absee 0.0.2.3 → 0.1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/absee.rb +276 -272
- metadata +5 -5
data/lib/absee.rb
CHANGED
@@ -1,309 +1,313 @@
|
|
1
1
|
# absee
|
2
|
-
#
|
3
|
-
# Jenny Cheng
|
2
|
+
#
|
3
|
+
# Jenny Cheng
|
4
4
|
# jencheng@ginkgobioworks.com
|
5
|
-
#
|
5
|
+
#
|
6
6
|
# based off of Abi.cs by Ronaldo Rodrigues Ferreira
|
7
|
-
#
|
7
|
+
#
|
8
8
|
# extracts the data from ABIF files
|
9
9
|
#
|
10
10
|
# MIT license 2012
|
11
11
|
|
12
|
-
|
13
|
-
|
14
|
-
#
|
15
|
-
#
|
16
|
-
|
17
|
-
#
|
18
|
-
|
19
|
-
#
|
20
|
-
|
21
|
-
#
|
22
|
-
|
23
|
-
#
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
12
|
+
module Absee
|
13
|
+
|
14
|
+
#opens the ABIF sequencing / chromatogram file
|
15
|
+
#checks for ABIF file type
|
16
|
+
#major ABIF versions greater than 1 are not supported
|
17
|
+
#
|
18
|
+
#== Parameters:
|
19
|
+
#filename::
|
20
|
+
# a string containing the filename (including the path and extensions)
|
21
|
+
#
|
22
|
+
#== Returns:
|
23
|
+
# Six arrays: trace data for A, C, G, T, called sequence, and peak indexes
|
24
|
+
def self.readAB(filename)
|
25
|
+
#opens ab1 as a File object
|
26
|
+
abFile = open(filename)
|
27
|
+
byteArray = ""
|
28
|
+
#// here we read the first four bytes. It is important
|
29
|
+
#// to remember that we do not seek back the file, just
|
30
|
+
#// because it is not necessary to do this.
|
31
|
+
abFile.seek(0, IO::SEEK_SET)
|
32
|
+
abFile.read(4, byteArray)
|
33
|
+
#ABIF file indicator
|
34
|
+
if byteArray == "ABIF"
|
35
|
+
return processAB(abFile)
|
36
|
+
else
|
37
|
+
return [],[],[],[],[],[]
|
38
|
+
end
|
36
39
|
end
|
37
|
-
end
|
38
40
|
|
39
|
-
#process the opened ABIF filestream, and calls subsequent methods to extract the data
|
40
|
-
#
|
41
|
-
#== Parameters:
|
42
|
-
#filestream:: an opened File
|
43
|
-
#
|
44
|
-
#== Returns:
|
45
|
-
#Six arrays: trace data for A, C, G, T, called sequence, and peak indexes
|
46
|
-
#readAB returns the results of this method
|
47
|
-
def processAB(filestream)
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
41
|
+
#process the opened ABIF filestream, and calls subsequent methods to extract the data
|
42
|
+
#
|
43
|
+
#== Parameters:
|
44
|
+
#filestream:: an opened File
|
45
|
+
#
|
46
|
+
#== Returns:
|
47
|
+
#Six arrays: trace data for A, C, G, T, called sequence, and peak indexes
|
48
|
+
#readAB returns the results of this method
|
49
|
+
def self.processAB(filestream)
|
50
|
+
#// here, we can read the ABIF header information
|
51
|
+
version = readUnsignedByte_2(4, filestream)
|
52
|
+
#// major versions greater than 1 are not supported
|
53
|
+
#// Applied Biosystems rules
|
54
|
+
if (version / 100 > 1)
|
55
|
+
return [], [], [], [], [], []
|
56
|
+
end
|
57
|
+
#// we just read ABIF, so we don't need more information than that
|
58
|
+
numElements = readUnsignedByte_4(18, filestream)
|
59
|
+
dataOffset = readUnsignedByte_4(26, filestream)
|
60
|
+
directory = readDirectoryEntry(filestream, dataOffset, numElements)
|
61
|
+
