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

Diff of /Sprout/Sprout.pm

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.4, Tue Jan 25 01:36:09 2005 UTC revision 1.113, Tue Aug 12 06:01:49 2008 UTC
# Line 2  Line 2 
2    
3          use Data::Dumper;          use Data::Dumper;
4          use strict;          use strict;
         use Carp;  
5          use DBKernel;          use DBKernel;
6          use XML::Simple;          use XML::Simple;
7          use DBQuery;          use DBQuery;
8          use DBObject;      use ERDBObject;
         use ERDB;  
9          use Tracer;          use Tracer;
10          use FIGRules;          use FIGRules;
11        use FidCheck;
12          use Stats;          use Stats;
13      use POSIX qw(strftime);      use POSIX qw(strftime);
14        use BasicLocation;
15        use CustomAttributes;
16        use RemoteCustomAttributes;
17        use CGI;
18        use WikiTools;
19        use base qw(ERDB);
20    
21  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
22    
# Line 25  Line 29 
29  on the constructor. For example, the following invocation specifies a PostgreSQL database named I<GenDB>  on the constructor. For example, the following invocation specifies a PostgreSQL database named I<GenDB>
30  whose definition and data files are in a co-directory named F<Data>.  whose definition and data files are in a co-directory named F<Data>.
31    
32  C<< my $sprout = Sprout->new('GenDB', { dbType => 'pg', dataDir => '../Data', xmlFileName => '../Data/SproutDBD.xml' }); >>      my $sprout = Sprout->new('GenDB', { dbType => 'pg', dataDir => '../Data', xmlFileName => '../Data/SproutDBD.xml' });
33    
34  Once you have a sprout object, you may use it to re-create the database, load the tables from  Once you have a sprout object, you may use it to re-create the database, load the tables from
35  tab-delimited flat files and perform queries. Several special methods are provided for common  tab-delimited flat files and perform queries. Several special methods are provided for common
36  query tasks. For example, L</genomes> lists the IDs of all the genomes in the database and  query tasks. For example, L</Genomes> lists the IDs of all the genomes in the database and
37  L</dna_seq> returns the DNA sequence for a specified genome location.  L</DNASeq> returns the DNA sequence for a specified genome location.
38    
39    The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.
40    
41  =cut  =cut
42    
43  #: Constructor SFXlate->new_sprout_only();  #: Constructor SFXlate->new_sprout_only();
44    
   
45  =head2 Public Methods  =head2 Public Methods
46    
47  =head3 new  =head3 new
48    
49  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
50    
51  This is the constructor for a sprout object. It connects to the database and loads the  This is the constructor for a sprout object. It connects to the database and loads the
52  database definition into memory. The positional first parameter specifies the name of the  database definition into memory. The positional first parameter specifies the name of the
# Line 63  Line 68 
68    
69  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)
70    
71  * B<userData> user name and password, delimited by a slash (default C<root/>)  * B<userData> user name and password, delimited by a slash (default same as SEED)
72    
73  * B<port> connection port (default C<0>)  * B<port> connection port (default C<0>)
74    
75    * B<sock> connection socket (default same as SEED)
76    
77  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)
78    
79  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
80    
81    * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
82    
83    * B<host> name of the database host
84    
85  =back  =back
86    
87  For example, the following constructor call specifies a database named I<Sprout> and a user name of  For example, the following constructor call specifies a database named I<Sprout> and a user name of
88  I<fig> with a password of I<admin>. The database load files are in the directory  I<fig> with a password of I<admin>. The database load files are in the directory
89  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
90    
91  C<< my $sprout = Sprout->new('Sprout', { userData =>; 'fig/admin', dataDir => '/usr/fig/SproutData' }); >>      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });
92    
93  =cut  =cut
94    
95  sub new {  sub new {
96          # Get the parameters.          # Get the parameters.
97          my ($class, $dbName, $options) = @_;          my ($class, $dbName, $options) = @_;
98        # Compute the DBD directory.
99        my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
100                                                      $FIG_Config::fig );
101          # Compute the options. We do this by starting with a table of defaults and overwriting with          # Compute the options. We do this by starting with a table of defaults and overwriting with
102          # the incoming data.          # the incoming data.
103          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
104                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
105                                             dataDir              => 'Data',                      # data file directory                                                          # database type
106                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
107                                             userData             => 'root/',                     # user name and password                                                          # data file directory
108                                             port                 => 0,                           # database connection port                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
109                                                            # database definition file name
110                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
111                                                            # user name and password
112                           port         => $FIG_Config::dbport,
113                                                            # database connection port
114                           sock         => $FIG_Config::dbsock,
115                           host         => $FIG_Config::sprout_host,
116                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
117                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
118                           noDBOpen     => 0,               # 1 to suppress the database open
119                                            }, $options);                                            }, $options);
120          # Get the data directory.          # Get the data directory.
121          my $dataDir = $optionTable->{dataDir};          my $dataDir = $optionTable->{dataDir};
# Line 101  Line 123 
123          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
124          my ($userName, $password) = ($1, $2);          my ($userName, $password) = ($1, $2);
125          # Connect to the database.          # Connect to the database.
126          my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
127        if (! $optionTable->{noDBOpen}) {
128            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
129            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
130                                    $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
131        }
132          # Create the ERDB object.          # Create the ERDB object.
133          my $xmlFileName = "$optionTable->{xmlFileName}";          my $xmlFileName = "$optionTable->{xmlFileName}";
134          my $erdb = ERDB->new($dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName);
135          # Create this object.      # Add the option table and XML file name.
136          my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName };      $retVal->{_options} = $optionTable;
137          # Bless and return it.      $retVal->{_xmlName} = $xmlFileName;
138          bless $self;      # Set up space for the group file data.
139          return $self;      $retVal->{groupHash} = undef;
140        # Set up space for the genome hash. We use this to identify NMPDR genomes.
141        $retVal->{genomeHash} = undef;
142        # Connect to the attributes.
143        if ($FIG_Config::attrURL) {
144            Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
145            $retVal->{_ca} = RemoteCustomAttributes->new($FIG_Config::attrURL);
146        } elsif ($FIG_Config::attrDbName) {
147            Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
148            my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
149            $retVal->{_ca} = CustomAttributes->new(user => $user);
150        }
151        # Insure we have access to the stem module.
152        WikiUse('Lingua::Stem');
153        $retVal->{stemmer} = Lingua::Stem->new();
154        $retVal->{stemmer}->stem_caching({ -level => 2 });
155        # Return it.
