabricators/motif_formats_fabricator.rb +116 -116
- data/spec/formatters/consensus_formatter_spec.rb +26 -0
- data/spec/formatters/raw_formatter_spec.rb +169 -0
- data/spec/parsers/matrix_parser_spec.rb +216 -0
- data/spec/parsers/motif_splitter_spec.rb +87 -0
- data/spec/spec_helper.rb +2 -2
- data/spec/spec_helper_source.rb +25 -5
- data/spec/support_spec.rb +31 -0
- metadata +43 -124
- data/bin/merge_into_collection +0 -4
- data/lib/bioinform/cli/merge_into_collection.rb +0 -80
- data/lib/bioinform/conversion_algorithms/ppm2pwm_converter.rb +0 -0
- data/lib/bioinform/data_models/collection.rb +0 -75
- data/lib/bioinform/data_models/motif.rb +0 -56
- data/lib/bioinform/formatters/raw_formatter.rb +0 -41
- data/lib/bioinform/parsers/jaspar_parser.rb +0 -35
- data/lib/bioinform/parsers/parser.rb +0 -92
- data/lib/bioinform/parsers/splittable_parser.rb +0 -57
- data/lib/bioinform/parsers/string_fantom_parser.rb +0 -35
- data/lib/bioinform/parsers/string_parser.rb +0 -72
- data/lib/bioinform/parsers/trivial_parser.rb +0 -34
- data/lib/bioinform/parsers/yaml_parser.rb +0 -35
- data/lib/bioinform/support/advanced_scan.rb +0 -8
- data/lib/bioinform/support/array_product.rb +0 -6
- data/lib/bioinform/support/array_zip.rb +0 -6
- data/lib/bioinform/support/collect_hash.rb +0 -7
- data/lib/bioinform/support/deep_dup.rb +0 -5
- data/lib/bioinform/support/delete_many.rb +0 -14
- data/lib/bioinform/support/inverf.rb +0 -13
- data/lib/bioinform/support/multiline_squish.rb +0 -6
- data/lib/bioinform/support/parameters.rb +0 -28
- data/lib/bioinform/support/partial_sums.rb +0 -16
- data/lib/bioinform/support/same_by.rb +0 -12
- data/lib/bioinform/support/third_part/active_support/core_ext/array/extract_options.rb +0 -29
- data/lib/bioinform/support/third_part/active_support/core_ext/hash/indifferent_access.rb +0 -23
- data/lib/bioinform/support/third_part/active_support/core_ext/hash/keys.rb +0 -54
- data/lib/bioinform/support/third_part/active_support/core_ext/module/attribute_accessors.rb +0 -64
- data/lib/bioinform/support/third_part/active_support/core_ext/object/try.rb +0 -57
- data/lib/bioinform/support/third_part/active_support/core_ext/string/access.rb +0 -99
- data/lib/bioinform/support/third_part/active_support/core_ext/string/behavior.rb +0 -6
- data/lib/bioinform/support/third_part/active_support/core_ext/string/filters.rb +0 -49
- data/lib/bioinform/support/third_part/active_support/core_ext/string/multibyte.rb +0 -72
- data/lib/bioinform/support/third_part/active_support/hash_with_indifferent_access.rb +0 -181
- data/lib/bioinform/support/third_part/active_support/multibyte.rb +0 -44
- data/lib/bioinform/support/third_part/active_support/multibyte/chars.rb +0 -476
- data/lib/bioinform/support/third_part/active_support/multibyte/exceptions.rb +0 -8
- data/lib/bioinform/support/third_part/active_support/multibyte/unicode.rb +0 -393
- data/lib/bioinform/support/third_part/active_support/multibyte/utils.rb +0 -60
- data/spec/cli/data/merge_into_collection/GABPA_f1.pwm +0 -14
- data/spec/cli/data/merge_into_collection/KLF4_f2.pwm +0 -11
