|
0
|
1 #!/usr/bin/perl -w
|
|
|
2 #
|
|
|
3 # $RCSfile: ExtractFromSequenceFiles.pl,v $
|
|
|
4 # $Date: 2015/02/28 20:46:19 $
|
|
|
5 # $Revision: 1.23 $
|
|
|
6 #
|
|
|
7 # Author: Manish Sud <msud@san.rr.com>
|
|
|
8 #
|
|
|
9 # Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
10 #
|
|
|
11 # This file is part of MayaChemTools.
|
|
|
12 #
|
|
|
13 # MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
14 # the terms of the GNU Lesser General Public License as published by the Free
|
|
|
15 # Software Foundation; either version 3 of the License, or (at your option) any
|
|
|
16 # later version.
|
|
|
17 #
|
|
|
18 # MayaChemTools is distributed in the hope that it will be useful, but without
|
|
|
19 # any warranty; without even the implied warranty of merchantability of fitness
|
|
|
20 # for a particular purpose. See the GNU Lesser General Public License for more
|
|
|
21 # details.
|
|
|
22 #
|
|
|
23 # You should have received a copy of the GNU Lesser General Public License
|
|
|
24 # along with MayaChemTools; if not, see <http://www.gnu.org/licenses/> or
|
|
|
25 # write to the Free Software Foundation Inc., 59 Temple Place, Suite 330,
|
|
|
26 # Boston, MA, 02111-1307, USA.
|
|
|
27 #
|
|
|
28
|
|
|
29 use strict;
|
|
|
30 use FindBin; use lib "$FindBin::Bin/../lib";
|
|
|
31 use Getopt::Long;
|
|
|
32 use File::Basename;
|
|
|
33 use Text::ParseWords;
|
|
|
34 use Benchmark;
|
|
|
35 use FileUtil;
|
|
|
36 use TextUtil;
|
|
|
37 use SequenceFileUtil;
|
|
|
38
|
|
|
39 my($ScriptName, %Options, $StartTime, $EndTime, $TotalTime);
|
|
|
40
|
|
|
41 # Autoflush STDOUT
|
|
|
42 $| = 1;
|
|
|
43
|
|
|
44 # Starting message...
|
|
|
45 $ScriptName = basename($0);
|
|
|
46 print "\n$ScriptName: Starting...\n\n";
|
|
|
47 $StartTime = new Benchmark;
|
|
|
48
|
|
|
49 # Setup script usage message...
|
|
|
50 SetupScriptUsage();
|
|
|
51 if ($Options{help} || @ARGV < 1) {
|
|
|
52 die GetUsageFromPod("$FindBin::Bin/$ScriptName");
|
|
|
53 }
|
|
|
54
|
|
|
55 # Expand wild card file names...
|
|
|
56 my(@SequenceFilesList);
|
|
|
57 @SequenceFilesList = ExpandFileNames(\@ARGV, "aln msf fasta fta pir");
|
|
|
58
|
|
|
59 # Process options...
|
|
|
60 print "Processing options...\n";
|
|
|
61 my(%OptionsInfo);
|
|
|
62 ProcessOptions();
|
|
|
63
|
|
|
64 # Set up information about input files...
|
|
|
65 print "Checking input sequence file(s)...\n";
|
|
|
66 my(%SequenceFilesInfo);
|
|
|
67 RetrieveSequenceFilesInfo();
|
|
|
68
|
|
|
69 # Process input files..
|
|
|
70 my($FileIndex);
|
|
|
71 if (@SequenceFilesList > 1) {
|
|
|
72 print "\nProcessing sequence files...\n";
|
|
|
73 }
|
|
|
74 for $FileIndex (0 .. $#SequenceFilesList) {
|
|
|
75 if ($SequenceFilesInfo{FilesOkay}[$FileIndex]) {
|
|
|
76 print "\nProcessing file $SequenceFilesList[$FileIndex]...\n";
|
|
|
77 ExtractFromSequenceFiles($FileIndex);
|
|
|
78 }
|
|
|
79 }
|
|
|
80 print "\n$ScriptName:Done...\n\n";
|
|
|
81
|
|
|
82 $EndTime = new Benchmark;
|
|
|
83 $TotalTime = timediff ($EndTime, $StartTime);
|
|
|
84 print "Total time: ", timestr($TotalTime), "\n";
|
|
|
85
|
|
|
86 ###############################################################################
|
|
|
87
|
|
|
88 # Extract from sequence files...
|
|
|
89 sub ExtractFromSequenceFiles {
|
|
|
90 my($FileIndex) = @_;
|
|
|
91 my($OutSequenceFile, $SequenceFile, $SequenceDataRef, $SpecifiedSequenceDataRef);
|
|
|
92
|
|
|
93 # Read sequence file...
