-
Notifications
You must be signed in to change notification settings - Fork 3
/
nucmer
executable file
·394 lines (335 loc) · 12.2 KB
/
nucmer
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
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
#!/opt/local/bin/perl
#-------------------------------------------------------------------------------
# Programmer: Adam M Phillippy, The Institute for Genomic Research
# File: nucmer
# Date: 04 / 09 / 03
#
# Usage:
# nucmer [options] <Reference> <Query>
#
# Try 'nucmer -h' for more information.
#
# Purpose: To create alignments between two multi-FASTA inputs by using
# the MUMmer matching and clustering algorithms.
#
#-------------------------------------------------------------------------------
use lib "/Users/garviz/Downloads/MUMmer3.23/scripts";
use Foundation;
use File::Spec::Functions;
use strict;
my $AUX_BIN_DIR = "/Users/garviz/Downloads/MUMmer3.23/aux_bin";
my $BIN_DIR = "/Users/garviz/Downloads/MUMmer3.23";
my $SCRIPT_DIR = "/Users/garviz/Downloads/MUMmer3.23/scripts";
my $VERSION_INFO = q~
NUCmer (NUCleotide MUMmer) version 3.1
~;
my $HELP_INFO = q~
USAGE: nucmer [options] <Reference> <Query>
DESCRIPTION:
nucmer generates nucleotide alignments between two mutli-FASTA input
files. The out.delta output file lists the distance between insertions
and deletions that produce maximal scoring alignments between each
sequence. The show-* utilities know how to read this format.
MANDATORY:
Reference Set the input reference multi-FASTA filename
Query Set the input query multi-FASTA filename
OPTIONS:
--mum Use anchor matches that are unique in both the reference
and query
--mumcand Same as --mumreference
--mumreference Use anchor matches that are unique in in the reference
but not necessarily unique in the query (default behavior)
--maxmatch Use all anchor matches regardless of their uniqueness
-b|breaklen Set the distance an alignment extension will attempt to
extend poor scoring regions before giving up (default 200)
--[no]banded Enforce absolute banding of dynamic programming matrix
based on diagdiff parameter EXPERIMENTAL (default no)
-c|mincluster Sets the minimum length of a cluster of matches (default 65)
--[no]delta Toggle the creation of the delta file (default --delta)
--depend Print the dependency information and exit
-D|diagdiff Set the maximum diagonal difference between two adjacent
anchors in a cluster (default 5)
-d|diagfactor Set the maximum diagonal difference between two adjacent
anchors in a cluster as a differential fraction of the gap
length (default 0.12)
--[no]extend Toggle the cluster extension step (default --extend)
-f
--forward Use only the forward strand of the Query sequences
-g|maxgap Set the maximum gap between two adjacent matches in a
cluster (default 90)
-h
--help Display help information and exit
-l|minmatch Set the minimum length of a single match (default 20)
-o
--coords Automatically generate the original NUCmer1.1 coords
output file using the 'show-coords' program
--[no]optimize Toggle alignment score optimization, i.e. if an alignment
extension reaches the end of a sequence, it will backtrack
to optimize the alignment score instead of terminating the
alignment at the end of the sequence (default --optimize)
-p|prefix Set the prefix of the output files (default "out")
-r
--reverse Use only the reverse complement of the Query sequences
--[no]simplify Simplify alignments by removing shadowed clusters. Turn
this option off if aligning a sequence to itself to look
for repeats (default --simplify)
-V
--version Display the version information and exit
~;
my $USAGE_INFO = q~