- data/spec/cli/data/merge_into_collection/SP1_f1.pwm +0 -12
- data/spec/cli/data/merge_into_collection/collection.txt.result +0 -40
- data/spec/cli/data/merge_into_collection/collection.yaml.result +0 -188
- data/spec/cli/data/merge_into_collection/collection_pwm.yaml.result +0 -188
- data/spec/cli/data/merge_into_collection/pwm_folder/GABPA_f1.pwm +0 -14
- data/spec/cli/data/merge_into_collection/pwm_folder/KLF4_f2.pwm +0 -11
- data/spec/cli/data/merge_into_collection/pwm_folder/SP1_f1.pwm +0 -12
- data/spec/cli/data/split_motifs/collection.yaml +0 -188
- data/spec/cli/merge_into_collection_spec.rb +0 -100
- data/spec/data_models/collection_spec.rb +0 -98
- data/spec/data_models/motif_spec.rb +0 -224
- data/spec/fabricators/collection_fabricator.rb +0 -8
- data/spec/fabricators/motif_fabricator.rb +0 -33
- data/spec/fabricators/pcm_fabricator.rb +0 -25
- data/spec/fabricators/pm_fabricator.rb +0 -52
- data/spec/fabricators/ppm_fabricator.rb +0 -14
- data/spec/fabricators/pwm_fabricator.rb +0 -16
- data/spec/parsers/parser_spec.rb +0 -152
- data/spec/parsers/string_fantom_parser_spec.rb +0 -70
- data/spec/parsers/string_parser_spec.rb +0 -77
- data/spec/parsers/trivial_parser_spec.rb +0 -64
- data/spec/parsers/yaml_parser_spec.rb +0 -50
- data/spec/support/advanced_scan_spec.rb +0 -32
- data/spec/support/array_product_spec.rb +0 -15
- data/spec/support/array_zip_spec.rb +0 -15
- data/spec/support/collect_hash_spec.rb +0 -15
- data/spec/support/delete_many_spec.rb +0 -44
- data/spec/support/inverf_spec.rb +0 -19
- data/spec/support/multiline_squish_spec.rb +0 -25
- data/spec/support/partial_sums_spec.rb +0 -30
- data/spec/support/same_by_spec.rb +0 -36
@@ -1,8 +0,0 @@
|
|
1
|
-
Fabricator(:three_elements_collection, class_name: Bioinform::Collection, aliases: [:pm_collection]) do
|
2
|
-
name 'PM_collection'
|
3
|
-
after_build{|collection| collection << Fabricate(:pm_1) << Fabricate(:pm_2) << Fabricate(:pm_3) }
|
4
|
-
end
|
5
|
-
|
6
|
-
Fabricator(:unnamed_pm_collection, from: :pm_collection) do
|
7
|
-
name nil
|
8
|
-
end
|
@@ -1,33 +0,0 @@
|
|
1
|
-
Fabricator(:motif, class_name: Bioinform::Motif) do
|
2
|
-
end
|
3
|
-
|
4
|
-
Fabricator(:motif_with_name, from: :motif) do
|
5
|
-
name 'Motif name'
|
6
|
-
end
|
7
|
-
|
8
|
-
Fabricator(:motif_pcm, from: :motif) do
|
9
|
-
pcm(fabricator: :pcm)
|
10
|
-
end
|
11
|
-
|
12
|
-
Fabricator(:motif_pwm, from: :motif) do
|
13
|
-
pwm(fabricator: :pwm)
|
14
|
-
end
|
15
|
-
|
16
|
-
Fabricator(:motif_ppm, from: :motif) do
|
17
|
-
ppm(fabricator: :ppm)
|
18
|
-
end
|
19
|
-
|
20
|
-
Fabricator(:motif_pcm_and_ppm, from: :motif) do
|
21
|
-
pcm(fabricator: :pcm)
|
22
|
-
ppm(fabricator: :ppm)
|
23
|
-
end
|
24
|
-
|
25
|
-
Fabricator(:motif_pwm_and_ppm, from: :motif) do
|
26
|
-
pwm(fabricator: :pwm)
|
27
|
-
ppm(fabricator: :ppm)
|
28
|
-
end
|
29
|
-
|
30
|
-
Fabricator(:motif_pcm_and_pwm, from: :motif) do
|
31
|
-
pcm(fabricator: :pcm)
|
32
|
-
pwm(fabricator: :pwm)
|
33
|
-
end
|
@@ -1,25 +0,0 @@
|
|
1
|
-
Fabricator(:pcm, class_name: Bioinform::PCM) do