|
|
|
94 $SequenceFile = $SequenceFilesList[$FileIndex];
|
|
|
95 open SEQUENCEFILE, "$SequenceFile" or die "Error: Can't open $SequenceFile: $! \n";
|
|
|
96 $SequenceDataRef = ReadSequenceFile($SequenceFile);
|
|
|
97 close SEQUENCEFILE;
|
|
|
98
|
|
|
99 $OutSequenceFile = $SequenceFilesInfo{OutFile}[$FileIndex];
|
|
|
100 print "Generating sequence file $OutSequenceFile...\n";
|
|
|
101
|
|
|
102 # Retrieve sequence data for specified sequences...
|
|
|
103 $SpecifiedSequenceDataRef = GetSpecifiedSequenceData($SequenceDataRef);
|
|
|
104
|
|
|
105 # Handle gaps...
|
|
|
106 if ($OptionsInfo{IgnoreGaps}) {
|
|
|
107 if (@{$SpecifiedSequenceDataRef->{IDs}} > 1) {
|
|
|
108 if (AreSequenceLengthsIdentical($SpecifiedSequenceDataRef)) {
|
|
|
109 $SpecifiedSequenceDataRef = RemoveSequenceAlignmentGapColumns($SpecifiedSequenceDataRef);
|
|
|
110 }
|
|
|
111 }
|
|
|
112 else {
|
|
|
113 # Remove the gaps from the sequence...
|
|
|
114 my($ID, $Sequence);
|
|
|
115 $ID = $SpecifiedSequenceDataRef->{IDs}[0];
|
|
|
116 $Sequence = $SpecifiedSequenceDataRef->{Sequence}{$ID};
|
|
|
117 $SpecifiedSequenceDataRef->{Sequence}{$ID} = RemoveSequenceGaps($Sequence);
|
|
|
118 }
|
|
|
119 }
|
|
|
120
|
|
|
121 # Write out the file...
|
|
|
122 WritePearsonFastaSequenceFile($OutSequenceFile, $SpecifiedSequenceDataRef, $OptionsInfo{MaxSequenceLength});
|
|
|
123 }
|
|
|
124
|
|
|
125 # Get specified sequence data...
|
|
|
126 sub GetSpecifiedSequenceData {
|
|
|
127 my($SequenceDataRef) = @_;
|
|
|
128
|
|
|
129 if ($OptionsInfo{Mode} =~ /^SequenceID$/i) {
|
|
|
130 return GetDataBySequenceIDs($SequenceDataRef);
|
|
|
131 }
|
|
|
132 elsif ($Options{mode} =~ /^SequenceNum$/i) {
|
|
|
133 return GetDataBySequenceNums($SequenceDataRef);
|
|
|
134 }
|
|
|
135 elsif ($Options{mode} =~ /^SequenceNumRange$/i) {
|
|
|
136 return GetDataBySequenceNumRange($SequenceDataRef);
|
|
|
137 }
|
|
|
138 else {
|
|
|
139 return undef;
|
|
|
140 }
|
|
|
141 }
|
|
|
142
|
|
|
143 # Get specified sequence data...
|
|
|
144 sub GetDataBySequenceIDs {
|
|
|
145 my($SequenceDataRef) = @_;
|
|
|
146 my($ID, $SequenceCount, $IDMatched, $SpecifiedID, %SpecifiedSequenceDataMap);
|
|
|
147
|
|
|
148 # Go over sequences and collect sequences for writing out a new sequence file...
|
|
|
149 %SpecifiedSequenceDataMap = ();
|
|
|
150 @{$SpecifiedSequenceDataMap{IDs}} = ();
|
|
|
151 %{$SpecifiedSequenceDataMap{Description}} = ();
|
|
|
152 %{$SpecifiedSequenceDataMap{Sequence}} = ();
|
|
|
153
|
|
|
154 $SequenceCount = 0;
|
|
|
155 ID: for $ID (@{$SequenceDataRef->{IDs}}) {
|
|
|
156 if ($OptionsInfo{MatchExactSequenceIDs}) {
|
|
|
157 if (!exists $OptionsInfo{SpecifiedSequenceIDsMap}{lc($ID)}) {
|
|
|
158 next ID;
|
|
|
159 }
|
|
|
160 if ($SequenceCount >= scalar @{$OptionsInfo{SpecifiedSequenceIDs}}) {
|
|
|
161 last ID;
|
|
|
162 }
|
|
|
163 $SequenceCount++;
|
|
|
164 }
|
|
|
165 else {
|
|
|
166 # Does this ID contains specified ID as substring...