numSamples, numBases = gatherInformation(directory, numElements)
|
62
|
+
samples_a, samples_c, samples_g, samples_t = getSamples(filestream, directory, numElements, numSamples)
|
63
|
+
called_sequence = getCalledSequence(filestream, directory, numElements, numBases)
|
64
|
+
peakIndexes = getPeakIndexes(filestream, directory, numElements, numBases)
|
65
|
+
return samples_a, samples_c, samples_g, samples_t, called_sequence, peakIndexes
|
54
66
|
end
|
55
|
-
#// we just read ABIF, so we don't need more information than that
|
56
|
-
numElements = readUnsignedByte_4(18, filestream)
|
57
|
-
dataOffset = readUnsignedByte_4(26, filestream)
|
58
|
-
directory = readDirectoryEntry(filestream, dataOffset, numElements)
|
59
|
-
numSamples, numBases = gatherInformation(directory, numElements)
|
60
|
-
samples_a, samples_c, samples_g, samples_t = getSamples(filestream, directory, numElements, numSamples)
|
61
|
-
called_sequence = getCalledSequence(filestream, directory, numElements, numBases)
|
62
|
-
peakIndexes = getPeakIndexes(filestream, directory, numElements, numBases)
|
63
|
-
return samples_a, samples_c, samples_g, samples_t, called_sequence, peakIndexes
|
64
|
-
end
|
65
67
|
|
66
|
-
#reads 2 unsigned bytes and orders by most significant byte first
|
67
|
-
#
|
68
|
-
#== Parameters:
|
69
|
-
#offset:: how many bytes to offset for the read
|
70
|
-
#filestream:: an opened File
|
71
|
-
#
|
72
|
-
#== Returns:
|
73
|
-
#an int ordered by most significant byte first
|
74
|
-
def readUnsignedByte_2(offset, filestream)
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
|
81
|
-
end
|
68
|
+
#reads 2 unsigned bytes and orders by most significant byte first
|
69
|
+
#
|
70
|
+
#== Parameters:
|
71
|
+
#offset:: how many bytes to offset for the read
|
72
|
+
#filestream:: an opened File
|
73
|
+
#
|
74
|
+
#== Returns:
|
75
|
+
#an int ordered by most significant byte first
|
76
|
+
def self.readUnsignedByte_2(offset, filestream)
|
77
|
+
#// most significant byte first
|
78
|
+
#// |byte0|byte1| <= |unsigned int|
|
79
|
+
byteArray = ""
|
80
|
+
filestream.seek(offset, IO::SEEK_SET)
|
81
|
+
byteArray = filestream.read(2, byteArray)
|
82
|
+
return (byteArray.getbyte(0) << 8) | byteArray.getbyte(1)
|
83
|
+
end
|
82
84
|
|
83
|
-
#reads 4 unsigned bytes and orders by most significant byte first
|
84
|
-
#
|
85
|
-
#== Parameters:
|
86
|
-
#offset:: how many bytes to offset for the read
|
87
|
-
#filestream:: an opened File
|
88
|
-
#
|
89
|
-
#== Returns:
|
90
|
-
#an int ordered by most significant byte first
|
91
|
-
def readUnsignedByte_4(offset, filestream)
|
92
|
-
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
end
|
85
|
+
#reads 4 unsigned bytes and orders by most significant byte first
|
86
|
+
#
|
87
|
+
#== Parameters:
|
88
|
+
#offset:: how many bytes to offset for the read
|
89
|
+
#filestream:: an opened File
|
90
|
+
#
|
91
|
+
#== Returns:
|
92
|
+
#an int ordered by most significant byte first
|
93
|
+
def self.readUnsignedByte_4(offset, filestream)
|
94
|
+
byteArray = ""
|
95
|
+
