bio-sambamba 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.travis.yml +12 -0
- data/Gemfile +11 -0
- data/LICENSE.txt +20 -0
- data/README.md +68 -0
- data/Rakefile +47 -0
- data/VERSION +1 -0
- data/features/iterate-alignments.feature +40 -0
- data/features/random-access.feature +10 -0
- data/features/sam-header.feature +23 -0
- data/features/step_definitions/iterate-alignments_steps.rb +83 -0
- data/features/step_definitions/random-access_steps.rb +22 -0
- data/features/step_definitions/sam-header_steps.rb +56 -0
- data/features/step_definitions/validation-steps.rb +34 -0
- data/features/support/env.rb +13 -0
- data/features/syntax-sugar.feature +17 -0
- data/features/validation.feature +16 -0
- data/lib/bio-sambamba.rb +8 -0
- data/lib/bio-sambamba/alignment.rb +131 -0
- data/lib/bio-sambamba/alignmentiterator.rb +45 -0
- data/lib/bio-sambamba/bamfile.rb +45 -0
- data/lib/bio-sambamba/samfile.rb +25 -0
- data/lib/bio-sambamba/samheader.rb +194 -0
- data/test/data/bins.bam +0 -0
- data/test/data/bins.bam.bai +0 -0
- data/test/data/c1215_fixmate.bam +0 -0
- data/test/data/corrupted_zlib_archive.bam +0 -0
- data/test/data/duplicated_block_size.bam +0 -0
- data/test/data/ex1_header.bam +0 -0
- data/test/data/ex1_header.bam.bai +0 -0
- data/test/data/ex1_header.sam +3273 -0
- data/test/data/ex1_header.uncompressed.bam +0 -0
- data/test/data/no_block_size.bam +0 -0
- data/test/data/tags.bam +0 -0
- data/test/data/tags.bam.bai +0 -0
- data/test/data/wrong_bc_subfield_length.bam +0 -0
- data/test/data/wrong_extra_gzip_length.bam +0 -0
- metadata +184 -0
@@ -0,0 +1,13 @@
|
|
1
|
+
require 'bundler'
|
2
|
+
begin
|
3
|
+
Bundler.setup(:default, :development)
|
4
|
+
rescue Bundler::BundlerError => e
|
5
|
+
$stderr.puts e.message
|
6
|
+
$stderr.puts "Run `bundle install` to install missing gems"
|
7
|
+
exit e.status_code
|
8
|
+
end
|
9
|
+
|
10
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__) + '/../../lib/')
|
11
|
+
require 'bio-sambamba.rb'
|
12
|
+
|
13
|
+
require 'rspec/expectations'
|
@@ -0,0 +1,17 @@
|
|
1
|
+
Feature: syntax sugar
|
2
|
+
|
3
|
+
In order to enjoy writing my scripts,
|
4
|
+
As a Rubyista,
|
5
|
+
I want some syntax sugar.
|
6
|
+
|
7
|
+
Scenario: fetching alignments
|
8
|
+
Given I have a BAM file
|
9
|
+
And associated BAI file
|
10
|
+
When I say "bam.alignments.referencing(chromosome).overlapping(500.kbp .. 600.kbp)"
|
11
|
+
Then I should get these alignments
|
12
|
+
|
13
|
+
Scenario: using shortcuts
|
14
|
+
Given I have a BAM file
|
15
|
+
And associated BAI file
|
16
|
+
When I say "bam[chromosome][500.kbp .. 600.kbp]"
|
17
|
+
Then I should get these alignments
|
@@ -0,0 +1,16 @@
|
|
1
|
+
Feature: alignment validation
|
2
|
+
|
3
|
+
In order to be able to filter out invalid reads,
|
4
|
+
As a developer,
|
5
|
+
I want validation support.