156        return $retVal;
157    }
158    
159    =head3 CoreGenomes
160    
161        my @genomes = $sprout->CoreGenomes($scope);
162    
163    Return the IDs of NMPDR genomes in the specified scope.
164    
165    =over 4
166    
167    =item scope
168    
169    Scope of the desired genomes. C<core> covers the original core genomes,
170    C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
171    genomes in the system.
172    
173    =item RETURN
174    
175    Returns a list of the IDs for the genomes in the specified scope.
176    
177    =back
178    
179    =cut
180    
181    sub CoreGenomes {
182        # Get the parameters.
183        my ($self, $scope) = @_;
184        # Declare the return variable.
185        my @retVal = ();
186        # If we want all genomes, then this is easy.
187        if ($scope eq 'all') {
188            @retVal = $self->Genomes();
189        } else {
190            # Here we're dealing with groups. Get the hash of all the
191            # genome groups.
192            my %groups = $self->GetGroups();
193            # Loop through the groups, keeping the ones that we want.
194            for my $group (keys %groups) {
195                # Decide if we want to keep this group.
196                my $keepGroup = 0;
197                if ($scope eq 'nmpdr') {
198                    # NMPDR mode: keep all groups.
199                    $keepGroup = 1;
200                } elsif ($scope eq 'core') {
201                    # CORE mode. Only keep real core groups.
202                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
203                        $keepGroup = 1;
204                    }
205                }
206                # Add this group if we're keeping it.
207                if ($keepGroup) {
208                    push @retVal, @{$groups{$group}};
209                }
210            }
211        }
212        # Return the result.
213        return @retVal;
214    }
215    
216    =head3 SuperGroup
217    
218        my $superGroup = $sprout->SuperGroup($groupName);
219    
220    Return the name of the super-group containing the specified NMPDR genome
221    group. If no appropriate super-group can be found, an error will be
222    thrown.
223    
224    =over 4
225    
226    =item groupName
227    
228    Name of the group whose super-group is desired.
229    
230    =item RETURN
231    
232    Returns the name of the super-group containing the incoming group.
233    
234    =back
235    
236    =cut
237    
238    sub SuperGroup {
239        # Get the parameters.
240        my ($self, $groupName) = @_;
241        # Declare the return variable.
242        my $retVal;
243        # Get the group hash.
244        my %groupHash = $self->CheckGroupFile();
245        # Find the super-group genus.
246        $groupName =~ /([A-Z]\w+)/;
247        my $nameThing = $1;
248        # See if it's directly in the group hash.
249        if (exists $groupHash{$nameThing}) {
250            # Yes, then it's our result.
251            $retVal = $nameThing;
252        } else {
253            # No, so we have to search.
254            for my $superGroup (keys %groupHash) {
255                # Get this super-group's item list.
256                my $list = $groupHash{$superGroup}->{contents};
257                # Search it.
258                if (grep { $_->[0] eq $nameThing } @{$list}) {
259                    $retVal = $superGroup;
260                }
261            }
262            # Make sure we found something.
263            if (! $retVal) {
264                Confess("No super-group found for \"$groupName\".");
265            }
266        }
267        # Return the result.
268        return $retVal;
269  }  }
270    
271  =head3 MaxSegment  =head3 MaxSegment
272    
273  C<< my $length = $sprout->MaxSegment(); >>      my $length = $sprout->MaxSegment();
274    
275  This method returns the maximum permissible length of a feature segment. The length is important  This method returns the maximum permissible length of a feature segment. The length is important
276  because it enables us to make reasonable guesses at how to find features inside a particular  because it enables us to make reasonable guesses at how to find features inside a particular
# Line 125  Line 281 
281  =cut  =cut
282  #: Return Type $;  #: Return Type $;
283  sub MaxSegment {  sub MaxSegment {
284          my $self = shift @_;      my ($self) = @_;
285          return $self->{_options}->{maxSegmentLength};          return $self->{_options}->{maxSegmentLength};
286  }  }
287    
288  =head3 MaxSequence  =head3 MaxSequence
289    
290  C<< my $length = $sprout->MaxSequence(); >>      my $length = $sprout->MaxSequence();
291    
292  This method returns the maximum permissible length of a contig sequence. A contig is broken  This method returns the maximum permissible length of a contig sequence. A contig is broken
293  into sequences in order to save memory resources. In particular, when manipulating features,  into sequences in order to save memory resources. In particular, when manipulating features,
# Line 140  Line 296 
296  =cut  =cut
297  #: Return Type $;  #: Return Type $;
298  sub MaxSequence {  sub MaxSequence {
299          my $self = shift @_;      my ($self) = @_;
300          return $self->{_options}->{maxSequenceLength};          return $self->{_options}->{maxSequenceLength};
301  }  }
302    
303  =head3 Get  =head3 Load
   
 C<< my $query = $sprout->Get(\@objectNames, $filterClause, \@parameterList); >>  
   
 This method allows a general query against the Sprout data using a specified filter clause.  
   
 The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each  
 field name represented in the form B<I<objectName>(I<fieldName>)>. For example, the  
 following call requests all B<Genome> objects for the genus specified in the variable  
 $genus.  
304    
305  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>      $sprout->Load($rebuild);;
306    
307  The WHERE clause contains a single question mark, so there is a single additional  Load the database from files in the data directory, optionally re-creating the tables.
 parameter representing the parameter value. It would also be possible to code  
308    
309  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  This method always deletes the data from the database before loading, even if the tables are not
310    re-created. The data is loaded into the relations from files in the data directory either having the
311    same name as the target relation with no extension or with an extension of C<.dtx>. Files without an
312    extension are used in preference to the files with an extension.
313    
314  however, this version of the call would generate a syntax error if there were any quote  The files are loaded based on the presumption that each line of the file is a record in the
315  characters inside the variable C<$genus>.  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside
316    fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must
317    be presented in the order given in the relation tables produced by the L</ShowMetaData> method.
318    
319  The use of the strange parenthesized notation for field names enables us to distinguish  =over 4
 hyphens contained within field names from minus signs that participate in the computation  
 of the WHERE clause. All of the methods that manipulate fields will use this same notation.  
320    
321  It is possible to specify multiple entity and relationship names in order to retrieve more than  =item rebuild
 one object's data at the same time, which allows highly complex joined queries. For example,  
322    
323  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>  TRUE if the data tables need to be created or re-created, else FALSE
324    
325  This query returns all the genomes for a particular genus and allows access to the  =item RETURN
 sources from which they came. The join clauses to go from Genome to Source are generated  
 automatically.  
