|
1
|
1 #!/usr/bin/perl -w
|
|
|
2 #
|
|
|
3 # $RCSfile: SplitSDFiles.pl,v $
|
|
|
4 # $Date: 2015/02/28 20:46:21 $
|
|
|
5 # $Revision: 1.36 $
|
|
|
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 "$FindBin::Bin/../lib";
|
|
|
31 use Getopt::Long;
|
|
|
32 use File::Basename;
|
|
|
33 use Benchmark;
|
|
|
34 use SDFileUtil;
|
|
|
35 use FileUtil;
|
|
|
36
|
|
|
37 my($ScriptName, %Options, $StartTime, $EndTime, $TotalTime);
|
|
|
38
|
|
|
39 # Autoflush STDOUT
|
|
|
40 $| = 1;
|
|
|
41
|
|
|
42 # Starting message...
|
|
|
43 $ScriptName = basename $0;
|
|
|
44 print "\n$ScriptName:Starting...\n\n";
|
|
|
45 $StartTime = new Benchmark;
|
|
|
46
|
|
|
47 # Get the options and setup script...
|
|
|
48 SetupScriptUsage();
|
|
|
49 if ($Options{help} || @ARGV < 1) {
|
|
|
50 die GetUsageFromPod("$FindBin::Bin/$ScriptName");
|
|
|
51 }
|
|
|
52
|
|
|
53 my(@SDFilesList);
|
|
|
54 @SDFilesList = ExpandFileNames(\@ARGV, "sdf sd");
|
|
|
55
|
|
|
56 # Process options...
|
|
|
57 print "Processing options...\n";
|
|
|
58 my(%OptionsInfo);
|
|
|
59 ProcessOptions();
|
|
|
60
|
|
|
61 # Setup information about input files...
|
|
|
62 my(%SDFilesInfo);
|
|
|
63 print "Checking input SD file(s)...\n";
|
|
|
64 RetrieveSDFilesInfo();
|
|
|
65
|
|
|
66 # Process input files..
|
|
|
67 my($FileIndex);
|
|
|
68 if (@SDFilesList > 1) {
|
|
|
69 print "\nProcessing SD files...\n";
|
|
|
70 }
|
|
|
71 for $FileIndex (0 .. $#SDFilesList) {
|
|
|
72 if ($SDFilesInfo{FileOkay}[$FileIndex]) {
|
|
|
73 print "\nProcessing file $SDFilesList[$FileIndex]...\n";
|
|
|
74 SplitSDFile($FileIndex);
|
|
|
75 }
|
|
|
76 }
|
|
|
77 print "\n$ScriptName:Done...\n\n";
|
|
|
78
|
|
|
79 $EndTime = new Benchmark;
|
|
|
80 $TotalTime = timediff ($EndTime, $StartTime);
|
|
|
81 print "Total time: ", timestr($TotalTime), "\n";
|
|
|
82
|
|
|
83 ###############################################################################
|
|
|
84
|
|
|
85 # Split a SD file...
|
|
|
86 #
|
|
|
87 sub SplitSDFile {
|
|
|
88 my($FileIndex) = @_;
|
|
|
89
|
|
|
90 if ($OptionsInfo{Mode} =~ /^Files$/i) {
|
|
|
91 SplitSDFileByNumOfFiles($FileIndex);
|
|
|
92 }
|
|
|
93 elsif ($OptionsInfo{Mode} =~ /^Cmpds$/i) {
|
|
|
94 SplitSDFileByNumOfCmpds($FileIndex);
|
|
|
95 }
|
|
|
96 }
|
|
|
97
|
|
|
98 # Split SD into specified number of files...