|
|
|
167 $IDMatched = 0;
|
|
|
168 SPECIFIEDID: for $SpecifiedID (@{$OptionsInfo{SpecifiedSequenceIDs}}) {
|
|
|
169 if ($ID =~ /$SpecifiedID/i) {
|
|
|
170 $IDMatched = 1;
|
|
|
171 last SPECIFIEDID;
|
|
|
172 }
|
|
|
173 }
|
|
|
174 if (!$IDMatched) {
|
|
|
175 next ID;
|
|
|
176 }
|
|
|
177 $SequenceCount++;
|
|
|
178 }
|
|
|
179 # Collect sequence data...
|
|
|
180 push @{$SpecifiedSequenceDataMap{IDs}}, $ID;
|
|
|
181 $SpecifiedSequenceDataMap{Description}{$ID} = $SequenceDataRef->{Description}{$ID};
|
|
|
182 $SpecifiedSequenceDataMap{Sequence}{$ID} = $SequenceDataRef->{Sequence}{$ID};
|
|
|
183 }
|
|
|
184
|
|
|
185 return \%SpecifiedSequenceDataMap;
|
|
|
186 }
|
|
|
187
|
|
|
188 # Get specified sequence data...
|
|
|
189 sub GetDataBySequenceNums {
|
|
|
190 my($SequenceDataRef) = @_;
|
|
|
191 my($ID, $SequenceNum, $SequenceCount, %SpecifiedSequenceDataMap);
|
|
|
192
|
|
|
193 # Go over sequences and collect sequences for writing out a new sequence file...
|
|
|
194 %SpecifiedSequenceDataMap = ();
|
|
|
195 @{$SpecifiedSequenceDataMap{IDs}} = ();
|
|
|
196 %{$SpecifiedSequenceDataMap{Description}} = ();
|
|
|
197 %{$SpecifiedSequenceDataMap{Sequence}} = ();
|
|
|
198
|
|
|
199 $SequenceNum = 0;
|
|
|
200 $SequenceCount = 0;
|
|
|
201 ID: for $ID (@{$SequenceDataRef->{IDs}}) {
|
|
|
202 $SequenceNum++;
|
|
|
203 if (!exists $OptionsInfo{SpecifiedSequenceIDsMap}{$SequenceNum}) {
|
|
|
204 next ID;
|
|
|
205 }
|
|
|
206 if ($SequenceCount >= scalar @{$OptionsInfo{SpecifiedSequenceIDs}}) {
|
|
|
207 last ID;
|
|
|
208 }
|
|
|
209 $SequenceCount++;
|
|
|
210
|
|
|
211 # Collect sequence data...
|
|
|
212 push @{$SpecifiedSequenceDataMap{IDs}}, $ID;
|
|
|
213 $SpecifiedSequenceDataMap{Description}{$ID} = $SequenceDataRef->{Description}{$ID};
|
|
|
214 $SpecifiedSequenceDataMap{Sequence}{$ID} = $SequenceDataRef->{Sequence}{$ID};
|
|
|
215 }
|
|
|
216
|
|
|
217 return \%SpecifiedSequenceDataMap;
|
|
|
218 }
|
|
|
219
|
|
|
220 # Get specified sequence data...
|
|
|
221 sub GetDataBySequenceNumRange {
|
|
|
222 my($SequenceDataRef) = @_;
|
|
|
223 my($ID, $SequenceNum, $SequenceCount, %SpecifiedSequenceDataMap);
|
|
|
224
|
|
|
225 # Go over sequences and collect sequences for writing out a new sequence file...
|
|
|
226 %SpecifiedSequenceDataMap = ();
|
|
|
227 @{$SpecifiedSequenceDataMap{IDs}} = ();
|
|
|
228 %{$SpecifiedSequenceDataMap{Description}} = ();
|
|
|
229 %{$SpecifiedSequenceDataMap{Sequence}} = ();
|
|
|
230
|
|
|
231 $SequenceNum = 0;
|
|
|
232 $SequenceCount = 0;
|
|
|
233 ID: for $ID (@{$SequenceDataRef->{IDs}}) {
|
|
|
234 $SequenceNum++;
|
|
|
235
|
|
|
236 if (!($SequenceNum >= $OptionsInfo{SpecifiedSequenceIDs}[0] && $SequenceNum <= $OptionsInfo{SpecifiedSequenceIDs}[1])) {
|
|
|
237 next ID;
|
|
|
238 }
|
|
|
239 if ($SequenceNum > $OptionsInfo{SpecifiedSequenceIDs}[1]) {
|
|
|
240 last ID;
|
|
|
241 }
|
|
|
242 $SequenceCount++;
|
|
|
243 # Collect sequence data...