filestream.seek(offset, IO::SEEK_SET)
|
96
|
+
byteArray = filestream.read(4, byteArray)
|
97
|
+
#// most significant byte first
|
98
|
+
#// |byte0|byte1|byte2|byte3| <= |unsigned int|
|
99
|
+
return (byteArray.getbyte(0)<<24) | (byteArray.getbyte(1)<<16) | (byteArray.getbyte(2)<<8) | byteArray.getbyte(3)
|
100
|
+
end
|
99
101
|
|
100
|
-
#reads the data from the directory
|
101
|
-
#
|
102
|
-
#== Parameters:
|
103
|
-
#dataOffset:: how many bytes to offset
|
104
|
-
#numElements:: number of elements in the file computed by gatherInformation
|
105
|
-
#filestream:: an opened File
|
106
|
-
#
|
107
|
-
#== Returns:
|
108
|
-
#an array of arrays, each with information from the directory
|
109
|
-
#[name, tag number, element type, element size, number of elements, data size, data offset]
|
110
|
-
def readDirectoryEntry(filestream, dataOffset, numElements)
|
111
|
-
filestream.seek(dataOffset, IO::SEEK_SET)
|
112
|
-
byteArray = ""
|
113
|
-
filestream.read(28*numElements, byteArray)
|
114
|
-
directory = []
|
115
|
-
pos = -1
|
116
|
-
|
117
|
-
|
118
|
-
#directory structure
|
102
|
+
#reads the data from the directory
|
103
|
+
#
|
104
|
+
#== Parameters:
|
105
|
+
#dataOffset:: how many bytes to offset
|
106
|
+
#numElements:: number of elements in the file computed by gatherInformation
|
107
|
+
#filestream:: an opened File
|
108
|
+
#
|
109
|
+
#== Returns:
|
110
|
+
#an array of arrays, each with information from the directory
|
119
111
|
#[name, tag number, element type, element size, number of elements, data size, data offset]
|
120
|
-
(
|
121
|
-
|
122
|
-
|
123
|
-
|
124
|
-
|
125
|
-
|
126
|
-
name << byteArray.getbyte(pos+=1).chr
|
127
|
-
name << byteArray.getbyte(pos+=1).chr
|
128
|
-
directory[i] << name
|
129
|
-
#// tag number
|
130
|
-
tag_number = byteArray.getbyte(pos+=1)<<24 | byteArray.getbyte(pos+=1)<<16 | byteArray.getbyte(pos+=1)<<8 | byteArray.getbyte(pos+=1)
|
131
|
-
directory[i] << tag_number
|
132
|
-
#// element type
|
133
|
-
element_type = byteArray.getbyte(pos+=1)<<8 | byteArray.getbyte(pos+=1)
|
134
|
-
directory[i] << element_type
|
135
|
-
#// element size
|
136
|
-
element_size = byteArray.getbyte(pos+=1)<<8 | byteArray.getbyte(pos+=1)
|
137
|
-
directory[i] << element_size
|
138
|
-
#// number of elements
|
139
|
-
number_of_elements = byteArray.getbyte(pos+=1)<<24 | byteArray.getbyte(pos+=1)<<16 | byteArray.getbyte(pos+=1)<<8 | byteArray.getbyte(pos+=1)
|
140
|
-
directory[i] << number_of_elements
|
141
|
-
#// data size
|
142
|
-
data_size = byteArray.getbyte(pos+=1)<<24 | byteArray.getbyte(pos+=1)<<16 | byteArray.getbyte(pos+=1)<<8 | byteArray.getbyte(pos+=1)
|
143
|
-
directory[i] << data_size
|
144
|
-
#// data offset
|
145
|
-
data_offset = byteArray.getbyte(pos+=1)<<24 | byteArray.getbyte(pos+=1)<<16 | byteArray.getbyte(pos+=1)<<8 | byteArray.getbyte(pos+=1)
|
146
|
-
directory[i] << data_offset
|
147
|
-
#// we do not save the dataHandle field
|
148
|
-
pos += 4;
|
149
|
-
end
|
150
|
-
return directory
|
151
|
-
end
|
112
|
+