|
|
|
99 #
|
|
|
100 sub SplitSDFileByNumOfFiles {
|
|
|
101 my($FileIndex) = @_;
|
|
|
102 my($SDFile, $CmpdCount, $MaxCmpdsPerFile, $MaxNumOfFiles);
|
|
|
103
|
|
|
104 $SDFile = $SDFilesList[$FileIndex];
|
|
|
105
|
|
|
106 if (!open SDFILE, "$SDFile") {
|
|
|
107 warn "Warning: Ignoring file $SDFile: Couldn't open it: $! \n";
|
|
|
108 return;
|
|
|
109 }
|
|
|
110
|
|
|
111 $MaxNumOfFiles = $OptionsInfo{NumOfFiles};
|
|
|
112
|
|
|
113 # Count number of compounds to figure out maximum number of compound per file...
|
|
|
114 $CmpdCount = 0;
|
|
|
115 while (<SDFILE>) {
|
|
|
116 if (/^\$\$\$\$/) {
|
|
|
117 $CmpdCount++;
|
|
|
118 }
|
|
|
119 }
|
|
|
120 close SDFILE;
|
|
|
121
|
|
|
122 if ($CmpdCount < $MaxNumOfFiles) {
|
|
|
123 warn "Warning: Ignoring file $SDFile: Total number of compounds, $CmpdCount, is smaller than number of new files, $MaxNumOfFiles\n";
|
|
|
124 return;
|
|
|
125 }
|
|
|
126
|
|
|
127 $MaxCmpdsPerFile = int $CmpdCount / $MaxNumOfFiles;
|
|
|
128
|
|
|
129 SplitSDFileByNumOfFilesAndCmpds($FileIndex, $MaxNumOfFiles, $MaxCmpdsPerFile);
|
|
|
130 }
|
|
|
131
|
|
|
132 # Split SD into files containing specified number of compounds...
|
|
|
133 #
|
|
|
134 sub SplitSDFileByNumOfCmpds {
|
|
|
135 my($FileIndex) = @_;
|
|
|
136
|
|
|
137 if ($OptionsInfo{NumOfCmpds} == 1) {
|
|
|
138 SplitSDFileByOneCmpdPerFile($FileIndex);
|
|
|
139 }
|
|
|
140 else {
|
|
|
141 SplitSDFileByNumOfCmpdsPerFile($FileIndex);
|
|
|
142 }
|
|
|
143 }
|
|
|
144
|
|
|
145 # Split SD into files containing one compound per file...
|
|
|
146 #
|
|
|
147 sub SplitSDFileByOneCmpdPerFile {
|
|
|
148 my($FileIndex) = @_;
|
|
|
149 my($SDFile, $NewSDFile, $NewSDFileRoot, $FileExt, $OutFileRoot, $OverwriteFiles, $UseDataField, $DataFieldName, $UseMolName, $CmpdCount, $CmpdString, @CmpdLines, %DataFieldValues);
|
|
|
150
|
|
|
151 $SDFile = $SDFilesList[$FileIndex];
|
|
|
152
|
|
|
153 if (!open SDFILE, "$SDFile") {
|
|
|
154 warn "Warning: Ignoring file $SDFile: Couldn't open it: $! \n";
|
|
|
155 return;
|
|
|
156 }
|
|
|
157
|
|
|
158 print "\n";
|
|
|
159
|
|
|
160 $CmpdCount = 0;
|
|
|
161
|
|
|
162 $FileExt = $SDFilesInfo{FileExt}[$FileIndex];
|
|
|
163
|
|
|
164 $OutFileRoot = $SDFilesInfo{OutFileRoot}[$FileIndex];
|
|
|
165 $OverwriteFiles = $OptionsInfo{OverwriteFiles};
|
|
|
166
|
|
|
167 $UseDataField = ($OptionsInfo{CmpdsMode} =~ /^DataField$/i) ? 1 : 0;
|
|
|
168 $DataFieldName = $OptionsInfo{DataField};
|
|
|
169
|
|
|
170 $UseMolName = ($OptionsInfo{CmpdsMode} =~ /^MolName$/i) ? 1 : 0;
|
|
|
171
|
|
|
172 CMPDSTRING: while ($CmpdString = ReadCmpdString(\*SDFILE)) {
|
|
|
173 $CmpdCount++;
|
|
|
174
|
|
|
175 # Setup SD file name...