326    
327  Finally, the filter clause can contain sort information. To do this, simply put an C<ORDER BY>  Returns a statistical object containing the number of records read, the number of duplicates found,
328  clause at the end of the filter. Field references in the ORDER BY section follow the same rules  the number of errors, and a list of the error messages.
 as they do in the filter itself; in other words, each one must be of the form B<I<objectName>(I<fieldName>)>.  
 For example, the following filter string gets all genomes for a particular genus and sorts  
 them by species name.  
329    
330  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ? ORDER BY Genome(species)", [$genus]); >>  =back
331    
332  It is also permissible to specify I<only> an ORDER BY clause. For example, the following invocation gets  =cut
333  all genomes ordered by genus and species.  #: Return Type %;
334    sub Load {
335        # Get the parameters.
336        my ($self, $rebuild) = @_;
337        # Load the tables from the data directory.
338        my $retVal = $self->LoadTables($self->{_options}->{dataDir}, $rebuild);
339        # Return the statistics.
340        return $retVal;
341    }
342    
343  C<< $query = $sprout->Get(['Genome'], "ORDER BY Genome(genus), Genome(species)"); >>  =head3 LoadUpdate
344    
345  Odd things may happen if one of the ORDER BY fields is in a secondary relation. So, for example, an      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
 attempt to order B<Feature>s by alias may (depending on the underlying database engine used) cause  
 a single feature to appear more than once.  
346    
347  If multiple names are specified, then the query processor will automatically determine a  Load updates to one or more database tables. This method enables the client to make changes to one
348  join path between the entities and relationships. The algorithm used is very simplistic.  or two tables without reloading the whole database. For each table, there must be a corresponding
349  In particular, you can't specify any entity or relationship more than once, and if a  file in the data directory, either with the same name as the table, or with a C<.dtx> suffix. So,
350  relationship is recursive, the path is determined by the order in which the entity  for example, to make updates to the B<FeatureTranslation> relation, there must be a
351  and the relationship appear. For example, consider a recursive relationship B<IsParentOf>  C<FeatureTranslation.dtx> file in the data directory. Unlike a full load, files without an extension
352  which relates B<People> objects to other B<People> objects. If the join path is  are not examined. This allows update files to co-exist with files from an original load.
 coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,  
 the join path is C<['IsParentOf', 'People']>, then the people returned will be children.  
353    
354  =over 4  =over 4
355    
356  =item objectNames  =item truncateFlag
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
357    
358  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  TRUE if the tables should be rebuilt before loading, else FALSE. A value of TRUE therefore causes
359  be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  current data and schema of the tables to be replaced, while a value of FALSE means the new data
360  B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  is added to the existing data in the various relations.
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
361    
362  =item parameterList  =item tableList
363    
364  List of the parameters to be substituted in for the parameters marks in the filter clause.  List of the tables to be updated.
365    
366  =item RETURN  =item RETURN
367    
368  Returns a B<DBQuery> that can be used to iterate through all of the results.  Returns a statistical object containing the number of records read, the number of duplicates found,
369    the number of errors encountered, and a list of error messages.
370    
371  =back  =back
372    
373  =cut  =cut
374    #: Return Type $%;
375  sub Get {  sub LoadUpdate {
376          # Get the parameters.          # Get the parameters.
377          my $self = shift @_;      my ($self, $truncateFlag, $tableList) = @_;
378          my ($objectNames, $filterClause, $parameterList) = @_;      # Declare the return value.
379          # We differ from the ERDB Get method in that the parameter list is passed in as a list reference      my $retVal = Stats->new();
380          # rather than a list of parameters. The next step is to convert the parameters from a reference      # Get the data directory.
381          # to a real list. We can only do this if the parameters have been specified.      my $optionTable = $self->{_options};
382          my @parameters;      my $dataDir = $optionTable->{dataDir};
383          if ($parameterList) { @parameters = @{$parameterList}; }      # Loop through the incoming table names.
384          return $self->{_erdb}->Get($objectNames, $filterClause, @parameters);      for my $tableName (@{$tableList}) {
385            # Find the table's file.
386            my $fileName = LoadFileName($dataDir, $tableName);
387            if (! $fileName) {
388                Trace("No load file found for $tableName in $dataDir.") if T(0);
389            } else {
390                # Attempt to load this table.
391                my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
392                # Accumulate the resulting statistics.
393                $retVal->Accumulate($result);
394            }
395        }
396        # Return the statistics.
397        return $retVal;
398  }  }
399    
400  =head3 GetEntity  =head3 GenomeCounts
401    
402  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>      my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
403    
404  Return an object describing the entity instance with a specified ID.  Count the number of genomes in each domain. If I<$complete> is TRUE, only complete
405    genomes will be included in the counts.
406    
407  =over 4  =over 4
408    
409  =item entityType  =item complete
   
 Entity type name.  
410    
411  =item ID  TRUE if only complete genomes are to be counted, FALSE if all genomes are to be
412    counted
 ID of the desired entity.  
413    
414  =item RETURN  =item RETURN
415    
416  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  A six-element list containing the number of genomes in each of six categories--
417  instance is found with the specified key.  Archaea, Bacteria, Eukaryota, Viral, Environmental, and Unknown, respectively.
418    
419  =back  =back
420    
421  =cut  =cut
422    
423  sub GetEntity {  sub GenomeCounts {
424          # Get the parameters.          # Get the parameters.
425          my $self = shift @_;      my ($self, $complete) = @_;
426          my ($entityType, $ID) = @_;      # Set the filter based on the completeness flag.
427          # Create a query.      my $filter = ($complete ? "Genome(complete) = 1" : "");
428          my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);      # Get all the genomes and the related taxonomy information.
429          # Get the first (and only) object.      my @genomes = $self->GetAll(['Genome'], $filter, [], ['Genome(id)', 'Genome(taxonomy)']);
430          my $retVal = $query->Fetch();      # Clear the counters.
431          # Return the result.      my ($arch, $bact, $euk, $vir, $env, $unk) = (0, 0, 0, 0, 0, 0);
432          return $retVal;      # Loop through, counting the domains.