def self.readDirectoryEntry(filestream, dataOffset, numElements)
|
113
|
+
filestream.seek(dataOffset, IO::SEEK_SET)
|
114
|
+
byteArray = ""
|
115
|
+
filestream.read(28*numElements, byteArray)
|
116
|
+
directory = []
|
117
|
+
pos = -1
|
152
118
|
|
153
119
|
|
154
|
-
#directory structure
|
155
|
-
#[name, tag number, element type, element size, number of elements, data size, data offset]
|
156
|
-
|
157
|
-
|
158
|
-
|
159
|
-
|
160
|
-
|
161
|
-
|
162
|
-
|
163
|
-
|
164
|
-
|
165
|
-
|
166
|
-
|
167
|
-
|
168
|
-
|
169
|
-
|
170
|
-
|
171
|
-
|
172
|
-
|
173
|
-
|
174
|
-
|
175
|
-
|
176
|
-
|
177
|
-
|
178
|
-
|
179
|
-
|
180
|
-
|
120
|
+
#directory structure
|
121
|
+
#[name, tag number, element type, element size, number of elements, data size, data offset]
|
122
|
+
(0..(numElements-1)).each do |i|
|
123
|
+
directory[i] = []
|
124
|
+
#// name
|
125
|
+
name = ""
|
126
|
+
name << byteArray.getbyte(pos+=1).chr
|
127
|
+
name << byteArray.getbyte(pos+=1).chr
|
128
|
+
name << byteArray.getbyte(pos+=1).chr
|
129
|
+
name << byteArray.getbyte(pos+=1).chr
|
130
|
+
directory[i] << name
|
131
|
+
#// tag number
|
132
|
+
tag_number = byteArray.getbyte(pos+=1)<<24 | byteArray.getbyte(pos+=1)<<16 | byteArray.getbyte(pos+=1)<<8 | byteArray.getbyte(pos+=1)
|
133
|
+
directory[i] << tag_number
|
134
|
+
#// element type
|
135
|
+
element_type = byteArray.getbyte(pos+=1)<<8 | byteArray.getbyte(pos+=1)
|
136
|
+
directory[i] << element_type
|
137
|
+
#// element size
|
138
|
+
element_size = byteArray.getbyte(pos+=1)<<8 | byteArray.getbyte(pos+=1)
|
139
|
+
directory[i] << element_size
|
140
|
+
#// number of elements
|
141
|
+
number_of_elements = byteArray.getbyte(pos+=1)<<24 | byteArray.getbyte(pos+=1)<<16 | byteArray.getbyte(pos+=1)<<8 | byteArray.getbyte(pos+=1)
|
142
|
+
directory[i] << number_of_elements
|
143
|
+
#// data size
|
144
|
+
data_size = byteArray.getbyte(pos+=1)<<24 | byteArray.getbyte(pos+=1)<<16 | byteArray.getbyte(pos+=1)<<8 | byteArray.getbyte(pos+=1)
|
145
|
+
directory[i] << data_size
|
146
|
+
#// data offset
|
147
|
+
data_offset = byteArray.getbyte(pos+=1)<<24 | byteArray.getbyte(pos+=1)<<16 | byteArray.getbyte(pos+=1)<<8 | byteArray.getbyte(pos+=1)
|
148
|
+
directory[i] << data_offset
|
149
|
+
#// we do not save the dataHandle field
|
150
|
+
pos += 4;
|
151
|
+
end
|
152
|
+
return directory
|
181
153
|
end
|
182
|
-
end
|
183
154
|
|
184
|
-
|
185
|
-
#
|
186
|
-
|
187
|
-
#
|
188
|
-
#
|
189
|
-
|
190
|
-
|
191
|
-
#
|
192
|
-
|
193
|
-
|
194
|
-
|
195
|
-
|
196
|
-
|
197
|
-
|
198
|
-
|
155
|
+
|
156
|
+
#directory structure
|
157
|
+
#[name, tag number, element type, element size, number of elements, data size, data offset]
|
158
|
+
#this is for easier index into the each directory array
|
159
|
+
#
|
160
|
+
#== Parameters:
|
161
|
+
#array:: an array with information from the directory
|
162
|
+
#element:: a string with type of information from the directory to retrieve: [name, tag_number, element_type, element_size, number_of_elements, data_size, data_offset
|
163
|
+
#
|
164