|
|
|
176 $NewSDFileRoot = '';
|
|
|
177 if ($UseDataField) {
|
|
|
178 @CmpdLines = split "\n", $CmpdString;
|
|
|
179 %DataFieldValues = GetCmpdDataHeaderLabelsAndValues(\@CmpdLines);
|
|
|
180 if (exists $DataFieldValues{$DataFieldName}) {
|
|
|
181 $NewSDFileRoot = $DataFieldValues{$DataFieldName};
|
|
|
182 }
|
|
|
183 }
|
|
|
184 elsif ($UseMolName) {
|
|
|
185 @CmpdLines = split "\n", $CmpdString;
|
|
|
186 $NewSDFileRoot = $CmpdLines[0];
|
|
|
187 }
|
|
|
188
|
|
|
189 # Check for any invalid file name characters in data field or molname values...
|
|
|
190 if ($NewSDFileRoot && $NewSDFileRoot =~ /[^a-zA-Z0-9_]/) {
|
|
|
191 $NewSDFileRoot =~ s/[^a-zA-Z0-9_]//g;
|
|
|
192 }
|
|
|
193
|
|
|
194 # Fall back plan for SD file name...
|
|
|
195 if (!$NewSDFileRoot) {
|
|
|
196 $NewSDFileRoot = "${OutFileRoot}Cmpd${CmpdCount}";
|
|
|
197 }
|
|
|
198
|
|
|
199 $NewSDFile = "${NewSDFileRoot}.${FileExt}";
|
|
|
200
|
|
|
201 if (!$OverwriteFiles) {
|
|
|
202 if (-e $NewSDFile) {
|
|
|
203 warn "Warning: Ignoring compound number, $CmpdCount, in $SDFile: New SD file, $NewSDFile, already exists\n";
|
|
|
204 next CMPDSTRING;
|
|
|
205 }
|
|
|
206 }
|
|
|
207
|
|
|
208 # Write out new SD file...
|
|
|
209
|
|
|
210 print "Generating $NewSDFile file\n";
|
|
|
211 open NEWSDFILE, ">$NewSDFile" or die "Error: Can't open $NewSDFile: $! \n";
|
|
|
212 print NEWSDFILE "$CmpdString\n";
|
|
|
213 close NEWSDFILE;
|
|
|
214
|
|
|
215 }
|
|
|
216 close SDFILE;
|
|
|
217 }
|
|
|
218
|
|
|
219 # Split SD into files containing specified number of compounds per file...
|
|
|
220 #
|
|
|
221 sub SplitSDFileByNumOfCmpdsPerFile {
|
|
|
222 my($FileIndex) = @_;
|
|
|
223 my($SDFile, $CmpdCount, $MaxCmpdsPerFile, $MaxNumOfFiles);
|
|
|
224
|
|
|
225 $SDFile = $SDFilesList[$FileIndex];
|
|
|
226
|
|
|
227 if (!open SDFILE, "$SDFile") {
|
|
|
228 warn "Warning: Ignoring file $SDFile: Couldn't open it: $! \n";
|
|
|
229 return;
|
|
|
230 }
|
|
|
231
|
|
|
232 $MaxCmpdsPerFile = $OptionsInfo{NumOfCmpds};
|
|
|
233
|
|
|
234 # Count number of compounds to figure out maximum number of files...