433        for my $genome (@genomes) {
434            if    ($genome->[1] =~ /^archaea/i)  { ++$arch }
435            elsif ($genome->[1] =~ /^bacter/i)   { ++$bact }
436            elsif ($genome->[1] =~ /^eukar/i)    { ++$euk }
437            elsif ($genome->[1] =~ /^vir/i)      { ++$vir }
438            elsif ($genome->[1] =~ /^env/i)      { ++$env }
439            else  { ++$unk }
440        }
441        # Return the counts.
442        return ($arch, $bact, $euk, $vir, $env, $unk);
443  }  }
444    
445  =head3 GetEntityValues  =head3 ContigCount
446    
447  C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>      my $count = $sprout->ContigCount($genomeID);
448    
449  Return a list of values from a specified entity instance.  Return the number of contigs for the specified genome ID.
450    
451  =over 4  =over 4
452    
453  =item entityType  =item genomeID
   
 Entity type name.  
   
 =item ID  
   
 ID of the desired entity.  
   
 =item fields  
454    
455  List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.  ID of the genome whose contig count is desired.
456    
457  =item RETURN  =item RETURN
458    
459  Returns a flattened list of the values of the specified fields for the specified entity.  Returns the number of contigs for the specified genome.
460    
461  =back  =back
462    
463  =cut  =cut
464  #: Return Type @;  
465  sub GetEntityValues {  sub ContigCount {
466          # Get the parameters.          # Get the parameters.
467          my $self = shift @_;      my ($self, $genomeID) = @_;
468          my ($entityType, $ID, $fields) = @_;      # Get the contig count.
469          # Get the specified entity.      my $retVal = $self->GetCount(['Contig', 'HasContig'], "HasContig(from-link) = ?", [$genomeID]);
         my $entity = $self->GetEntity($entityType, $ID);  
         # Declare the return list.  
         my @retVal = ();  
         # If we found the entity, push the values into the return list.  
         if ($entity) {  
                 push @retVal, $entity->Values($fields);  
         }  
470          # Return the result.          # Return the result.
471          return @retVal;      return $retVal;
472  }  }
473    
474  =head3 ShowMetaData  =head3 GenomeMenu
475    
476  C<< $sprout->ShowMetaData($fileName); >>      my $html = $sprout->GenomeMenu(%options);
477    
478  This method outputs a description of the database to an HTML file in the data directory.  Generate a genome selection control with the specified name and options.
479    This control is almost but not quite the same as the genome control in the
480    B<SearchHelper> class. Eventually, the two will be combined.
481    
482  =over 4  =over 4
483    
484  =item fileName  =item options
485    
486    Optional parameters for the control (see below).
487    
488    =item RETURN
489    
490  Fully-qualified name to give to the output file.  Returns the HTML for a genome selection control on a form (sometimes called a popup menu).
491    
492  =back  =back
493    
494  =cut  The valid options are as follows.
495    
496  sub ShowMetaData {  =over 4
         # Get the parameters.  
         my $self = shift @_;  
         my ($fileName) = @_;  
         # Compute the file name.  
         my $options = $self->{_options};  
         # Call the show method on the underlying ERDB object.  
         $self->{_erdb}->ShowMetaData($fileName);  
 }  
497    
498  =head3 Load  =item name
499    
500  C<< $sprout->Load($rebuild); >>;  Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
501    Terrible things will happen if you have two controls with the same name on the same page.
502    
503  Load the database from files in the data directory, optionally re-creating the tables.  =item filter
504    
505  This method always deletes the data from the database before loading, even if the tables are not  If specified, a filter for the list of genomes to display. The filter should be in the form of a
506  re-created. The data is loaded into the relations from files in the data directory either having the  list reference. The first element of the list should be the filter string, and the remaining elements
507  same name as the target relation with no extension or with an extension of C<.dtx>. Files without an  the filter parameters.
 extension are used in preference to the files with an extension.  
508    
509  The files are loaded based on the presumption that each line of the file is a record in the  =item multiSelect
 relation, and the individual fields are delimited by tabs. Tab and new-line characters inside  
 fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must  
 be presented in the order given in the relation tables produced by the L</ShowMetaData> method.  
510    
511  =over 4  If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
512    
513  =item rebuild  =item size
514    
515  TRUE if the data tables need to be created or re-created, else FALSE  Number of rows to display in the control. The default is C<10>
516    
517  =item RETURN  =item id
518    
519  Returns a statistical object containing the number of records read, the number of duplicates found,  ID to give this control. The default is the value of the C<name> option. Nothing will work correctly
520  the number of errors, and a list of the error messages.  unless this ID is unique.
521    
522    =item selected
523    
524    A comma-delimited list of selected genomes, or a reference to a list of selected genomes. The
525    default is none.
526    
527    =item class
528    
529    If specified, a style class to assign to the genome control.
530    
531  =back  =back
532    
533  =cut  =cut
534  #: Return Type %;  
535  sub Load {  sub GenomeMenu {
536          # Get the parameters.          # Get the parameters.
537          my $self = shift @_;      my ($self, %options) = @_;
538          my ($rebuild) = @_;      # Get the control's name and ID.
539          # Get the database object.      my $menuName = $options{name} || 'myGenomeControl';
540          my $erdb = $self->{_erdb};      my $menuID = $options{id} || $menuName;
541          # Load the tables from the data directory.      # Compute the IDs for the status display.
542          my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild);      my $divID = "${menuID}_status";
543          # Return the statistics.      my $urlID = "${menuID}_url";
544        # Compute the code to show selected genomes in the status area.
545        my $showSelect = "showSelected('$menuID', '$divID', '$urlID', 1000)";
546        # Check for single-select or multi-select.
547        my $multiSelect = $options{multiSelect} || 0;
548        # Get the style data.
549        my $class = $options{class} || '';
550        # Get the list of pre-selected items.
551        my $selections = $options{selected} || [];
552        if (ref $selections ne 'ARRAY') {
553            $selections = [ split /\s*,\s*/, $selections ];
554        }
555        my %selected = map { $_ => 1 } @{$selections};
556        # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
557        # string or a list reference.
558        my $filterParms = $options{filter} || "";
559        if (! ref $filterParms) {
560            $filterParms = [split /\t|\\t/, $filterParms];
561        }
562        my $filterString = shift @{$filterParms};
563        # Get a list of all the genomes in group order. In fact, we only need them ordered
564        # by name (genus,species,strain), but putting primary-group in front enables us to
565        # take advantage of an existing index.
566        my @genomeList = $self->GetAll(['Genome'], "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
567                                       $filterParms,
568                                       [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
569        # Create a hash to organize the genomes by group. Each group will contain a list of
570        # 2-tuples, the first element being the genome ID and the second being the genome
571        # name.
