gfa 0.6.0 → 0.6.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/bin/gfa-add-gaf +7 -5
- data/bin/gfa-paths-to-fasta +7 -0
- data/lib/gfa/graph.rb +1 -1
- data/lib/gfa/record/path.rb +55 -0
- data/lib/gfa/record/segment.rb +8 -0
- data/lib/gfa/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 8069525ab289a4299c4d51df9a58a083df95292cd7bc59b83516ac4c5e7508f2
|
4
|
+
data.tar.gz: c1398a889d1f49431bfa01b196084ee9c448c60426fb179801151e7731538c03
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: d97f574a6081727f5687e259a954881351bf7767ec36d1f5ac8b2e6eef939a59a9406077619b306d9782e99357ec2cb98536b4e73474a9aad75c61614c7f7d13
|
7
|
+
data.tar.gz: 385a463ad705401ec083375b917d3654633f44e3828fcc93546422fb80712fc4bc22dbc2dd128dbdf1db44a8c60ed4d7a31df558db8786eb1fca12225a29b2ab
|
data/bin/gfa-add-gaf
CHANGED
@@ -18,11 +18,13 @@ unless degree
|
|
18
18
|
<input-gaf> Input GAF file to read
|
19
19
|
<output> Output GFA file to write
|
20
20
|
<degree> Maximum degree of separation between the segment set in the GAF
|
21
|
-
and any other
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
21
|
+
and any other segments included in the output GFA.
|
22
|
+
- -1: include the complete original GAF without subsetting.
|
23
|
+
- 0: only segments in the GAF are included.
|
24
|
+
- 1: only the target segments in the GAF, records linking to
|
25
|
+
them, and segments linked by those records are included.
|
26
|
+
- Any integer > 1: include additional expansion rounds for
|
27
|
+
those linked segments.
|
26
28
|
<pref> A prefix to name all recorded paths
|
27
29
|
By default: Based on the GAF file name
|
28
30
|
<threads> If passed, parallelize process with these many threads
|
data/bin/gfa-paths-to-fasta
CHANGED
@@ -26,4 +26,11 @@ end
|
|
26
26
|
$stderr.puts "Loading GFA: #{input}"
|
27
27
|
gfa = GFA.load_parallel(input, (threads || 1).to_i)
|
28
28
|
|
29
|
+
$stderr.puts "Saving path sequences: #{output}"
|
30
|
+
File.open(output, 'w') do |fasta|
|
31
|
+
gfa.paths.set.each do |path|
|
32
|
+
fasta.puts '>%s' % path.path_name.value
|
33
|
+
fasta.puts path.sequence(gfa)
|
34
|
+
end
|
35
|
+
end
|
29
36
|
|
data/lib/gfa/graph.rb
CHANGED
@@ -146,7 +146,7 @@ class GFA
|
|
146
146
|
|
147
147
|
def internally_linking_records(segments, edges)
|
148
148
|
$stderr.puts '- Gathering internally linking records'
|
149
|
-
segments = Hash[segments.
|
149
|
+
segments = Hash[segments.map { |i| [i.name.value, true]}]
|
150
150
|
edges.select { |record| record.segment_names_a.all? { |s| segments[s] } }
|
151
151
|
end
|
152
152
|
|
data/lib/gfa/record/path.rb
CHANGED
@@ -42,4 +42,59 @@ class GFA::Record::Path < GFA::Record
|
|
42
42
|
|
43
43
|
segment_names_a.any? { |name| segment.name == name }
|
44
44
|
end
|
45
|
+
|
46
|
+
##
|
47
|
+
# Array of GFA::Field::String with the sequences from each segment featuring
|
48
|
+
# the correct orientation from a +gfa+ (which *must* be indexed)
|
49
|
+
#
|
50
|
+
# TODO: Distinguish between a direct path (separated by comma) and a
|
51
|
+
# jump (separated by semicolon). Jumps include a distance estimate
|
52
|
+
# (column 6, optional) which could be used to add Ns between segment
|
53
|
+
# sequences (from GFA 1.2)
|
54
|
+
def segment_sequences(gfa)
|
55
|
+
raise "Unindexed GFA" unless gfa.indexed?
|
56
|
+
segment_names.value.split(/[,;]/).map do |i|
|
57
|
+
orientation = i[-1]
|
58
|
+
i[-1] = ''
|
59
|
+
segment = gfa.segments[i]
|
60
|
+
|
61
|
+
case orientation
|
62
|
+
when '+' ; segment.sequence
|
63
|
+
when '-' ; segment.rc
|
64
|
+
else ; raise "Unknown orientation: #{orientation} (path: #{path_name})"
|
65
|
+
end
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
##
|
70
|
+
# Produce the contiguous path sequence based on the segment sequences and
|
71
|
+
# orientations from a +gfa+ (which *must* be indexed)
|
72
|
+
#
|
73
|
+
# TODO: Estimate gaps (Ns) from Jump distances (see +segment_sequences+)
|
74
|
+
#
|
75
|
+
# TODO: Attempt reading CIGAR values from the path first, the corresponding
|
76
|
+
# links next, and actually performing the pairwise overlap as last resort
|
77
|
+
#
|
78
|
+
# TODO: Support ambiguous IUPAC codes for overlap evaluation
|
79
|
+
def sequence(gfa)
|
80
|
+
segment_sequences(gfa).map(&:value)
|
81
|
+
.inject('') { |a, b| a + after_overlap(a, b) }
|
82
|
+
end
|
83
|
+
|
84
|
+
private
|
85
|
+
##
|
86
|
+
# Find the overlap between sequences +a+ and +b+ (Strings) and return
|
87
|
+
# only the part of +b+ after the overlap. Assumes that +a+ starts
|
88
|
+
# at the same point or before +b+. If no overlap is found, returns +b+
|
89
|
+
# in its entirety.
|
90
|
+
def after_overlap(a, b)
|
91
|
+
(0 .. a.length - 1).each do |a_from|
|
92
|
+
a_to = b.length + a_from > a.length ? a.length : b.length + a_from
|
93
|
+
b_to = b.length + a_from > a.length ? a.length - a_from : b.length
|
94
|
+
if a[a_from .. a_to - 1] == b[0 .. b_to - 1]
|
95
|
+
return b[b_to .. b.length].to_s
|
96
|
+
end
|
97
|
+
end
|
98
|
+
b
|
99
|
+
end
|
45
100
|
end
|
data/lib/gfa/record/segment.rb
CHANGED
@@ -32,4 +32,12 @@ class GFA::Record::Segment < GFA::Record
|
|
32
32
|
def length
|
33
33
|
sequence.value.length
|
34
34
|
end
|
35
|
+
|
36
|
+
##
|
37
|
+
# Returns the reverse-complement of the sequence (as a Z field)
|
38
|
+
def rc
|
39
|
+
GFA::Field::String.new(
|
40
|
+
sequence.value.upcase.reverse.tr('ACGTURYSWKMBDHVN', 'TGCAAYRSWMKVHDBN')
|
41
|
+
)
|
42
|
+
end
|
35
43
|
end
|
data/lib/gfa/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: gfa
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.6.
|
4
|
+
version: 0.6.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Luis M. Rodriguez-R
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2023-10-
|
11
|
+
date: 2023-10-06 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rgl
|