|
+
#== Returns:
|
165
|
+
#the element from the array
|
166
|
+
def self.get(array, element)
|
167
|
+
if element == "name"
|
168
|
+
return array[0]
|
169
|
+
elsif element == "tag_number"
|
170
|
+
return array[1]
|
171
|
+
elsif element == "element_type"
|
172
|
+
return array[2]
|
173
|
+
elsif element == "element_size"
|
174
|
+
return array[3]
|
175
|
+
elsif element == "number_of_elements"
|
176
|
+
return array[4]
|
177
|
+
elsif element == "data_size"
|
178
|
+
return array[5]
|
179
|
+
elsif element == "data_offset"
|
180
|
+
return array[6]
|
199
181
|
else
|
200
|
-
|
201
|
-
numBases = get(directory[i], "number_of_elements") #number of elements
|
202
|
-
end
|
182
|
+
return array[0]
|
203
183
|
end
|
204
184
|
end
|
205
|
-
|
206
|
-
return numSamples, numBases
|
207
|
-
end
|
208
185
|
|
209
|
-
#
|
210
|
-
#
|
211
|
-
#== Parameters:
|
212
|
-
#
|
213
|
-
#
|
214
|
-
#
|
215
|
-
|
216
|
-
#
|
217
|
-
|
218
|
-
|
219
|
-
|
220
|
-
samples_a = []
|
221
|
-
samples_c = []
|
222
|
-
samples_g = []
|
223
|
-
samples_t = []
|
186
|
+
#counts the number of samples and number of bases contained in this ABIF file
|
187
|
+
#
|
188
|
+
#== Parameters:
|
189
|
+
#directory:: an array of array generated from readDirectoryEntry
|
190
|
+
#numElements:: an int indicating the number of elements in this ABIF file
|
191
|
+
#
|
192
|
+
#== Returns:
|
193
|
+
#number of samples and number of bases contained in this ABIF file
|
194
|
+
def self.gatherInformation(directory, numElements)
|
195
|
+
numSamples = 0
|
196
|
+
numBases = 0
|
224
197
|
|
225
|
-
|
226
|
-
|
227
|
-
|
228
|
-
|
229
|
-
|
230
|
-
|
231
|
-
filestream.read(get(directory[i], "number_of_elements")*2, byteArray_samples)
|
232
|
-
pos = -1
|
233
|
-
if tag_number == 9 #G
|
234
|
-
(0..numSamples-1).each do |j|
|
235
|
-
value = byteArray_samples.getbyte(pos+=1) << 8 | byteArray_samples.getbyte(pos+=1)
|
236
|
-
samples_g[j] = value
|
237
|
-
end
|
238
|
-
elsif tag_number == 10 #A
|
239
|
-
(0..numSamples-1).each do |j|
|
240
|
-
value = byteArray_samples.getbyte(pos+=1) << 8 | byteArray_samples.getbyte(pos+=1)
|
241
|
-
samples_a[j] = value
|
198
|
+
(0..(numElements-1)).each do |i|
|
199
|
+
if (get(directory[i],"name") == "DATA") && (get(directory[i], "tag_number") == 9)
|
200
|
+
numSamples = get(directory[i], "number_of_elements") #number of elements
|
201
|
+
else
|
202
|
+
if (get(directory[i], "name") == "PBAS") && (get(directory[i], "tag_number") == 2)
|
203
|
+
numBases = get(directory[i], "number_of_elements") #number of elements
|
242
204
|
end
|
243
|
-
|
244
|
-
|
245
|
-
|
246
|
-
|
247
|
-
|
248
|
-
|
249
|
-
|
250
|
-
|
251
|
-
|
205
|
+
end
|
206
|
+
end
|
207
|
+
|
208
|
+
return numSamples, numBases
|
209
|
+
end
|
210
|
+
|
211
|
+
#extracts the trace information for the bases
|
212
|
+
#
|
213
|
+
#== Parameters:
|
214
|
+
#filestream:: an open File
|
215
|
+
#directory:: an array of array generated by readDirectoryEntry
|
216
|
+
#numElements:: an int indicating the number of elements in this ABIF file
|