572        my %gHash = ();
573        for my $genome (@genomeList) {
574            # Get the genome data.
575            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
576            # Compute its name. This is the genus, species, strain (if any), and the contig count.
577            my $name = "$genus $species ";
578            $name .= "$strain " if $strain;
579            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
580            # Now we get the domain. The domain tells us the display style of the organism.
581            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
582            # Now compute the display group. This is normally the primary group, but if the
583            # organism is supporting, we blank it out.
584            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
585            # Push the genome into the group's list. Note that we use the real group
586            # name for the hash key here, not the display group name.
587            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
588        }
589        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
590        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
591        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
592        # that aren't "other". At some point, we will want to make this less complicated.
593        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
594                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
595        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
596        # Remember the number of NMPDR groups.
597        my $nmpdrGroupCount = scalar @groups;
598        # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
599        # of the domains found.
600        my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
601        my @domains = ();
602        for my $genomeData (@otherGenomes) {
603            my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
604            if (exists $gHash{$domain}) {
605                push @{$gHash{$domain}}, $genomeData;
606            } else {
607                $gHash{$domain} = [$genomeData];
608                push @domains, $domain;
609            }
610        }
611        # Add the domain groups at the end of the main group list. The main group list will now
612        # contain all the categories we need to display the genomes.
613        push @groups, sort @domains;
614        # Delete the supporting group.
615        delete $gHash{$FIG_Config::otherGroup};
616        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
617        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
618        # and use that to make the selections.
619        my $nmpdrCount = 0;
620        # Create the type counters.
621        my $groupCount = 1;
622        # Get the number of rows to display.
623        my $rows = $options{size} || 10;
624        # If we're multi-row, create an onChange event.
625        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
626        # Set up the multiple-select flag.
627        my $multipleTag = ($multiSelect ? " multiple" : "" );
628        # Set up the style class.
629        my $classTag = ($class ? " class=\"$class\"" : "" );
630        # Create the SELECT tag and stuff it into the output array.
631        my @lines = ("<SELECT name=\"$menuID\" id=\"$menuID\" $onChangeTag$multipleTag$classTag size=\"$rows\">");
632        # Loop through the groups.
633        for my $group (@groups) {
634            # Get the genomes in the group.
635            for my $genome (@{$gHash{$group}}) {
636                # If this is an NMPDR organism, we add an extra style and count it.
637                my $nmpdrStyle = "";
638                if ($nmpdrGroupCount > 0) {
639                    $nmpdrCount++;
640                    $nmpdrStyle = " Core";
641                }
642                # Get the organism ID, name, contig count, and domain.
643                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
644                # See if we're pre-selected.
645                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
646                # Compute the display name.
647                my $nameString = "$name ($genomeID$contigCount)";
648                # Generate the option tag.
649                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
650                push @lines, "    $optionTag";
651            }
652            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
653            # groups.
654            $nmpdrGroupCount--;
655        }
656        # Close the SELECT tag.
657        push @lines, "</SELECT>";
658        if ($rows > 1) {
659            # We're in a non-compact mode, so we need to add some selection helpers. First is
660            # the search box. This allows the user to type text and change which genomes are
661            # displayed. For multiple-select mode, we include a button that selects the displayed
662            # genes. For single-select mode, we use a plain label instead.
663            my $searchThingName = "${menuID}_SearchThing";
664            my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"
665                                                 : "Show genomes containing");
666            push @lines, "<br />$searchThingLabel&nbsp;" .
667                         "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />";
668            # For multi-select mode, we also have buttons to set and clear selections.
669            if ($multiSelect) {
670                push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll('$menuID'); $showSelect\" />";
671                push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll('$menuID'); $showSelect\" />";
672                push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome('$menuID', $nmpdrCount, true); $showSelect;\" />";
673            }
674            # Add a hidden field we can use to generate organism page hyperlinks.
675            push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/seedviewer.cgi?page=Organism;organism=\" />";
676            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
677            push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";
678        }
679        # Assemble all the lines into a string.
680        my $retVal = join("\n", @lines, "");
681        # Return the result.
682          return $retVal;          return $retVal;
683  }  }
684    
 =head3 LoadUpdate  
   
 C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>  
685    
686  Load updates to one or more database tables. This method enables the client to make changes to one  =head3 Stem
 or two tables without reloading the whole database. For each table, there must be a corresponding  
 file in the data directory, either with the same name as the table, or with a C<.dtx> suffix. So,  
 for example, to make updates to the B<FeatureTranslation> relation, there must be a  
 C<FeatureTranslation.dtx> file in the data directory. Unlike a full load, files without an extension  
 are not examined. This allows update files to co-exist with files from an original load.  
687    
688  =over 4      my $stem = $sprout->Stem($word);
689    
690  =item truncateFlag  Return the stem of the specified word, or C<undef> if the word is not
691    stemmable. Note that even if the word is stemmable, the stem may be
692    the same as the original word.
693    
694  TRUE if the tables should be rebuilt before loading, else FALSE. A value of TRUE therefore causes  =over 4
 current data and schema of the tables to be replaced, while a value of FALSE means the new data  
 is added to the existing data in the various relations.  
695    
696  =item tableList  =item word
697    
698  List of the tables to be updated.  Word to convert into a stem.
699    
700  =item RETURN  =item RETURN
701    
702  Returns a statistical object containing the number of records read, the number of duplicates found,  Returns a stem of the word (which may be the word itself), or C<undef> if
703  the number of errors encountered, and a list of error messages.  the word is not stemmable.
704    
705  =back  =back
706    
707  =cut  =cut
708  #: Return Type %;  
709  sub LoadUpdate {  sub Stem {
710          # Get the parameters.          # Get the parameters.
711          my $self = shift @_;      my ($self, $word) = @_;
712          my ($truncateFlag, $tableList) = @_;      # Declare the return variable.
713          # Get the database object.      my $retVal;
714          my $erdb = $self->{_erdb};      # See if it's stemmable.
715          # Declare the return value.      if ($word =~ /^[A-Za-z]+$/) {
716          my $retVal = Stats->new();          # Compute the stem.
717          # Get the data directory.          my $stemList = $self->{stemmer}->stem($word);
718          my $optionTable = $self->{_options};          my $stem = $stemList->[0];
719          my $dataDir = $optionTable->{dataDir};          # Check to see if it's long enough.