|
2
|
-
initialize_with{ Bioinform::PCM.new(matrix: [[1, 2, 3, 1],[4, 0, 1, 2]], name: 'PCM_name') }
|
3
|
-
end
|
4
|
-
|
5
|
-
Fabricator(:pcm_with_floats, from: :pcm) do
|
6
|
-
matrix [[1, 2.3, 3.2, 1],[4.4, 0.1, 0.9, 2.1]]
|
7
|
-
end
|
8
|
-
|
9
|
-
Fabricator(:completely_different_pcm, from: :pcm) do
|
10
|
-
matrix [[101,207,138,248],[85,541,7,61]]
|
11
|
-
name 'PCM_another_name'
|
12
|
-
end
|
13
|
-
|
14
|
-
Fabricator(:pcm_1, from: :pcm) do
|
15
|
-
matrix [[7,10,2,3],[4,5,6,7]]
|
16
|
-
name 'motif_1'
|
17
|
-
end
|
18
|
-
Fabricator(:pcm_2, from: :pcm) do
|
19
|
-
matrix [[5,7,4,6],[11,6,2,3],[10,3,3,6]]
|
20
|
-
name 'motif_2'
|
21
|
-
end
|
22
|
-
Fabricator(:pcm_3, from: :pcm) do
|
23
|
-
matrix [[3,4,1,14],[9,2,9,2]]
|
24
|
-
name 'motif_3'
|
25
|
-
end
|
@@ -1,52 +0,0 @@
|
|
1
|
-
Fabricator(:pm, class_name: Bioinform::PM) do
|
2
|
-
initialize_with{ Bioinform::PM.new(matrix: [[1,2,3,4],[5,6,7,8]], name: 'PM_name') }
|
3
|
-
end
|
4
|
-
|
5
|
-
Fabricator(:pm_unnamed, from: :pm) do
|
6
|
-
name nil
|
7
|
-
end
|
8
|
-
|
9
|
-
|
10
|
-
Fabricator(:pm_first, from: :pm) do
|
11
|
-
name 'PM_first'
|
12
|
-
end
|
13
|
-
|
14
|
-
Fabricator(:pm_second, from: :pm) do
|
15
|
-
matrix [[15,16,17,18],[11,21,31,41]]
|
16
|
-
name 'PM_second'
|
17
|
-
end
|
18
|
-
|
19
|
-
|
20
|
-
Fabricator(:pm_4x4, from: :pm) do
|
21
|
-
matrix [[1,2,3,4],[5,6,7,8],[9,10,11,12],[13,14,15,16]]
|
22
|
-
end
|
23
|
-
|
24
|
-
Fabricator(:pm_4x4_unnamed, from: :pm_4x4) do
|
25
|
-
name nil
|
26
|
-
end
|
27
|
-
|
28
|
-
Fabricator(:pm_with_floats, from: :pm_unnamed) do
|
29
|
-
matrix [[1.23, 4.56, 7.8, 9.0], [9, -8.7, 6.54, -3210]]
|
30
|
-
end
|
31
|
-
|
32
|
-
Fabricator(:pm_1, from: :pm) do
|
33
|
-
matrix [[0,1,2,3],[4,5,6,7]]
|
34
|
-
name 'motif_1'
|
35
|
-
end
|
36
|
-
Fabricator(:pm_2, from: :pm) do
|
37
|
-
matrix [[1,2,3,4],[5,6,7,8],[9,10,11,12]]
|
38
|
-
name 'motif_2'
|
39
|
-
end
|
40
|
-
Fabricator(:pm_3, from: :pm) do
|
41
|
-
matrix [[2,3,4,5],[6,7,8,9]]
|
42
|
-
name 'motif_3'
|
43
|
-
end
|
44
|
-
|
45
|
-
Fabricator(:pm_4,from: :pm) do
|
46
|
-
matrix [[1,0,1,0],[0,0,0,0],[1,2,3,4]]
|
47
|
-
name 'pm 4'
|
48
|
-
end
|
49
|
-
Fabricator(:pm_5, from: :pm) do
|
50
|
-
matrix [[1,2,1,2],[0,3,6,9],[1,2,3,4]]
|
51
|
-
name 'pm 5'
|
52
|
-
end
|
@@ -1,14 +0,0 @@
|
|
1
|
-
Fabricator(:ppm, class_name: Bioinform::PPM) do
|
2
|
-
initialize_with{ Bioinform::PPM.new(matrix: [[0.2, 0.3, 0.3, 0.2],[0.7, 0.2, 0.0, 0.1]]) }
|
3
|
-
name 'PPM_name'
|
4
|
-
end
|
5
|
-
|
6
|
-
# It has the same name as original pcm because PCM#to_ppm doesn't change the name
|
7
|
-
Fabricator(:ppm_by_pcm, class_name: Bioinform::PPM) do
|
8
|
-
initialize_with{ Fabricate(:pcm).to_ppm }
|
9
|
-
end
|
10
|
-
|
11
|
-
Fabricator(:ppm_pcm_divided_by_count, from: :ppm) do
|
12
|
-
# this matrix should be initialized manually - it's used for spec checking PCM#to_ppm
|
13
|
-
matrix [[1.0/7.0, 2.0/7.0, 3.0/7.0, 1.0/7.0], [4.0/7.0, 0.0/7.0, 1.0/7.0, 2.0/7.0]]
|
14
|
-
end
|
@@ -1,16 +0,0 @@
|
|
1
|
-
Fabricator(:pwm, class_name: Bioinform::PWM) do