|
|
|
235 $CmpdCount = 0;
|
|
|
236 while (<SDFILE>) {
|
|
|
237 if (/^\$\$\$\$/) {
|
|
|
238 $CmpdCount++;
|
|
|
239 }
|
|
|
240 }
|
|
|
241 close SDFILE;
|
|
|
242
|
|
|
243 $MaxNumOfFiles = int $CmpdCount / $MaxCmpdsPerFile;
|
|
|
244
|
|
|
245 if (($MaxNumOfFiles * $MaxCmpdsPerFile) < $CmpdCount) {
|
|
|
246 $MaxNumOfFiles++;
|
|
|
247 }
|
|
|
248
|
|
|
249 if ($CmpdCount <= $MaxCmpdsPerFile) {
|
|
|
250 warn "Warning: Ignoring file $SDFile: Total number of compounds, $CmpdCount, is <= specified number of compunds per file, $MaxCmpdsPerFile\n";
|
|
|
251 return;
|
|
|
252 }
|
|
|
253
|
|
|
254 SplitSDFileByNumOfFilesAndCmpds($FileIndex, $MaxNumOfFiles, $MaxCmpdsPerFile);
|
|
|
255 }
|
|
|
256
|
|
|
257 # Split SD files into specified number of files with specified number of compounds
|
|
|
258 # in each file...
|
|
|
259 #
|
|
|
260 sub SplitSDFileByNumOfFilesAndCmpds {
|
|
|
261 my($FileIndex, $NumOfFiles, $NumOfCmpdsPerFile) = @_;
|
|
|
262 my($SDFile, $CmpdCount, $NewFileIndex, $NewFileName, $MaxCmpdsCount, @NewSDFilesList);
|
|
|
263
|
|
|
264 $SDFile = $SDFilesList[$FileIndex];
|
|
|
265
|
|
|
266 if (!open SDFILE, "$SDFile") {
|
|
|
267 warn "Warning: Ignoring file $SDFile: Couldn't open it: $! \n";
|
|
|
268 return;
|
|
|
269 }
|
|
|
270
|
|
|
271 # Setup new file names list...
|
|
|
272 @NewSDFilesList = ();
|
|
|
273 for $NewFileIndex (1 .. $NumOfFiles) {
|
|
|
274 $NewFileName = $SDFilesInfo{OutFileRoot}[$FileIndex] . "Part${NewFileIndex}." . $SDFilesInfo{FileExt}[$FileIndex];
|
|
|
275 if (!$OptionsInfo{OverwriteFiles}) {
|
|
|
276 if (-e $NewFileName) {
|
|
|
277 warn "Warning: Ignoring file $SDFile: New SD file, $NewFileName, already exists\n";
|
|
|
278 return;
|
|
|
279 }
|
|
|
280 }
|
|
|
281 push @NewSDFilesList, $NewFileName;
|
|
|
282 }
|
|
|
283
|
|
|
284 $MaxCmpdsCount = $NumOfCmpdsPerFile;
|
|
|
285
|
|
|
286 $CmpdCount = 0;
|
|
|
287 $NewFileIndex = 1;
|
|
|
288
|
|
|
289 open NEWSDFILE, ">$NewSDFilesList[$NewFileIndex - 1]" or die "Error: Can't open $NewSDFilesList[$NewFileIndex -1]: $! \n";
|
|
|
290 print "\nGenerating $NewSDFilesList[$NewFileIndex - 1] file\n";
|
|
|
291
|
|
|
292 open SDFILE, "$SDFile" or die "Error: Can't open $SDFile: $! \n";
|
|
|
293
|
|
|
294 while (<SDFILE>) {
|
|
|
295 s/(\r\n)|(\r)/\n/g;
|
|
|
296 print NEWSDFILE;
|
|
|
297
|
|
|
298 if ( /^\$\$\$\$/ ) {
|
|
|
299 $CmpdCount++;
|
|
|
300 if ($NewFileIndex <= $NumOfFiles) {
|
|
|
301 if ($CmpdCount >= $MaxCmpdsCount) {
|
|
|
302 if ($NewFileIndex < $NumOfFiles) {
|
|
|
303 close NEWSDFILE;
|
|
|
304 }
|
|
|
305 $NewFileIndex++;
|
|
|
306 $MaxCmpdsCount = $NumOfCmpdsPerFile * $NewFileIndex;
|
|
|
307
|
|
|
308 if ($NewFileIndex <= $NumOfFiles) {
|
|
|
309 open NEWSDFILE, ">$NewSDFilesList[$NewFileIndex - 1]" or die "Error: Can't open $NewSDFilesList[$NewFileIndex - 1]: $! \n";
|
|
|
310 print "Generating $NewSDFilesList[$NewFileIndex - 1] file...\n";
|
|
|
311 }
|
|
|
312 }
|
|
|
313 }
|
|
|
314 }
|
|
|
315 }
|
|
|
316 close NEWSDFILE;
|
|
|
317 }
|
|
|
318
|
|
|
319 # Retrieve information about SD files...