720          # Loop through the incoming table names.          if (length $stem >= 3) {
721          for my $tableName (@{$tableList}) {              # Yes, keep it.
722                  # Find the table's file.              $retVal = $stem;
723                  my $fileName = "$dataDir/$tableName";          } else {
724                  if (! -e $fileName) {              # No, use the original word.
725                          $fileName = "$fileName.dtx";              $retVal = $word;
726                  }                  }
                 # Attempt to load this table.  
                 my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);  
                 # Accumulate the resulting statistics.  
                 $retVal->Accumulate($result);  
727          }          }
728          # Return the statistics.      # Return the result.
729          return $retVal;          return $retVal;
730  }  }
731    
732    
733  =head3 Build  =head3 Build
734    
735  C<< $sprout->Build(); >>      $sprout->Build();
736    
737  Build the database. The database will be cleared and the tables re-created from the metadata.  Build the database. The database will be cleared and the tables re-created from the metadata.
738  This method is useful when a database is brand new or when the database definition has  This method is useful when a database is brand new or when the database definition has
# Line 464  Line 742 
742  #: Return Type ;  #: Return Type ;
743  sub Build {  sub Build {
744          # Get the parameters.          # Get the parameters.
745          my $self = shift @_;      my ($self) = @_;
746          # Create the tables.          # Create the tables.
747          $self->{_erdb}->CreateTables;      $self->CreateTables();
748  }  }
749    
750  =head3 Genomes  =head3 Genomes
751    
752  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
753    
754  Return a list of all the genome IDs.  Return a list of all the genome IDs.
755    
# Line 479  Line 757 
757  #: Return Type @;  #: Return Type @;
758  sub Genomes {  sub Genomes {
759          # Get the parameters.          # Get the parameters.
760          my $self = shift @_;      my ($self) = @_;
761          # Get all the genomes.          # Get all the genomes.
762          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');
763          # Return the list of IDs.          # Return the list of IDs.
# Line 488  Line 766 
766    
767  =head3 GenusSpecies  =head3 GenusSpecies
768    
769  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
770    
771  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
772    
# Line 509  Line 787 
787  #: Return Type $;  #: Return Type $;
788  sub GenusSpecies {  sub GenusSpecies {
789          # Get the parameters.          # Get the parameters.
790          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
791          # Get the data for the specified genome.          # Get the data for the specified genome.
792          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',
793                                                                                                                            'Genome(unique-characterization)']);                                                                                                                            'Genome(unique-characterization)']);
# Line 521  Line 798 
798    
799  =head3 FeaturesOf  =head3 FeaturesOf
800    
801  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
802    
803  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
804    
# Line 546  Line 823 
823  #: Return Type @;  #: Return Type @;
824  sub FeaturesOf {  sub FeaturesOf {
825          # Get the parameters.          # Get the parameters.
826          my $self = shift @_;      my ($self, $genomeID,$ftype) = @_;
         my ($genomeID,$ftype) = @_;  
827          # Get the features we want.          # Get the features we want.
828          my @features;          my @features;
829          if (!$ftype) {          if (!$ftype) {
# Line 567  Line 843 
843    
844  =head3 FeatureLocation  =head3 FeatureLocation
845    
846  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
847    
848  Return the location of a feature in its genome's contig segments. In a list context, this method  Return the location of a feature in its genome's contig segments. In a list context, this method
849  will return a list of the locations. In a scalar context, it will return the locations as a space-  will return a list of the locations. In a scalar context, it will return the locations as a space-
# Line 591  Line 867 
867  =item RETURN  =item RETURN
868    
869  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
870  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context. An empty list means the feature
871    wasn't found.
872    
873  =back  =back
874    
875  =cut  =cut
876  #: Return Type @;  
 #: Return Type $;  
877  sub FeatureLocation {  sub FeatureLocation {
878          # Get the parameters.          # Get the parameters.
879          my $self = shift @_;      my ($self, $featureID) = @_;
880          my ($featureID) = @_;      # Declare the return variable.
         # Create a query for the feature locations.  
         my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",  
                                                    [$featureID]);  
         # Create the return list.  
881          my @retVal = ();          my @retVal = ();
882          # Set up the variables used to determine if we have adjacent segments. This initial setup will      # Get the feature record.
883          # not match anything.      my $object = $self->GetEntity('Feature', $featureID);
884          my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);      # Only proceed if we found it.
885          # Loop through the query results, creating location specifiers.      if (defined $object) {
886          while (my $location = $query->Fetch()) {          # Get the location string.
887                  # Get the location parameters.          my $locString = $object->PrimaryValue('Feature(location-string)');
888                  my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',          # Create the return list.
889                          'IsLocatedIn(beg)', 'IsLocatedIn(dir)', 'IsLocatedIn(len)']);          @retVal = split /\s*,\s*/, $locString;
                 # Check to see if we are adjacent to the previous segment.  
                 if ($prevContig eq $contigID && $dir eq $prevDir) {  
                         # Here the new segment is in the same direction on the same contig. Insure the  
                         # new segment's beginning is next to the old segment's end.  
                         if (($dir eq "-" && $beg == $prevBeg - $prevLen) ||  
                                 ($dir eq "+" && $beg == $prevBeg + $prevLen)) {  
                                 # Here we need to merge two segments. Adjust the beginning and length values  
                                 # to include both segments.  
                                 $beg = $prevBeg;  
                                 $len += $prevLen;  
                                 # Pop the old segment off. The new one will replace it later.  
                                 pop @retVal;  
                         }  
                 }  
                 # Remember this specifier for the adjacent-segment test the next time through.  
                 ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);  
                 # Add the specifier to the list.  
                 push @retVal, "${contigID}_$beg$dir$len";  
890          }          }
891          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
892          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
893  }  }
894    
895  =head3 ParseLocation  =head3 ParseLocation
896    
897  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
898    
899  Split a location specifier into the contig ID, the starting point, the direction, and the  Split a location specifier into the contig ID, the starting point, the direction, and the
900  length.  length.
# Line 659  Line 913 
913  =back  =back
914    
915  =cut  =cut
916  #: Return Type @;  
917  sub ParseLocation {  sub ParseLocation {
918          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
919        # the first parameter.
920        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
921          my ($location) = @_;          my ($location) = @_;
922          # Parse it into segments.          # Parse it into segments.