|
6
|
+
|
7
|
+
Scenario: checking single read
|
8
|
+
Given I have an alignment from a BAM file
|
9
|
+
When I call 'valid?' method
|
10
|
+
Then it should return whether it is valid or not
|
11
|
+
|
12
|
+
Scenario: iterating over valid records
|
13
|
+
Given I have a BAM file
|
14
|
+
When I want to iterate over its records
|
15
|
+
Then I should have an option to skip invalid ones
|
16
|
+
And all the reads in this case should be valid
|
data/lib/bio-sambamba.rb
ADDED
@@ -0,0 +1,131 @@
|
|
1
|
+
module Bio
|
2
|
+
module Bam
|
3
|
+
|
4
|
+
# Class representing an alignment record
|
5
|
+
class Alignment
|
6
|
+
|
7
|
+
# Creates a new object from JSON output of sambamba tool
|
8
|
+
def initialize(json)
|
9
|
+
@json = json
|
10
|
+
end
|
11
|
+
|
12
|
+
# Access a record tag
|
13
|
+
def [](tag)
|
14
|
+
raise 'tag length must be two' unless tag.length == 2
|
15
|
+
@json['tags'][tag]
|
16
|
+
end
|
17
|
+
|
18
|
+
# Hash of record tags
|
19
|
+
attr_reader :tags if false
|
20
|
+
|
21
|
+
# Name of reference sequence
|
22
|
+
attr_reader :reference if false
|
23
|
+
|
24
|
+
# Query template name
|
25
|
+
attr_reader :read_name if false
|
26
|
+
|
27
|
+
# 1-based leftmost mapping position
|
28
|
+
attr_reader :position if false
|
29
|
+
|
30
|
+
# Mapping quality
|
31
|
+
attr_reader :mapping_quality if false
|
32
|
+
|
33
|
+
# CIGAR string
|
34
|
+
attr_reader :cigar_string if false
|
35
|
+
|
36
|
+
# Observed template length
|
37
|
+
attr_reader :template_length if false
|
38
|
+
|
39
|
+
# Bitwise flag
|
40
|
+
attr_reader :flag if false
|
41
|
+
|
42
|
+
# Phred-scaled base quality, an integer array
|
43
|
+
# of the same length as the sequence
|
44
|
+
attr_reader :quality if false
|
45
|
+
|
46
|
+
# Segment sequence
|
47
|
+
attr_reader :sequence if false
|
48
|
+
|
49
|
+
# Reference sequence name of the mate/next segment
|
50
|
+
attr_reader :mate_reference if false
|
51
|
+
|
52
|
+
# 1-based leftmost position of the mate/next segment
|
53
|
+
attr_reader :mate_position if false
|
54
|
+
|
55
|
+
{'tags' => 'tags',
|
56
|
+
'reference' => 'rname',
|
57
|
+
'read_name' => 'qname',
|
58
|
+
'position' => 'pos',
|
59
|
+
'mapping_quality' => 'mapq',
|
60
|
+
'cigar_string' => 'cigar',
|
61
|
+
'template_length' => 'tlen',
|
62
|
+
'flag' => 'flag',
|
63
|
+
'quality' => 'qual',
|
64
|
+
'sequence' => 'seq',
|
65
|
+
'mate_reference' => 'rnext',
|
66
|
+
'mate_position' => 'pnext'}.each do |k, v|
|
67
|
+
eval <<-DEFINE_READER
|
68
|
+
def #{k}
|
69
|
+
@json['#{v}']
