1
2
3
4
5
6
7
8
9
10
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
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
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
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
|
# Sam language definition file for less pipe
# bioSyntax v0.1
# Depends on sam.style + bioSyntax.outlang
# Variables ----------------------------------
vardef NUCLEOTIDE = '[ATCGNXatcgnxRYSWKM]'
vardef PHRED = '[!-K]' #PHRED 1.8
# Header-section -----------------------------
environment header start '^(?=@)' begin
# Standard Headers HD | SQ | PG
environment header_hd delim '(?=@(HD|SQ|PG))' '$' begin
header = '@[HSPC][DQGO]'
#HD
numeric = '(?<=VN:)\S*'
mal = '(?<=SO:)(unsorted|unknown)'
bon = '(?<=SO:)(coordinate|queryname)'
mal = '(?<=SO:)\S*'
mal = '(?<=GO:)(none|)'
bon = '(?<=GO:)(query|reference)'
mal = '(?<=GO:)\S*'
#SQ
chr = '(?<=SN:)\S*'
chrStart = '(?<=LN:)\S*'
chr = '(?<=AH:)\S*'
chr = '(?<=AN:)\S*'
chr = '(?<=AS:)\S*'
string = '(?<=M5:)\S*'
chr = '(?<=SP:)\S*'
numeric = '(?<=UR:)\S*'
#PG
software = '(?<=ID:)\S*'
software = '(?<=PN:)\S*'
commandline = '(?<=CL:)[\S ]*'
software = '(?<=PP:)\S*'
string = '(?<=DS:)\S*'
#numeric = '(?<=VN:)\S*'
end
# Readgroup Header
environment header_co delim '(?=@RG)' '$' begin
header = '@RG'
sample = '(?<=ID:)\S*'
string = '(?<=CN:)\S*'
string = '(?<=DS:)\S*'
numeric = '(?<=DT:)\S*'
string = '(?<=FO:)\S*'
string = '(?<=KS:)\S*'
sample = '(?<=LB:)\S*'
software = '(?<=PG:)\S*'
numeric = '(?<=PI:)\S*'
string = '(?<=PL:)\S*'
string = '(?<=PM:)\S*'
string = '(?<=PU:)\S*'
sample = '(?<=SM:)\S*'
end
# Comment Header
environment header_co delim '(?=@CO)' '$' begin
header = '@CO'
comment = '.*'
end
end #Header
# -------------------------------------------
# align-section -----------------------------
environment align start '(?=^[^$])' begin
drop = '$' exitall # stops multi-line searching
# Column 1: CHROM
string = '^\S+'
# Column 2: FLAG
environment push2 = '\t?' begin
drop = '(?=$)' exitall
# Read Flag
# If flag > 512
# read is QC-fail | PCRdup | 2'
numeric = '\A[0-9]{1,2}(?=\t)'
numeric = '\A[1-4][0-9]{1,2}(?=\t)'
numeric = '\A[5][0][0-9](?=\t)'
numeric = '\A[5][1][01](?=\t)'
# Flag > 512 (QC fail / PCR dup / Supp Read)
string = '\A\d\d\d+'
# Column 3: RNAME
environment push3 = '\t?' begin
drop = '(?=$)' exitall
chr = '\A\S+'
# Column 4: POSition
environment push4 = '\t?' begin
drop = '(?=$)' exitall
chrStart = '\A\d+'
# Column 5: MAPQuality
environment push5 = '\t?' begin
drop = '(?=$)' exitall
# MAPQ Scale (-log10 P)
# Incriment size = 10
gradbw1 = '\A255(?=\t)' # MAPQ NA
gradbw1 = '\A[0-9](?=\t)'
grasbw6 = '\A[1][0-9]'
gradbw8 = '\A[2][0-9]'
gradbw10 = '\A[3][0-9]'
gradbw10i = '\A[4-9][0-9]'
gradbw1 = '\A\d+'
# Column 6: CIGAR string
environment push6 = '\t?' begin
drop = '(?=$)' exitall
# CIGAR Strings
# M: Alignment match
# I: Insertion
# D: Deletion
# N: Skipped region (intron)
# S: Soft Clip
# H: Hard Clip
# P: Padding
# =: Sequence Match
# X: Sequence Mismatch
# *: String Absent
clip = '\A\d++[NSHP]' # clips
default = '\A\d++[M=]' # match
mismatch = '\A\d++[X]' # mismatch
insertion = '\A\d++[I]' # insertion
deletion = '\A\d++[D]' # deletion
comment = '\A\S++' # else
# Column 7: RNEXT & PNEXT
environment push7 = '\t?' begin
drop = '(?=$)' exitall
# Match Chromosome
chrStart = '\A=\t\d+\t'
# Unmapped Rnext
string = '\A\\*\t\d+\t'
# Different Chromosome Rnext
string = '\A\S+\t\d+\t'
# Column 8: TLEN
environment push8 = '(?=\d)' begin
drop = '(?=$)' exitall
numeric = '\d+'
# Column 9: Sequence Data
environment push9 = '\t?' begin
drop = '(?=$)' exitall
ntA = '\A[Aa]++'
ntT = '\A[TtUu]++'
ntG = '\A[Gg]++'
ntC = '\A[Cc]++'
ntN = '\A[NnXx]++'
ntN = '\A[RrYySsWwKkMm]++'
# Column 10: PHRED
environment push10 = '\t?' begin
drop = '(?=$)' exitall
# Illumina 1.8 Scale
# !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJ...j
# | | | | | | | | | |...
gradbw1 = '\A[!-%]++'
gradbw3 = '\A[!-(]++'
gradbw6 = '\A[)-0]++'
gradbw8 = '\A[1-8]++'
gradbw10 = '\A[9-@]++'
gradbw10b = '\A[A-D]++'
gradbw10i = '\A[E-j]++'
# Column 11+ Tags
environment push11 = '\t' begin
drop = '(?=$)' exitall
# AB:i:1337
# A Printable
# i signed integer
# f floating point
# Z string with spaces
# H byte array hex
# B Integer/Numeric Array
string = '[A-Z]{2}:'
(comment,numeric) = `([ifH]:)(\S*)`
(comment,keyword) = `([AZB]:)(\S*)`
end #col11+
end #col10
end #col9
end #col8
end #col7
end #col6
end # col5
end # col4
end # col3
end # col2
end # align section
|