|
2
|
-
initialize_with{ Bioinform::PWM.new(matrix: [[1,2,3,4],[5,6,7,8]], name: 'PWM_name')}
|
3
|
-
end
|
4
|
-
|
5
|
-
# It has name 'PCM_name' because name isn't converted during #to_pwm
|
6
|
-
Fabricator(:pwm_by_pcm, class_name: Bioinform::PWM) do
|
7
|
-
initialize_with{ Fabricate(:pcm).to_pwm }
|
8
|
-
end
|
9
|
-
|
10
|
-
Fabricator(:rounded_upto_3_digits_pwm_by_pcm_with_pseudocount_1, from: :pwm) do
|
11
|
-
matrix [[-0.47, 0.118, 0.486, -0.47],[0.754, -2.079, -0.47, 0.118]]
|
12
|
-
end
|
13
|
-
|
14
|
-
Fabricator(:rounded_upto_3_digits_pwm_by_pcm_with_pseudocount_10, from: :pwm) do
|
15
|
-
matrix [[-0.194, 0.057, 0.258, -0.194],[0.425, -0.531, -0.194, 0.057]]
|
16
|
-
end
|
data/spec/parsers/parser_spec.rb
DELETED
@@ -1,152 +0,0 @@
|
|
1
|
-
require_relative '../spec_helper'
|
2
|
-
require_relative '../../lib/bioinform/parsers/parser'
|
3
|
-
|
4
|
-
module Bioinform
|
5
|
-
describe Parser do
|
6
|
-
context '#initialize' do
|
7
|
-
it 'should accept an array correctly' do
|
8
|
-
Parser.new([[1,2,3,4],[5,6,7,8]]).parse.matrix.should == [[1,2,3,4],[5,6,7,8]]
|
9
|
-
end
|
10
|
-
it 'should treat several arguments as an array composed of them' do
|
11
|
-
Parser.new([1,2,3,4],[5,6,7,8]).parse.should == Parser.new([[1,2,3,4],[5,6,7,8]]).parse
|
12
|
-
end
|
13
|
-
it 'should treat one Array of numbers as an Array(with 1 element) of Arrays' do
|
14
|
-
Parser.new([1,2,3,4]).parse.should == Parser.new([[1,2,3,4]]).parse
|
15
|
-
end
|
16
|
-
end
|
17
|
-
|
18
|
-
context '::parse!' do
|
19
|
-
it 'should behave like Parser.new(input).parse!' do
|
20
|
-
Parser.parse!([1,2,3,4],[5,6,7,8]).should == Parser.new([1,2,3,4],[5,6,7,8]).parse!
|
21
|
-
expect{ Parser.parse!([1,2,3],[4,5,6]) }.to raise_error
|
22
|
-
end
|
23
|
-
end
|
24
|
-
|
25
|
-
context '::parse' do
|
26
|
-
it 'should behave like Parser.new(input).parse!' do
|
27
|
-
Parser.parse([1,2,3,4],[5,6,7,8]).should == Parser.new([1,2,3,4],[5,6,7,8]).parse
|
28
|
-
Parser.parse([1,2,3],[4,5,6]).should be_nil
|
29
|
-
end
|
30
|
-
end
|
31
|
-
|
32
|
-
context '::choose' do
|
33
|
-
it 'should create parser of appropriate type' do
|
34
|
-
Parser.choose([[1,2,3,4],[5,6,7,8]]).should be_kind_of(Parser)
|
35
|
-
Parser.choose([[1,2,3,4],[5,6,7,8]]).input.should == [[1,2,3,4],[5,6,7,8]]
|
36
|
-
Parser.choose(matrix: [[1,2,3,4],[5,6,7,8]], name: 'Name').should be_kind_of(TrivialParser)
|
37
|
-
Parser.choose(matrix: [[1,2,3,4],[5,6,7,8]], name: 'Name').input.should == {matrix: [[1,2,3,4],[5,6,7,8]], name: 'Name'}
|
38
|
-
Parser.choose("1 2 3 4\n5 6 7 8").should be_kind_of(StringParser)
|
39
|
-
Parser.choose("1 2 3 4\n5 6 7 8").input.should == "1 2 3 4\n5 6 7 8"
|
40
|
-
end
|
41
|
-
end
|
42
|
-
|
43
|
-
context '::split_on_motifs' do
|
44
|
-
it 'should be able to get a single PM' do
|
45
|
-
Parser.split_on_motifs([[1,2,3,4],[5,6,7,8]], PM).should == [ PM.new(matrix: [[1,2,3,4],[5,6,7,8]], name:nil) ]
|
46
|
-
end
|
47
|
-
end
|
48
|
-
|
49
|
-
context '::normalize_hash_keys' do
|
50
|
-
