[Bio] / Sprout / Sprout.pm Repository:
ViewVC logotype

Annotation of /Sprout/Sprout.pm

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.53 - (view) (download) (as text)

1 : parrello 1.1 package Sprout;
2 :    
3 : parrello 1.15 use Data::Dumper;
4 :     use strict;
5 :     use Carp;
6 :     use DBKernel;
7 :     use XML::Simple;
8 :     use DBQuery;
9 :     use DBObject;
10 :     use ERDB;
11 :     use Tracer;
12 :     use FIGRules;
13 :     use Stats;
14 : parrello 1.3 use POSIX qw(strftime);
15 : parrello 1.1
16 :    
17 :     =head1 Sprout Database Manipulation Object
18 :    
19 :     =head2 Introduction
20 :    
21 :     This object enables the user to load and query the Sprout genome database using a few simple methods.
22 :     To construct the object, specify the name of the database. By default, the database is assumed to be a
23 :     MySQL database accessed via the user ID I<root> with no password and the database definition will
24 :     be in a file called F<SproutDBD.xml>. All of these defaults can be overridden
25 :     on the constructor. For example, the following invocation specifies a PostgreSQL database named I<GenDB>
26 :     whose definition and data files are in a co-directory named F<Data>.
27 :    
28 :     C<< my $sprout = Sprout->new('GenDB', { dbType => 'pg', dataDir => '../Data', xmlFileName => '../Data/SproutDBD.xml' }); >>
29 :    
30 :     Once you have a sprout object, you may use it to re-create the database, load the tables from
31 :     tab-delimited flat files and perform queries. Several special methods are provided for common
32 :     query tasks. For example, L</genomes> lists the IDs of all the genomes in the database and
33 :     L</dna_seq> returns the DNA sequence for a specified genome location.
34 :    
35 :     =cut
36 :    
37 : parrello 1.3 #: Constructor SFXlate->new_sprout_only();
38 :    
39 : parrello 1.1 =head2 Public Methods
40 :    
41 :     =head3 new
42 :    
43 :     C<< my $sprout = Sprout->new($dbName, \%options); >>
44 :    
45 :     This is the constructor for a sprout object. It connects to the database and loads the
46 :     database definition into memory. The positional first parameter specifies the name of the
47 :     database.
48 :    
49 :     =over 4
50 :    
51 :     =item dbName
52 :    
53 :     Name of the database.
54 :    
55 :     =item options
56 :    
57 :     Table of options.
58 :    
59 :     * B<dbType> type of database (currently C<mysql> for MySQL and C<pg> for PostgreSQL) (default C<mysql>)
60 :    
61 :     * B<dataDir> directory containing the database definition file and the flat files used to load the data (default C<Data>)
62 :    
63 :     * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)
64 :    
65 :     * B<userData> user name and password, delimited by a slash (default C<root/>)
66 :    
67 :     * B<port> connection port (default C<0>)
68 :    
69 :     * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)
70 :    
71 :     * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
72 :    
73 : parrello 1.25 * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
74 :    
75 : parrello 1.1 =back
76 :    
77 :     For example, the following constructor call specifies a database named I<Sprout> and a user name of
78 :     I<fig> with a password of I<admin>. The database load files are in the directory
79 :     F</usr/fig/SproutData>.
80 :    
81 :     C<< my $sprout = Sprout->new('Sprout', { userData =>; 'fig/admin', dataDir => '/usr/fig/SproutData' }); >>
82 :    
83 :     =cut
84 :    
85 :     sub new {
86 : parrello 1.15 # Get the parameters.
87 :     my ($class, $dbName, $options) = @_;
88 :     # Compute the options. We do this by starting with a table of defaults and overwriting with
89 :     # the incoming data.
90 :     my $optionTable = Tracer::GetOptions({
91 : parrello 1.18 dbType => $FIG_Config::dbms,
92 :     # database type
93 :     dataDir => $FIG_Config::sproutData,
94 :     # data file directory
95 :     xmlFileName => "$FIG_Config::sproutData/SproutDBD.xml",
96 :     # database definition file name
97 :     userData => "$FIG_Config::dbuser/$FIG_Config::dbpass",
98 :     # user name and password
99 :     port => $FIG_Config::dbport,
100 :     # database connection port
101 : parrello 1.15 maxSegmentLength => 4500, # maximum feature segment length
102 :     maxSequenceLength => 8000, # maximum contig sequence length
103 : parrello 1.25 noDBOpen => 0, # 1 to suppress the database open
104 : parrello 1.15 }, $options);
105 :     # Get the data directory.
106 :     my $dataDir = $optionTable->{dataDir};
107 :     # Extract the user ID and password.
108 :     $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
109 :     my ($userName, $password) = ($1, $2);
110 :     # Connect to the database.
111 : parrello 1.25 my $dbh;
112 :     if (! $optionTable->{noDBOpen}) {
113 :     $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
114 :     $password, $optionTable->{port});
115 :     }
116 : parrello 1.15 # Create the ERDB object.
117 :     my $xmlFileName = "$optionTable->{xmlFileName}";
118 :     my $erdb = ERDB->new($dbh, $xmlFileName);
119 :     # Create this object.
120 :     my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName };
121 :     # Bless and return it.
122 :     bless $self;
123 :     return $self;
124 : parrello 1.1 }
125 :    
126 :     =head3 MaxSegment
127 :    
128 :     C<< my $length = $sprout->MaxSegment(); >>
129 :    
130 :     This method returns the maximum permissible length of a feature segment. The length is important
131 :     because it enables us to make reasonable guesses at how to find features inside a particular
132 :     contig region. For example, if the maximum length is 4000 and we're looking for a feature that
133 :     overlaps the region from 6000 to 7000 we know that the starting position must be between 2001
134 :     and 10999.
135 :    
136 :     =cut
137 : parrello 1.3 #: Return Type $;
138 : parrello 1.1 sub MaxSegment {
139 : parrello 1.15 my ($self) = @_;
140 :     return $self->{_options}->{maxSegmentLength};
141 : parrello 1.1 }
142 :    
143 :     =head3 MaxSequence
144 :    
145 :     C<< my $length = $sprout->MaxSequence(); >>
146 :    
147 :     This method returns the maximum permissible length of a contig sequence. A contig is broken
148 :     into sequences in order to save memory resources. In particular, when manipulating features,
149 :     we generally only need a few sequences in memory rather than the entire contig.
150 :    
151 :     =cut
152 : parrello 1.3 #: Return Type $;
153 : parrello 1.1 sub MaxSequence {
154 : parrello 1.15 my ($self) = @_;
155 :     return $self->{_options}->{maxSequenceLength};
156 : parrello 1.1 }
157 :    
158 :     =head3 Get
159 :    
160 :     C<< my $query = $sprout->Get(\@objectNames, $filterClause, \@parameterList); >>
161 :    
162 :     This method allows a general query against the Sprout data using a specified filter clause.
163 :    
164 :     The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each
165 :     field name represented in the form B<I<objectName>(I<fieldName>)>. For example, the
166 :     following call requests all B<Genome> objects for the genus specified in the variable
167 :     $genus.
168 :    
169 :     C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>
170 :    
171 :     The WHERE clause contains a single question mark, so there is a single additional
172 :     parameter representing the parameter value. It would also be possible to code
173 :    
174 :     C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>
175 :    
176 :     however, this version of the call would generate a syntax error if there were any quote
177 :     characters inside the variable C<$genus>.
178 :    
179 :     The use of the strange parenthesized notation for field names enables us to distinguish
180 :     hyphens contained within field names from minus signs that participate in the computation
181 :     of the WHERE clause. All of the methods that manipulate fields will use this same notation.
182 :    
183 :     It is possible to specify multiple entity and relationship names in order to retrieve more than
184 :     one object's data at the same time, which allows highly complex joined queries. For example,
185 :    
186 :     C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>
187 :    
188 :     This query returns all the genomes for a particular genus and allows access to the
189 :     sources from which they came. The join clauses to go from Genome to Source are generated
190 :     automatically.
191 :    
192 :     Finally, the filter clause can contain sort information. To do this, simply put an C<ORDER BY>
193 :     clause at the end of the filter. Field references in the ORDER BY section follow the same rules
194 :     as they do in the filter itself; in other words, each one must be of the form B<I<objectName>(I<fieldName>)>.
195 :     For example, the following filter string gets all genomes for a particular genus and sorts
196 :     them by species name.
197 :    
198 :     C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ? ORDER BY Genome(species)", [$genus]); >>
199 :    
200 :     It is also permissible to specify I<only> an ORDER BY clause. For example, the following invocation gets
201 :     all genomes ordered by genus and species.
202 :    
203 :     C<< $query = $sprout->Get(['Genome'], "ORDER BY Genome(genus), Genome(species)"); >>
204 :    
205 :     Odd things may happen if one of the ORDER BY fields is in a secondary relation. So, for example, an
206 :     attempt to order B<Feature>s by alias may (depending on the underlying database engine used) cause
207 :     a single feature to appear more than once.
208 :    
209 :     If multiple names are specified, then the query processor will automatically determine a
210 :     join path between the entities and relationships. The algorithm used is very simplistic.
211 :     In particular, you can't specify any entity or relationship more than once, and if a
212 :     relationship is recursive, the path is determined by the order in which the entity
213 :     and the relationship appear. For example, consider a recursive relationship B<IsParentOf>
214 :     which relates B<People> objects to other B<People> objects. If the join path is
215 :     coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,
216 :     the join path is C<['IsParentOf', 'People']>, then the people returned will be children.
217 :    
218 :     =over 4
219 :    
220 :     =item objectNames
221 :    
222 :     List containing the names of the entity and relationship objects to be retrieved.
223 :    
224 :     =item filterClause
225 :    
226 :     WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
227 :     be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
228 :     B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
229 :     parameter list as additional parameters. The fields in a filter clause can come from primary
230 :     entity relations, relationship relations, or secondary entity relations; however, all of the
231 :     entities and relationships involved must be included in the list of object names.
232 :    
233 :     =item parameterList
234 :    
235 :     List of the parameters to be substituted in for the parameters marks in the filter clause.
236 :    
237 :     =item RETURN
238 :    
239 :     Returns a B<DBQuery> that can be used to iterate through all of the results.
240 :    
241 :     =back
242 :    
243 :     =cut
244 :    
245 :     sub Get {
246 : parrello 1.15 # Get the parameters.
247 :     my ($self, $objectNames, $filterClause, $parameterList) = @_;
248 :     # We differ from the ERDB Get method in that the parameter list is passed in as a list reference
249 :     # rather than a list of parameters. The next step is to convert the parameters from a reference
250 :     # to a real list. We can only do this if the parameters have been specified.
251 :     my @parameters;
252 :     if ($parameterList) { @parameters = @{$parameterList}; }
253 :     return $self->{_erdb}->Get($objectNames, $filterClause, @parameters);
254 : parrello 1.1 }
255 :    
256 :     =head3 GetEntity
257 :    
258 :     C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>
259 :    
260 :     Return an object describing the entity instance with a specified ID.
261 :    
262 :     =over 4
263 :    
264 :     =item entityType
265 :    
266 :     Entity type name.
267 :    
268 :     =item ID
269 :    
270 :     ID of the desired entity.
271 :    
272 :     =item RETURN
273 :    
274 :     Returns a B<DBObject> representing the desired entity instance, or an undefined value if no
275 :     instance is found with the specified key.
276 :    
277 :     =back
278 :    
279 :     =cut
280 :    
281 :     sub GetEntity {
282 : parrello 1.15 # Get the parameters.
283 :     my ($self, $entityType, $ID) = @_;
284 :     # Call the ERDB method.
285 :     return $self->{_erdb}->GetEntity($entityType, $ID);
286 : parrello 1.1 }
287 :    
288 :     =head3 GetEntityValues
289 :    
290 :     C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>
291 :    
292 :     Return a list of values from a specified entity instance.
293 :    
294 :     =over 4
295 :    
296 :     =item entityType
297 :    
298 :     Entity type name.
299 :    
300 :     =item ID
301 :    
302 :     ID of the desired entity.
303 :    
304 :     =item fields
305 :    
306 :     List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.
307 :    
308 :     =item RETURN
309 :    
310 :     Returns a flattened list of the values of the specified fields for the specified entity.
311 :    
312 :     =back
313 :    
314 :     =cut
315 : parrello 1.3 #: Return Type @;
316 : parrello 1.1 sub GetEntityValues {
317 : parrello 1.15 # Get the parameters.
318 :     my ($self, $entityType, $ID, $fields) = @_;
319 :     # Call the ERDB method.
320 :     return $self->{_erdb}->GetEntityValues($entityType, $ID, $fields);
321 : parrello 1.1 }
322 :    
323 :     =head3 ShowMetaData
324 :    
325 :     C<< $sprout->ShowMetaData($fileName); >>
326 :    
327 :     This method outputs a description of the database to an HTML file in the data directory.
328 :    
329 :     =over 4
330 :    
331 :     =item fileName
332 :    
333 :     Fully-qualified name to give to the output file.
334 :    
335 :     =back
336 :    
337 :     =cut
338 :    
339 :     sub ShowMetaData {
340 : parrello 1.15 # Get the parameters.
341 :     my ($self, $fileName) = @_;
342 :     # Compute the file name.
343 :     my $options = $self->{_options};
344 :     # Call the show method on the underlying ERDB object.
345 :     $self->{_erdb}->ShowMetaData($fileName);
346 : parrello 1.1 }
347 :    
348 :     =head3 Load
349 :    
350 :     C<< $sprout->Load($rebuild); >>;
351 :    
352 :     Load the database from files in the data directory, optionally re-creating the tables.
353 :    
354 :     This method always deletes the data from the database before loading, even if the tables are not
355 :     re-created. The data is loaded into the relations from files in the data directory either having the
356 :     same name as the target relation with no extension or with an extension of C<.dtx>. Files without an
357 :     extension are used in preference to the files with an extension.
358 :    
359 :     The files are loaded based on the presumption that each line of the file is a record in the
360 :     relation, and the individual fields are delimited by tabs. Tab and new-line characters inside
361 :     fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must
362 :     be presented in the order given in the relation tables produced by the L</ShowMetaData> method.
363 :    
364 :     =over 4
365 :    
366 :     =item rebuild
367 :    
368 :     TRUE if the data tables need to be created or re-created, else FALSE
369 :    
370 :     =item RETURN
371 :    
372 :     Returns a statistical object containing the number of records read, the number of duplicates found,
373 :     the number of errors, and a list of the error messages.
374 :    
375 :     =back
376 :    
377 :     =cut
378 : parrello 1.3 #: Return Type %;
379 : parrello 1.1 sub Load {
380 : parrello 1.15 # Get the parameters.
381 :     my ($self, $rebuild) = @_;
382 :     # Get the database object.
383 :     my $erdb = $self->{_erdb};
384 :     # Load the tables from the data directory.
385 :     my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild);
386 :     # Return the statistics.
387 :     return $retVal;
388 : parrello 1.1 }
389 :    
390 :     =head3 LoadUpdate
391 :    
392 : parrello 1.44 C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>
393 : parrello 1.1
394 :     Load updates to one or more database tables. This method enables the client to make changes to one
395 :     or two tables without reloading the whole database. For each table, there must be a corresponding
396 :     file in the data directory, either with the same name as the table, or with a C<.dtx> suffix. So,
397 :     for example, to make updates to the B<FeatureTranslation> relation, there must be a
398 :     C<FeatureTranslation.dtx> file in the data directory. Unlike a full load, files without an extension
399 :     are not examined. This allows update files to co-exist with files from an original load.
400 :    
401 :     =over 4
402 :    
403 :     =item truncateFlag
404 :    
405 :     TRUE if the tables should be rebuilt before loading, else FALSE. A value of TRUE therefore causes
406 :     current data and schema of the tables to be replaced, while a value of FALSE means the new data
407 :     is added to the existing data in the various relations.
408 :    
409 :     =item tableList
410 :    
411 :     List of the tables to be updated.
412 :    
413 :     =item RETURN
414 :    
415 :     Returns a statistical object containing the number of records read, the number of duplicates found,
416 :     the number of errors encountered, and a list of error messages.