|
|
|
244 push @{$SpecifiedSequenceDataMap{IDs}}, $ID;
|
|
|
245 $SpecifiedSequenceDataMap{Description}{$ID} = $SequenceDataRef->{Description}{$ID};
|
|
|
246 $SpecifiedSequenceDataMap{Sequence}{$ID} = $SequenceDataRef->{Sequence}{$ID};
|
|
|
247 }
|
|
|
248
|
|
|
249 return \%SpecifiedSequenceDataMap;
|
|
|
250 }
|
|
|
251
|
|
|
252
|
|
|
253 # Process option values...
|
|
|
254 sub ProcessOptions {
|
|
|
255 %OptionsInfo = ();
|
|
|
256
|
|
|
257 # Miscellaneous options...
|
|
|
258 $OptionsInfo{IgnoreGaps} = ($Options{ignoregaps} =~ /Yes/i) ? 1 : 0;
|
|
|
259
|
|
|
260 $OptionsInfo{Mode} = $Options{mode};
|
|
|
261 $OptionsInfo{MatchExactSequenceIDs} = $Options{sequenceidmatch} =~ /Exact/i ? 1 :0;
|
|
|
262
|
|
|
263 # Check specified sequences value...
|
|
|
264 $OptionsInfo{SpecifiedSequences} = $Options{sequences};
|
|
|
265 @{$OptionsInfo{SpecifiedSequenceIDs}} = ();
|
|
|
266 %{$OptionsInfo{SpecifiedSequenceIDsMap}} = ();
|
|
|
267
|
|
|
268 my(@SpecifiedSequenceIDs) = ();
|
|
|
269 if ($Options{mode} =~ /^SequenceID$/i) {
|
|
|
270 if (!$Options{sequences}) {
|
|
|
271 die "Error: No value specified for option \"-s, --Sequences\" during \"SequenceID\" of \"-m, --mode\" option\n";
|
|
|
272 }
|
|
|
273 @SpecifiedSequenceIDs = split /\,/, $Options{sequences};
|
|
|
274 }
|
|
|
275 elsif ($Options{mode} =~ /^SequenceNum$/i) {
|
|
|
276 if ($Options{sequences}) {
|
|
|
277 @SpecifiedSequenceIDs = split /\,/, $Options{sequences};
|
|
|
278 my($SequenceNum);
|
|
|
279 for $SequenceNum (@SpecifiedSequenceIDs) {
|
|
|
280 if (!IsPositiveInteger($SequenceNum)) {
|
|
|
281 die "Error: The value specified, $SequenceNum, in \"$Options{sequences}\" for option \"-s, --Sequences\" is not valid: Valid values: > 0\n";
|
|
|
282 }
|
|
|
283 }
|
|
|
284 }
|
|
|
285 else {
|
|
|
286 push @SpecifiedSequenceIDs, "1";
|
|
|
287 }
|
|
|
288 }
|
|
|
289 elsif ($Options{mode} =~ /^SequenceNumRange$/i) {
|
|
|
290 if (!$Options{sequences}) {
|
|
|
291 die "Error: No value specified for option \"-s, --Sequences\" during \"SequenceNumRange\" of \"-m, --mode\" option\n";
|
|
|
292 }
|
|
|
293 @SpecifiedSequenceIDs = split /\,/, $Options{sequences};
|
|
|
294 if (@SpecifiedSequenceIDs != 2) {
|
|
|
295 die "Error: The number of values", scalar @SpecifiedSequenceIDs, " specified, $Options{sequences}, for option \"-s, --Sequences\" are not valid. Number of values must be 2 to indicate starting and ending sequence number.\n";
|
|
|
296 }
|
|
|
297 my($SequenceNum);
|
|
|
298 for $SequenceNum (@SpecifiedSequenceIDs) {
|
|
|
299 if (!IsPositiveInteger($SequenceNum)) {
|
|
|
300 die "Error: The value specified, $SequenceNum, in \"$Options{sequences}\" for option \"-s, --Sequences\" is not valid: Valid values: > 0\n";
|
|
|
301 }
|
|
|
302 }
|
|
|
303 if ($SpecifiedSequenceIDs[0] > $SpecifiedSequenceIDs[1]) {
|
|
|
304 die "Error: The value specified \"$Options{sequences}\" for option \"-s, --Sequences\" are not valid: Starting sequence number $SpecifiedSequenceIDs[0] must be smaller than ending sequence number $SpecifiedSequenceIDs[1]\n";
|
|
|
305 }
|
|
|
306 }
|
|
|
307 push @{$OptionsInfo{SpecifiedSequenceIDs}}, @SpecifiedSequenceIDs;
|
|
|
308 my($SequenceID);
|
|
|
309 for $SequenceID (@SpecifiedSequenceIDs) {
|
|
|
310 if ($Options{mode} =~ /^SequenceID$/i) {
|
|
|
311 $OptionsInfo{SpecifiedSequenceIDsMap}{lc($SequenceID)} = $SequenceID;
|
|
|
312 }
|
|
|
313 else {
|
|
|
314 $OptionsInfo{SpecifiedSequenceIDsMap}{$SequenceID} = $SequenceID;
|
|
|
315 }
|
|
|
316 }
|
|
|
317
|
|
|
318 $OptionsInfo{MaxSequenceLength} = $Options{sequencelength};
|
|
|
319 $OptionsInfo{OverwriteFiles} = $Options{overwrite} ? 1 : 0;
|
|
|
320 $OptionsInfo{OutFileRoot} = $Options{root} ? $Options{root} : 0;
|
|
|
321 }
|
|
|
322
|
|
|
323 # Retrieve information about sequence files...