USAGE: nucmer [options] <Reference> <Query>
~;
my @DEPEND_INFO =
(
"$BIN_DIR/mummer",
"$BIN_DIR/mgaps",
"$BIN_DIR/show-coords",
"$AUX_BIN_DIR/postnuc",
"$AUX_BIN_DIR/prenuc",
"$SCRIPT_DIR/Foundation.pm"
);
my %DEFAULT_PARAMETERS =
(
"OUTPUT_PREFIX" => "out", # prefix for all output files
"MATCH_ALGORITHM" => "-mumreference", # match finding algo switch
"MATCH_DIRECTION" => "-b", # match direction switch
"MIN_MATCH" => "20", # minimum match size
"MAX_GAP" => "90", # maximum gap between matches
"MIN_CLUSTER" => "65", # minimum cluster size
"DIAG_DIFF" => "5", # diagonal difference absolute
"DIAG_FACTOR" => ".12", # diagonal difference fraction
"BREAK_LEN" => "200", # extension break length
"POST_SWITCHES" => "" # switches for the post processing
);
sub main ( )
{
my $tigr; # TIGR::Foundation object
my @err; # Error variable
my $ref_file; # path of the reference input file
my $qry_file; # path of the query input file
#-- The command line options for the various programs
my $pfx = $DEFAULT_PARAMETERS { "OUTPUT_PREFIX" };
my $algo = $DEFAULT_PARAMETERS { "MATCH_ALGORITHM" };
my $mdir = $DEFAULT_PARAMETERS { "MATCH_DIRECTION" };
my $size = $DEFAULT_PARAMETERS { "MIN_MATCH" };
my $gap = $DEFAULT_PARAMETERS { "MAX_GAP" };
my $clus = $DEFAULT_PARAMETERS { "MIN_CLUSTER" };
my $ddiff = $DEFAULT_PARAMETERS { "DIAG_DIFF" };
my $dfrac = $DEFAULT_PARAMETERS { "DIAG_FACTOR" };
my $blen = $DEFAULT_PARAMETERS { "BREAK_LEN" };
my $psw = $DEFAULT_PARAMETERS { "POST_SWITCHES" };
my $fwd; # if true, use forward strand
my $rev; # if true, use reverse strand
my $maxmatch; # matching algorithm switches
my $mumreference;
my $mum;
my $banded = 0; # if true, enforce absolute dp banding
my $extend = 1; # if true, extend clusters
my $delta = 1; # if true, create the delta file
my $optimize = 1; # if true, optimize alignment scores
my $simplify = 1; # if true, simplify shadowed alignments
my $generate_coords;
#-- Initialize TIGR::Foundation
$tigr = new TIGR::Foundation;
if ( !defined ($tigr) ) {
print (STDERR "ERROR: TIGR::Foundation could not be initialized");
exit (1);
}
#-- Set help and usage information
$tigr->setHelpInfo ($HELP_INFO);
$tigr->setUsageInfo ($USAGE_INFO);
$tigr->setVersionInfo ($VERSION_INFO);
$tigr->addDependInfo (@DEPEND_INFO);
#-- Get command line parameters
$err[0] = $tigr->TIGR_GetOptions
(
"maxmatch" => \$maxmatch,
"mumcand" => \$mumreference,
"mumreference" => \$mumreference,
"mum" => \$mum,
"b|breaklen=i" => \$blen,
"banded!" => \$banded,
"c|mincluster=i" => \$clus,
"delta!" => \$delta,
"D|diagdiff=i" => \$ddiff,
"d|diagfactor=f" => \$dfrac,
"extend!" => \$extend,
"f|forward" => \$fwd,
"g|maxgap=i" => \$gap,
"l|minmatch=i" => \$size,
"o|coords" => \$generate_coords,
"optimize!" => \$optimize,
"p|prefix=s" => \$pfx,
"r|reverse" => \$rev,
"simplify!" => \$simplify
);
#-- Check if the parsing was successful
if ( $err[0] == 0 || $#ARGV != 1 ) {
$tigr->printUsageInfo( );
print (STDERR "Try '$0 -h' for more information.\n");
exit (1);
}
$ref_file = File::Spec->rel2abs ($ARGV[0]);
$qry_file = File::Spec->rel2abs ($ARGV[1]);
#-- Set up the program parameters
if ( $fwd && $rev ) {
$mdir = "-b";
} elsif ( $fwd ) {
$mdir = "";
} elsif ( $rev ) {
$mdir = "-r";
}
if ( ! $extend ) {
$psw .= "-e ";
}
if ( ! $delta ) {
$psw .= "-d ";
}
if ( ! $optimize ) {
$psw .= "-t ";
}
if ( ! $simplify ) {
$psw .= "-s ";
}
undef (@err);
$err[0] = 0;
if ( $mum ) {
$err[0] ++;
$algo = "-mum";
}
if ( $mumreference ) {
$err[0] ++;
$algo = "-mumreference";
}
if ( $maxmatch ) {
$err[0] ++;
$algo = "-maxmatch";
}
if ( $err[0] > 1 ) {
$tigr->printUsageInfo( );
print (STDERR "ERROR: Multiple matching algorithms selected\n");