417 :    
418 :     =back
419 :    
420 :     =cut
421 : parrello 1.7 #: Return Type $%;
422 : parrello 1.1 sub LoadUpdate {
423 : parrello 1.15 # Get the parameters.
424 :     my ($self, $truncateFlag, $tableList) = @_;
425 :     # Get the database object.
426 :     my $erdb = $self->{_erdb};
427 :     # Declare the return value.
428 :     my $retVal = Stats->new();
429 :     # Get the data directory.
430 :     my $optionTable = $self->{_options};
431 :     my $dataDir = $optionTable->{dataDir};
432 :     # Loop through the incoming table names.
433 :     for my $tableName (@{$tableList}) {
434 :     # Find the table's file.
435 : parrello 1.18 my $fileName = LoadFileName($dataDir, $tableName);
436 :     if (! $fileName) {
437 :     Trace("No load file found for $tableName in $dataDir.") if T(0);
438 :     } else {
439 :     # Attempt to load this table.
440 :     my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);
441 :     # Accumulate the resulting statistics.
442 :     $retVal->Accumulate($result);
443 : parrello 1.15 }
444 :     }
445 :     # Return the statistics.
446 :     return $retVal;
447 : parrello 1.1 }
448 :    
449 :     =head3 Build
450 :    
451 :     C<< $sprout->Build(); >>
452 :    
453 :     Build the database. The database will be cleared and the tables re-created from the metadata.
454 :     This method is useful when a database is brand new or when the database definition has
455 :     changed.
456 :    
457 :     =cut
458 : parrello 1.3 #: Return Type ;
459 : parrello 1.1 sub Build {
460 : parrello 1.15 # Get the parameters.
461 :     my ($self) = @_;
462 :     # Create the tables.
463 :     $self->{_erdb}->CreateTables;
464 : parrello 1.1 }
465 :    
466 :     =head3 Genomes
467 :    
468 :     C<< my @genomes = $sprout->Genomes(); >>
469 :    
470 :     Return a list of all the genome IDs.
471 :    
472 :     =cut
473 : parrello 1.3 #: Return Type @;
474 : parrello 1.1 sub Genomes {
475 : parrello 1.15 # Get the parameters.
476 :     my ($self) = @_;
477 :     # Get all the genomes.
478 :     my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');
479 :     # Return the list of IDs.
480 :     return @retVal;
481 : parrello 1.1 }
482 :    
483 :     =head3 GenusSpecies
484 :    
485 :     C<< my $infoString = $sprout->GenusSpecies($genomeID); >>
486 :    
487 :     Return the genus, species, and unique characterization for a genome.
488 :    
489 :     =over 4
490 :    
491 :     =item genomeID
492 :    
493 :     ID of the genome whose genus and species is desired
494 :    
495 :     =item RETURN
496 :    
497 :     Returns the genus and species of the genome, with the unique characterization (if any). If the genome
498 :     does not exist, returns an undefined value.
499 :    
500 :     =back
501 :    
502 :     =cut
503 : parrello 1.3 #: Return Type $;
504 : parrello 1.1 sub GenusSpecies {
505 : parrello 1.15 # Get the parameters.
506 :     my ($self, $genomeID) = @_;
507 :     # Get the data for the specified genome.
508 :     my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',
509 :     'Genome(unique-characterization)']);
510 :     # Format the result and return it.
511 :     my $retVal = join(' ', @values);
512 :     return $retVal;
513 : parrello 1.1 }
514 :    
515 :     =head3 FeaturesOf
516 :    
517 :     C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>
518 :    
519 :     Return a list of the features relevant to a specified genome.
520 :    
521 :     =over 4
522 :    
523 :     =item genomeID
524 :    
525 :     Genome whose features are desired.
526 :    
527 :     =item ftype
528 :    
529 :     Type of feature desired. If omitted, all features will be returned.
530 :    
531 :     =item RETURN
532 :    
533 :     Returns a list of the feature IDs for features relevant to the genome. If the genome does not exist,
534 :     will return an empty list.
535 :    
536 :     =back
537 :    
538 :     =cut
539 : parrello 1.3 #: Return Type @;
540 : parrello 1.1 sub FeaturesOf {
541 : parrello 1.15 # Get the parameters.
542 :     my ($self, $genomeID,$ftype) = @_;
543 :     # Get the features we want.
544 :     my @features;
545 :     if (!$ftype) {
546 :     @features = $self->GetFlat(['HasContig', 'IsLocatedIn'], "HasContig(from-link) = ?",
547 :     [$genomeID], 'IsLocatedIn(from-link)');
548 :     } else {
549 :     @features = $self->GetFlat(['HasContig', 'IsLocatedIn', 'Feature'],
550 :     "HasContig(from-link) = ? AND Feature(feature-type) = ?",
551 :     [$genomeID, $ftype], 'IsLocatedIn(from-link)');
552 :     }
553 :     # Return the list with duplicates merged out. We need to merge out duplicates because
554 :     # a feature will appear twice if it spans more than one contig.
555 :     my @retVal = Tracer::Merge(@features);
556 :     # Return the list of feature IDs.
557 :     return @retVal;
558 : parrello 1.1 }
559 :    
560 :     =head3 FeatureLocation
561 :    
562 :     C<< my @locations = $sprout->FeatureLocation($featureID); >>
563 :    
564 :     Return the location of a feature in its genome's contig segments. In a list context, this method
565 :     will return a list of the locations. In a scalar context, it will return the locations as a space-
566 :     delimited string. Each location will be of the form I<contigID>C<_>I<begin>I<dir>I<len> where
567 :     I<begin> is the starting position, I<dir> is C<+> for a forward transcription or C<-> for a backward
568 :     transcription, and I<len> is the length. So, for example, C<1999.1_NC123_4000+200> describes a location
569 :     beginning at position 4000 of contig C<1999.1_NC123> and ending at position 4199. Similarly,
570 :     C<1999.1_NC123_2000-400> describes a location in the same contig starting at position 2000 and ending
571 :     at position 1601.
572 :    
573 :     This process is complicated by the fact that we automatically split up feature segments longer than
574 :     the maximum segment length. When we find two segments that are adjacent to each other, we must
575 :     put them back together.
576 :    
577 :     =over 4
578 :    
579 :     =item featureID
580 :    
581 :     FIG ID of the desired feature
582 :    
583 :     =item RETURN
584 :    
585 :     Returns a list of the feature's contig segments. The locations are returned as a list in a list
586 : parrello 1.20 context and as a comma-delimited string in a scalar context.
587 : parrello 1.1
588 :     =back
589 :    
590 :     =cut
591 : parrello 1.3 #: Return Type @;
592 :     #: Return Type $;
593 : parrello 1.1 sub FeatureLocation {
594 : parrello 1.15 # Get the parameters.
595 :     my ($self, $featureID) = @_;
596 :     # Create a query for the feature locations.
597 :     my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",
598 :     [$featureID]);
599 :     # Create the return list.
600 :     my @retVal = ();
601 :     # Set up the variables used to determine if we have adjacent segments. This initial setup will
602 :     # not match anything.
603 :     my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);
604 :     # Loop through the query results, creating location specifiers.
605 :     while (my $location = $query->Fetch()) {
606 :     # Get the location parameters.
607 :     my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',
608 :     'IsLocatedIn(beg)', 'IsLocatedIn(dir)', 'IsLocatedIn(len)']);
609 :     # Check to see if we are adjacent to the previous segment.
610 :     if ($prevContig eq $contigID && $dir eq $prevDir) {
611 :     # Here the new segment is in the same direction on the same contig. Insure the
612 :     # new segment's beginning is next to the old segment's end.
613 : parrello 1.41 if ($dir eq "-" && $beg + $len == $prevBeg) {
614 :     # Here we're merging two backward blocks, so we keep the new begin point
615 :     # and adjust the length.
616 :     $len += $prevLen;
617 :     # Pop the old segment off. The new one will replace it later.
618 :     pop @retVal;
619 :     } elsif ($dir eq "+" && $beg == $prevBeg + $prevLen) {
620 :     # Here we need to merge two forward blocks. Adjust the beginning and
621 :     # length values to include both segments.
622 : parrello 1.15 $beg = $prevBeg;
623 :     $len += $prevLen;
624 :     # Pop the old segment off. The new one will replace it later.
625 :     pop @retVal;
626 :     }
627 :     }
628 :     # Remember this specifier for the adjacent-segment test the next time through.
629 :     ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);
630 : parrello 1.32 # Compute the initial base pair.
631 :     my $start = ($dir eq "+" ? $beg : $beg + $len - 1);
632 : parrello 1.15 # Add the specifier to the list.
633 : parrello 1.33 push @retVal, "${contigID}_$start$dir$len";
634 : parrello 1.15 }
635 :     # Return the list in the format indicated by the context.
636 : parrello 1.20 return (wantarray ? @retVal : join(',', @retVal));
637 : parrello 1.1 }
638 :    
639 :     =head3 ParseLocation
640 :    
641 :     C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>
642 :    
643 :     Split a location specifier into the contig ID, the starting point, the direction, and the
644 :     length.
645 :    
646 :     =over 4
647 :    
648 :     =item location
649 :    
650 :     A location specifier (see L</FeatureLocation> for a description).
651 :    
652 :     =item RETURN
653 :    
654 :     Returns a list containing the contig ID, the start position, the direction (C<+> or C<->),
655 :     and the length indicated by the incoming location specifier.
656 :    
657 :     =back
658 :    
659 :     =cut
660 : parrello 1.3 #: Return Type @;
661 : parrello 1.1 sub ParseLocation {
662 : parrello 1.15 # Get the parameter. Note that if we're called as an instance method, we ignore
663 : parrello 1.10 # the first parameter.
664 :     shift if UNIVERSAL::isa($_[0],__PACKAGE__);
665 : parrello 1.15 my ($location) = @_;
666 :     # Parse it into segments.
667 : parrello 1.40 $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
668 : parrello 1.15 my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
669 :     # If the direction is an underscore, convert it to a + or -.
670 :     if ($dir eq "_") {
671 :     if ($start < $len) {
672 :     $dir = "+";
673 :     $len = $len - $start + 1;
674 :     } else {
675 :     $dir = "-";
676 :     $len = $start - $len + 1;
677 :     }
678 :     }
679 :     # Return the result.
680 :     return ($contigID, $start, $dir, $len);
681 : parrello 1.1 }
682 :    
683 : parrello 1.10 =head3 PointLocation
684 :    
685 :     C<< my $found = Sprout::PointLocation($location, $point); >>
686 :    
687 :     Return the offset into the specified location of the specified point on the contig. If
688 :     the specified point is before the location, a negative value will be returned. If it is
689 : parrello 1.19 beyond the location, an undefined value will be returned. It is assumed that the offset
690 :     is for the location's contig. The location can either be new-style (using a C<+> or C<->
691 : parrello 1.10 and a length) or old-style (using C<_> and start and end positions.
692 :    
693 :     =over 4
694 :    
695 :     =item location
696 :    
697 :     A location specifier (see L</FeatureLocation> for a description).
698 :    
699 :     =item point
700 :    
701 :     The offset into the contig of the point in which we're interested.
702 :    
703 :     =item RETURN
704 :    
705 :     Returns the offset inside the specified location of the specified point, a negative
706 :     number if the point is before the location, or an undefined value if the point is past
707 :     the location. If the length of the location is 0, this method will B<always> denote
708 :     that it is outside the location. The offset will always be relative to the left-most
709 :     position in the location.
710 :    
711 :     =back
712 :    
713 :     =cut
714 :     #: Return Type $;
715 :     sub PointLocation {
716 : parrello 1.15 # Get the parameter. Note that if we're called as an instance method, we ignore
717 : parrello 1.10 # the first parameter.
718 :     shift if UNIVERSAL::isa($_[0],__PACKAGE__);
719 : parrello 1.15 my ($location, $point) = @_;
720 : parrello 1.10 # Parse out the location elements. Note that this works on both old-style and new-style
721 :     # locations.
722 :     my ($contigID, $start, $dir, $len) = ParseLocation($location);
723 :     # Declare the return variable.
724 :     my $retVal;
725 :     # Compute the offset. The computation is dependent on the direction of the location.
726 :     my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
727 :     # Return the offset if it's valid.
728 :     if ($offset < $len) {
729 :     $retVal = $offset;
730 :     }
731 :     # Return the offset found.
732 :     return $retVal;
733 :     }
734 :    
735 : parrello 1.1 =head3 DNASeq
736 :    
737 :     C<< my $sequence = $sprout->DNASeq(\@locationList); >>
738 :    
739 :     This method returns the DNA sequence represented by a list of locations. The list of locations
740 : parrello 1.2 should be of the form returned by L</featureLocation> when in a list context. In other words,
741 : parrello 1.1 each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.
742 :    
743 :     =over 4
744 :    
745 :     =item locationList
746 :    
747 :     List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see
748 :     L</FeatureLocation> for more about this format).
749 :    
750 :     =item RETURN
751 :    
752 :     Returns a string of nucleotides corresponding to the DNA segments in the location list.
753 :    
754 :     =back
755 :    
756 :     =cut
757 : parrello 1.3 #: Return Type $;
758 : parrello 1.1 sub DNASeq {
759 : parrello 1.15 # Get the parameters.
760 :     my ($self, $locationList) = @_;
761 :     # Create the return string.
762 :     my $retVal = "";
763 :     # Loop through the locations.
764 :     for my $location (@{$locationList}) {
765 :     # Set up a variable to contain the DNA at this location.
766 :     my $locationDNA = "";
767 :     # Parse out the contig ID, the beginning point, the direction, and the end point.
768 :     my ($contigID, $beg, $dir, $len) = ParseLocation($location);
769 :     # Now we must create a query to return all the sequences in the contig relevant to the region
770 :     # specified. First, we compute the start and stop points when reading through the sequences.
771 :     # For a forward transcription, the start point is the beginning; for a backward transcription,
772 :     # the start point is the ending. Note that in the latter case we must reverse the DNA string
773 :     # before putting it in the return value.
774 :     my ($start, $stop);
775 : parrello 1.34 Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
776 : parrello 1.15 if ($dir eq "+") {
777 :     $start = $beg;
778 : parrello 1.38 $stop = $beg + $len - 1;
779 : parrello 1.15 } else {
780 : parrello 1.38 $start = $beg - $len + 1;
781 :     $stop = $beg;
782 : parrello 1.15 }
783 : parrello 1.38 Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
784 : parrello 1.15 my $query = $self->Get(['IsMadeUpOf','Sequence'],
785 :     "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
786 : parrello 1.38 " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
787 : parrello 1.15 [$contigID, $start, $stop]);
788 :     # Loop through the sequences.
789 :     while (my $sequence = $query->Fetch()) {
790 :     # Determine whether the location starts, stops, or continues through this sequence.
791 :     my ($startPosition, $sequenceData, $sequenceLength) =
792 :     $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
793 :     'IsMadeUpOf(len)']);
794 :     my $stopPosition = $startPosition + $sequenceLength;
795 : parrello 1.29 Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
796 : parrello 1.15 # Figure out the start point and length of the relevant section.
797 :     my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
798 : parrello 1.39 my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
799 : parrello 1.29 Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
800 : parrello 1.15 # Add the relevant data to the location data.
801 : parrello 1.29 $locationDNA .= substr($sequenceData, $pos1, $len1);
802 : parrello 1.15 }
803 :     # Add this location's data to the return string. Note that we may need to reverse it.
804 :     if ($dir eq '+') {
805 :     $retVal .= $locationDNA;
806 :     } else {
807 : parrello 1.27 $retVal .= FIG::reverse_comp($locationDNA);
808 : parrello 1.15 }
809 :     }
810 :     # Return the result.
811 :     return $retVal;
812 : parrello 1.1 }
813 :    
814 :     =head3 AllContigs
815 :    
816 :     C<< my @idList = $sprout->AllContigs($genomeID); >>
817 :    
818 :     Return a list of all the contigs for a genome.
819 :    
820 :     =over 4
821 :    
822 :     =item genomeID
823 :    
824 :     Genome whose contigs are desired.
825 :    
826 :     =item RETURN
827 :    
828 :     Returns a list of the IDs for the genome's contigs.
829 :    
830 :     =back
831 :    
832 :     =cut
833 : parrello 1.3 #: Return Type @;
834 : parrello 1.1 sub AllContigs {
835 : parrello 1.15 # Get the parameters.