it 'should convert both symbolic and string keys, in both upcase and downcase to symbolic upcases' do
|
51
|
-
Parser.normalize_hash_keys( {a: 1, C: 2, 'g' => 3, 'T' => 4} ).should == {A: 1, C: 2, G: 3, T: 4}
|
52
|
-
end
|
53
|
-
end
|
54
|
-
|
55
|
-
context '::need_transpose?' do
|
56
|
-
it 'should point whether matrix have positions(need not be transposed -- false) or letters(true) as first index' do
|
57
|
-
Parser.need_tranpose?([[1,3,5,7], [2,4,6,8]]).should be_false
|
58
|
-
Parser.need_tranpose?([[1,2],[3,4],[5,6],[7,8]]).should be_true
|
59
|
-
end
|
60
|
-
end
|
61
|
-
context '::array_from_acgt_hash' do
|
62
|
-
it 'should convert hash of arrays to a transposed array of arrays' do
|
63
|
-
input = {A: [1,2,3], C: [2,3,4], G: [3,4,5], T: [4,5,6]}
|
64
|
-
Parser.array_from_acgt_hash(input).should == [[1,2,3], [2,3,4], [3,4,5], [4,5,6]].transpose
|
65
|
-
end
|
66
|
-
it 'should convert hash of numbers to an array of numbers' do
|
67
|
-
input = {A: 1, C: 2, G: 3, T: 4}
|
68
|
-
Parser.array_from_acgt_hash(input).should == [1,2,3,4]
|
69
|
-
end
|
70
|
-
it 'should process both symbolic and string keys, in both upcase and downcase' do
|
71
|
-
input_normal_keys = {A: 1, C: 2, G: 3, T: 4}
|
72
|
-
input_different_keys = {:A => 1, :c => 2, 'g' => 3, 'T' => 4}
|
73
|
-
Parser.array_from_acgt_hash(input_different_keys).should == Parser.array_from_acgt_hash(input_normal_keys)
|
74
|
-
end
|
75
|
-
end
|
76
|
-
|
77
|
-
context '::try_convert_to_array' do
|
78
|
-
it 'should not change array' do
|
79
|
-
inputs = []
|
80
|
-
inputs << [[1,2,3,4], [2,3,4,5], [3,4,5,6]]
|
81
|
-
inputs << [{A:1, C:2, G:3, T:4}, {A:2, C:3, G:4, T:5}, {A:3, C:4, G:5, T:6}]
|
82
|
-
inputs.each do |input|
|
83
|
-
Parser.try_convert_to_array( input ).should == input
|
84
|
-
end
|
85
|
-
end
|
86
|
-
it 'should convert ACGT-Hashes to an array of positions (not letters)' do
|
87
|
-
Parser.try_convert_to_array( {:A => [1,2,3], :c => [2,3,4], 'g' => [3,4,5], 'T' => [4,5,6]} ).should == [[1,2,3],[2,3,4],[3,4,5],[4,5,6]].transpose
|
88
|
-
end
|
89
|
-
end
|
90
|
-
|
91
|
-
context '#parse' do
|
92
|
-
it 'should give the same result as #parse!' do
|
93
|
-
parser = Parser.new('stub parser')
|
94
|
-
parser.stub(:parse!).and_return('stub result')
|
95
|
-
parser.parse.should == 'stub result'
|
96
|
-
end
|
97
|
-
it 'should return nil if #parse! raised an exception' do
|
98
|
-
parser = Parser.new('stub parser')
|
99
|
-
parser.stub(:parse!).and_raise
|
100
|
-
parser.parse.should be_nil
|
101
|
-
end
|
102
|
-
end
|
103
|
-
|
104
|
-
good_cases = {
|
105
|
-
'Array Nx4' => {input: [[1,2,3,4],[5,6,7,8]],
|
106
|
-
result: Fabricate(:pm_unnamed) },
|
107
|
-
|
108
|
-
'Array 4xN' => {input: [[1,5],[2,6],[3,7],[4,8]],
|
109
|
-
result: Fabricate(:pm_unnamed) },
|
110
|
-
|
111
|
-
'Hash A,C,G,T => Arrays' => { input: {:A => [1,5], :c => [2,6],'g' => [3,7],'T' => [4,8]},
|
112
|
-
result: Fabricate(:pm_unnamed) },
|
113
|
-
|
114
|
-
'Hash array of hashes' => { input: [{:A => 1,:c => 2,'g' => 3,'T' => 4}, {:A => 5,:c => 6,'g' => 7,'T' => 8}],
|
115
|
-