923          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
924          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
925          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
926          if ($dir eq "_") {          if ($dir eq "_") {
# Line 680  Line 936 
936          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
937  }  }
938    
939    
940    
941    =head3 PointLocation
942    
943        my $found = Sprout::PointLocation($location, $point);
944    
945    Return the offset into the specified location of the specified point on the contig. If
946    the specified point is before the location, a negative value will be returned. If it is
947    beyond the location, an undefined value will be returned. It is assumed that the offset
948    is for the location's contig. The location can either be new-style (using a C<+> or C<->
949    and a length) or old-style (using C<_> and start and end positions.
950    
951    =over 4
952    
953    =item location
954    
955    A location specifier (see L</FeatureLocation> for a description).
956    
957    =item point
958    
959    The offset into the contig of the point in which we're interested.
960    
961    =item RETURN
962    
963    Returns the offset inside the specified location of the specified point, a negative
964    number if the point is before the location, or an undefined value if the point is past
965    the location. If the length of the location is 0, this method will B<always> denote
966    that it is outside the location. The offset will always be relative to the left-most
967    position in the location.
968    
969    =back
970    
971    =cut
972    
973    sub PointLocation {
974        # Get the parameter. Note that if we're called as an instance method, we ignore
975        # the first parameter.
976        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
977        my ($location, $point) = @_;
978        # Parse out the location elements. Note that this works on both old-style and new-style
979        # locations.
980        my ($contigID, $start, $dir, $len) = ParseLocation($location);
981        # Declare the return variable.
982        my $retVal;
983        # Compute the offset. The computation is dependent on the direction of the location.
984        my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
985        # Return the offset if it's valid.
986        if ($offset < $len) {
987            $retVal = $offset;
988        }
989        # Return the offset found.
990        return $retVal;
991    }
992    
993  =head3 DNASeq  =head3 DNASeq
994    
995  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
996    
997  This method returns the DNA sequence represented by a list of locations. The list of locations  This method returns the DNA sequence represented by a list of locations. The list of locations
998  should be of the form returned by L</featureLocation> when in a list context. In other words,  should be of the form returned by L</featureLocation> when in a list context. In other words,
999  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.
1000    
1001    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
1002    between positions 1401 and 1532, inclusive.
1003    
1004        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
1005    
1006  =over 4  =over 4
1007    
1008  =item locationList  =item locationList
1009    
1010  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
1011  L</FeatureLocation> for more about this format).  I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
1012    
1013  =item RETURN  =item RETURN
1014    
# Line 705  Line 1020 
1020  #: Return Type $;  #: Return Type $;
1021  sub DNASeq {  sub DNASeq {
1022          # Get the parameters.          # Get the parameters.
1023          my $self = shift @_;      my ($self, $locationList) = @_;
         my ($locationList) = @_;  
1024          # Create the return string.          # Create the return string.
1025          my $retVal = "";          my $retVal = "";
1026          # Loop through the locations.          # Loop through the locations.
# Line 721  Line 1035 
1035                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
1036                  # before putting it in the return value.                  # before putting it in the return value.
1037                  my ($start, $stop);                  my ($start, $stop);
1038            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
1039                  if ($dir eq "+") {                  if ($dir eq "+") {
1040                          $start = $beg;                          $start = $beg;
1041                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
1042                  } else {                  } else {
1043                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
1044                          $stop = $beg;                          $stop = $beg;
1045                  }                  }
1046            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
1047                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
1048                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
1049                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 739  Line 1055 
1055                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
1056                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
1057                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
1058                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
1059                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
1060                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
1061                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
1062                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
1063                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
1064                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
1065                  }                  }
1066                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
1067                  if ($dir eq '+') {                  if ($dir eq '+') {
1068                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
1069                  } else {                  } else {
1070                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
1071                  }                  }
1072          }          }
1073          # Return the result.          # Return the result.
# Line 759  Line 1076 
1076    
1077  =head3 AllContigs  =head3 AllContigs
1078    
1079  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1080    
1081  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1082    
# Line 779  Line 1096 
1096  #: Return Type @;  #: Return Type @;
1097  sub AllContigs {  sub AllContigs {
1098          # Get the parameters.          # Get the parameters.
1099          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
1100          # Ask for the genome's Contigs.          # Ask for the genome's Contigs.
1101          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
1102                                                                  'HasContig(to-link)');                                                                  'HasContig(to-link)');
# Line 788  Line 1104 
1104          return @retVal;          return @retVal;
1105  }  }
1106    
1107    =head3 GenomeLength
1108    
1109        my $length = $sprout->GenomeLength($genomeID);
1110    
1111    Return the length of the specified genome in base pairs.
1112    
1113    =over 4
1114    
1115    =item genomeID
1116    
1117    ID of the genome whose base pair count is desired.
1118    
1119    =item RETURN
1120    
1121    Returns the number of base pairs in all the contigs of the specified
1122    genome.
1123    
1124    =back
1125    
1126    =cut
1127    
1128    sub GenomeLength {
1129        # Get the parameters.
1130        my ($self, $genomeID) = @_;
1131        # Declare the return variable.
1132        my $retVal = 0;
1133        # Get the genome's contig sequence lengths.
1134        my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',
1135                           [$genomeID], 'IsMadeUpOf(len)');
1136        # Sum the lengths.
1137        map { $retVal += $_ } @lens;
1138        # Return the result.
1139        return $retVal;
1140    }
1141    
1142    =head3 FeatureCount
1143    
1144        my $count = $sprout->FeatureCount($genomeID, $type);
1145    
1146    Return the number of features of the specified type in the specified genome.
1147    
1148    =over 4
1149    
1150    =item genomeID
1151    
1152    ID of the genome whose feature count is desired.
1153    
1154    =item type
1155    
1156    Type of feature to count (eg. C<peg>, C<rna>, etc.).
1157    
1158    =item RETURN
1159    
1160    Returns the number of features of the specified type for the specified genome.
1161    
1162    =back
1163    
1164    =cut
1165    
1166    sub FeatureCount {
1167        # Get the parameters.
1168        my ($self, $genomeID, $type) = @_;
1169        # Compute the count.
1170        my $retVal = $self->GetCount(['HasFeature', 'Feature'],
1171                                    "HasFeature(from-link) = ? AND Feature(feature-type) = ?",
1172                                    [$genomeID, $type]);
1173        # Return the result.
1174        return $retVal;
1175    }
1176    
1177    =head3 GenomeAssignments
1178    
1179        my $fidHash = $sprout->GenomeAssignments($genomeID);
1180    
1181    Return a list of a genome's assigned features. The return hash will contain each
1182    assigned feature of the genome mapped to the text of its most recent functional
1183    assignment.