836 :     my ($self, $genomeID) = @_;
837 :     # Ask for the genome's Contigs.
838 :     my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
839 :     'HasContig(to-link)');
840 :     # Return the list of Contigs.
841 :     return @retVal;
842 : parrello 1.1 }
843 :    
844 :     =head3 ContigLength
845 :    
846 :     C<< my $length = $sprout->ContigLength($contigID); >>
847 :    
848 :     Compute the length of a contig.
849 :    
850 :     =over 4
851 :    
852 :     =item contigID
853 :    
854 :     ID of the contig whose length is desired.
855 :    
856 : parrello 1.3 =item RETURN
857 :    
858 :     Returns the number of positions in the contig.
859 :    
860 : parrello 1.1 =back
861 :    
862 :     =cut
863 : parrello 1.3 #: Return Type $;
864 : parrello 1.1 sub ContigLength {
865 : parrello 1.15 # Get the parameters.
866 :     my ($self, $contigID) = @_;
867 :     # Get the contig's last sequence.
868 :     my $query = $self->Get(['IsMadeUpOf'],
869 :     "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
870 :     [$contigID]);
871 :     my $sequence = $query->Fetch();
872 :     # Declare the return value.
873 :     my $retVal = 0;
874 :     # Set it from the sequence data, if any.
875 :     if ($sequence) {
876 :     my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
877 : parrello 1.40 $retVal = $start + $len - 1;
878 :     }
879 :     # Return the result.
880 :     return $retVal;
881 :     }
882 :    
883 :     =head3 ClusterPEGs
884 :    
885 :     C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>
886 :    
887 :     Cluster the PEGs in a list according to the cluster coding scheme of the specified
888 :     subsystem. In order for this to work properly, the subsystem object must have
889 :     been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.
890 :     This causes the cluster numbers to be pulled into the subsystem's color hash.
891 :     If a PEG is not found in the color hash, it will not appear in the output
892 :     sequence.
893 :    
894 :     =over 4
895 :    
896 :     =item sub
897 :    
898 :     Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
899 :     method.
900 :    
901 :     =item pegs
902 :    
903 :     Reference to the list of PEGs to be clustered.
904 :    
905 :     =item RETURN
906 :    
907 :     Returns a list of the PEGs, grouped into smaller lists by cluster number.
908 :    
909 :     =back
910 :    
911 :     =cut
912 :     #: Return Type $@@;
913 :     sub ClusterPEGs {
914 :     # Get the parameters.
915 :     my ($self, $sub, $pegs) = @_;
916 :     # Declare the return variable.
917 :     my $retVal = [];
918 :     # Loop through the PEGs, creating arrays for each cluster.
919 :     for my $pegID (@{$pegs}) {
920 :     my $clusterNumber = $sub->get_cluster_number($pegID);
921 :     # Only proceed if the PEG is in a cluster.
922 :     if ($clusterNumber >= 0) {
923 :     # Push this PEG onto the sub-list for the specified cluster number.
924 :     push @{$retVal->[$clusterNumber]}, $pegID;
925 :     }
926 : parrello 1.15 }
927 :     # Return the result.
928 :     return $retVal;
929 : parrello 1.1 }
930 :    
931 :     =head3 GenesInRegion
932 :    
933 :     C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>
934 :    
935 :     List the features which overlap a specified region in a contig.
936 :    
937 :     =over 4
938 :    
939 :     =item contigID
940 :    
941 :     ID of the contig containing the region of interest.
942 :    
943 :     =item start
944 :    
945 :     Offset of the first residue in the region of interest.
946 :    
947 :     =item stop
948 :    
949 :     Offset of the last residue in the region of interest.
950 :    
951 :     =item RETURN
952 :    
953 :     Returns a three-element list. The first element is a list of feature IDs for the features that
954 :     overlap the region of interest. The second and third elements are the minimum and maximum
955 :     locations of the features provided on the specified contig. These may extend outside
956 : parrello 1.9 the start and stop values. The first element (that is, the list of features) is sorted
957 :     roughly by location.
958 : parrello 1.1
959 :     =back
960 :    
961 :     =cut
962 : parrello 1.9 #: Return Type @@;
963 : parrello 1.1 sub GenesInRegion {
964 : parrello 1.15 # Get the parameters.
965 :     my ($self, $contigID, $start, $stop) = @_;
966 :     # Get the maximum segment length.
967 :     my $maximumSegmentLength = $self->MaxSegment;
968 :     # Create a hash to receive the feature list. We use a hash so that we can eliminate
969 :     # duplicates easily. The hash key will be the feature ID. The value will be a two-element
970 : parrello 1.19 # containing the minimum and maximum offsets. We will use the offsets to sort the results
971 : parrello 1.15 # when we're building the result set.
972 :     my %featuresFound = ();
973 :     # Prime the values we'll use for the returned beginning and end.
974 :     my @initialMinMax = ($self->ContigLength($contigID), 0);
975 :     my ($min, $max) = @initialMinMax;
976 :     # Create a table of parameters for each query. Each query looks for features travelling in
977 :     # a particular direction. The query parameters include the contig ID, the feature direction,
978 :     # the lowest possible start position, and the highest possible start position. This works
979 :     # because each feature segment length must be no greater than the maximum segment length.
980 :     my %queryParms = (forward => [$contigID, '+', $start - $maximumSegmentLength + 1, $stop],
981 :     reverse => [$contigID, '-', $start, $stop + $maximumSegmentLength - 1]);
982 :     # Loop through the query parameters.
983 :     for my $parms (values %queryParms) {
984 :     # Create the query.
985 :     my $query = $self->Get(['IsLocatedIn'],
986 :     "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
987 :     $parms);
988 :     # Loop through the feature segments found.
989 :     while (my $segment = $query->Fetch) {
990 :     # Get the data about this segment.
991 :     my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',
992 :     'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);
993 :     # Determine if this feature actually overlaps the region. The query insures that
994 :     # this will be the case if the segment is the maximum length, so to fine-tune
995 :     # the results we insure that the inequality from the query holds using the actual
996 :     # length.
997 :     my ($found, $end) = (0, 0);
998 :     if ($dir eq '+') {
999 :     $end = $beg + $len;
1000 :     if ($end >= $start) {
1001 :     # Denote we found a useful feature.
1002 :     $found = 1;
1003 :     }
1004 :     } elsif ($dir eq '-') {
1005 :     # Note we switch things around so that the beginning is to the left of the
1006 :     # ending.
1007 :     ($beg, $end) = ($beg - $len, $beg);
1008 :     if ($beg <= $stop) {
1009 :     # Denote we found a useful feature.
1010 :     $found = 1;
1011 :     }
1012 :     }
1013 :     if ($found) {
1014 :     # Here we need to record the feature and update the minima and maxima. First,
1015 :     # get the current entry for the specified feature.
1016 :     my ($loc1, $loc2) = (exists $featuresFound{$featureID} ? @{$featuresFound{$featureID}} :
1017 :     @initialMinMax);
1018 :     # Merge the current segment's begin and end into the feature begin and end and the
1019 :     # global min and max.
1020 :     if ($beg < $loc1) {
1021 :     $loc1 = $beg;
1022 :     $min = $beg if $beg < $min;
1023 :     }
1024 :     if ($end > $loc2) {
1025 :     $loc2 = $end;
1026 :     $max = $end if $end > $max;
1027 :     }
1028 :     # Store the entry back into the hash table.
1029 :     $featuresFound{$featureID} = [$loc1, $loc2];
1030 :     }
1031 :     }
1032 :     }
1033 :     # Now we must compute the list of the IDs for the features found. We start with a list
1034 :     # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1035 :     # but the result of the sort will be the same.)
1036 :     my @list = map { [$featuresFound{$_}->[0] + $featuresFound{$_}->[1], $_] } keys %featuresFound;
1037 :     # Now we sort by midpoint and yank out the feature IDs.
1038 :     my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1039 :     # Return it along with the min and max.
1040 :     return (\@retVal, $min, $max);
1041 : parrello 1.1 }
1042 :    
1043 :     =head3 FType
1044 :    
1045 :     C<< my $ftype = $sprout->FType($featureID); >>
1046 :    
1047 :     Return the type of a feature.
1048 :    
1049 :     =over 4
1050 :    
1051 :     =item featureID
1052 :    
1053 :     ID of the feature whose type is desired.
1054 :    
1055 :     =item RETURN
1056 :    
1057 :     A string indicating the type of feature (e.g. peg, rna). If the feature does not exist, returns an
1058 :     undefined value.
1059 :    
1060 :     =back
1061 :    
1062 :     =cut
1063 : parrello 1.3 #: Return Type $;
1064 : parrello 1.1 sub FType {
1065 : parrello 1.15 # Get the parameters.
1066 :     my ($self, $featureID) = @_;
1067 :     # Get the specified feature's type.
1068 :     my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1069 :     # Return the result.
1070 :     return $retVal;
1071 : parrello 1.1 }
1072 :    
1073 :     =head3 FeatureAnnotations
1074 :    
1075 : parrello 1.40 C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>
1076 : parrello 1.1
1077 :     Return the annotations of a feature.
1078 :    
1079 :     =over 4
1080 :    
1081 :     =item featureID
1082 :    
1083 :     ID of the feature whose annotations are desired.
1084 :    
1085 : parrello 1.40 =item rawFlag
1086 :    
1087 :     If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1088 :     will be returned in human-readable form.
1089 :    
1090 : parrello 1.1 =item RETURN
1091 :    
1092 :     Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1093 :    
1094 :     * B<featureID> ID of the relevant feature.
1095 :    
1096 : parrello 1.40 * B<timeStamp> time the annotation was made.
1097 : parrello 1.1
1098 :     * B<user> ID of the user who made the annotation
1099 :    
1100 :     * B<text> text of the annotation.
1101 :    
1102 :     =back
1103 :    
1104 :     =cut
1105 : parrello 1.3 #: Return Type @%;
1106 : parrello 1.1 sub FeatureAnnotations {
1107 : parrello 1.15 # Get the parameters.
1108 : parrello 1.40 my ($self, $featureID, $rawFlag) = @_;
1109 : parrello 1.15 # Create a query to get the feature's annotations and the associated users.
1110 :     my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1111 :     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
1112 :     # Create the return list.
1113 :     my @retVal = ();
1114 :     # Loop through the annotations.
1115 :     while (my $annotation = $query->Fetch) {
1116 :     # Get the fields to return.
1117 :     my ($featureID, $timeStamp, $user, $text) =
1118 :     $annotation->Values(['IsTargetOfAnnotation(from-link)',
1119 :     'Annotation(time)', 'MadeAnnotation(from-link)',
1120 :     'Annotation(annotation)']);
1121 : parrello 1.40 # Convert the time, if necessary.
1122 :     if (! $rawFlag) {
1123 :     $timeStamp = FriendlyTimestamp($timeStamp);
1124 :     }
1125 : parrello 1.15 # Assemble them into a hash.
1126 : parrello 1.3 my $annotationHash = { featureID => $featureID,
1127 : parrello 1.40 timeStamp => $timeStamp,
1128 : parrello 1.15 user => $user, text => $text };
1129 :     # Add it to the return list.
1130 :     push @retVal, $annotationHash;
1131 :     }
1132 :     # Return the result list.
1133 :     return @retVal;
1134 : parrello 1.1 }
1135 :    
1136 :     =head3 AllFunctionsOf
1137 :    
1138 :     C<< my %functions = $sprout->AllFunctionsOf($featureID); >>
1139 :    
1140 :     Return all of the functional assignments for a particular feature. The data is returned as a
1141 : parrello 1.11 hash of functional assignments to user IDs. A functional assignment is a type of annotation,
1142 : parrello 1.19 Functional assignments are described in the L</ParseAssignment> function. Its worth noting that
1143 :     we cannot filter on the content of the annotation itself because it's a text field; however,
1144 :     this is not a big problem because most features only have a small number of annotations.
1145 :     Finally, if a single user has multiple functional assignments, we will only keep the most
1146 : parrello 1.11 recent one.
1147 : parrello 1.1
1148 :     =over 4
1149 :    
1150 :     =item featureID
1151 :    
1152 :     ID of the feature whose functional assignments are desired.
1153 :    
1154 : parrello 1.3 =item RETURN
1155 :    
1156 : parrello 1.46 Returns a hash mapping the user IDs to functional assignment IDs.
1157 : parrello 1.3
1158 : parrello 1.1 =back
1159 :    
1160 :     =cut
1161 : parrello 1.3 #: Return Type %;
1162 : parrello 1.1 sub AllFunctionsOf {
1163 : parrello 1.15 # Get the parameters.
1164 :     my ($self, $featureID) = @_;
1165 :     # Get all of the feature's annotations.
1166 : parrello 1.47 my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1167 : parrello 1.15 "IsTargetOfAnnotation(from-link) = ?",
1168 : parrello 1.47 [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1169 :     'MadeAnnotation(from-link)']);
1170 : parrello 1.15 # Declare the return hash.
1171 :     my %retVal;
1172 : parrello 1.5 # Now we sort the assignments by timestamp in reverse.
1173 :     my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1174 : parrello 1.15 # Loop until we run out of annotations.
1175 : parrello 1.5 for my $annotation (@sortedQuery) {
1176 :     # Get the annotation fields.
1177 : parrello 1.47 my ($timeStamp, $text, $user) = @{$annotation};
1178 : parrello 1.15 # Check to see if this is a functional assignment.
1179 : parrello 1.48 my ($actualUser, $function) = _ParseAssignment($user, $text);
1180 :     if ($actualUser && ! exists $retVal{$actualUser}) {
1181 : parrello 1.5 # Here it is a functional assignment and there has been no
1182 :     # previous assignment for this user, so we stuff it in the
1183 :     # return hash.
1184 : parrello 1.48 $retVal{$actualUser} = $function;
1185 : parrello 1.15 }
1186 :     }
1187 :     # Return the hash of assignments found.
1188 :     return %retVal;
1189 : parrello 1.1 }
1190 :    
1191 :     =head3 FunctionOf
1192 :    
1193 :     C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>
1194 :    
1195 : parrello 1.3 Return the most recently-determined functional assignment of a particular feature.
1196 :    
1197 :     The functional assignment is handled differently depending on the type of feature. If
1198 :     the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1199 : parrello 1.11 assignment is a type of annotation. The format of an assignment is described in
1200 : parrello 1.45 L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1201 : parrello 1.19 annotation itself because it's a text field; however, this is not a big problem because
1202 : parrello 1.11 most features only have a small number of annotations.
1203 : parrello 1.1
1204 : parrello 1.3 Each user has an associated list of trusted users. The assignment returned will be the most
1205 :     recent one by at least one of the trusted users. If no trusted user list is available, then
1206 :     the specified user and FIG are considered trusted. If the user ID is omitted, only FIG
1207 :     is trusted.
1208 :    
1209 :     If the feature is B<not> identified by a FIG ID, then the functional assignment
1210 :     information is taken from the B<ExternalAliasFunc> table. If the table does
1211 :     not contain an entry for the feature, an undefined value is returned.
1212 :    
1213 : parrello 1.1 =over 4
1214 :    
1215 :     =item featureID
1216 :    
1217 :     ID of the feature whose functional assignment is desired.
1218 :    
1219 :     =item userID (optional)
1220 :    
1221 : parrello 1.3 ID of the user whose function determination is desired. If omitted, only the latest
1222 :     C<FIG> assignment will be returned.
1223 : parrello 1.1
1224 :     =item RETURN
1225 :    
1226 :     Returns the text of the assigned function.
1227 :    
1228 :     =back
1229 :    
1230 :     =cut
1231 : parrello 1.3 #: Return Type $;
1232 : parrello 1.1 sub FunctionOf {
1233 : parrello 1.15 # Get the parameters.
1234 :     my ($self, $featureID, $userID) = @_;
1235 : parrello 1.3 # Declare the return value.
1236 :     my $retVal;
1237 :     # Determine the ID type.
1238 :     if ($featureID =~ m/^fig\|/) {
1239 :     # Here we have a FIG feature ID. We must build the list of trusted
1240 :     # users.
1241 :     my %trusteeTable = ();
1242 :     # Check the user ID.