result: Fabricate(:pm_unnamed) },
|
116
|
-
|
117
|
-
'Array 4x4 (rows treated as positions, columns are treated as letter)' => { input: [[1,2,3,4],[5,6,7,8],[9,10,11,12],[13,14,15,16]],
|
118
|
-
result: Fabricate(:pm_4x4_unnamed) },
|
119
|
-
|
120
|
-
'Hash A,C,G,T => 4-Arrays' => { input: {:A => [1,5,9,13], :c => [2,6,10,14],'g' => [3,7,11,15],'T' => [4,8,12,16]},
|
121
|
-
result: Fabricate(:pm_4x4_unnamed) },
|
122
|
-
|
123
|
-
'4-Arrays of A,C,G,T hashes' => { input: [{:A => 1, :c => 2, 'g' => 3, 'T' => 4},
|
124
|
-
{:A => 5, :c => 6, 'g' => 7, 'T' => 8},
|
125
|
-
{:A => 9, :c => 10, 'g' => 11, 'T' => 12},
|
126
|
-
{:A => 13, :c => 14, 'g' => 15, 'T' => 16}],
|
127
|
-
result: Fabricate(:pm_4x4_unnamed) }
|
128
|
-
}
|
129
|
-
|
130
|
-
bad_cases = {
|
131
|
-
'Nil object on input' => {input: nil},
|
132
|
-
'Empty array on input' => {input: []},
|
133
|
-
'Different sizes of row arrays' => {input: [[1,2,3,4],[5,6,7,8,9]] },
|
134
|
-
'Different sizes of column arrays' => {input: [[0,10],[1,11],[2,12],[3]] },
|
135
|
-
'No one dimension have size 4' => {input: [[0,1,2,3,4],[10,11,12,13,14], [0,1,2,3,4]] },
|
136
|
-
'Missing keys in column hashes' => {input: [{:A => 0, :c => 1, 'g' => 2, 'T' => 3}, {:A => 10, :c => 11, 'g' => 12}] },
|
137
|
-
'Bad keys in column hashes' => {input: [{:A => 0, :c => 1, 'g' => 2, 'T' => 3}, {:A => 10, :c => 11, 'g' => 12, :X =>1000}] },
|
138
|
-
'Excessing keys in column hashes' => { input: [{:A => 0,:c => 1,'g' => 2,'T' => 3}, {:A => 10,:c => 11,'g' => 12,'T' => 13, :X => 1000}] },
|
139
|
-
'Different sizes of row hashes' => {input: {:A => [0,10], :c => [1,11],'g' => [2,12],'T' => [3,13,14]} },
|
140
|
-
'Missing keys in row hashes' => {input: {:A => [0,10], :c => [1,11],'g' => [2,12]} },
|
141
|
-
'Wrong keys in row hashes' => {input: {:A => [0,10], :c => [1,11],'X' => [2,12]} },
|
142
|
-
'Excessing keys in row hashes' => {input: {:A => [0,10], :c => [1,11],'g' => [2,12], 'T' => [3,12], :X => [4,14]} }
|
143
|
-
}
|
144
|
-
|
145
|
-
parser_specs(Parser, good_cases, bad_cases)
|
146
|
-
context '#parser!' do
|
147
|
-
it "should raise an exception on parsing empty list to parser" do
|
148
|
-
expect{ Parser.new().parse! }.to raise_error
|
149
|
-
end
|
150
|
-
end
|
151
|
-
end
|
152
|
-
end
|
@@ -1,70 +0,0 @@
|
|
1
|
-
require_relative '../spec_helper'
|
2
|
-
require_relative '../../lib/bioinform/parsers/string_fantom_parser'
|
3
|
-
|
4
|
-
module Bioinform
|
5
|
-
describe StringFantomParser do
|
6
|
-
describe '#split_on_motifs' do
|
7
|
-
it 'should be able to parse several motifs' do
|
8
|
-
input = "
|
9
|
-
//
|
10
|
-
NA motif_1
|
11
|
-
P0 A C G T
|
12
|
-
P1 0 1 2 3
|
13
|
-
P2 4 5 6 7
|
14
|
-
//
|
15
|
-
//
|
16
|
-
NA motif_2
|
17
|
-
P0 A C G T
|
18
|
-
P1 1 2 3 4
|
19
|
-
P2 5 6 7 8
|
20
|
-
P3 9 10 11 12
|
21
|
-
//
|
22
|
-
NA motif_3
|
23
|
-
P0 A C G T
|
24
|
-
P1 2 3 4 5
|
25
|
-
P2 6 7 8 9"
|
26
|
-
StringFantomParser.split_on_motifs(input).should == [ Fabricate(:pm_1), Fabricate(:pm_2), Fabricate(:pm_3) ]
|
27
|
-
end
|
28
|
-
end
|
29
|
-
|
30
|
-