|
70
|
+
end
|
71
|
+
DEFINE_READER
|
72
|
+
end
|
73
|
+
|
74
|
+
# Template having multiple segments in sequencing
|
75
|
+
def is_paired
|
76
|
+
(flag & 0x1) != 0
|
77
|
+
end
|
78
|
+
|
79
|
+
# Each segment properly aligned according to the aligner
|
80
|
+
def proper_pair
|
81
|
+
(flag & 0x2) != 0
|
82
|
+
end
|
83
|
+
|
84
|
+
# Segment unmapped
|
85
|
+
def is_unmapped
|
86
|
+
(flag & 0x4) != 0
|
87
|
+
end
|
88
|
+
|
89
|
+
# Next segment in the template unmapped
|
90
|
+
def mate_is_unmapped
|
91
|
+
(flag & 0x8) != 0
|
92
|
+
end
|
93
|
+
|
94
|
+
# Sequence being reverse complemented
|
95
|
+
def is_reverse_strand
|
96
|
+
(flag & 0x10) != 0
|
97
|
+
end
|
98
|
+
|
99
|
+
# Sequence of the next segment in the template being reversed
|
100
|
+
def mate_is_reverse_strand
|
101
|
+
(flag & 0x20) != 0
|
102
|
+
end
|
103
|
+
|
104
|
+
# The first segment in the template
|
105
|
+
def is_first_of_pair
|
106
|
+
(flag & 0x40) != 0
|
107
|
+
end
|
108
|
+
|
109
|
+
# The last segment in the template
|
110
|
+
def is_second_of_pair
|
111
|
+
(flag & 0x80) != 0
|
112
|
+
end
|
113
|
+
|
114
|
+
# Secondary alignment
|
115
|
+
def is_secondary_alignment
|
116
|
+
(flag & 0x100) != 0
|
117
|
+
end
|
118
|
+
|
119
|
+
# Not passing quality controls
|
120
|
+
def failed_quality_control
|
121
|
+
(flag & 0x200) != 0
|
122
|
+
end
|
123
|
+
|
124
|
+
# PCR or optical duplicate
|
125
|
+
def is_duplicate
|
126
|
+
(flag & 0x400) != 0
|
127
|
+
end
|
128
|
+
end
|
129
|
+
|
130
|
+
end
|
131
|
+
end
|
@@ -0,0 +1,45 @@
|
|
1
|
+
module Bio
|
2
|
+
module Bam
|
3
|
+
|
4
|
+
# Class for iterating through alignments
|
5
|
+
class AlignmentIterator
|
6
|
+
include Enumerable
|
7
|
+
|
8
|
+
# Creates a new AlignmentIterator object which will
|
9
|
+
# parse JSON outputted by a specified command.
|
10
|
+
def initialize(command)
|
11
|
+
@command = command
|
12
|
+
end
|
13
|
+
|
14
|
+
# Iterate only through valid alignments
|
15
|
+
def each_valid
|
16
|
+
|
17
|
+
return enum_for(:each_valid) if not block_given?
|
18
|
+
|
19
|
+
command = @command
|
20
|
+
if command.index('--valid').nil?
|
21
|
+
command.push '--valid'
|
22
|
+
end
|
23
|
+
|
24
|
+
AlignmentIterator.new(command).each do |read|
|
25
|
+
yield read
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
# Iterate through all alignments skipping
|
30
|
+
# validation checks
|
31
|
+
def each
|
32
|
+
|
33
|
+
return enum_for(:each) if not block_given?
|
34
|
+
|
35
|
+
Bio::Command.call_command(@command) do |io|
|
36
|
+
io.each do |line|
|
37
|
+
raise line unless line[0] == '{'
|
38
|
+
yield Bio::Bam::Alignment.new(Oj.load(line))
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
end
|
45
|
+
end
|
@@ -0,0 +1,45 @@
|
|
1
|
+
module Bio
|
2
|
+
|
3
|
+
# Module for reading BAM files
|
4
|
+
module Bam
|
5
|
+
|
6
|
+
# Class providing access to BAM files
|
7
|
+
class File
|
8
|
+
|
9
|
+
# Creates an object for access to BAM file
|
10
|
+
def initialize(filename)
|
11
|
+
@filename = filename
|
12
|
+
end
|
13
|
+
|
14
|
+
# SAM header
|
15
|
+
def header
|
16
|
+
@header ||= Bio::Bam::SamHeader.new(@filename)
|
17
|
+
end
|
18
|
+
|
19
|
+
# Returns an AlignmentIterator object for iterating over all alignments in the file
|
20
|
+
def alignments
|
21
|
+
Bio::Bam::AlignmentIterator.new ['sambamba', '--format=json', @filename]
|
22
|
+
end
|
23
|
+
|
24
|
+
# True if index file was found
|
25
|
+
def has_index?
|
26
|
+
File::File.exists?(@filename + '.bai') ||
|
27
|
+
File::File.exists?(@filename[0...-1] + 'i')