|
|
|
320 #
|
|
|
321 sub RetrieveSDFilesInfo {
|
|
|
322 my($SDFile, $Index, $FileDir, $FileName, $FileExt, $OutFileRoot);
|
|
|
323
|
|
|
324 %SDFilesInfo = ();
|
|
|
325 @{$SDFilesInfo{FileOkay}} = ();
|
|
|
326 @{$SDFilesInfo{FileExt}} = ();
|
|
|
327 @{$SDFilesInfo{OutFileRoot}} = ();
|
|
|
328
|
|
|
329 FILELIST: for $Index (0 .. $#SDFilesList) {
|
|
|
330 $SDFile = $SDFilesList[$Index];
|
|
|
331
|
|
|
332 $SDFilesInfo{FileOkay}[$Index] = 0;
|
|
|
333 $SDFilesInfo{FileExt}[$Index] = '';
|
|
|
334 $SDFilesInfo{OutFileRoot}[$Index] = '';
|
|
|
335
|
|
|
336 $SDFile = $SDFilesList[$Index];
|
|
|
337 if (!(-e $SDFile)) {
|
|
|
338 warn "Warning: Ignoring file $SDFile: It doesn't exist\n";
|
|
|
339 next FILELIST;
|
|
|
340 }
|
|
|
341 if (!CheckFileType($SDFile, "sd sdf")) {
|
|
|
342 warn "Warning: Ignoring file $SDFile: It's not a SD file\n";
|
|
|
343 next FILELIST;
|
|
|
344 }
|
|
|
345
|
|
|
346 # Setup output file root...
|
|
|
347 $FileDir = ""; $FileName = ""; $FileExt = "";
|
|
|
348 ($FileDir, $FileName, $FileExt) = ParseFileName($SDFile);
|
|
|
349
|
|
|
350 if ($OptionsInfo{OutFileRoot} && (@SDFilesList == 1)) {
|
|
|
351 my ($RootFileDir, $RootFileName, $RootFileExt) = ParseFileName($OptionsInfo{OutFileRoot});
|
|
|
352 if ($RootFileName && $RootFileExt) {
|
|
|
353 $FileName = $RootFileName;
|
|
|
354 }
|
|
|
355 else {
|
|
|
356 $FileName = $OptionsInfo{OutFileRoot};
|
|
|
357 }
|
|
|
358 $OutFileRoot = $FileName;
|
|
|
359 }
|
|
|
360 else {
|
|
|
361 $OutFileRoot = "$FileName";
|
|
|
362 }
|
|
|
363
|
|
|
364 $SDFilesInfo{FileOkay}[$Index] = 1;
|
|
|
365 $SDFilesInfo{FileExt}[$Index] = $FileExt;
|
|
|
366 $SDFilesInfo{OutFileRoot}[$Index] = $OutFileRoot;
|
|
|
367 }
|
|
|
368 }
|
|
|
369
|
|
|
370 # Process option values...