1243 :     if (!$userID) {
1244 :     # No user ID, so only FIG is trusted.
1245 :     $trusteeTable{FIG} = 1;
1246 :     } else {
1247 :     # Add this user's ID.
1248 :     $trusteeTable{$userID} = 1;
1249 :     # Look for the trusted users in the database.
1250 :     my @trustees = $self->GetFlat(['IsTrustedBy'], 'IsTrustedBy(from-link) = ?', [$userID], 'IsTrustedBy(to-link)');
1251 :     if (! @trustees) {
1252 :     # None were found, so build a default list.
1253 :     $trusteeTable{FIG} = 1;
1254 :     } else {
1255 :     # Otherwise, put all the trustees in.
1256 :     for my $trustee (@trustees) {
1257 :     $trusteeTable{$trustee} = 1;
1258 :     }
1259 :     }
1260 :     }
1261 :     # Build a query for all of the feature's annotations, sorted by date.
1262 : parrello 1.48 my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1263 : parrello 1.3 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1264 :     [$featureID]);
1265 :     my $timeSelected = 0;
1266 :     # Loop until we run out of annotations.
1267 :     while (my $annotation = $query->Fetch()) {
1268 :     # Get the annotation text.
1269 : parrello 1.48 my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1270 :     'Annotation(time)', 'MadeAnnotation(from-link)']);
1271 : parrello 1.3 # Check to see if this is a functional assignment for a trusted user.
1272 : parrello 1.48 my ($actualUser, $function) = _ParseAssignment($user, $text);
1273 : parrello 1.49 Trace("Assignment user is $actualUser, text is $function.") if T(4);
1274 : parrello 1.48 if ($actualUser) {
1275 : parrello 1.3 # Here it is a functional assignment. Check the time and the user
1276 :     # name. The time must be recent and the user must be trusted.
1277 : parrello 1.50 if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1278 : parrello 1.3 $retVal = $function;
1279 :     $timeSelected = $time;
1280 :     }
1281 :     }
1282 :     }
1283 :     } else {
1284 :     # Here we have a non-FIG feature ID. In this case the user ID does not
1285 :     # matter. We simply get the information from the External Alias Function
1286 :     # table.
1287 : parrello 1.4 ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);
1288 : parrello 1.3 }
1289 : parrello 1.15 # Return the assignment found.
1290 :     return $retVal;
1291 : parrello 1.1 }
1292 :    
1293 : parrello 1.45 =head3 FunctionsOf
1294 :    
1295 :     C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>
1296 :    
1297 :     Return the functional assignments of a particular feature.
1298 :    
1299 :     The functional assignment is handled differently depending on the type of feature. If
1300 :     the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1301 :     assignment is a type of annotation. The format of an assignment is described in
1302 :     L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1303 :     annotation itself because it's a text field; however, this is not a big problem because
1304 :     most features only have a small number of annotations.
1305 :    
1306 :     If the feature is B<not> identified by a FIG ID, then the functional assignment
1307 :     information is taken from the B<ExternalAliasFunc> table. If the table does
1308 :     not contain an entry for the feature, an empty list is returned.
1309 :    
1310 :     =over 4
1311 :    
1312 :     =item featureID
1313 :    
1314 :     ID of the feature whose functional assignments are desired.
1315 :    
1316 :     =item RETURN
1317 :    
1318 :     Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1319 :     that user.
1320 :    
1321 :     =back
1322 :    
1323 :     =cut
1324 :     #: Return Type @@;
1325 :     sub FunctionsOf {
1326 :     # Get the parameters.
1327 :     my ($self, $featureID) = @_;
1328 :     # Declare the return value.
1329 :     my @retVal = ();
1330 :     # Determine the ID type.
1331 :     if ($featureID =~ m/^fig\|/) {
1332 :     # Here we have a FIG feature ID. We must build the list of trusted
1333 :     # users.
1334 :     my %trusteeTable = ();
1335 :     # Build a query for all of the feature's annotations, sorted by date.
1336 : parrello 1.48 my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1337 : parrello 1.45 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1338 :     [$featureID]);
1339 :     my $timeSelected = 0;
1340 :     # Loop until we run out of annotations.
1341 :     while (my $annotation = $query->Fetch()) {
1342 :     # Get the annotation text.
1343 : parrello 1.48 my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1344 :     'Annotation(time)',
1345 :     'MadeAnnotation(user)']);
1346 : parrello 1.45 # Check to see if this is a functional assignment for a trusted user.
1347 : parrello 1.48 my ($actualUser, $function) = _ParseAssignment($user, $text);
1348 :     if ($actualUser) {
1349 : parrello 1.45 # Here it is a functional assignment.
1350 : parrello 1.48 push @retVal, [$actualUser, $function];
1351 : parrello 1.45 }
1352 :     }
1353 :     } else {
1354 :     # Here we have a non-FIG feature ID. In this case the user ID does not
1355 :     # matter. We simply get the information from the External Alias Function
1356 :     # table.
1357 : parrello 1.48 my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1358 :     ['ExternalAliasFunc(func)']);
1359 :     push @retVal, map { ['master', $_] } @assignments;
1360 : parrello 1.45 }
1361 :     # Return the assignments found.
1362 :     return @retVal;
1363 :     }
1364 :    
1365 : parrello 1.1 =head3 BBHList
1366 :    
1367 :     C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>
1368 :    
1369 :     Return a hash mapping the features in a specified list to their bidirectional best hits
1370 :     on a specified target genome.
1371 :    
1372 :     =over 4
1373 :    
1374 :     =item genomeID
1375 :    
1376 :     ID of the genome from which the best hits should be taken.
1377 :    
1378 :     =item featureList
1379 :    
1380 :     List of the features whose best hits are desired.
1381 :    
1382 :     =item RETURN
1383 :    
1384 : parrello 1.15 Returns a reference to a hash that maps the IDs of the incoming features to the best hits
1385 :     on the target genome.
1386 : parrello 1.1
1387 :     =back
1388 :    
1389 :     =cut
1390 : parrello 1.3 #: Return Type %;
1391 : parrello 1.1 sub BBHList {
1392 : parrello 1.15 # Get the parameters.
1393 :     my ($self, $genomeID, $featureList) = @_;
1394 :     # Create the return structure.
1395 :     my %retVal = ();
1396 :     # Loop through the incoming features.
1397 :     for my $featureID (@{$featureList}) {
1398 :     # Create a query to get the feature's best hit.
1399 :     my $query = $self->Get(['IsBidirectionalBestHitOf'],
1400 :     "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1401 :     [$featureID, $genomeID]);
1402 : parrello 1.40 # Peel off the BBHs found.
1403 :     my @found = ();
1404 :     while (my $bbh = $query->Fetch) {
1405 :     push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
1406 : parrello 1.15 }
1407 : parrello 1.40 $retVal{$featureID} = \@found;
1408 : parrello 1.15 }
1409 :     # Return the mapping.
1410 :     return \%retVal;
1411 :     }
1412 :    
1413 :     =head3 SimList
1414 :    
1415 :     C<< my %similarities = $sprout->SimList($featureID, $count); >>
1416 :    
1417 :     Return a list of the similarities to the specified feature.
1418 :    
1419 :     Sprout does not support real similarities, so this method just returns the bidirectional
1420 :     best hits.
1421 :    
1422 :     =over 4
1423 :    
1424 :     =item featureID
1425 :    
1426 :     ID of the feature whose similarities are desired.
1427 :    
1428 :     =item count
1429 :    
1430 :     Maximum number of similar features to be returned, or C<0> to return them all.
1431 :    
1432 :     =back
1433 :    
1434 :     =cut
1435 :     #: Return Type %;
1436 :     sub SimList {
1437 :     # Get the parameters.
1438 :     my ($self, $featureID, $count) = @_;
1439 :     # Ask for the best hits.
1440 :     my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1441 :     "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1442 :     [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1443 :     $count);
1444 :     # Create the return value.
1445 :     my %retVal = ();
1446 :     for my $tuple (@lists) {
1447 :     $retVal{$tuple->[0]} = $tuple->[1];
1448 :     }
1449 :     # Return the result.
1450 :     return %retVal;
1451 :     }
1452 :    
1453 :    
1454 :    
1455 :     =head3 IsComplete
1456 :    
1457 :     C<< my $flag = $sprout->IsComplete($genomeID); >>
1458 :    
1459 :     Return TRUE if the specified genome is complete, else FALSE.
1460 :    
1461 :     =over 4
1462 :    
1463 :     =item genomeID
1464 :    
1465 :     ID of the genome whose completeness status is desired.
1466 :    
1467 :     =item RETURN
1468 :    
1469 :     Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1470 :     not found.
1471 :    
1472 :     =back
1473 :    
1474 :     =cut
1475 :     #: Return Type $;
1476 :     sub IsComplete {
1477 :     # Get the parameters.
1478 :     my ($self, $genomeID) = @_;
1479 :     # Declare the return variable.
1480 :     my $retVal;
1481 :     # Get the genome's data.
1482 :     my $genomeData = $self->GetEntity('Genome', $genomeID);
1483 :     if ($genomeData) {
1484 :     # The genome exists, so get the completeness flag.
1485 : parrello 1.51 ($retVal) = $genomeData->Value('Genome(complete)');
1486 : parrello 1.15 }
1487 :     # Return the result.
1488 :     return $retVal;
1489 : parrello 1.1 }
1490 :    
1491 :     =head3 FeatureAliases
1492 :    
1493 :     C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
1494 :    
1495 :     Return a list of the aliases for a specified feature.
1496 :    
1497 :     =over 4
1498 :    
1499 :     =item featureID
1500 :    
1501 :     ID of the feature whose aliases are desired.
1502 :    
1503 :     =item RETURN
1504 :    
1505 :     Returns a list of the feature's aliases. If the feature is not found or has no aliases, it will
1506 :     return an empty list.
1507 :    
1508 :     =back
1509 :    
1510 :     =cut
1511 : parrello 1.3 #: Return Type @;
1512 : parrello 1.1 sub FeatureAliases {
1513 : parrello 1.15 # Get the parameters.
1514 :     my ($self, $featureID) = @_;
1515 :     # Get the desired feature's aliases
1516 :     my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);
1517 :     # Return the result.
1518 :     return @retVal;
1519 : parrello 1.1 }
1520 :    
1521 :     =head3 GenomeOf
1522 :    
1523 :     C<< my $genomeID = $sprout->GenomeOf($featureID); >>
1524 :    
1525 :     Return the genome that contains a specified feature.
1526 :    
1527 :     =over 4
1528 :    
1529 :     =item featureID
1530 :    
1531 :     ID of the feature whose genome is desired.
1532 :    
1533 :     =item RETURN
1534 :    
1535 :     Returns the ID of the genome for the specified feature. If the feature is not found, returns
1536 :     an undefined value.
1537 :    
1538 :     =back
1539 :    
1540 :     =cut
1541 : parrello 1.3 #: Return Type $;
1542 : parrello 1.1 sub GenomeOf {
1543 : parrello 1.15 # Get the parameters.
1544 :     my ($self, $featureID) = @_;
1545 :     # Create a query to find the genome associated with the feature.
1546 :     my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);
1547 :     # Declare the return value.
1548 :     my $retVal;
1549 :     # Get the genome ID.
1550 :     if (my $relationship = $query->Fetch()) {
1551 :     ($retVal) = $relationship->Value('HasContig(from-link)');
1552 :     }
1553 :     # Return the value found.
1554 :     return $retVal;
1555 : parrello 1.1 }
1556 :    
1557 :     =head3 CoupledFeatures
1558 :    
1559 :     C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>
1560 :    
1561 :     Return the features functionally coupled with a specified feature. Features are considered
1562 :     functionally coupled if they tend to be clustered on the same chromosome.
1563 :    
1564 :     =over 4
1565 :    
1566 :     =item featureID
1567 :    
1568 :     ID of the feature whose functionally-coupled brethren are desired.
1569 :    
1570 :     =item RETURN
1571 :    
1572 :     A hash mapping the functionally-coupled feature IDs to the coupling score.
1573 :    
1574 :     =back
1575 :    
1576 :     =cut
1577 : parrello 1.3 #: Return Type %;
1578 : parrello 1.1 sub CoupledFeatures {
1579 : parrello 1.15 # Get the parameters.
1580 :     my ($self, $featureID) = @_;
1581 :     # Create a query to retrieve the functionally-coupled features.
1582 :     my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1583 :     "ParticipatesInCoupling(from-link) = ?", [$featureID]);
1584 :     # This value will be set to TRUE if we find at least one coupled feature.
1585 :     my $found = 0;
1586 :     # Create the return hash.
1587 :     my %retVal = ();
1588 :     # Retrieve the relationship records and store them in the hash.
1589 :     while (my $clustering = $query->Fetch()) {
1590 :     # Get the ID and score of the coupling.
1591 :     my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1592 :     'Coupling(score)']);
1593 :     # The coupling ID contains the two feature IDs separated by a space. We use
1594 :     # this information to find the ID of the other feature.
1595 :     my ($fid1, $fid2) = split / /, $couplingID;
1596 :     my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1597 :     # Attach the other feature's score to its ID.
1598 :     $retVal{$otherFeatureID} = $score;
1599 :     $found = 1;
1600 :     }
1601 :     # Functional coupling is reflexive. If we found at least one coupled feature, we must add
1602 :     # the incoming feature as well.
1603 :     if ($found) {
1604 :     $retVal{$featureID} = 9999;
1605 :     }
1606 :     # Return the hash.
1607 :     return %retVal;
1608 :     }
1609 :    
1610 :     =head3 CouplingEvidence
1611 :    
1612 :     C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1613 :    
1614 :     Return the evidence for a functional coupling.
1615 :    
1616 :     A pair of features is considered evidence of a coupling between two other
1617 :     features if they occur close together on a contig and both are similar to
1618 :     the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1619 :     B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1620 :     B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1621 :     similar to B<A2>.
1622 :    
1623 :     The score of a coupling is determined by the number of pieces of evidence
1624 :     that are considered I<representative>. If several evidence items belong to
1625 :     a group of genomes that are close to each other, only one of those items
1626 :     is considered representative. The other evidence items are presumed to be
1627 :     there because of the relationship between the genomes rather than because
1628 :     the two proteins generated by the features have a related functionality.
1629 :    
1630 :     Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1631 :     I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1632 :     is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1633 :     and FALSE otherwise.
1634 :    
1635 :     =over 4
1636 :    
1637 :     =item peg1
1638 :    
1639 :     ID of the feature of interest.
1640 :    
1641 :     =item peg2
1642 :    
1643 :     ID of a feature functionally coupled to the feature of interest.
1644 :    
1645 :     =item RETURN
1646 :    
1647 :     Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1648 :     of interest, a feature similar to the functionally coupled feature, and a flag
1649 :     that is TRUE for a representative piece of evidence and FALSE otherwise.
1650 :    
1651 :     =back
1652 :    
1653 :     =cut
1654 :     #: Return Type @@;
1655 :     sub CouplingEvidence {
1656 :     # Get the parameters.
1657 :     my ($self, $peg1, $peg2) = @_;
1658 :     # Declare the return variable.
1659 :     my @retVal = ();
1660 : parrello 1.18 # Our first task is to find out the nature of the coupling: whether or not
1661 :     # it exists, its score, and whether the features are stored in the same
1662 :     # order as the ones coming in.
1663 : parrello 1.15 my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1664 :     # Only proceed if a coupling exists.
1665 :     if ($couplingID) {
1666 :     # Determine the ordering to place on the evidence items. If we're
1667 : parrello 1.18 # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1668 :     # we want feature 1 before feature 2 (normal).
1669 : parrello 1.21 Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1670 : parrello 1.15 my $ordering = ($inverted ? "DESC" : "");
1671 :     # Get the coupling evidence.
1672 :     my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1673 :     "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1674 :     [$couplingID],
1675 : overbeek 1.17 ['PCH(used)', 'UsesAsEvidence(to-link)']);
1676 : parrello 1.15 # Loop through the evidence items. Each piece of evidence is represented by two
1677 :     # positions in the evidence list, one for each feature on the other side of the
1678 :     # evidence link. If at some point we want to generalize to couplings with
1679 :     # more than two positions, this section of code will need to be re-done.