|
|
|
324 sub RetrieveSequenceFilesInfo {
|
|
|
325 my($Index, $SequenceFile, $FileSupported, $FileFormat, $SequenceCount, $FileDir, $FileName, $FileExt, $OutFileRoot, $OutFileExt, $OutFileMode, $SequenceDataRef);
|
|
|
326
|
|
|
327 %SequenceFilesInfo = ();
|
|
|
328 @{$SequenceFilesInfo{FilesOkay}} = ();
|
|
|
329 @{$SequenceFilesInfo{OutFileRoot}} = ();
|
|
|
330 @{$SequenceFilesInfo{OutFileExt}} = ();
|
|
|
331 @{$SequenceFilesInfo{OutFile}} = ();
|
|
|
332 @{$SequenceFilesInfo{Format}} = ();
|
|
|
333 @{$SequenceFilesInfo{SequenceCount}} = ();
|
|
|
334
|
|
|
335 FILELIST: for $Index (0 .. $#SequenceFilesList) {
|
|
|
336 $SequenceFile = $SequenceFilesList[$Index];
|
|
|
337 $SequenceFilesInfo{FilesOkay}[$Index] = 0;
|
|
|
338 $SequenceFilesInfo{OutFileRoot}[$Index] = '';
|
|
|
339 $SequenceFilesInfo{OutFileExt}[$Index] = '';
|
|
|
340 $SequenceFilesInfo{OutFile}[$Index] = '';
|
|
|
341 $SequenceFilesInfo{Format}[$Index] = 'NotSupported';
|
|
|
342 $SequenceFilesInfo{SequenceCount}[$Index] = 0;
|
|
|
343
|
|
|
344 if (! open SEQUENCEFILE, "$SequenceFile") {
|
|
|
345 warn "Warning: Ignoring file $SequenceFile: Couldn't open it: $! \n";
|
|
|
346 next FILELIST;
|
|
|
347 }
|
|
|
348 close SEQUENCEFILE;
|
|
|
349
|
|
|
350 ($FileSupported, $FileFormat) = IsSupportedSequenceFile($SequenceFile);
|
|
|
351 if (!$FileSupported) {
|
|
|
352 warn "Warning: Ignoring file $SequenceFile: Sequence file format is not supported.\n";
|
|
|
353 next FILELIST;
|
|
|
354 }
|
|
|
355 $SequenceDataRef = ReadSequenceFile($SequenceFile);
|
|
|
356
|
|
|
357 $SequenceCount = $SequenceDataRef->{Count};
|
|
|
358 if (!$SequenceCount) {
|
|
|
359 warn "Warning: Ignoring file $SequenceFile: Sequence data is missing.\n";
|
|
|
360 next FILELIST;
|
|
|
361 }
|
|
|
362
|
|
|
363 # Setup output file names...