|
|
|
371 sub ProcessOptions {
|
|
|
372 %OptionsInfo = ();
|
|
|
373
|
|
|
374 $OptionsInfo{Mode} = $Options{mode};
|
|
|
375
|
|
|
376 $OptionsInfo{CmpdsMode} = $Options{cmpdsmode};
|
|
|
377
|
|
|
378 $OptionsInfo{NumOfFiles} = $Options{numfiles};
|
|
|
379 $OptionsInfo{NumOfCmpds} = $Options{numcmpds};
|
|
|
380
|
|
|
381 $OptionsInfo{DataField} = '';
|
|
|
382 if ($Options{mode} =~ /^Cmpds$/i && $Options{cmpdsmode} =~ /^DataField$/i) {
|
|
|
383 if (!$Options{datafield}) {
|
|
|
384 die "Error: You must specify a value for \"-d, --DataField\" option in \"DataField\" value of \"-c, --CmpdsMode\" during \"Cmpds\" \"-m, --mode\" value. \n";
|
|
|
385 }
|
|
|
386 $OptionsInfo{DataField} = $Options{datafield};
|
|
|
387 }
|
|
|
388
|
|
|
389 $OptionsInfo{OverwriteFiles} = $Options{overwrite} ? 1 : 0;
|
|
|
390
|
|
|
391 $OptionsInfo{OutFileRoot} = $Options{root} ? $Options{root} : 0;
|
|
|
392 }
|
|
|
393
|
|
|
394
|
|
|
395 # Setup script usage and retrieve command line arguments specified using various options...
|
|
|
396 sub SetupScriptUsage {
|
|
|
397
|
|
|
398 # Retrieve all the options...
|
|
|
399 %Options = ();
|
|
|
400
|
|
|
401 $Options{cmpdsmode} = 'RootPrefix';
|
|
|
402 $Options{mode} = 'Files';
|
|
|
403
|
|
|
404 $Options{numfiles} = 2;
|
|
|
405 $Options{numcmpds} = 1;
|
|
|
406
|
|
|
407
|
|
|
408 if (!GetOptions(\%Options, "cmpdsmode|c=s", "datafield|d=s", "help|h", "mode|m=s", "numfiles|n=i", "numcmpds=i", "overwrite|o", "root|r=s", "workingdir|w=s")) {
|
|
|
409 die "\nTo get a list of valid options and their values, use \"$ScriptName -h\" or\n\"perl -S $ScriptName -h\" command and try again...\n";
|
|
|
410 }
|
|
|
411 if ($Options{workingdir}) {
|
|
|
412 if (! -d $Options{workingdir}) {
|
|
|
413 die "Error: The value specified, $Options{workingdir}, for option \"-w --workingdir\" is not a directory name.\n";
|
|
|
414 }
|
|
|
415 chdir $Options{workingdir} or die "Error: Error: Couldn't chdir $Options{workingdir}: $! \n";
|
|
|
416 }
|
|
|
417 if ($Options{cmpdsmode} !~ /^(DataField|MolName|RootPrefix)$/i) {
|
|
|
418 die "Error: The value specified, $Options{cmpdsmode}, for option \"-c, --CmpdsMode\" is not valid. Allowed values: DataField, MolName, RootPrefix\n";
|
|
|
419 }
|
|
|
420 if ($Options{mode} !~ /^(Cmpds|Files)$/i) {
|
|
|
421 die "Error: The value specified, $Options{mode}, for option \"-m, --mode\" is not valid. Allowed values: Cmpds, Files\n";
|
|
|
422 }
|
|
|
423 if ($Options{numfiles} < 2) {
|
|
|
424 die "Error: The value specified, $Options{numfiles}, for option \"-n --numfiles\" is not valid. Allowed values: >= 2 \n";
|
|
|
425 }
|
|
|
426 if ($Options{numcmpds} < 1) {
|
|
|
427 die "Error: The value specified, $Options{numcmpds}, for option \"-n --numcmpds\" is not valid. Allowed values: >= 1 \n";