|
28
|
+
end
|
29
|
+
|
30
|
+
# Fetches alignments overlapping a region.
|
31
|
+
# Returns an AlignmentIterator object.
|
32
|
+
#
|
33
|
+
# ---
|
34
|
+
# *Arguments*:
|
35
|
+
# * _chr_: reference sequence
|
36
|
+
# * _region_: a Range representing an interval. Coordinates are 1-based.
|
37
|
+
def fetch(chr, region)
|
38
|
+
Bio::Bam::AlignmentIterator.new ['sambamba', '--format=json',
|
39
|
+
@filename,
|
40
|
+
"#{chr}:#{region.min}-#{region.max}"]
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
end
|
45
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
module Bio
|
2
|
+
# Module for reading SAM files
|
3
|
+
module Sam
|
4
|
+
|
5
|
+
# Class providing access to SAM files
|
6
|
+
class File
|
7
|
+
|
8
|
+
# Creates an object for access to SAM file
|
9
|
+
def initialize(filename)
|
10
|
+
@filename = filename
|
11
|
+
end
|
12
|
+
|
13
|
+
# SAM header
|
14
|
+
def header
|
15
|
+
@header ||= Bio::Bam::SamHeader.new(@filename, ['-S'])
|
16
|
+
end
|
17
|
+
|
18
|
+
# Returns an AlignmentIterator object for iterating over all alignments in the file
|
19
|
+
def alignments
|
20
|
+
Bio::Bam::AlignmentIterator.new ['sambamba', '--format=json', '-S', @filename]
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
end
|
25
|
+
end
|
@@ -0,0 +1,194 @@
|
|
1
|
+
module Bio
|
2
|
+
module Bam
|
3
|
+
|
4
|
+
# Represents SAM header
|
5
|
+
class SamHeader
|
6
|
+
|
7
|
+
# Creates a new SamHeader object for a specified file,
|
8
|
+
# specifying additional options to pass to sambamba tool
|
9
|
+
def initialize(filename, opts=[])
|
10
|
+
@filename = filename
|
11
|
+
@opts = opts
|
12
|
+
end
|
13
|
+
|
14
|
+
# Raw text of SAM header
|
15
|
+
def raw_contents
|
16
|
+
if @raw_contents.nil? then
|
17
|
+
@raw_contents = Bio::Command.query_command(['sambamba', '-H', @filename] + @opts)
|
18
|
+
if @raw_contents.start_with? "sambamba" then
|
19
|
+
raise @raw_contents
|
20
|
+
end
|
21
|
+
end
|
22
|
+
@raw_contents
|
23
|
+
end
|
24
|
+
|
25
|
+
# Format version
|
26
|
+
def version
|
27
|
+
@json ||= get_json
|
28
|
+
@json['format_version']
|
29
|
+
end
|
30
|
+
|
31
|
+
# Sorting order
|
32
|
+
def sorting_order
|
33
|
+
@json ||= get_json
|
34
|
+
@json['sorting_order']
|
35
|
+
end
|
36
|
+
|
37
|
+
# An array of SQLine objects
|
38
|
+
def sq_lines
|
39
|
+
@json ||= get_json
|
40
|
+
@sq_lines ||= @json['sq_lines'].map{|json| SQLine.new(json)}
|
41
|
+
end
|
42
|
+
|
43
|
+
# An array of RGLine objects
|
44
|
+
def rg_lines
|
45
|
+
@json ||= get_json
|
46
|
+
@sq_lines ||= @json['rg_lines'].map{|json| RGLine.new(json)}
|
47
|
+
end
|
48
|
+
|
49
|
+
# An array of PGLine objects
|
50
|
+
def pg_lines
|
51
|
+
@json ||= get_json
|
52
|
+
@sq_lines ||= @json['pg_lines'].map{|json| PGLine.new(json)}
|
53
|
+
end
|
54
|
+
|
55
|
+
private
|
56
|
+
# Calls sambamba to get underlying JSON object
|
57
|
+
def get_json
|
58
|
+
command = ['sambamba', '-H', '--format=json', @filename] + @opts
|
59
|
+
line = Bio::Command.query_command(command)
|
60
|
+
raise line if line[0] != '{'
|
61
|
+
@json = Oj.load(line)
|
62
|
+
end
|
63
|
+
end
|
64
|
+
|
65
|
+
# Represents a @SQ line from SAM header
|
66
|
+
class SQLine
|
67
|
+
|
68
|
+
# Wrap JSON object from sambamba output
|
69
|
+
def initialize(json)
|
70
|
+
@json = json
|
71
|
+
end
|
72
|
+
|
73
|
+
# Reference sequence name
|
74
|
+
attr_reader :sequence_name if false
|
75
|
+
|
76
|
+
# Reference sequence length
|
77
|
+
attr_reader :sequence_length if false
|
78
|
+
|
79
|
+
# Genome assembly identifier
|
80
|
+
attr_reader :assembly if false
|
81
|
+
|
82
|
+