1680 :     while (@evidenceList > 0) {
1681 :     my $peg1Data = shift @evidenceList;
1682 :     my $peg2Data = shift @evidenceList;
1683 : parrello 1.21 Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1684 : parrello 1.15 push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1685 :     }
1686 : parrello 1.22 Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1687 : parrello 1.1 }
1688 : parrello 1.15 # Return the result.
1689 :     return @retVal;
1690 :     }
1691 :    
1692 :     =head3 GetCoupling
1693 :    
1694 :     C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1695 :    
1696 :     Return the coupling (if any) for the specified pair of PEGs. If a coupling
1697 :     exists, we return the coupling ID along with an indicator of whether the
1698 :     coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1699 :     In the second case, we say the coupling is I<inverted>. The importance of an
1700 :     inverted coupling is that the PEGs in the evidence will appear in reverse order.
1701 :    
1702 :     =over 4
1703 :    
1704 :     =item peg1
1705 :    
1706 :     ID of the feature of interest.
1707 :    
1708 :     =item peg2
1709 :    
1710 :     ID of the potentially coupled feature.
1711 :    
1712 :     =item RETURN
1713 :    
1714 :     Returns a three-element list. The first element contains the database ID of
1715 :     the coupling. The second element is FALSE if the coupling is stored in the
1716 :     database in the caller specified order and TRUE if it is stored in the
1717 :     inverted order. The third element is the coupling's score. If the coupling
1718 :     does not exist, all three list elements will be C<undef>.
1719 :    
1720 :     =back
1721 :    
1722 :     =cut
1723 :     #: Return Type $%@;
1724 :     sub GetCoupling {
1725 :     # Get the parameters.
1726 :     my ($self, $peg1, $peg2) = @_;
1727 :     # Declare the return values. We'll start with the coupling ID and undefine the
1728 :     # flag and score until we have more information.
1729 :     my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1730 :     # Find the coupling data.
1731 :     my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1732 :     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1733 : overbeek 1.17 [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1734 : parrello 1.15 # Check to see if we found anything.
1735 :     if (!@pegs) {
1736 : parrello 1.23 Trace("No coupling found.") if T(Coupling => 4);
1737 : parrello 1.15 # No coupling, so undefine the return value.
1738 :     $retVal = undef;
1739 :     } else {
1740 :     # We have a coupling! Get the score and check for inversion.
1741 :     $score = $pegs[0]->[1];
1742 : parrello 1.23 my $firstFound = $pegs[0]->[0];
1743 :     $inverted = ($firstFound ne $peg1);
1744 :     Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1745 : parrello 1.15 }
1746 :     # Return the result.
1747 :     return ($retVal, $inverted, $score);
1748 :     }
1749 :    
1750 :     =head3 CouplingID
1751 :    
1752 :     C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1753 :    
1754 :     Return the coupling ID for a pair of feature IDs.
1755 :    
1756 :     The coupling ID is currently computed by joining the feature IDs in
1757 :     sorted order with a space. Client modules (that is, modules which
1758 :     use Sprout) should not, however, count on this always being the
1759 :     case. This method provides a way for abstracting the concept of a
1760 :     coupling ID. All that we know for sure about it is that it can be
1761 :     generated easily from the feature IDs and the order of the IDs
1762 :     in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1763 :     will have the same value as C<CouplingID("b1", "a1")>.
1764 :    
1765 :     =over 4
1766 :    
1767 :     =item peg1
1768 :    
1769 :     First feature of interest.
1770 :    
1771 :     =item peg2
1772 :    
1773 :     Second feature of interest.
1774 :    
1775 :     =item RETURN
1776 :    
1777 :     Returns the ID that would be used to represent a functional coupling of
1778 :     the two specified PEGs.
1779 :    
1780 :     =back
1781 :    
1782 :     =cut
1783 :     #: Return Type $;
1784 :     sub CouplingID {
1785 :     return join " ", sort @_;
1786 : parrello 1.1 }
1787 :    
1788 :     =head3 GetEntityTypes
1789 :    
1790 :     C<< my @entityList = $sprout->GetEntityTypes(); >>
1791 :    
1792 :     Return the list of supported entity types.
1793 :    
1794 :     =cut
1795 : parrello 1.3 #: Return Type @;
1796 : parrello 1.1 sub GetEntityTypes {
1797 : parrello 1.15 # Get the parameters.
1798 :     my ($self) = @_;
1799 :     # Get the underlying database object.
1800 :     my $erdb = $self->{_erdb};
1801 :     # Get its entity type list.
1802 :     my @retVal = $erdb->GetEntityTypes();
1803 : parrello 1.1 }
1804 :    
1805 :     =head3 ReadFasta
1806 :    
1807 :     C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>
1808 :    
1809 :     Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
1810 :     one or more lines of data. The first line begins with a > character and contains an ID.
1811 :     The remaining lines contain the sequence data in order.
1812 :    
1813 :     =over 4
1814 :    
1815 :     =item fileName
1816 :    
1817 :     Name of the FASTA file.
1818 :    
1819 :     =item prefix (optional)
1820 :    
1821 :     Prefix to be put in front of each ID found.
1822 :    
1823 :     =item RETURN
1824 :    
1825 :     Returns a hash that maps each ID to its sequence.
1826 :    
1827 :     =back
1828 :    
1829 :     =cut
1830 : parrello 1.3 #: Return Type %;
1831 : parrello 1.1 sub ReadFasta {
1832 : parrello 1.15 # Get the parameters.
1833 :     my ($fileName, $prefix) = @_;
1834 :     # Create the return hash.
1835 :     my %retVal = ();
1836 :     # Open the file for input.
1837 :     open FASTAFILE, '<', $fileName;
1838 :     # Declare the ID variable and clear the sequence accumulator.
1839 :     my $sequence = "";
1840 :     my $id = "";
1841 :     # Loop through the file.
1842 :     while (<FASTAFILE>) {
1843 :     # Get the current line.
1844 :     my $line = $_;
1845 :     # Check for a header line.
1846 :     if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1847 :     # Here we have a new header. Store the current sequence if we have one.
1848 :     if ($id) {
1849 : parrello 1.24 $retVal{$id} = lc $sequence;
1850 : parrello 1.15 }
1851 :     # Clear the sequence accumulator and save the new ID.
1852 :     ($id, $sequence) = ("$prefix$1", "");
1853 :     } else {
1854 :     # Here we have a data line, so we add it to the sequence accumulator.
1855 : parrello 1.24 # First, we get the actual data out. Note that we normalize to lower
1856 : parrello 1.15 # case.
1857 :     $line =~ /^\s*(.*?)(\s|\n)/;
1858 :     $sequence .= $1;
1859 :     }
1860 :     }
1861 :     # Flush out the last sequence (if any).
1862 :     if ($sequence) {
1863 : parrello 1.24 $retVal{$id} = lc $sequence;
1864 : parrello 1.15 }
1865 :     # Close the file.
1866 :     close FASTAFILE;
1867 :     # Return the hash constructed from the file.
1868 :     return %retVal;
1869 : parrello 1.1 }
1870 :    
1871 :     =head3 FormatLocations
1872 :    
1873 :     C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>
1874 :    
1875 :     Insure that a list of feature locations is in the Sprout format. The Sprout feature location
1876 :     format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward
1877 : parrello 1.10 gene. The old format is I<contig>_I<beg>_I<end>. If a feature is in the new format already,
1878 : parrello 1.19 it will not be changed; otherwise, it will be converted. This method can also be used to
1879 : parrello 1.10 perform the reverse task-- insuring that all the locations are in the old format.
1880 : parrello 1.1
1881 :     =over 4
1882 :    
1883 :     =item prefix
1884 :    
1885 :     Prefix to be put in front of each contig ID (or an empty string if the contig ID should not
1886 :     be changed.
1887 :    
1888 :     =item locations
1889 :    
1890 :     List of locations to be normalized.
1891 :    
1892 :     =item oldFormat
1893 :    
1894 :     TRUE to convert the locations to the old format, else FALSE
1895 :    
1896 :     =item RETURN
1897 :    
1898 :     Returns a list of updated location descriptors.
1899 :    
1900 :     =back
1901 :    
1902 :     =cut
1903 : parrello 1.3 #: Return Type @;
1904 : parrello 1.1 sub FormatLocations {
1905 : parrello 1.15 # Get the parameters.
1906 :     my ($self, $prefix, $locations, $oldFormat) = @_;
1907 :     # Create the return list.
1908 :     my @retVal = ();
1909 :     # Check to see if any locations were passed in.
1910 :     if ($locations eq '') {
1911 :     Confess("No locations specified.");
1912 :     } else {
1913 :     # Loop through the locations, converting them to the new format.
1914 :     for my $location (@{$locations}) {
1915 :     # Parse the location elements.
1916 :     my ($contig, $beg, $dir, $len) = ParseLocation($location);
1917 :     # Process according to the desired output format.
1918 :     if (!$oldFormat) {
1919 :     # Here we're producing the new format. Add the location to the return list.
1920 :     push @retVal, "$prefix${contig}_$beg$dir$len";
1921 :     } elsif ($dir eq '+') {
1922 :     # Here we're producing the old format and it's a forward gene.
1923 :     my $end = $beg + $len - 1;
1924 :     push @retVal, "$prefix${contig}_${beg}_$end";
1925 :     } else {
1926 :     # Here we're producting the old format and it's a backward gene.
1927 :     my $end = $beg - $len + 1;
1928 :     push @retVal, "$prefix${contig}_${beg}_$end";
1929 :     }
1930 :     }
1931 :     }
1932 :     # Return the normalized list.
1933 :     return @retVal;
1934 : parrello 1.1 }
1935 :    
1936 :     =head3 DumpData
1937 :    
1938 :     C<< $sprout->DumpData(); >>
1939 :    
1940 :     Dump all the tables to tab-delimited DTX files. The files will be stored in the data directory.
1941 :    
1942 :     =cut
1943 :    
1944 :     sub DumpData {
1945 : parrello 1.15 # Get the parameters.
1946 :     my ($self) = @_;
1947 :     # Get the data directory name.
1948 :     my $outputDirectory = $self->{_options}->{dataDir};
1949 :     # Dump the relations.
1950 :     $self->{_erdb}->DumpRelations($outputDirectory);
1951 : parrello 1.1 }
1952 :    
1953 :     =head3 XMLFileName
1954 :    
1955 :     C<< my $fileName = $sprout->XMLFileName(); >>
1956 :    
1957 :     Return the name of this database's XML definition file.
1958 :    
1959 :     =cut
1960 : parrello 1.3 #: Return Type $;
1961 : parrello 1.1 sub XMLFileName {
1962 : parrello 1.15 my ($self) = @_;
1963 :     return $self->{_xmlName};
1964 : parrello 1.1 }
1965 :    
1966 :     =head3 Insert
1967 :    
1968 :     C<< $sprout->Insert($objectType, \%fieldHash); >>
1969 :    
1970 :     Insert an entity or relationship instance into the database. The entity or relationship of interest
1971 :     is defined by a type name and then a hash of field names to values. Field values in the primary
1972 :     relation are represented by scalars. (Note that for relationships, the primary relation is
1973 :     the B<only> relation.) Field values for the other relations comprising the entity are always
1974 :     list references. For example, the following line inserts an inactive PEG feature named
1975 :     C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.
1976 :    
1977 :     C<< $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>
1978 :    
1979 :     The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
1980 :     property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
1981 :    
1982 : parrello 1.15 C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1983 : parrello 1.1
1984 :     =over 4
1985 :    
1986 :     =item newObjectType
1987 :    
1988 :     Type name of the entity or relationship to insert.
1989 :    
1990 :     =item fieldHash
1991 :    
1992 :     Hash of field names to values.
1993 :    
1994 :     =back
1995 :    
1996 :     =cut
1997 : parrello 1.3 #: Return Type ;
1998 : parrello 1.1 sub Insert {
1999 : parrello 1.15 # Get the parameters.
2000 :     my ($self, $objectType, $fieldHash) = @_;
2001 :     # Call the underlying method.
2002 :     $self->{_erdb}->InsertObject($objectType, $fieldHash);
2003 : parrello 1.1 }
2004 :    
2005 :     =head3 Annotate
2006 :    
2007 :     C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>
2008 :    
2009 :     Annotate a feature. This inserts an Annotation record into the database and links it to the
2010 :     specified feature and user.
2011 :    
2012 :     =over 4
2013 :    
2014 :     =item fid
2015 :    
2016 :     ID of the feature to be annotated.
2017 :    
2018 :     =item timestamp
2019 :    
2020 :     Numeric timestamp to apply to the annotation. This is concatenated to the feature ID to create the
2021 :     key.
2022 :    
2023 :     =item user
2024 :    
2025 :     ID of the user who is making the annotation.
2026 :    
2027 :     =item text
2028 :    
2029 :     Text of the annotation.
2030 :    
2031 :     =item RETURN
2032 :    
2033 :     Returns 1 if successful, 2 if an error occurred.
2034 :    
2035 :     =back
2036 :    
2037 :     =cut
2038 : parrello 1.3 #: Return Type $;
2039 : parrello 1.1 sub Annotate {
2040 : parrello 1.15 # Get the parameters.
2041 :     my ($self, $fid, $timestamp, $user, $text) = @_;
2042 :     # Create the annotation ID.
2043 :     my $aid = "$fid:$timestamp";
2044 :     # Insert the Annotation object.
2045 :     my $retVal = $self->Insert('Annotation', { id => $aid, time => $timestamp, annotation => $text });
2046 :     if ($retVal) {
2047 :     # Connect it to the user.
2048 :     $retVal = $self->Insert('MadeAnnotation', { 'from-link' => $user, 'to-link' => $aid });
2049 :     if ($retVal) {
2050 :     # Connect it to the feature.
2051 :     $retVal = $self->Insert('IsTargetOfAnnotation', { 'from-link' => $fid,
2052 :     'to-link' => $aid });
2053 :     }
2054 :     }
2055 :     # Return the success indicator.
2056 :     return $retVal;
2057 : parrello 1.1 }
2058 :    
2059 :     =head3 AssignFunction
2060 :    
2061 : parrello 1.11 C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>
2062 : parrello 1.1
2063 :     This method assigns a function to a feature. Functions are a special type of annotation. The general
2064 : parrello 1.11 format is described in L</ParseAssignment>.
2065 : parrello 1.1
2066 :     =over 4
2067 :    
2068 :     =item featureID
2069 :    
2070 :     ID of the feature to which the assignment is being made.
2071 :    
2072 :     =item user
2073 :    
2074 : parrello 1.11 Name of the user group making the assignment, such as C<kegg> or C<fig>.
2075 : parrello 1.1
2076 :     =item function
2077 :    
2078 :     Text of the function being assigned.
2079 :    
2080 : parrello 1.11 =item assigningUser (optional)
2081 :    
2082 :     Name of the individual user making the assignment. If omitted, defaults to the user group.
2083 :    
2084 : parrello 1.1 =item RETURN
2085 :    
2086 :     Returns 1 if successful, 0 if an error occurred.
2087 :    
2088 :     =back
2089 :    
2090 :     =cut
2091 : parrello 1.3 #: Return Type $;
2092 : parrello 1.1 sub AssignFunction {
2093 : parrello 1.15 # Get the parameters.
2094 :     my ($self, $featureID, $user, $function, $assigningUser) = @_;
2095 : parrello 1.11 # Default the assigning user.
2096 :     if (! $assigningUser) {
2097 :     $assigningUser = $user;
2098 :     }
2099 : parrello 1.15 # Create an annotation string from the parameters.
2100 :     my $annotationText = "$assigningUser\nset $user function to\n$function";
2101 :     # Get the current time.
2102 :     my $now = time;
2103 :     # Declare the return variable.
2104 :     my $retVal = 1;
2105 :     # Locate the genome containing the feature.
2106 :     my $genome = $self->GenomeOf($featureID);
2107 :     if (!$genome) {
2108 :     # Here the genome was not found. This probably means the feature ID is invalid.
2109 :     Trace("No genome found for feature $featureID.") if T(0);
2110 :     $retVal = 0;
2111 :     } else {
2112 :     # Here we know we have a feature with a genome. Store the annotation.