good_cases = {
|
31
|
-
'string in Fantom-format' => {input: "
|
32
|
-
NA PM_name
|
33
|
-
P0 A C G T
|
34
|
-
P1 1 2 3 4
|
35
|
-
P2 5 6 7 8",
|
36
|
-
result: Fabricate(:pm)
|
37
|
-
},
|
38
|
-
|
39
|
-
'motif with additional rows' => {input: "
|
40
|
-
NA PM_name
|
41
|
-
P0 A C G T S P
|
42
|
-
P1 1 2 3 4 5 10
|
43
|
-
P2 5 6 7 8 5 11",
|
44
|
-
result: Fabricate(:pm)
|
45
|
-
},
|
46
|
-
|
47
|
-
'string with more than 10 positions(2-digit row numbers)' => {input: "
|
48
|
-
NA PM_name
|
49
|
-
P0 A C G T
|
50
|
-
P1 1 2 3 4
|
51
|
-
P2 5 6 7 8
|
52
|
-
P3 1 2 3 4
|
53
|
-
P4 5 6 7 8
|
54
|
-
P5 1 2 3 4
|
55
|
-
P6 5 6 7 8
|
56
|
-
P7 1 2 3 4
|
57
|
-
P8 5 6 7 8
|
58
|
-
P9 1 2 3 4
|
59
|
-
P10 5 6 7 8
|
60
|
-
P11 1 2 3 4
|
61
|
-
P12 5 6 7 8",
|
62
|
-
result: Fabricate(:pm, matrix: [[1,2,3,4],[5,6,7,8]] * 6 )
|
63
|
-
}
|
64
|
-
}
|
65
|
-
|
66
|
-
bad_cases = { }
|
67
|
-
|
68
|
-
parser_specs(StringFantomParser, good_cases, bad_cases)
|
69
|
-
end
|
70
|
-
end
|
@@ -1,77 +0,0 @@
|
|
1
|
-
require_relative '../spec_helper'
|
2
|
-
require_relative '../../lib/bioinform/parsers/string_parser'
|
3
|
-
|
4
|
-
module Bioinform
|
5
|
-
describe StringParser do
|
6
|
-
|
7
|
-
describe '#each' do
|
8
|
-
it 'should yield consequent results of #parse! while it returns result' do
|
9
|
-
parser = StringParser.new("1 2 3 4\n5 6 7 8\n\n1 2 3 4\n1 2 3 4\nName\n4 3 2 1\n1 1 1 1\n0 0 0 0")
|
10
|
-
expect{|b| parser.each(&b)}.to yield_successive_args(OpenStruct.new(matrix:[[1,2,3,4],[5,6,7,8]], name:nil),
|
11
|
-
OpenStruct.new(matrix:[[1,2,3,4],[1,2,3,4]], name:nil),
|
12
|
-
OpenStruct.new(matrix:[[4,3,2,1],[1,1,1,1],[0,0,0,0]], name:'Name') )
|
13
|
-
end
|
14
|
-
it 'should restart parser from the beginning each time' do
|
15
|
-
parser = StringParser.new("1 2 3 4\n5 6 7 8\n\n1 2 3 4\n1 2 3 4\nName\n4 3 2 1\n1 1 1 1\n0 0 0 0")
|
16
|
-
3.times do
|
17
|
-
expect{|b| parser.each(&b)}.to yield_successive_args(OpenStruct.new(matrix:[[1,2,3,4],[5,6,7,8]], name:nil),
|
18
|
-
OpenStruct.new(matrix:[[1,2,3,4],[1,2,3,4]], name:nil),
|
19
|
-
OpenStruct.new(matrix:[[4,3,2,1],[1,1,1,1],[0,0,0,0]], name:'Name') )
|
20
|
-
end
|
21
|
-
end
|
22
|
-
end
|
23
|
-
|
24
|
-
context '::split_on_motifs' do
|
25
|
-
it 'should be able to get a single PM' do
|
26
|
-
StringParser.split_on_motifs("1 2 3 4 \n 5 6 7 8").should == [ Fabricate(:pm_unnamed) ]
|
27
|
-
end
|
28
|
-
it 'should be able to split several PMs separated with an empty line' do
|
29
|
-
StringParser.split_on_motifs("1 2 3 4 \n 5 6 7 8 \n\n 15 16 17 18 \n 11 21 31 41").should ==
|
30
|
-
[ Fabricate(:pm_first, name: nil), Fabricate(:pm_second, name: nil) ]
|
31
|
-
end
|
32
|
-
it 'should be able to split several PMs separated with name' do
|
33
|
-
StringParser.split_on_motifs("1 2 3 4 \n 5 6 7 8 \nPM_second\n 15 16 17 18 \n 11 21 31 41").should ==
|
34
|
-
[ Fabricate(:pm_first, name: nil), Fabricate(:pm_second) ]
|
35
|
-
end
|
36
|
-
it 'should be able to split several PMs separated with both name and empty line' do
|
37
|
-