# MD5 checksum of the sequence in uppercase, with gaps and spaces removed
|
83
|
+
attr_reader :md5 if false
|
84
|
+
|
85
|
+
# Species
|
86
|
+
attr_reader :species if false
|
87
|
+
|
88
|
+
# URI of the sequence
|
89
|
+
attr_reader :uri if false
|
90
|
+
|
91
|
+
['sequence_name', 'sequence_length',
|
92
|
+
'assembly', 'md5', 'species', 'uri'].each do |sq_line_field|
|
93
|
+
eval <<-DEFINE_READER
|
94
|
+
def #{sq_line_field}
|
95
|
+
@json['#{sq_line_field}']
|
96
|
+
end
|
97
|
+
DEFINE_READER
|
98
|
+
end
|
99
|
+
end
|
100
|
+
|
101
|
+
# Represents @RG line from SAM header, i.e. a read group
|
102
|
+
class RGLine
|
103
|
+
|
104
|
+
# Wrap JSON object from sambamba output
|
105
|
+
def initialize(json)
|
106
|
+
@json = json
|
107
|
+
end
|
108
|
+
|
109
|
+
# Unique read group identifier
|
110
|
+
attr_reader :identifier if false
|
111
|
+
|
112
|
+
# Name of sequencing center
|
113
|
+
attr_reader :sequencing_center if false
|
114
|
+
|
115
|
+
# Description
|
116
|
+
attr_reader :description if false
|
117
|
+
|
118
|
+
# Date the run was produced (ISO8601 date or date/time)
|
119
|
+
attr_reader :date if false
|
120
|
+
|
121
|
+
# Flow order. The array of nucleotide bases that correspond to the
|
122
|
+
# nucleotides used for each flow of each read. Multi-base flows are
|
123
|
+
# encoded in IUPAC format, and non-nucleotide flows by various other
|
124
|
+
# characters.
|
125
|
+
attr_reader :flow_order if false
|
126
|
+
|
127
|
+
# The array of nucleotide bases that correspond to the key sequence of each read
|
128
|
+
attr_reader :key_sequence if false
|
129
|
+
|
130
|
+
# Library
|
131
|
+
attr_reader :library if false
|
132
|
+
|
133
|
+
# Programs used for processing the read group
|
134
|
+
attr_reader :programs if false
|
135
|
+
|
136
|
+
# Predicted median insert size
|
137
|
+
attr_reader :predicted_insert_size if false
|
138
|
+
|
139
|
+
# Platform/technology used to produce the reads
|
140
|
+
attr_reader :platform if false
|
141
|
+
|
142
|
+
# Platform unit (e.g. flowcell-barcode.lane for Illumina or slide for SOLiD). Unique identifier.
|
143
|
+
attr_reader :platform_unit if false
|
144
|
+
|
145
|
+
# Sample
|
146
|
+
attr_reader :sample if false
|
147
|
+
|
148
|
+
['identifier', 'sequencing_center', 'description', 'date',
|
149
|
+
'flow_order', 'key_sequence', 'library', 'programs',
|
150
|
+
'predicted_insert_size', 'platform',
|
151
|
+
'platform_unit', 'sample'].each do |rg_line_field|
|
152
|
+
eval <<-DEFINE_READER
|
153
|
+
def #{rg_line_field}
|
154
|
+
@json['#{rg_line_field}']
|
155
|
+
end
|
156
|
+
DEFINE_READER
|
157
|
+
end
|
158
|
+
end
|
159
|
+
|
160
|
+
# Represents @PG line from SAM header (program record)
|
161
|
+
class PGLine
|
162
|
+
|
163
|
+
# Wrap JSON object from sambamba output
|
164
|
+
def initialize(json)
|
165
|
+
@json = json
|
166
|
+
end
|
167
|
+
|
168
|
+
# Unique program record identifier
|
169
|
+
attr_reader :identifier if false
|
170
|
+
|
171
|
+
# Program name
|
172
|
+
attr_reader :program_name if false
|
173
|
+
|
174
|
+
# Command line
|
175
|
+
attr_reader :command_line if false
|
176
|
+
|
177
|
+
# Identifier of previous program in chain
|
178
|
+
attr_reader :previous_program if false
|
179
|
+
|
180
|
+
# Program version
|
181
|
+
attr_reader :program_version if false
|
182
|
+
|
183
|
+
['identifier', 'program_name', 'command_line',
|
184
|
+
'previous_program', 'program_version'].each do |rg_line_field|
|
185
|
+
eval <<-DEFINE_READER
|
186
|
+
def #{rg_line_field}
|
187
|
+
@json['#{rg_line_field}']
|
188
|
+
end
|
189
|
+
DEFINE_READER
|
190
|
+
end
|
191
|
+
end
|
192
|
+
|
193
|
+
end
|
194
|
+
end
|