2113 : parrello 1.5 $retVal = $self->Annotate($featureID, $now, $user, $annotationText);
2114 : parrello 1.15 }
2115 :     # Return the success indicator.
2116 :     return $retVal;
2117 : parrello 1.1 }
2118 :    
2119 :     =head3 FeaturesByAlias
2120 :    
2121 :     C<< my @features = $sprout->FeaturesByAlias($alias); >>
2122 :    
2123 :     Returns a list of features with the specified alias. The alias is parsed to determine
2124 :     the type of the alias. A string of digits is a GenBack ID and a string of exactly 6
2125 :     alphanumerics is a UniProt ID. A built-in FIG.pm method is used to analyze the alias
2126 :     string and attach the necessary prefix. If the result is a FIG ID then it is returned
2127 :     unmodified; otherwise, we look for an alias.
2128 :    
2129 :     =over 4
2130 :    
2131 :     =item alias
2132 :    
2133 :     Alias whose features are desired.
2134 :    
2135 :     =item RETURN
2136 :    
2137 :     Returns a list of the features with the given alias.
2138 :    
2139 :     =back
2140 :    
2141 :     =cut
2142 : parrello 1.3 #: Return Type @;
2143 : parrello 1.1 sub FeaturesByAlias {
2144 : parrello 1.15 # Get the parameters.
2145 :     my ($self, $alias) = @_;
2146 :     # Declare the return variable.
2147 :     my @retVal = ();
2148 :     # Parse the alias.
2149 :     my ($mappedAlias, $flag) = FIGRules::NormalizeAlias($alias);
2150 :     # If it's a FIG alias, we're done.
2151 :     if ($flag) {
2152 :     push @retVal, $mappedAlias;
2153 :     } else {
2154 :     # Here we have a non-FIG alias. Get the features with the normalized alias.
2155 :     @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');
2156 :     }
2157 :     # Return the result.
2158 :     return @retVal;
2159 : parrello 1.1 }
2160 :    
2161 :     =head3 Exists
2162 :    
2163 :     C<< my $found = $sprout->Exists($entityName, $entityID); >>
2164 :    
2165 :     Return TRUE if an entity exists, else FALSE.
2166 :    
2167 :     =over 4
2168 :    
2169 :     =item entityName
2170 :    
2171 :     Name of the entity type (e.g. C<Feature>) relevant to the existence check.
2172 :    
2173 :     =item entityID
2174 :    
2175 :     ID of the entity instance whose existence is to be checked.
2176 :    
2177 :     =item RETURN
2178 :    
2179 :     Returns TRUE if the entity instance exists, else FALSE.
2180 :    
2181 :     =back
2182 :    
2183 :     =cut
2184 : parrello 1.3 #: Return Type $;
2185 : parrello 1.1 sub Exists {
2186 : parrello 1.15 # Get the parameters.
2187 :     my ($self, $entityName, $entityID) = @_;
2188 :     # Check for the entity instance.
2189 : parrello 1.26 Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2190 : parrello 1.15 my $testInstance = $self->GetEntity($entityName, $entityID);
2191 :     # Return an existence indicator.
2192 :     my $retVal = ($testInstance ? 1 : 0);
2193 :     return $retVal;
2194 : parrello 1.1 }
2195 :    
2196 :     =head3 FeatureTranslation
2197 :    
2198 :     C<< my $translation = $sprout->FeatureTranslation($featureID); >>
2199 :    
2200 :     Return the translation of a feature.
2201 :    
2202 :     =over 4
2203 :    
2204 :     =item featureID
2205 :    
2206 :     ID of the feature whose translation is desired
2207 :    
2208 :     =item RETURN
2209 :    
2210 :     Returns the translation of the specified feature.
2211 :    
2212 :     =back
2213 :    
2214 :     =cut
2215 : parrello 1.3 #: Return Type $;
2216 : parrello 1.1 sub FeatureTranslation {
2217 : parrello 1.15 # Get the parameters.
2218 :     my ($self, $featureID) = @_;
2219 :     # Get the specified feature's translation.
2220 :     my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2221 :     return $retVal;
2222 : parrello 1.1 }
2223 :    
2224 :     =head3 Taxonomy
2225 :    
2226 :     C<< my @taxonomyList = $sprout->Taxonomy($genome); >>
2227 :    
2228 :     Return the taxonomy of the specified genome. This will be in the form of a list
2229 :     containing the various classifications in order from domain (eg. C<Bacteria>, C<Archaea>,
2230 :     or C<Eukaryote>) to sub-species. For example,
2231 :    
2232 :     C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>
2233 :    
2234 :     =over 4
2235 :    
2236 :     =item genome
2237 :    
2238 :     ID of the genome whose taxonomy is desired.
2239 :    
2240 :     =item RETURN
2241 :    
2242 :     Returns a list containing all the taxonomy classifications for the specified genome's organism.
2243 :    
2244 :     =back
2245 :    
2246 :     =cut
2247 : parrello 1.3 #: Return Type @;
2248 : parrello 1.1 sub Taxonomy {
2249 : parrello 1.15 # Get the parameters.
2250 :     my ($self, $genome) = @_;
2251 :     # Find the specified genome's taxonomy string.
2252 :     my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);
2253 :     # Declare the return variable.
2254 :     my @retVal = ();
2255 :     # If we found the genome, return its taxonomy string.
2256 :     if ($list) {
2257 :     @retVal = split /\s*;\s*/, $list;
2258 :     } else {
2259 :     Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0);
2260 :     }
2261 :     # Return the value found.
2262 :     return @retVal;
2263 : parrello 1.1 }
2264 :    
2265 :     =head3 CrudeDistance
2266 :    
2267 :     C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>
2268 :    
2269 :     Returns a crude estimate of the distance between two genomes. The distance is construed so
2270 :     that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.
2271 :    
2272 :     =over 4
2273 :    
2274 :     =item genome1
2275 :    
2276 :     ID of the first genome to compare.
2277 :    
2278 :     =item genome2
2279 :    
2280 :     ID of the second genome to compare.
2281 :    
2282 :     =item RETURN
2283 :    
2284 :     Returns a value from 0 to 1, with 0 meaning identical organisms, and 1 meaning organisms from
2285 :     different domains.
2286 :    
2287 :     =back
2288 :    
2289 :     =cut
2290 : parrello 1.3 #: Return Type $;
2291 : parrello 1.1 sub CrudeDistance {
2292 : parrello 1.15 # Get the parameters.
2293 :     my ($self, $genome1, $genome2) = @_;
2294 :     # Insure that the distance is commutative by sorting the genome IDs.
2295 :     my ($genomeA, $genomeB);
2296 :     if ($genome2 < $genome2) {
2297 :     ($genomeA, $genomeB) = ($genome1, $genome2);
2298 :     } else {
2299 :     ($genomeA, $genomeB) = ($genome2, $genome1);
2300 :     }
2301 :     my @taxA = $self->Taxonomy($genomeA);
2302 :     my @taxB = $self->Taxonomy($genomeB);
2303 :     # Initialize the distance to 1. We'll reduce it each time we find a match between the
2304 :     # taxonomies.
2305 :     my $retVal = 1.0;
2306 :     # Initialize the subtraction amount. This amount determines the distance reduction caused
2307 :     # by a mismatch at the current level.
2308 :     my $v = 0.5;
2309 :     # Loop through the taxonomies.
2310 :     for (my $i = 0; ($i < @taxA) && ($i < @taxB) && ($taxA[$i] eq $taxB[$i]); $i++) {
2311 :     $retVal -= $v;
2312 :     $v /= 2;
2313 :     }
2314 : parrello 1.1 return $retVal;
2315 :     }
2316 :    
2317 :     =head3 RoleName
2318 :    
2319 :     C<< my $roleName = $sprout->RoleName($roleID); >>
2320 :    
2321 :     Return the descriptive name of the role with the specified ID. In general, a role
2322 :     will only have a descriptive name if it is coded as an EC number.
2323 :    
2324 :     =over 4
2325 :    
2326 :     =item roleID
2327 :    
2328 :     ID of the role whose description is desired.
2329 :    
2330 :     =item RETURN
2331 :    
2332 :     Returns the descriptive name of the desired role.
2333 :    
2334 :     =back
2335 :    
2336 :     =cut
2337 : parrello 1.3 #: Return Type $;
2338 : parrello 1.1 sub RoleName {
2339 : parrello 1.15 # Get the parameters.
2340 :     my ($self, $roleID) = @_;
2341 :     # Get the specified role's name.
2342 :     my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2343 :     # Use the ID if the role has no name.
2344 :     if (!$retVal) {
2345 :     $retVal = $roleID;
2346 :     }
2347 :     # Return the name.
2348 :     return $retVal;
2349 : parrello 1.1 }
2350 :    
2351 :     =head3 RoleDiagrams
2352 :    
2353 :     C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>
2354 :    
2355 :     Return a list of the diagrams containing a specified functional role.
2356 :    
2357 :     =over 4
2358 :    
2359 :     =item roleID
2360 :    
2361 :     ID of the role whose diagrams are desired.
2362 :    
2363 :     =item RETURN
2364 :    
2365 :     Returns a list of the IDs for the diagrams that contain the specified functional role.
2366 :    
2367 :     =back
2368 :    
2369 :     =cut
2370 : parrello 1.3 #: Return Type @;
2371 : parrello 1.1 sub RoleDiagrams {
2372 : parrello 1.15 # Get the parameters.
2373 :     my ($self, $roleID) = @_;
2374 :     # Query for the diagrams.
2375 :     my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2376 :     'RoleOccursIn(to-link)');
2377 :     # Return the result.
2378 :     return @retVal;
2379 : parrello 1.1 }
2380 :    
2381 : parrello 1.19 =head3 GetProperties
2382 :    
2383 :     C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2384 :    
2385 :     Return a list of the properties with the specified characteristics.
2386 :    
2387 :     Properties are arbitrary key-value pairs associated with a feature. (At some point they
2388 :     will also be associated with genomes.) A property value is represented by a 4-tuple of
2389 :     the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2390 :    
2391 :     =over 4
2392 :    
2393 :     =item fid
2394 :    
2395 :     ID of the feature possessing the property.
2396 :    
2397 :     =item key
2398 :    
2399 :     Name or key of the property.
2400 :    
2401 :     =item value
2402 :    
2403 :     Value of the property.
2404 :    
2405 :     =item url
2406 :    
2407 :     URL of the document that indicated the property should have this particular value, or an
2408 :     empty string if no such document exists.
2409 :    
2410 :     =back
2411 :    
2412 :     The parameters act as a filter for the desired data. Any non-null parameter will
2413 :     automatically match all the tuples returned. So, specifying just the I<$fid> will
2414 :     return all the properties of the specified feature; similarly, specifying the I<$key>
2415 :     and I<$value> parameters will return all the features having the specified property
2416 :     value.
2417 :    
2418 :     A single property key can have many values, representing different ideas about the
2419 :     feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2420 :     virulent, and another may declare that it is not virulent. A query about the virulence of
2421 :     C<fig|83333.1.peg.10> would be coded as
2422 :    
2423 :     my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2424 :    
2425 :     Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2426 :     not to be filtered. The tuples returned would be
2427 :    
2428 :     ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2429 :     ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2430 :    
2431 :     =cut
2432 :     #: Return Type @@;
2433 :     sub GetProperties {
2434 :     # Get the parameters.
2435 :     my ($self, @parms) = @_;
2436 :     # Declare the return variable.
2437 :     my @retVal = ();
2438 :     # Now we need to create a WHERE clause that will get us the data we want. First,
2439 :     # we create a list of the columns containing the data for each parameter.
2440 :     my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2441 :     'Property(property-value)', 'HasProperty(evidence)');
2442 :     # Now we build the WHERE clause and the list of parameter values.
2443 :     my @where = ();
2444 :     my @values = ();
2445 :     for (my $i = 0; $i <= $#colNames; $i++) {
2446 :     my $parm = $parms[$i];
2447 :     if (defined $parm && ($parm ne '')) {
2448 :     push @where, "$colNames[$i] = ?";
2449 :     push @values, $parm;
2450 :     }
2451 :     }
2452 :     # Format the WHERE clause.
2453 :     my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2454 :     # Ask for all the propertie values with the desired characteristics.
2455 :     my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2456 :     while (my $valueObject = $query->Fetch()) {
2457 :     my @tuple = $valueObject->Values(\@colNames);
2458 :     push @retVal, \@tuple;
2459 :     }
2460 :     # Return the result.
2461 :     return @retVal;
2462 :     }
2463 :    
2464 : parrello 1.1 =head3 FeatureProperties
2465 :    
2466 :     C<< my @properties = $sprout->FeatureProperties($featureID); >>
2467 :    
2468 :     Return a list of the properties for the specified feature. Properties are key-value pairs
2469 :     that specify special characteristics of the feature. For example, a property could indicate
2470 :     that a feature is essential to the survival of the organism or that it has benign influence
2471 :     on the activities of a pathogen. Each property is returned as a triple of the form
2472 :     C<($key,$value,$url)>, where C<$key> is the property name, C<$value> is its value (commonly
2473 :     a 1 or a 0, but possibly a string or a floating-point value), and C<$url> is a string describing
2474 :     the web address or citation in which the property's value for the feature was identified.
2475 :    
2476 :     =over 4
2477 :    
2478 :     =item featureID
2479 :    
2480 :     ID of the feature whose properties are desired.
2481 :    
2482 :     =item RETURN
2483 :    
2484 :     Returns a list of triples, each triple containing the property name, its value, and a URL or
2485 :     citation.
2486 :    
2487 :     =back
2488 :    
2489 :     =cut
2490 : parrello 1.3 #: Return Type @@;
2491 : parrello 1.1 sub FeatureProperties {
2492 : parrello 1.15 # Get the parameters.
2493 :     my ($self, $featureID) = @_;
2494 :     # Get the properties.
2495 :     my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],
2496 :     ['Property(property-name)', 'Property(property-value)',
2497 :     'HasProperty(evidence)']);
2498 :     # Return the resulting list.
2499 :     return @retVal;
2500 : parrello 1.1 }
2501 :    
2502 :     =head3 DiagramName
2503 :    
2504 :     C<< my $diagramName = $sprout->DiagramName($diagramID); >>
2505 :    
2506 :     Return the descriptive name of a diagram.
2507 :    
2508 :     =over 4
2509 :    
2510 :     =item diagramID
2511 :    
2512 :     ID of the diagram whose description is desired.
2513 :    
2514 :     =item RETURN
2515 :    
2516 :     Returns the descripive name of the specified diagram.
2517 :    
2518 :     =back
2519 :    
2520 :     =cut
2521 : parrello 1.3 #: Return Type $;
2522 : parrello 1.1 sub DiagramName {
2523 : parrello 1.15 # Get the parameters.
2524 :     my ($self, $diagramID) = @_;
2525 :     # Get the specified diagram's name and return it.
2526 :     my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2527 :     return $retVal;
2528 : parrello 1.1 }
2529 :    
2530 :     =head3 MergedAnnotations
2531 :    
2532 :     C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>
2533 :    
2534 :     Returns a merged list of the annotations for the features in a list. Each annotation is
2535 :     represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
2536 :     C<$fid> is the ID of a feature, C<$timestamp> is the time at which the annotation was made,
2537 :     C<$userID> is the ID of the user who made the annotation, and C<$annotation> is the annotation
2538 :     text. The list is sorted by timestamp.
2539 :    
2540 :     =over 4
2541 :    
2542 :     =item list
2543 :    
2544 :     List of the IDs for the features whose annotations are desired.
2545 :    
2546 :     =item RETURN
2547 :    
2548 :     Returns a list of annotation descriptions sorted by the annotation time.
2549 :    
2550 :     =back
2551 :    
2552 :     =cut
2553 : parrello 1.3 #: Return Type @;
2554 : parrello 1.1 sub MergedAnnotations {
2555 : parrello 1.15 # Get the parameters.
2556 :     my ($self, $list) = @_;
2557 :     # Create a list to hold the annotation tuples found.
2558 :     my @tuples = ();
2559 :     # Loop through the features in the input list.
2560 :     for my $fid (@{$list}) {
2561 :     # Create a list of this feature's annotation tuples.