StringParser.split_on_motifs("PM_first\n1 2 3 4 \n 5 6 7 8 \n\nPM_second\n 15 16 17 18 \n 11 21 31 41\n\n\n").should ==
|
38
|
-
[ Fabricate(:pm_first), Fabricate(:pm_second) ]
|
39
|
-
end
|
40
|
-
it 'should create PMs by default' do
|
41
|
-
result = StringParser.split_on_motifs("1 2 3 4 \n 5 6 7 8 \n 9 10 11 12 \nName\n 9 10 11 12 \n 1 2 3 4 \n 5 6 7 8")
|
42
|
-
result.each{|pm| pm.class.should == PM}
|
43
|
-
end
|
44
|
-
it 'should create PM subclass when it\'s specified' do
|
45
|
-
result = StringParser.split_on_motifs("1 2 3 4 \n 5 6 7 8 \n 9 10 11 12 \nName\n 9 10 11 12 \n 1 2 3 4 \n 5 6 7 8", PWM)
|
46
|
-
result.each{|pm| pm.class.should == PWM}
|
47
|
-
end
|
48
|
-
end
|
49
|
-
|
50
|
-
good_cases = {
|
51
|
-
'Nx4 string' => {input: "1 2 3 4\n5 6 7 8", result: Fabricate(:pm_unnamed) },
|
52
|
-
'4xN string' => {input: "1 5\n2 6\n3 7\n 4 8", result: Fabricate(:pm_unnamed) },
|
53
|
-
'string with name' => {input: "PM_name\n1 5\n2 6\n3 7\n 4 8", result: Fabricate(:pm) },
|
54
|
-
'string with name (with introduction sign)' => {input: ">\t PM_name\n1 5\n2 6\n3 7\n 4 8", result: Fabricate(:pm) },
|
55
|
-
'string with name (with special characters)' => {input: "Testmatrix_first:subname+sub-subname\n1 5\n2 6\n3 7\n 4 8",
|
56
|
-
result: Fabricate(:pm, name: 'Testmatrix_first:subname+sub-subname') },
|
57
|
-
'string with float numerics' => {input: "1.23 4.56 7.8 9.0\n9 -8.7 6.54 -3210", result: Fabricate(:pm_with_floats) },
|
58
|
-
'string with exponents' => {input: "123e-2 0.456e+1 7.8 9.0\n9 -87000000000E-10 6.54 -3.210e3", result: Fabricate(:pm_with_floats) },
|
59
|
-
'string with multiple spaces and tabs' => {input: "1 \t\t 2 3 4\n 5 6 7 8", result: Fabricate(:pm_unnamed) },
|
60
|
-
'string with preceeding and terminating newlines' => {input: "\n\n\t 1 2 3 4\n5 6 7 8 \n\t\n", result: Fabricate(:pm_unnamed) },
|
61
|
-
'string with windows crlf' => {input: "1 2 3 4\r\n5 6 7 8", result: Fabricate(:pm_unnamed) },
|
62
|
-
'Nx4 string with acgt-header' => {input: "A C G T\n1 2 3 4\n5 6 7 8", result: Fabricate(:pm_unnamed) },
|
63
|
-
'Nx4 string with name and acgt-header' => {input: "PM_name\nA C G T\n1 2 3 4\n5 6 7 8", result: Fabricate(:pm)},
|
64
|
-
'Nx4 string with acgt-row-markers' => {input: "A 1 5\nC : 2 6\nG3 7\nT |4 8", result: Fabricate(:pm_unnamed) },
|
65
|
-
'4x4 string with acgt-header' => {input: "A C G T\n1 2 3 4\n5 6 7 8\n9 10 11 12\n13 14 15 16", result: Fabricate(:pm_4x4_unnamed) },
|
66
|
-
'4x4 string with acgt-row-markers' => {input: "A|1 5 9 13\nC|2 6 10 14\nG|3 7 11 15\nT|4 8 12 16", result: Fabricate(:pm_4x4_unnamed) },
|
67
|
-
'4x4 string with name and acgt-row-markers' => {input: "PM_name\nA:1 5 9 13\nC:2 6 10 14\nG:3 7 11 15\nT:4 8 12 16", result: Fabricate(:pm_4x4) }
|
68
|
-
}
|
69
|
-
|
70
|
-
bad_cases = {
|
71
|
-
'string with non-numeric input' => {input: "1.23 4.56 78aaa 9.0\n9 -8.7 6.54 -3210" },
|
72
|
-
'string with empty exponent sign' => {input: "1.23 4.56 7.8 9.0\n 9e -8.7 6.54 3210" }
|
73
|
-
}
|
74
|
-
|
75
|
-
parser_specs(StringParser, good_cases, bad_cases)
|
76
|
-
end
|
77
|
-
end
|