print (STDERR "Try '$0 -h' for more information.\n");
exit (1);
}
#-- Set up the program path names
my $algo_path = "$BIN_DIR/mummer";
my $mgaps_path = "$BIN_DIR/mgaps";
my $prenuc_path = "$AUX_BIN_DIR/prenuc";
my $postnuc_path = "$AUX_BIN_DIR/postnuc";
my $showcoords_path = "$BIN_DIR/show-coords";
#-- Check that the files needed are all there and readable/writable
{
undef (@err);
if ( !$tigr->isExecutableFile ($algo_path) ) {
push (@err, $algo_path);
}
if ( !$tigr->isExecutableFile ($mgaps_path) ) {
push (@err, $mgaps_path);
}
if ( !$tigr->isExecutableFile ($prenuc_path) ) {
push (@err, $prenuc_path);
}
if ( !$tigr->isExecutableFile ($postnuc_path) ) {
push (@err, $postnuc_path);
}
if ( !$tigr->isReadableFile ($ref_file) ) {
push (@err, $ref_file);
}
if ( !$tigr->isReadableFile ($qry_file) ) {
push (@err, $qry_file);
}
if ( !$tigr->isCreatableFile ("$pfx.ntref") ) {
if ( !$tigr->isWritableFile ("$pfx.ntref") ) {
push (@err, "$pfx.ntref");
}
}
if ( !$tigr->isCreatableFile ("$pfx.mgaps") ) {
if ( !$tigr->isWritableFile ("$pfx.mgaps") ) {
push (@err, "$pfx.mgaps");
}
}
if ( !$tigr->isCreatableFile ("$pfx.delta") ) {
if ( !$tigr->isWritableFile ("$pfx.delta") ) {
push (@err, "$pfx.delta");
}
}
if ( $generate_coords ) {
if ( !$tigr->isExecutableFile ($showcoords_path) ) {
push (@err, $showcoords_path);
}
if ( !$tigr->isCreatableFile ("$pfx.coords") ) {
if ( !$tigr->isWritableFile ("$pfx.coords") ) {
push (@err, "$pfx.coords");
}
}
}
#-- If 1 or more files could not be processed, terminate script
if ( $#err >= 0 ) {
$tigr->logError
("ERROR: The following critical files could not be used", 1);
while ( $#err >= 0 ) {
$tigr->logError (pop(@err), 1);
}
$tigr->logError
("Check your paths and file permissions and try again", 1);
$tigr->bail( );
}
}
#-- Run prenuc and assert return value is zero
print (STDERR "1: PREPARING DATA\n");
$err[0] = $tigr->runCommand
("$prenuc_path $ref_file > $pfx.ntref");
if ( $err[0] != 0 ) {
$tigr->bail
("ERROR: prenuc returned non-zero\n");
}
#-- Run mummer | mgaps and assert return value is zero
print (STDERR "2,3: RUNNING mummer AND CREATING CLUSTERS\n");
open(ALGO_PIPE, "$algo_path $algo $mdir -l $size -n $pfx.ntref $qry_file |")
or $tigr->bail ("ERROR: could not open $algo_path output pipe $!");
open(CLUS_PIPE, "| $mgaps_path -l $clus -s $gap -d $ddiff -f $dfrac > $pfx.mgaps")
or $tigr->bail ("ERROR: could not open $mgaps_path input pipe $!");
while ( <ALGO_PIPE> ) {
print CLUS_PIPE
or $tigr->bail ("ERROR: could not write to $mgaps_path pipe $!");
}
$err[0] = close(ALGO_PIPE);
$err[1] = close(CLUS_PIPE);
if ( $err[0] == 0 || $err[1] == 0 ) {
$tigr->bail ("ERROR: mummer and/or mgaps returned non-zero\n");
}
#-- Run postnuc and assert return value is zero
print (STDERR "4: FINISHING DATA\n");
if ( $banded )
{
$err[0] = $tigr->runCommand
("$postnuc_path $psw -b $blen -B $ddiff $ref_file $qry_file $pfx < $pfx.mgaps");
}
else
{
$err[0] = $tigr->runCommand
("$postnuc_path $psw -b $blen $ref_file $qry_file $pfx < $pfx.mgaps");
}
if ( $err[0] != 0 ) {
$tigr->bail ("ERROR: postnuc returned non-zero\n");
}
#-- If the -o flag was set, run show-coords using NUCmer1.1 settings
if ( $generate_coords ) {
print (STDERR "5: GENERATING COORDS FILE\n");
$err[0] = $tigr->runCommand
("$showcoords_path -r $pfx.delta > $pfx.coords");
if ( $err[0] != 0 ) {
$tigr->bail ("ERROR: show-coords returned non-zero\n");
}
}
#-- Remove the temporary output
$err[0] = unlink ("$pfx.ntref", "$pfx.mgaps");
if ( $err[0] != 2 ) {
$tigr->logError ("WARNING: there was a problem deleting".
" the temporary output files", 1);
}
#-- Return success
return (0);
}
exit ( main ( ) );
#-- END OF SCRIPT