2562 :     my @newTuples = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
2563 :     "IsTargetOfAnnotation(from-link) = ?", [$fid],
2564 :     ['IsTargetOfAnnotation(from-link)', 'Annotation(time)',
2565 :     'MadeAnnotation(from-link)', 'Annotation(annotation)']);
2566 :     # Put it in the result list.
2567 :     push @tuples, @newTuples;
2568 :     }
2569 :     # Sort the result list by timestamp.
2570 :     my @retVal = sort { $a->[1] <=> $b->[1] } @tuples;
2571 : parrello 1.3 # Loop through and make the time stamps friendly.
2572 :     for my $tuple (@retVal) {
2573 :     $tuple->[1] = FriendlyTimestamp($tuple->[1]);
2574 :     }
2575 : parrello 1.15 # Return the sorted list.
2576 :     return @retVal;
2577 : parrello 1.1 }
2578 :    
2579 :     =head3 RoleNeighbors
2580 :    
2581 :     C<< my @roleList = $sprout->RoleNeighbors($roleID); >>
2582 :    
2583 :     Returns a list of the roles that occur in the same diagram as the specified role. Because
2584 :     diagrams and roles are in a many-to-many relationship with each other, the list is
2585 :     essentially the set of roles from all of the maps that contain the incoming role. Such
2586 :     roles are considered neighbors because they are used together in cellular subsystems.
2587 :    
2588 :     =over 4
2589 :    
2590 :     =item roleID
2591 :    
2592 :     ID of the role whose neighbors are desired.
2593 :    
2594 :     =item RETURN
2595 :    
2596 :     Returns a list containing the IDs of the roles that are related to the incoming role.
2597 :    
2598 :     =back
2599 :    
2600 :     =cut
2601 : parrello 1.3 #: Return Type @;
2602 : parrello 1.1 sub RoleNeighbors {
2603 : parrello 1.15 # Get the parameters.
2604 :     my ($self, $roleID) = @_;
2605 :     # Get all the diagrams containing this role.
2606 :     my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2607 :     'RoleOccursIn(to-link)');
2608 :     # Create the return list.
2609 :     my @retVal = ();
2610 :     # Loop through the diagrams.
2611 :     for my $diagramID (@diagrams) {
2612 :     # Get all the roles in this diagram.
2613 :     my @roles = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(to-link) = ?", [$diagramID],
2614 :     'RoleOccursIn(from-link)');
2615 :     # Add them to the return list.
2616 :     push @retVal, @roles;
2617 :     }
2618 :     # Merge the duplicates from the list.
2619 :     return Tracer::Merge(@retVal);
2620 : parrello 1.1 }
2621 :    
2622 :     =head3 FeatureLinks
2623 :    
2624 :     C<< my @links = $sprout->FeatureLinks($featureID); >>
2625 :    
2626 :     Return a list of the web hyperlinks associated with a feature. The web hyperlinks are
2627 :     to external websites describing either the feature itself or the organism containing it
2628 :     and are represented in raw HTML.
2629 :    
2630 :     =over 4
2631 :    
2632 :     =item featureID
2633 :    
2634 :     ID of the feature whose links are desired.
2635 :    
2636 :     =item RETURN
2637 :    
2638 :     Returns a list of the web links for this feature.
2639 :    
2640 :     =back
2641 :    
2642 :     =cut
2643 : parrello 1.3 #: Return Type @;
2644 : parrello 1.1 sub FeatureLinks {
2645 : parrello 1.15 # Get the parameters.
2646 :     my ($self, $featureID) = @_;
2647 :     # Get the feature's links.
2648 :     my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
2649 :     # Return the feature's links.
2650 :     return @retVal;
2651 : parrello 1.1 }
2652 :    
2653 :     =head3 SubsystemsOf
2654 :    
2655 :     C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2656 :    
2657 :     Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped
2658 : parrello 1.20 to the roles the feature performs.
2659 : parrello 1.1
2660 :     =over 4
2661 :    
2662 :     =item featureID
2663 :    
2664 :     ID of the feature whose subsystems are desired.
2665 :    
2666 :     =item RETURN
2667 :    
2668 : parrello 1.20 Returns a hash mapping all the feature's subsystems to a list of the feature's roles.
2669 : parrello 1.1
2670 :     =back
2671 :    
2672 :     =cut
2673 : parrello 1.20 #: Return Type %@;
2674 : parrello 1.1 sub SubsystemsOf {
2675 : parrello 1.15 # Get the parameters.
2676 :     my ($self, $featureID) = @_;
2677 : parrello 1.16 # Get the subsystem list.
2678 : parrello 1.15 my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2679 :     "ContainsFeature(to-link) = ?", [$featureID],
2680 :     ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2681 :     # Create the return value.
2682 :     my %retVal = ();
2683 : parrello 1.42 # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2684 :     # in two spreadsheet cells.
2685 :     my %dupHash = ();
2686 : parrello 1.15 # Loop through the results, adding them to the hash.
2687 :     for my $record (@subsystems) {
2688 : parrello 1.42 # Get this subsystem and role.
2689 : parrello 1.20 my ($subsys, $role) = @{$record};
2690 : parrello 1.42 # Insure it's the first time for both.
2691 :     my $dupKey = "$subsys\n$role";
2692 :     if (! exists $dupHash{"$subsys\n$role"}) {
2693 :     $dupHash{$dupKey} = 1;
2694 : parrello 1.20 push @{$retVal{$subsys}}, $role;
2695 :     }
2696 : parrello 1.15 }
2697 :     # Return the hash.
2698 :     return %retVal;
2699 : parrello 1.1 }
2700 :    
2701 : parrello 1.16 =head3 SubsystemList
2702 :    
2703 :     C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2704 :    
2705 :     Return a list containing the names of the subsystems in which the specified
2706 :     feature participates. Unlike L</SubsystemsOf>, this method only returns the
2707 :     subsystem names, not the roles.
2708 :    
2709 :     =over 4
2710 :    
2711 :     =item featureID
2712 :    
2713 :     ID of the feature whose subsystem names are desired.
2714 :    
2715 :     =item RETURN
2716 :    
2717 :     Returns a list of the names of the subsystems in which the feature participates.
2718 :    
2719 :     =back
2720 :    
2721 :     =cut
2722 :     #: Return Type @;
2723 :     sub SubsystemList {
2724 :     # Get the parameters.
2725 :     my ($self, $featureID) = @_;
2726 :     # Get the list of names.
2727 :     my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2728 :     [$featureID], 'HasSSCell(from-link)');
2729 :     # Return the result.
2730 :     return @retVal;
2731 :     }
2732 :    
2733 : parrello 1.1 =head3 RelatedFeatures
2734 :    
2735 :     C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
2736 :    
2737 :     Return a list of the features which are bi-directional best hits of the specified feature and
2738 :     have been assigned the specified function by the specified user. If no such features exists,
2739 :     an empty list will be returned.
2740 :    
2741 :     =over 4
2742 :    
2743 :     =item featureID
2744 :    
2745 :     ID of the feature to whom the desired features are related.
2746 :    
2747 :     =item function
2748 :    
2749 :     Functional assignment (as returned by C</FunctionOf>) that is used to determine which related
2750 :     features should be selected.
2751 :    
2752 :     =item userID
2753 :    
2754 :     ID of the user whose functional assignments are to be used. If omitted, C<FIG> is assumed.
2755 :    
2756 :     =item RETURN
2757 :    
2758 :     Returns a list of the related features with the specified function.
2759 :    
2760 :     =back
2761 :    
2762 :     =cut
2763 : parrello 1.3 #: Return Type @;
2764 : parrello 1.1 sub RelatedFeatures {
2765 : parrello 1.15 # Get the parameters.
2766 :     my ($self, $featureID, $function, $userID) = @_;
2767 :     # Get a list of the features that are BBHs of the incoming feature.
2768 :     my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],
2769 :     "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],
2770 :     'IsBidirectionalBestHitOf(to-link)');
2771 :     # Now we loop through the features, pulling out the ones that have the correct
2772 :     # functional assignment.
2773 :     my @retVal = ();
2774 :     for my $bbhFeature (@bbhFeatures) {
2775 :     # Get this feature's functional assignment.
2776 :     my $newFunction = $self->FunctionOf($bbhFeature, $userID);
2777 :     # If it matches, add it to the result list.
2778 :     if ($newFunction eq $function) {
2779 :     push @retVal, $bbhFeature;
2780 :     }
2781 :     }
2782 :     # Return the result list.
2783 :     return @retVal;
2784 : parrello 1.1 }
2785 :    
2786 :     =head3 TaxonomySort
2787 :    
2788 :     C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>
2789 :    
2790 :     Return a list formed by sorting the specified features by the taxonomy of the containing
2791 :     genome. This will cause genomes from similar organisms to float close to each other.
2792 :    
2793 :     This task could almost be handled by the database; however, the taxonomy string in the
2794 :     database is a text field and can't be indexed. Instead, we create a hash table that maps
2795 :     taxonomy strings to lists of features. We then process the hash table using a key sort
2796 :     and merge the feature lists together to create the output.
2797 :    
2798 :     =over 4
2799 :    
2800 :     =item $featureIDs
2801 :    
2802 :     List of features to be taxonomically sorted.
2803 :    
2804 :     =item RETURN
2805 :    
2806 :     Returns the list of features sorted by the taxonomies of the containing genomes.
2807 :    
2808 :     =back
2809 :    
2810 :     =cut
2811 : parrello 1.3 #: Return Type @;
2812 : parrello 1.1 sub TaxonomySort {
2813 : parrello 1.15 # Get the parameters.
2814 :     my ($self, $featureIDs) = @_;
2815 :     # Create the working hash table.
2816 :     my %hashBuffer = ();
2817 :     # Loop through the features.
2818 :     for my $fid (@{$featureIDs}) {
2819 :     # Get the taxonomy of the feature's genome.
2820 :     my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
2821 :     [$fid], 'Genome(taxonomy)');
2822 :     # Add this feature to the hash buffer.
2823 : parrello 1.10 Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);
2824 : parrello 1.15 }
2825 :     # Sort the keys and get the elements.
2826 :     my @retVal = ();
2827 :     for my $taxon (sort keys %hashBuffer) {
2828 :     push @retVal, @{$hashBuffer{$taxon}};
2829 :     }
2830 :     # Return the result.
2831 :     return @retVal;
2832 : parrello 1.1 }
2833 :    
2834 :     =head3 GetAll
2835 :    
2836 :     C<< my @list = $sprout->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>
2837 :    
2838 :     Return a list of values taken from the objects returned by a query. The first three
2839 :     parameters correspond to the parameters of the L</Get> method. The final parameter is
2840 :     a list of the fields desired from each record found by the query. The field name
2841 :     syntax is the standard syntax used for fields in the B<ERDB> system--
2842 :     B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity
2843 :     or relationship and I<fieldName> is the name of the field.
2844 :    
2845 :     The list returned will be a list of lists. Each element of the list will contain
2846 :     the values returned for the fields specified in the fourth parameter. If one of the
2847 :     fields specified returns multiple values, they are flattened in with the rest. For
2848 :     example, the following call will return a list of the features in a particular
2849 :     spreadsheet cell, and each feature will be represented by a list containing the
2850 :     feature ID followed by all of its aliases.
2851 :    
2852 :     C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>
2853 :    
2854 :     =over 4
2855 :    
2856 :     =item objectNames
2857 :    
2858 :     List containing the names of the entity and relationship objects to be retrieved.
2859 :    
2860 :     =item filterClause
2861 :    
2862 :     WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2863 :     be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
2864 :     B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
2865 :     parameter list as additional parameters. The fields in a filter clause can come from primary
2866 :     entity relations, relationship relations, or secondary entity relations; however, all of the
2867 :     entities and relationships involved must be included in the list of object names.
2868 :    
2869 :     =item parameterList
2870 :    
2871 :     List of the parameters to be substituted in for the parameters marks in the filter clause.
2872 :    
2873 :     =item fields
2874 :    
2875 :     List of the fields to be returned in each element of the list returned.
2876 :    
2877 :     =item count
2878 :    
2879 :     Maximum number of records to return. If omitted or 0, all available records will be returned.
2880 :    
2881 :     =item RETURN
2882 :    
2883 :     Returns a list of list references. Each element of the return list contains the values for the
2884 :     fields specified in the B<fields> parameter.
2885 :    
2886 :     =back
2887 :    
2888 :     =cut
2889 : parrello 1.3 #: Return Type @@;
2890 : parrello 1.1 sub GetAll {
2891 : parrello 1.15 # Get the parameters.
2892 :     my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2893 :     # Call the ERDB method.
2894 :     my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2895 :     $fields, $count);
2896 :     # Return the resulting list.
2897 :     return @retVal;
2898 : parrello 1.1 }
2899 :    
2900 :     =head3 GetFlat
2901 :    
2902 :     C<< my @list = $sprout->GetFlat(\@objectNames, $filterClause, $parameterList, $field); >>
2903 :    
2904 :     This is a variation of L</GetAll> that asks for only a single field per record and
2905 :     returns a single flattened list.
2906 :    
2907 :     =over 4
2908 :    
2909 :     =item objectNames
2910 :    
2911 :     List containing the names of the entity and relationship objects to be retrieved.
2912 :    
2913 :     =item filterClause
2914 :    
2915 :     WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can
2916 :     be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form
2917 :     B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the
2918 :     parameter list as additional parameters. The fields in a filter clause can come from primary
2919 :     entity relations, relationship relations, or secondary entity relations; however, all of the
2920 :     entities and relationships involved must be included in the list of object names.
2921 :    
2922 :     =item parameterList
2923 :    
2924 :     List of the parameters to be substituted in for the parameters marks in the filter clause.
2925 :    
2926 :     =item field
2927 :    
2928 :     Name of the field to be used to get the elements of the list returned.
2929 :    
2930 :     =item RETURN
2931 :    
2932 :     Returns a list of values.
2933 :    
2934 :     =back
2935 :    
2936 :     =cut
2937 : parrello 1.3 #: Return Type @;
2938 : parrello 1.1 sub GetFlat {
2939 : parrello 1.15 # Get the parameters.
2940 :     my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
2941 :     # Construct the query.
2942 :     my $query = $self->Get($objectNames, $filterClause, $parameterList);
2943 :     # Create the result list.
2944 :     my @retVal = ();
2945 :     # Loop through the records, adding the field values found to the result list.
2946 :     while (my $row = $query->Fetch()) {
2947 :     push @retVal, $row->Value($field);
2948 :     }
2949 :     # Return the list created.
2950 :     return @retVal;
2951 : parrello 1.1 }
2952 :    
2953 :     =head3 Protein
2954 :    
2955 :     C<< my $protein = Sprout::Protein($sequence, $table); >>
2956 :    
2957 :     Translate a DNA sequence into a protein sequence.
2958 :    
2959 :     =over 4
2960 :    
2961 :     =item sequence
2962 :    
2963 :     DNA sequence to translate.
2964 :    
2965 :     =item table (optional)
2966 :    
2967 :     Reference to a Hash that translates DNA triples to proteins. A triple that does not
2968 :     appear in the hash will be translated automatically to C<X>.
2969 :    
2970 :     =item RETURN
2971 :    
2972 :     Returns the protein sequence that would be created by the DNA sequence.
2973 :    
2974 :     =back
2975 :    
2976 :     =cut
2977 :    
2978 :     # This is the translation table for protein synthesis.