|
|
|
364 $FileDir = ""; $FileName = ""; $FileExt = "";
|
|
|
365 ($FileDir, $FileName, $FileExt) = ParseFileName($SequenceFile);
|
|
|
366 $OutFileExt = 'fasta';
|
|
|
367 if ($OptionsInfo{OutFileRoot} && (@SequenceFilesList == 1)) {
|
|
|
368 my ($RootFileDir, $RootFileName, $RootFileExt) = ParseFileName($OptionsInfo{OutFileRoot});
|
|
|
369 if ($RootFileName && $RootFileExt) {
|
|
|
370 $FileName = $RootFileName;
|
|
|
371 }
|
|
|
372 else {
|
|
|
373 $FileName = $OptionsInfo{OutFileRoot};
|
|
|
374 }
|
|
|
375 $OutFileRoot = $FileName;
|
|
|
376 }
|
|
|
377 else {
|
|
|
378 $OutFileRoot = $FileName;
|
|
|
379 }
|
|
|
380 MODE: {
|
|
|
381 if ($OptionsInfo{Mode} =~ /^SequenceID$/i) { $OutFileMode = 'SequenceID'; last MODE;}
|
|
|
382 if ($OptionsInfo{Mode} =~ /^SequenceNum$/i) { $OutFileMode = 'SequenceNum'; last MODE;}
|
|
|
383 if ($OptionsInfo{Mode} =~ /^SequenceNumRange$/i) { $OutFileMode = 'SequenceNumRange'; last MODE;}
|
|
|
384 $OutFileMode = '';
|
|
|
385 }
|
|
|
386 if (!$OptionsInfo{OverwriteFiles}) {
|
|
|
387 if (-e "${OutFileRoot}${OutFileMode}.${OutFileExt}") {
|
|
|
388 warn "Warning: Ignoring file $SequenceFile: The file ${OutFileRoot}${OutFileMode}.${OutFileExt} already exists\n";
|
|
|
389 next FILELIST;
|
|
|
390 }
|
|
|
391 }
|
|
|
392
|
|
|
393 $SequenceFilesInfo{FilesOkay}[$Index] = 1;
|
|
|
394 $SequenceFilesInfo{OutFileRoot}[$Index] = $OutFileRoot;
|
|
|
395 $SequenceFilesInfo{OutFileExt}[$Index] = $OutFileExt;
|
|
|
396 $SequenceFilesInfo{OutFile}[$Index] = "${OutFileRoot}${OutFileMode}.${OutFileExt}";
|
|
|
397
|
|
|
398 $SequenceFilesInfo{Format}[$Index] = $FileFormat;
|
|
|
399 $SequenceFilesInfo{SequenceCount}[$Index] = $SequenceCount;
|
|
|
400 }
|
|
|
401 }
|
|
|
402
|
|
|
403 # Setup script usage and retrieve command line arguments specified using various options...
|
|
|
404 sub SetupScriptUsage {
|
|
|
405
|
|
|
406 # Retrieve all the options...
|
|
|
407 %Options = ();
|
|
|
408 $Options{ignoregaps} = 'Yes';
|
|
|
409 $Options{mode} = 'SequenceNum';
|
|
|
410 $Options{sequenceidmatch} = 'Relaxed';
|
|
|
411 $Options{sequencelength} = 80;
|
|
|
412
|
|
|
413 if (!GetOptions(\%Options, "help|h", "ignoregaps|i=s", "mode|m=s", "overwrite|o", "root|r=s", "sequences|s=s", "sequenceidmatch=s", "sequencelength=i", "workingdir|w=s")) {
|
|
|
414 die "\nTo get a list of valid options and their values, use \"$ScriptName -h\" or\n\"perl -S $ScriptName -h\" command and try again...\n";
|
|
|
415 }
|
|
|
416 if ($Options{workingdir}) {
|
|
|
417 if (! -d $Options{workingdir}) {
|
|
|
418 die "Error: The value specified, $Options{workingdir}, for option \"-w --workingdir\" is not a directory name.\n";
|
|
|
419 }
|
|
|
420 chdir $Options{workingdir} or die "Error: Couldn't chdir $Options{workingdir}: $! \n";
|
|
|
421 }
|
|
|
422 if ($Options{ignoregaps} !~ /^(yes|no)$/i) {
|
|
|
423 die "Error: The value specified, $Options{ignoregaps}, for option \"-q --quote\" is not valid. Allowed values: yes or no\n";
|
|
|
424 }
|
|
|
425 if ($Options{mode} !~ /^(SequenceID|SequenceNum|SequenceNumRange)$/i) {
|
|
|
426 die "Error: The value specified, $Options{mode}, for option \"-m --mode\" is not valid. Allowed values: SequenceID, SequenceNum, or SequenceNumRange\n";
|
|
|
427 }
|
|
|
428 if ($Options{sequenceidmatch} !~ /^(Exact|Relaxed)$/i) {
|
|
|
429 die "Error: The value specified, $Options{sequenceidmatch}, for option \"--SequenceIDMatch\" is not valid. Allowed values: Exact or Relaxed\n";
|
|
|
430 }
|
|
|
431 if (!IsPositiveInteger($Options{sequencelength})) {
|
|
|
432 die "Error: The value specified, $Options{sequencelength}, for option \"--SequenceLength\" is not valid. Allowed values: >0\n";