217
|
+
#numSamples:: an int calculated by gatherInformation
|
218
|
+
#
|
219
|
+
#== Returns:
|
220
|
+
#four arrays with trace data in the order ACGT
|
221
|
+
def self.getSamples(filestream, directory, numElements, numSamples)
|
222
|
+
samples_a = []
|
223
|
+
samples_c = []
|
224
|
+
samples_g = []
|
225
|
+
samples_t = []
|
226
|
+
|
227
|
+
#// we guess the order being GATC, as Ferreira and Staden does
|
228
|
+
(0..numElements-1).each do |i|
|
229
|
+
tag_number = get(directory[i], "tag_number")
|
230
|
+
if (get(directory[i],"name") == "DATA") && ([9,10,11,12].include? tag_number)
|
231
|
+
byteArray_samples = ""
|
232
|
+
filestream.seek(get(directory[i],"data_offset"), IO::SEEK_SET)
|
233
|
+
filestream.read(get(directory[i], "number_of_elements")*2, byteArray_samples)
|
234
|
+
pos = -1
|
235
|
+
if tag_number == 9 #G
|
236
|
+
(0..numSamples-1).each do |j|
|
237
|
+
value = byteArray_samples.getbyte(pos+=1) << 8 | byteArray_samples.getbyte(pos+=1)
|
238
|
+
samples_g[j] = value
|
239
|
+
end
|
240
|
+
elsif tag_number == 10 #A
|
241
|
+
(0..numSamples-1).each do |j|
|
242
|
+
value = byteArray_samples.getbyte(pos+=1) << 8 | byteArray_samples.getbyte(pos+=1)
|
243
|
+
samples_a[j] = value
|
244
|
+
end
|
245
|
+
elsif tag_number == 11 #T
|
246
|
+
(0..numSamples-1).each do |j|
|
247
|
+
value = byteArray_samples.getbyte(pos+=1) << 8 | byteArray_samples.getbyte(pos+=1)
|
248
|
+
samples_t[j] = value
|
249
|
+
end
|
250
|
+
else #C
|
251
|
+
(0..numSamples-1).each do |j|
|
252
|
+
value = byteArray_samples.getbyte(pos+=1) << 8 | byteArray_samples.getbyte(pos+=1)
|
253
|
+
samples_c[j] = value
|
254
|
+
end
|
252
255
|
end
|
253
256
|
end
|
254
257
|
end
|
258
|
+
return samples_a, samples_c, samples_g, samples_t
|
255
259
|
end
|
256
|
-
return samples_a, samples_c, samples_g, samples_t
|
257
|
-
end
|
258
260
|
|
259
|
-
#extracts the called sequence information
|
260
|
-
#
|
261
|
-
#== Parameters:
|
262
|
-
#filestream:: an open File
|
263
|
-
#directory:: an array of array generated by readDirectoryEntry
|
264
|
-
#numElements:: an int indicating the number of elements in this ABIF file
|
265
|
-
#numBases:: an int calculated by gatherInformation
|
266
|
-
#
|
267
|
-
#== Returns:
|
268
|
-
#an array with the called sequence
|
269
|
-
def getCalledSequence(filestream, directory, numElements, numBases)
|
270
|
-
|
271
|
-
|
272
|
-
|
273
|
-
|
274
|
-
|
275
|
-
|
276
|
-
|
277
|
-
|
261
|
+
#extracts the called sequence information
|
262
|
+
#
|
263
|
+
#== Parameters:
|
264
|
+
#filestream:: an open File
|
265
|
+
#directory:: an array of array generated by readDirectoryEntry
|
266
|
+
#numElements:: an int indicating the number of elements in this ABIF file
|
267
|
+
#numBases:: an int calculated by gatherInformation
|
268
|
+
#
|
269
|
+
#== Returns:
|
270
|
+
#an array with the called sequence
|
271
|
+
def self.getCalledSequence(filestream, directory, numElements, numBases)
|
272
|
+
calledSequence = []
|
273
|
+
(0..numElements-1).each do |i|
|
274
|
+