|
|
|
428 }
|
|
|
429 }
|
|
|
430
|
|
|
431 __END__
|
|
|
432
|
|
|
433 =head1 NAME
|
|
|
434
|
|
|
435 SplitSDFiles.pl - Split SDFile(s) into multiple SD files
|
|
|
436
|
|
|
437 =head1 SYNOPSIS
|
|
|
438
|
|
|
439 SplitSDFiles.pl SDFile(s)...
|
|
|
440
|
|
|
441 SplitSDFiles.pl [B<-c, --CmpdsMode> DataField | MolName | RootPrefix]
|
|
|
442 [B<-d, --DataField> DataFieldName] [B<-h, --help>] [B<-m, --mode> Cmpds | Files]
|
|
|
443 [B<-n, --numfiles> number] [B<--numcmpds> number] [B<-o, --overwrite>]
|
|
|
444 [B<-r, --root> rootname] [B<-w,--workingdir> dirname] SDFile(s)...
|
|
|
445
|
|
|
446 =head1 DESCRIPTION
|
|
|
447
|
|
|
448 Split I<SDFile(s)> into multiple SD files. Each new SDFile contains a compound
|
|
|
449 subset of similar size from the initial file. Multiple I<SDFile(s)> names are separated
|
|
|
450 by space. The valid file extensions are I<.sdf> and I<.sd>. All other file names are
|
|
|
451 ignored. All the SD files in a current directory can be specified either by I<*.sdf>
|
|
|
452 or the current directory name.
|
|
|
453
|
|
|
454 =head1 OPTIONS
|
|
|
455
|
|
|
456 =over 4
|
|
|
457
|
|
|
458 =item B<-c, --CmpdsMode> I<DataField | MolName | RootPrefix>
|
|
|
459
|
|
|
460 This option is only used during I<Cmpds> value of <-m, --mode> option with
|
|
|
461 specified B<--numcmpds> value of 1.
|
|
|
462
|
|
|
463 Specify how to generate new file names during I<Cmpds> value of <-m, --mode>
|
|
|
464 option: use I<SDFile(s)> datafield value or molname line for a specific compound;
|
|
|
465 generate a sequential ID using root prefix specified by B<-r, --root> option.
|
|
|
466
|
|
|
467 Possible values: I<DataField | MolName | RootPrefix | RootPrefix>.
|
|
|
468 Default: I<RootPrefix>.
|
|
|
469
|
|
|
470 For empty I<MolName> and I<DataField> values during these specified modes, file
|
|
|
471 name is automatically generated using I<RootPrefix>.
|
|
|
472
|
|
|
473 For I<RootPrefix> value of B<-c, --CmpdsMode> option, new file names are
|
|
|
474 generated using by appending compound record number to value of B<-r, --root> option.
|
|
|
475 For example: I<RootName>Cmd<RecordNumber>.sdf.
|
|
|
476
|
|
|
477 Allowed characters in file names are: a-zA-Z0-9_. All other characters in datafield
|
|
|
478 values, molname line, and root prefix are ignore during generation of file names.
|
|
|
479
|
|
|
480 =item B<-d, --DataField> I<DataFieldName>
|
|
|
481
|
|
|
482 This option is only used during I<DataField> value of <-c, --CmpdsMode> option.
|
|
|
483
|
|
|
484 Specify I<SDFile(s)> datafield label name whose value is used for generation of new file
|
|
|
485 for a specific compound. Default value: I<None>.
|
|
|
486
|
|
|
487 =item B<-h, --help>
|
|
|
488
|
|
|
489 Print this help message.
|
|
|
490
|
|
|
491 =item B<-m, --mode> I<Cmpds | Files>
|
|
|
492
|
|
|
493 Specify how to split I<SDFile(s)>: split into files with each file containing specified
|
|
|
494 number of compounds or split into a specified number of files.
|
|
|
495
|
|
|
496 Possible values: I<Cmpds | Files>. Default: I<Files>.
|
|
|
497
|
|
|
498 For I<Cmpds> value of B<-m, --mode> option, value of B<--numcmpds> option
|
|
|
499 determines the number of new files. And value of B<-n, --numfiles> option is
|
|
|
500 used to figure out the number of new files for I<Files> value of B<-m, --mode> option.