|
|
|
433 }
|
|
|
434 }
|
|
|
435
|
|
|
436 __END__
|
|
|
437
|
|
|
438 =head1 NAME
|
|
|
439
|
|
|
440 ExtractFromSequenceFiles.pl - Extract data from sequence and alignment files
|
|
|
441
|
|
|
442 =head1 SYNOPSIS
|
|
|
443
|
|
|
444 ExtractFromSequenceFiles.pl SequenceFile(s) AlignmentFile(s)...
|
|
|
445
|
|
|
446 ExtractFromSequenceFiles.pl [B<-h, --help>] [B<-i, --IgnoreGaps> yes | no]
|
|
|
447 [B<-m, --mode> SequenceID | SequenceNum | SequenceNumRange] [B<-o, --overwrite>]
|
|
|
448 [B<-r, --root> rootname] [B<-s, --Sequences> "SequenceID, [SequenceID,...]" | "SequenceNum, [SequenceNum,...]" |
|
|
|
449 "StartingSeqNum, EndingSeqNum"] [B<--SequenceIDMatch> Exact | Relaxed]
|
|
|
450 [B<-w, --WorkingDir> dirname] SequenceFile(s) AlignmentFile(s)...
|
|
|
451
|
|
|
452 =head1 DESCRIPTION
|
|
|
453
|
|
|
454 Extract specific data from I<SequenceFile(s) and AlignmentFile(s)> and generate
|
|
|
455 FASTA files. You can extract sequences using sequence IDs or sequence numbers.
|
|
|
456
|
|
|
457 The file names are separated by spaces. All the sequence files in a current directory can
|
|
|
458 be specified by I<*.aln>, I<*.msf>, I<*.fasta>, I<*.fta>, I<*.pir> or any other supported
|
|
|
459 formats; additionally, I<DirName> corresponds to all the sequence files in the current directory
|
|
|
460 with any of the supported file extension: I<.aln, .msf, .fasta, .fta, and .pir>.
|
|
|
461
|
|
|
462 Supported sequence formats are: I<ALN/CLustalW>, I<GCG/MSF>, I<PILEUP/MSF>, I<Pearson/FASTA>,
|
|
|
463 and I<NBRF/PIR>. Instead of using file extensions, file formats are detected by parsing the contents
|
|
|
464 of I<SequenceFile(s) and AlignmentFile(s)>.
|
|
|
465
|
|
|
466 =head1 OPTIONS
|
|
|
467
|
|
|
468 =over 4
|
|
|
469
|
|
|
470 =item B<-h, --help>
|
|
|
471
|
|
|
472 Print this help message.
|
|
|
473
|
|
|
474 =item B<-i, --IgnoreGaps> I<yes | no>
|
|
|
475
|
|
|
476 Ignore gaps or gap columns during during generation of new sequence or alignment file(s).
|
|
|
477 Possible values: I<yes or no>. Default value: I<yes>.
|
|
|
478
|
|
|
479 In order to remove gap columns, length of all the sequence must be same; otherwise,
|
|
|
480 this option is ignored.
|
|
|
481
|
|
|
482 =item B<-m, --mode> I<SequenceID | SequenceNum | SequenceNumRange>
|
|
|
483
|
|
|
484 Specify how to extract data from sequence files: extract sequences using sequence
|
|
|
485 IDs or sequence numbers. Possible values: I<SequenceID | SequenceNum
|
|
|
486 | SequenceNumRange>. Default: I<SequenceNum> with value of 1.
|
|
|
487
|
|
|
488 The sequence numbers correspond to position of sequences starting from 1 for first sequence
|
|
|
489 in I<SequenceFile(s) and AlignmentFile(s)>.
|
|
|
490
|
|
|
491 =item B<-o, --overwrite>
|
|
|
492
|
|
|
493 Overwrite existing files.
|
|
|
494
|
|
|
495 =item B<-r, --root> I<rootname>
|
|
|
496
|
|
|
497 New sequence file name is generated using the root: <Root><Mode>.<Ext>. Default new file:
|
|
|
498 <SequenceFileName><Mode>.<Ext>. This option is ignored for multiple input files.
|
|
|
499
|
|
|
500 =item B<-s, --Sequences> I<"SequenceID,[SequenceID,...]" | "SequenceNum,[SequenceNum,...]" | "StartingSeqNum,EndingSeqNum">
|
|
|
501
|
|
|
502 This value is B<-m, --mode> specific. In general, it's a comma delimites list of sequence IDs or sequence
|
|
|
503 numbers.