if (get(directory[i], "name") == "PBAS") && (get(directory[i], "tag_number") == 2)
|
275
|
+
byteArray_seq = ""
|
276
|
+
filestream.seek(get(directory[i], "data_offset"))
|
277
|
+
filestream.read(numBases,byteArray_seq)
|
278
|
+
(0..numBases-1).each do |j|
|
279
|
+
calledSequence[j] = byteArray_seq.getbyte(j).chr
|
280
|
+
end
|
278
281
|
end
|
279
282
|
end
|
283
|
+
return calledSequence
|
280
284
|
end
|
281
|
-
return calledSequence
|
282
|
-
end
|
283
285
|
|
284
|
-
#extracts the trace information for the bases
|
285
|
-
#
|
286
|
-
#== Parameters:
|
287
|
-
#filestream:: an open File
|
288
|
-
#directory:: an array of array generated by readDirectoryEntry
|
289
|
-
#numElements:: an int indicating the number of elements in this ABIF file
|
290
|
-
#numBases:: an int calculated by gatherInformation
|
291
|
-
#
|
292
|
-
#== Returns:
|
293
|
-
#an array with the indexes of the peaks
|
294
|
-
def getPeakIndexes(filestream, directory, numElements, numBases)
|
295
|
-
|
296
|
-
|
297
|
-
|
298
|
-
|
299
|
-
|
300
|
-
|
301
|
-
|
302
|
-
|
303
|
-
|
304
|
-
|
286
|
+
#extracts the trace information for the bases
|
287
|
+
#
|
288
|
+
#== Parameters:
|
289
|
+
#filestream:: an open File
|
290
|
+
#directory:: an array of array generated by readDirectoryEntry
|
291
|
+
#numElements:: an int indicating the number of elements in this ABIF file
|
292
|
+
#numBases:: an int calculated by gatherInformation
|
293
|
+
#
|
294
|
+
#== Returns:
|
295
|
+
#an array with the indexes of the peaks
|
296
|
+
def self.getPeakIndexes(filestream, directory, numElements, numBases)
|
297
|
+
peakIndexes = []
|
298
|
+
(0..numElements-1).each do |i|
|
299
|
+
if (get(directory[i], "name") == "PLOC") && (get(directory[i], "tag_number") == 2)
|
300
|
+
byteArray_peak = ""
|
301
|
+
filestream.seek(get(directory[i], "data_offset"), IO::SEEK_SET)
|
302
|
+
filestream.read(get(directory[i], "number_of_elements")*4, byteArray_peak)
|
303
|
+
pos = -1
|
304
|
+
(0..numBases-1).each do |j|
|
305
|
+
peakIndex = byteArray_peak.getbyte(pos+=1) << 8 | byteArray_peak.getbyte(pos+=1)
|
306
|
+
peakIndexes[j] = peakIndex
|
307
|
+
end
|
305
308
|
end
|
306
309
|
end
|
310
|
+
return peakIndexes
|
307
311
|
end
|
308
|
-
|
312
|
+
|
309
313
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: absee
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.1.0.0
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,10 +9,10 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-
|
12
|
+
date: 2012-11-14 00:00:00.000000000 Z
|
13
13
|
dependencies: []
|
14
|
-
description:
|
15
|
-
|
14
|
+
description: .ab1 reader / ABIF reader; extracts the peak indexes, called sequence,
|
15
|
+
and ACGT values from sequencing files
|
16
16
|
email: jencheng@ginkgobioworks.com
|
17
17
|
executables: []
|
18
18
|
extensions: []
|
@@ -43,6 +43,6 @@ rubyforge_project:
|
|
43
43
|
rubygems_version: 1.8.23
|
44
44
|
signing_key:
|
45
45
|
specification_version: 3
|
46
|
-
summary:
|
46
|
+
summary: .ab1 reader / ABIF reader
|
47
47
|
test_files: []
|
48
48
|
has_rdoc:
|