|
|
|
501
|
|
|
502 =item B<-n, --numfiles> I<number>
|
|
|
503
|
|
|
504 Number of new files to generate for each I<SDFile(s)>. Default: I<2>.
|
|
|
505
|
|
|
506 This value is only used during I<Files> value of B<-m, --mode> option.
|
|
|
507
|
|
|
508 =item B<--numcmpds> I<number>
|
|
|
509
|
|
|
510 Number of compounds in each new file corresponding to each I<SDFile(s)>.
|
|
|
511 Default: I<1>.
|
|
|
512
|
|
|
513 This value is only used during I<Cmpds> value of B<-m, --mode> option.
|
|
|
514
|
|
|
515 =item B<-o, --overwrite>
|
|
|
516
|
|
|
517 Overwrite existing files.
|
|
|
518
|
|
|
519 =item B<-r, --root> I<rootname>
|
|
|
520
|
|
|
521 New SD file names are generated using the root: <Root>Part<Count>.sdf.
|
|
|
522 Default new file names: <InitialSDFileName> Part<Count>.sdf. This option
|
|
|
523 is ignored for multiple input files.
|
|
|
524
|
|
|
525 =item B<-w,--workingdir> I<dirname>
|
|
|
526
|
|
|
527 Location of working directory. Default: current directory.
|
|
|
528
|
|
|
529 =back
|
|
|
530
|
|
|
531 =head1 EXAMPLES
|
|
|
532
|
|
|
533 To split each SD file into 5 new SD files, type:
|
|
|
534
|
|
|
535 % SplitSDFiles.pl -n 5 -o Sample1.sdf Sample2.sdf
|
|
|
536 % SplitSDFiles.pl -n 5 -o *.sdf
|
|
|
537
|
|
|
538 To split Sample1.sdf into 10 new NewSample*.sdf files, type:
|
|
|
539
|
|
|
540 % SplitSDFiles.pl -m Files -n 10 -r NewSample -o Sample1.sdf
|
|
|
541
|
|
|
542 To split Sample1.sdf into new NewSample*.sdf files containing maximum of 5 compounds
|
|
|
543 in each file, type:
|
|
|
544
|
|
|
545 % SplitSDFiles.pl -m Cmpds --numcmpds 5 -r NewSample -o Sample1.sdf
|
|
|
546
|
|
|
547 To split Sample1.sdf into new SD files containing one compound each with new file
|
|
|
548 names corresponding to molname line, type:
|
|
|
549
|
|
|
550 % SplitSDFiles.pl -m Cmpds --numcmpds 1 -c MolName -o Sample1.sdf
|
|
|
551
|
|
|
552 To split Sample1.sdf into new SD files containing one compound each with new file
|
|
|
553 names corresponding to value of datafield MolID, type:
|
|
|
554
|
|
|
555 % SplitSDFiles.pl -m Cmpds --numcmpds 1 -c DataField -d MolID
|
|
|
556 -o Sample1.sdf
|
|
|
557
|
|
|
558 =head1 AUTHOR
|
|
|
559
|
|
|
560 Manish Sud <msud@san.rr.com>
|
|
|
561
|
|
|
562 =head1 SEE ALSO
|
|
|
563
|
|
|
564 InfoSDFiles.pl, JoinSDFiles.pl, MolFilesToSD.pl, SDToMolFiles.pl
|
|
|
565
|
|
|
566 =head1 COPYRIGHT
|
|
|
567
|
|
|
568 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
569
|
|
|
570 This file is part of MayaChemTools.
|
|
|
571
|
|
|
572 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
573 the terms of the GNU Lesser General Public License as published by the Free
|
|
|
574 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
575 any later version.
|
|
|
576
|
|
|
577 =cut
|