|
|
|
504
|
|
|
505 For I<SequenceID> value of B<-m, --mode> option, input value format is: I<SequenceID,...>. Examples:
|
|
|
506
|
|
|
507 ACHE_BOVIN
|
|
|
508 ACHE_BOVIN,ACHE_HUMAN
|
|
|
509
|
|
|
510 For I<SequenceNum> value of B<-m, --mode> option, input value format is: I<SequenceNum,...>. Examples:
|
|
|
511
|
|
|
512 2
|
|
|
513 1,5
|
|
|
514
|
|
|
515 For I<SequenceNum> value of B<-m, --mode> option, input value format is: I<StaringSeqNum,EndingSeqNum>. Examples:
|
|
|
516
|
|
|
517 2,4
|
|
|
518
|
|
|
519 =item B<--SequenceIDMatch> I<Exact | Relaxed>
|
|
|
520
|
|
|
521 Sequence IDs matching criterion during I<SequenceID> value of B<-m, --mode> option: match
|
|
|
522 specified sequence ID exactly or as sub string against sequence IDs in the files. Possible
|
|
|
523 values: I<Exact | Relaxed>. Default: I<Relaxed>. Sequence ID match is case insenstitive
|
|
|
524 during both options.
|
|
|
525
|
|
|
526 =item B<--SequenceLength> I<number>
|
|
|
527
|
|
|
528 Maximum sequence length per line in sequence file(s). Default: I<80>.
|
|
|
529
|
|
|
530 =item B<-w --WorkingDir> I<text>
|
|
|
531
|
|
|
532 Location of working directory. Default: current directory.
|
|
|
533
|
|
|
534 =back
|
|
|
535
|
|
|
536 =head1 EXAMPLES
|
|
|
537
|
|
|
538 To extract first sequence from Sample1.fasta sequence file and generate Sample1SequenceNum.fasta
|
|
|
539 sequence file, type:
|
|
|
540
|
|
|
541 % ExtractFromSequenceFiles.pl -o Sample1.fasta
|
|
|
542
|
|
|
543 To extract first sequence from Sample1.aln alignment file and generate Sample1SequenceNum.fasta
|
|
|
544 sequence file without any column gaps, type:
|
|
|
545
|
|
|
546 % ExtractFromSequenceFiles.pl -o Sample1.aln
|
|
|
547
|
|
|
548 To extract first sequence from Sample1.aln alignment file and generate Sample1SequenceNum.fasta
|
|
|
549 sequence file with column gaps, type:
|
|
|
550
|
|
|
551 % ExtractFromSequenceFiles.pl --IgnroreGaps No -o Sample1.aln
|
|
|
552
|
|
|
553 To extract sequence number 1 and 4 from Sample1.fasta sequence file and generate
|
|
|
554 Sample1SequenceNum.fasta sequence file, type:
|
|
|
555
|
|
|
556 % ExtractFromSequenceFiles.pl -o -m SequenceNum --Sequences 1,4
|
|
|
557 -o Sample1.fasta
|
|
|
558
|
|
|
559 To extract sequences from sequence number 1 to 4 from Sample1.fasta sequence file and generate
|
|
|
560 Sample1SequenceNumRange.fasta sequence file, type:
|
|
|
561
|
|
|
562 % ExtractFromSequenceFiles.pl -o -m SequenceNumRange --Sequences
|
|
|
563 1,4 -o Sample1.fasta
|
|
|
564
|
|
|
565 To extract sequence ID "Q9P993/104-387" from sequence from Sample1.fasta sequence file and generate
|
|
|
566 Sample1SequenceID.fasta sequence file, type:
|
|
|
567
|
|
|
568 % ExtractFromSequenceFiles.pl -o -m SequenceID --Sequences
|
|
|
569 "Q9P993/104-387" --SequenceIDMatch Exact -o Sample1.fasta
|
|
|
570
|
|
|
571 =head1 AUTHOR
|
|
|
572
|
|
|
573 Manish Sud <msud@san.rr.com>
|
|
|
574
|
|
|
575 =head1 SEE ALSO
|
|
|
576
|
|
|
577 AnalyzeSequenceFilesData.pl, InfoSequenceFiles.pl
|
|
|
578
|
|
|
579 =head1 COPYRIGHT
|
|
|
580
|
|
|
581 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
582
|
|
|
583 This file is part of MayaChemTools.
|
|
|
584
|
|
|
585 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
586 the terms of the GNU Lesser General Public License as published by the Free
|
|
|
587 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
588 any later version.
|
|
|
589
|
|
|
590 =cut
|