2979 :     my $ProteinTable = { AAA => 'K', AAG => 'K', AAT => 'N', AAC => 'N',
2980 : parrello 1.15 AGA => 'R', AGG => 'R', AGT => 'S', AGC => 'S',
2981 :     ATA => 'I', ATG => 'M', ATT => 'I', ATC => 'I',
2982 :     ACA => 'T', ACG => 'T', ACT => 'T', ACC => 'T',
2983 :     GAA => 'E', GAG => 'E', GAT => 'D', GAC => 'D',
2984 :     GTA => 'V', GTG => 'V', GTT => 'V', GTC => 'V',
2985 :     GGA => 'G', GGG => 'G', GGT => 'G', GGC => 'G',
2986 :     GCA => 'A', GCG => 'A', GCT => 'A', GCC => 'A',
2987 :     CAA => 'Q', CAG => 'Q', CAT => 'H', CAC => 'H',
2988 :     CTA => 'L', CTG => 'L', CTT => 'L', CTC => 'L',
2989 :     CGA => 'R', CGG => 'R', CGT => 'R', CGC => 'R',
2990 :     CCA => 'P', CCG => 'P', CCT => 'P', CCC => 'P',
2991 :     TAA => '*', TAG => '*', TAT => 'Y', TAC => 'Y',
2992 :     TGA => '*', TGG => 'W', TGT => 'C', TGC => 'C',
2993 :     TTA => 'L', TTG => 'L', TTT => 'F', TTC => 'F',
2994 :     TCA => 'S', TCG => 'S', TCT => 'S', TCC => 'S',
2995 :     AAR => 'K', AAY => 'N',
2996 :     AGR => 'R', AGY => 'S',
2997 :     ATY => 'I',
2998 :     ACR => 'T', ACY => 'T', 'ACX' => 'T',
2999 :     GAR => 'E', GAY => 'D',
3000 :     GTR => 'V', GTY => 'V', GTX => 'V',
3001 :     GGR => 'G', GGY => 'G', GGX => 'G',
3002 :     GCR => 'A', GCY => 'A', GCX => 'A',
3003 :     CAR => 'Q', CAY => 'H',
3004 :     CTR => 'L', CTY => 'L', CTX => 'L',
3005 :     CGR => 'R', CGY => 'R', CGX => 'R',
3006 :     CCR => 'P', CCY => 'P', CCX => 'P',
3007 :     TAR => '*', TAY => 'Y',
3008 :     TGY => 'C',
3009 :     TTR => 'L', TTY => 'F',
3010 :     TCR => 'S', TCY => 'S', TCX => 'S'
3011 :     };
3012 : parrello 1.1
3013 :     sub Protein {
3014 : parrello 1.15 # Get the paraeters.
3015 :     my ($sequence, $table) = @_;
3016 :     # If no table was specified, use the default.
3017 :     if (!$table) {
3018 :     $table = $ProteinTable;
3019 :     }
3020 :     # Create the return value.
3021 :     my $retVal = "";
3022 :     # Loop through the input triples.
3023 :     my $n = length $sequence;
3024 :     for (my $i = 0; $i < $n; $i += 3) {
3025 :     # Get the current triple from the sequence.
3026 :     my $triple = substr($sequence, $i, 3);
3027 :     # Translate it using the table.
3028 :     my $protein = "X";
3029 :     if (exists $table->{$triple}) { $protein = $table->{$triple}; }
3030 :     $retVal .= $protein;
3031 :     }
3032 :     # Remove the stop codon (if any).
3033 :     $retVal =~ s/\*$//;
3034 :     # Return the result.
3035 :     return $retVal;
3036 : parrello 1.1 }
3037 :    
3038 :     =head3 LoadInfo
3039 :    
3040 :     C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>
3041 :    
3042 :     Return the name of the directory from which data is to be loaded and a list of the relation
3043 :     names. This information is useful when trying to analyze what needs to be put where in order
3044 :     to load the entire database.
3045 :    
3046 :     =cut
3047 : parrello 1.3 #: Return Type @;
3048 : parrello 1.1 sub LoadInfo {
3049 : parrello 1.15 # Get the parameters.
3050 :     my ($self) = @_;
3051 :     # Create the return list, priming it with the name of the data directory.
3052 :     my @retVal = ($self->{_options}->{dataDir});
3053 :     # Concatenate the table names.
3054 :     push @retVal, $self->{_erdb}->GetTableNames();
3055 :     # Return the result.
3056 :     return @retVal;
3057 : parrello 1.1 }
3058 :    
3059 :     =head3 LowBBHs
3060 :    
3061 :     C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>
3062 :    
3063 :     Return the bidirectional best hits of a feature whose score is no greater than a
3064 :     specified cutoff value. A higher cutoff value will allow inclusion of hits with
3065 :     a greater score. The value returned is a map of feature IDs to scores.
3066 :    
3067 :     =over 4
3068 :    
3069 :     =item featureID
3070 :    
3071 :     ID of the feature whose best hits are desired.
3072 :    
3073 :     =item cutoff
3074 :    
3075 :     Maximum permissible score for inclusion in the results.
3076 :    
3077 :     =item RETURN
3078 :    
3079 :     Returns a hash mapping feature IDs to scores.
3080 :    
3081 :     =back
3082 :    
3083 :     =cut
3084 : parrello 1.3 #: Return Type %;
3085 : parrello 1.1 sub LowBBHs {
3086 : parrello 1.15 # Get the parsameters.
3087 :     my ($self, $featureID, $cutoff) = @_;
3088 :     # Create the return hash.
3089 :     my %retVal = ();
3090 :     # Create a query to get the desired BBHs.
3091 :     my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],
3092 :     'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',
3093 :     [$cutoff, $featureID],
3094 :     ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);
3095 :     # Form the results into the return hash.
3096 :     for my $pair (@bbhList) {
3097 :     $retVal{$pair->[0]} = $pair->[1];
3098 :     }
3099 :     # Return the result.
3100 :     return %retVal;
3101 : parrello 1.1 }
3102 :    
3103 : parrello 1.7 =head3 GetGroups
3104 :    
3105 : parrello 1.8 C<< my %groups = $sprout->GetGroups(\@groupList); >>
3106 :    
3107 :     Return a hash mapping each group to the IDs of the genomes in the group.
3108 :     A list of groups may be specified, in which case only those groups will be
3109 :     shown. Alternatively, if no parameter is supplied, all groups will be
3110 :     included. Genomes that are not in any group are omitted.
3111 :    
3112 : parrello 1.7 =cut
3113 :     #: Return Type %@;
3114 :     sub GetGroups {
3115 : parrello 1.8 # Get the parameters.
3116 : parrello 1.10 my ($self, $groupList) = @_;
3117 : parrello 1.8 # Declare the return value.
3118 :     my %retVal = ();
3119 :     # Determine whether we are getting all the groups or just some.
3120 :     if (defined $groupList) {
3121 :     # Here we have a group list. Loop through them individually,
3122 :     # getting a list of the relevant genomes.
3123 :     for my $group (@{$groupList}) {
3124 :     my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",
3125 :     [$group], "Genome(id)");
3126 :     $retVal{$group} = \@genomeIDs;
3127 :     }
3128 :     } else {
3129 :     # Here we need all of the groups. In this case, we run through all
3130 :     # of the genome records, putting each one found into the appropriate
3131 :     # group. Note that we use a filter clause to insure that only genomes
3132 :     # in groups are included in the return set.
3133 :     my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],
3134 :     ['Genome(id)', 'Genome(group-name)']);
3135 :     # Loop through the genomes found.
3136 :     for my $genome (@genomes) {
3137 :     # Pop this genome's ID off the current list.
3138 :     my @groups = @{$genome};
3139 :     my $genomeID = shift @groups;
3140 :     # Loop through the groups, adding the genome ID to each group's
3141 :     # list.
3142 :     for my $group (@groups) {
3143 : parrello 1.10 Tracer::AddToListMap(\%retVal, $group, $genomeID);
3144 : parrello 1.8 }
3145 :     }
3146 :     }
3147 :     # Return the hash we just built.
3148 :     return %retVal;
3149 : parrello 1.7 }
3150 :    
3151 : parrello 1.18 =head3 MyGenomes
3152 :    
3153 :     C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3154 :    
3155 :     Return a list of the genomes to be included in the Sprout.
3156 :    
3157 :     This method is provided for use during the Sprout load. It presumes the Genome load file has
3158 :     already been created. (It will be in the Sprout data directory and called either C<Genome>
3159 :     or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3160 :     IDs.
3161 :    
3162 :     =over 4
3163 :    
3164 :     =item dataDir
3165 :    
3166 :     Directory containing the Sprout load files.
3167 :    
3168 :     =back
3169 :    
3170 :     =cut
3171 :     #: Return Type @;
3172 :     sub MyGenomes {
3173 :     # Get the parameters.
3174 :     my ($dataDir) = @_;
3175 :     # Compute the genome file name.
3176 :     my $genomeFileName = LoadFileName($dataDir, "Genome");
3177 :     # Extract the genome IDs from the files.
3178 :     my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3179 :     # Return the result.
3180 :     return @retVal;
3181 :     }
3182 :    
3183 :     =head3 LoadFileName
3184 :    
3185 :     C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3186 :    
3187 :     Return the name of the load file for the specified table in the specified data
3188 :     directory.
3189 :    
3190 :     =over 4
3191 :    
3192 :     =item dataDir
3193 :    
3194 :     Directory containing the Sprout load files.
3195 :    
3196 :     =item tableName
3197 :    
3198 :     Name of the table whose load file is desired.
3199 :    
3200 :     =item RETURN
3201 :    
3202 :     Returns the name of the file containing the load data for the specified table, or
3203 :     C<undef> if no load file is present.
3204 :    
3205 :     =back
3206 :    
3207 :     =cut
3208 :     #: Return Type $;
3209 :     sub LoadFileName {
3210 :     # Get the parameters.
3211 :     my ($dataDir, $tableName) = @_;
3212 :     # Declare the return variable.
3213 :     my $retVal;
3214 :     # Check for the various file names.
3215 :     if (-e "$dataDir/$tableName") {
3216 :     $retVal = "$dataDir/$tableName";
3217 :     } elsif (-e "$dataDir/$tableName.dtx") {
3218 :     $retVal = "$dataDir/$tableName.dtx";
3219 :     }
3220 :     # Return the result.
3221 :     return $retVal;
3222 :     }
3223 :    
3224 : parrello 1.53 =head3 DeleteGenome
3225 :    
3226 :     C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>
3227 :    
3228 :     Delete a genome from the database.
3229 :    
3230 :     =over 4
3231 :    
3232 :     =item genomeID
3233 :    
3234 :     ID of the genome to delete
3235 :    
3236 :     =item testFlag
3237 :    
3238 :     If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3239 :    
3240 :     =item RETURN
3241 :    
3242 :     Returns a statistics object describing the rows deleted.
3243 :    
3244 :     =back
3245 :    
3246 :     =cut
3247 :     #: Return Type $%;
3248 :     sub DeleteGenome {
3249 :     # Get the parameters.
3250 :     my ($self, $genomeID, $testFlag) = @_;
3251 :     # Perform the delete for the genome's features.
3252 :     my $retVal = $self->{_erdb}->Delete('Feature', "fig|$genomeID.%", $testFlag);
3253 :     # Perform the delete for the primary genome data.
3254 :     my $stats = $self->{_erdb}->Delete('Genome', $genomeID, $testFlag);
3255 :     $retVal->Accumulate($stats);
3256 :     # Return the result.
3257 :     return $retVal;
3258 :     }
3259 :    
3260 : parrello 1.1 =head2 Internal Utility Methods
3261 :    
3262 :     =head3 ParseAssignment
3263 :    
3264 :     Parse annotation text to determine whether or not it is a functional assignment. If it is,
3265 : parrello 1.19 the user, function text, and assigning user will be returned as a 3-element list. If it
3266 : parrello 1.11 isn't, an empty list will be returned.
3267 :    
3268 :     A functional assignment is always of the form
3269 :    
3270 : parrello 1.48 C<set >I<YYYY>C< function to\n>I<ZZZZZ>
3271 : parrello 1.19
3272 : parrello 1.48 where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
3273 :     the user and the assigning user (from MadeAnnotation) will be the same, but that is
3274 :     not always the case.
3275 : parrello 1.1
3276 : parrello 1.52 In addition, the functional role may contain extra data that is stripped, such as
3277 :     terminating spaces or a comment separated from the rest of the text by a tab.
3278 :    
3279 : parrello 1.1 This is a static method.
3280 :    
3281 :     =over 4
3282 :    
3283 : parrello 1.48 =item user
3284 :    
3285 :     Name of the assigning user.
3286 :    
3287 : parrello 1.1 =item text
3288 :    
3289 :     Text of the annotation.
3290 :    
3291 :     =item RETURN
3292 :    
3293 :     Returns an empty list if the annotation is not a functional assignment; otherwise, returns
3294 :     a two-element list containing the user name and the function text.
3295 :    
3296 :     =back
3297 :    
3298 :     =cut
3299 :    
3300 : parrello 1.11 sub _ParseAssignment {
3301 : parrello 1.15 # Get the parameters.
3302 : parrello 1.48 my ($user, $text) = @_;
3303 : parrello 1.15 # Declare the return value.
3304 :     my @retVal = ();
3305 :     # Check to see if this is a functional assignment.
3306 : parrello 1.43 my ($type, $function) = split(/\n/, $text);
3307 : parrello 1.48 if ($type =~ m/^set function to$/i) {
3308 :     # Here we have an assignment without a user, so we use the incoming user ID.
3309 :     @retVal = ($user, $function);
3310 :     } elsif ($type =~ m/^set (\S+) function to$/i) {
3311 : parrello 1.52 # Here we have an assignment with a user that is passed back to the caller.
3312 : parrello 1.43 @retVal = ($1, $function);
3313 : parrello 1.15 }
3314 : parrello 1.52 # If we have an assignment, we need to clean the function text. There may be
3315 :     # extra junk at the end added as a note from the user.
3316 :     if (@retVal) {
3317 :     $retVal[1] =~ s/(\t\S)?\s*$//;
3318 :     }
3319 : parrello 1.15 # Return the result list.
3320 :     return @retVal;
3321 : parrello 1.1 }
3322 :    
3323 : parrello 1.3 =head3 FriendlyTimestamp
3324 :    
3325 :     Convert a time number to a user-friendly time stamp for display.
3326 :    
3327 :     This is a static method.
3328 :    
3329 :     =over 4
3330 :    
3331 :     =item timeValue
3332 :    
3333 :     Numeric time value.
3334 :    
3335 :     =item RETURN
3336 :    
3337 :     Returns a string containing the same time in user-readable format.
3338 :    
3339 :     =back
3340 :    
3341 :     =cut
3342 :    
3343 :     sub FriendlyTimestamp {
3344 :     my ($timeValue) = @_;
3345 : parrello 1.40 my $retVal = localtime($timeValue);
3346 : parrello 1.3 return $retVal;
3347 :     }
3348 :    
3349 : parrello 1.15 =head3 AddProperty
3350 :    
3351 :     C<< my = $sprout->AddProperty($featureID, $key, $value, $url); >>
3352 :    
3353 :     Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3354 :     be added to almost any object. In Sprout, they can only be added to features. In
3355 :     Sprout, attributes are implemented using I<properties>. A property represents a key/value
3356 :     pair. If the particular key/value pair coming in is not already in the database, a new
3357 :     B<Property> record is created to hold it.
3358 :    
3359 :     =over 4
3360 :    
3361 :     =item peg
3362 :    
3363 :     ID of the feature to which the attribute is to be replied.
3364 :    
3365 :     =item key
3366 :    
3367 :     Name of the attribute (key).
3368 :    
3369 :     =item value
3370 :    
3371 :     Value of the attribute.
3372 :    
3373 :     =item url
3374 :    
3375 :     URL or text citation from which the property was obtained.
3376 :    
3377 :     =back
3378 :    
3379 :     =cut
3380 :     #: Return Type ;
3381 :     sub AddProperty {
3382 :     # Get the parameters.
3383 :     my ($self, $featureID, $key, $value, $url) = @_;
3384 :     # Declare the variable to hold the desired property ID.
3385 :     my $propID;
3386 :     # Attempt to find a property record for this key/value pair.
3387 :     my @properties = $self->GetFlat(['Property'],
3388 :     "Property(property-name) = ? AND Property(property-value) = ?",
3389 :     [$key, $value], 'Property(id)');
3390 :     if (@properties) {
3391 :     # Here the property is already in the database. We save its ID.
3392 :     $propID = $properties[0];
3393 :     # Here the property value does not exist. We need to generate an ID. It will be set
3394 :     # to a number one greater than the maximum value in the database. This call to
3395 :     # GetAll will stop after one record.
3396 :     my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3397 :     1);
3398 :     $propID = $maxProperty[0]->[0] + 1;
3399 :     # Insert the new property value.
3400 :     $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3401 :     }
3402 :     # Now we connect the incoming feature to the property.
3403 :     $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3404 :     }
3405 :    
3406 : parrello 1.51
3407 : parrello 1.48 1;

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3