1184    
1185    =over 4
1186    
1187    =item genomeID
1188    
1189    ID of the genome whose functional assignments are desired.
1190    
1191    =item RETURN
1192    
1193    Returns a reference to a hash which maps each feature to its most recent
1194    functional assignment.
1195    
1196    =back
1197    
1198    =cut
1199    
1200    sub GenomeAssignments {
1201        # Get the parameters.
1202        my ($self, $genomeID) = @_;
1203        # Declare the return variable.
1204        my $retVal = {};
1205        # Query the genome's features.
1206        my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?",
1207                               [$genomeID]);
1208        # Loop through the features.
1209        while (my $data = $query->Fetch) {
1210            # Get the feature ID and assignment.
1211            my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
1212            if ($assignment) {
1213                $retVal->{$fid} = $assignment;
1214            }
1215        }
1216        # Return the result.
1217        return $retVal;
1218    }
1219    
1220  =head3 ContigLength  =head3 ContigLength
1221    
1222  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->ContigLength($contigID);
1223    
1224  Compute the length of a contig.  Compute the length of a contig.
1225    
# Line 810  Line 1239 
1239  #: Return Type $;  #: Return Type $;
1240  sub ContigLength {  sub ContigLength {
1241          # Get the parameters.          # Get the parameters.
1242          my $self = shift @_;      my ($self, $contigID) = @_;
         my ($contigID) = @_;  
1243          # Get the contig's last sequence.          # Get the contig's last sequence.
1244          my $query = $self->Get(['IsMadeUpOf'],          my $query = $self->Get(['IsMadeUpOf'],
1245                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
# Line 822  Line 1250 
1250          # Set it from the sequence data, if any.          # Set it from the sequence data, if any.
1251          if ($sequence) {          if ($sequence) {
1252                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
1253                  $retVal = $start + $len;          $retVal = $start + $len - 1;
1254        }
1255        # Return the result.
1256        return $retVal;
1257    }
1258    
1259    =head3 ClusterPEGs
1260    
1261        my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1262    
1263    Cluster the PEGs in a list according to the cluster coding scheme of the specified
1264    subsystem. In order for this to work properly, the subsystem object must have
1265    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> or
1266    B<get_row> methods. This causes the cluster numbers to be pulled into the
1267    subsystem's color hash. If a PEG is not found in the color hash, it will not
1268    appear in the output sequence.
1269    
1270    =over 4
1271    
1272    =item sub
1273    
1274    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
1275    method.
1276    
1277    =item pegs
1278    
1279    Reference to the list of PEGs to be clustered.
1280    
1281    =item RETURN
1282    
1283    Returns a list of the PEGs, grouped into smaller lists by cluster number.
1284    
1285    =back
1286    
1287    =cut
1288    #: Return Type $@@;
1289    sub ClusterPEGs {
1290        # Get the parameters.
1291        my ($self, $sub, $pegs) = @_;
1292        # Declare the return variable.
1293        my $retVal = [];
1294        # Loop through the PEGs, creating arrays for each cluster.
1295        for my $pegID (@{$pegs}) {
1296            my $clusterNumber = $sub->get_cluster_number($pegID);
1297            # Only proceed if the PEG is in a cluster.
1298            if ($clusterNumber >= 0) {
1299                # Push this PEG onto the sub-list for the specified cluster number.
1300                push @{$retVal->[$clusterNumber]}, $pegID;
1301            }
1302          }          }
1303          # Return the result.          # Return the result.
1304          return $retVal;          return $retVal;
# Line 830  Line 1306 
1306    
1307  =head3 GenesInRegion  =head3 GenesInRegion
1308    
1309  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1310    
1311  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1312    
# Line 853  Line 1329 
1329  Returns a three-element list. The first element is a list of feature IDs for the features that  Returns a three-element list. The first element is a list of feature IDs for the features that
1330  overlap the region of interest. The second and third elements are the minimum and maximum  overlap the region of interest. The second and third elements are the minimum and maximum
1331  locations of the features provided on the specified contig. These may extend outside  locations of the features provided on the specified contig. These may extend outside
1332  the start and stop values.  the start and stop values. The first element (that is, the list of features) is sorted
1333    roughly by location.
1334    
1335  =back  =back
1336    
1337  =cut  =cut
1338  #: Return Type @;  
1339  sub GenesInRegion {  sub GenesInRegion {
1340          # Get the parameters.          # Get the parameters.
1341          my $self = shift @_;      my ($self, $contigID, $start, $stop) = @_;
1342          my ($contigID, $start, $stop) = @_;      # Get the maximum segment length.
1343        my $maximumSegmentLength = $self->MaxSegment;
1344        # Prime the values we'll use for the returned beginning and end.
1345        my @initialMinMax = ($self->ContigLength($contigID), 0);
1346        my ($min, $max) = @initialMinMax;
1347        # Get the overlapping features.
1348        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1349        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1350        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1351        # of the feature's locations.
1352        my %featureMap = ();
1353        # Loop through them to do the begin/end analysis.
1354        for my $featureObject (@featureObjects) {
1355            # Get the feature's location string. This may contain multiple actual locations.
1356            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1357            my @locationSegments = split /\s*,\s*/, $locations;
1358            # Loop through the locations.
1359            for my $locationSegment (@locationSegments) {
1360                # Construct an object for the location.
1361                my $locationObject = BasicLocation->new($locationSegment);
1362                # Merge the current segment's begin and end into the min and max.
1363                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1364                my ($beg, $end);
1365                if (exists $featureMap{$fid}) {
1366                    ($beg, $end) = @{$featureMap{$fid}};
1367                    $beg = $left if $left < $beg;
1368                    $end = $right if $right > $end;
1369                } else {
1370                    ($beg, $end) = ($left, $right);
1371                }
1372                $min = $beg if $beg < $min;
1373                $max = $end if $end > $max;
1374                # Store the feature's new extent back into the hash table.
1375                $featureMap{$fid} = [$beg, $end];
1376            }
1377        }
1378        # Now we must compute the list of the IDs for the features found. We start with a list
1379        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1380        # but the result of the sort will be the same.)
1381        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1382        # Now we sort by midpoint and yank out the feature IDs.
1383        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1384        # Return it along with the min and max.
1385        return (\@retVal, $min, $max);
1386    }
1387    
1388    =head3 GeneDataInRegion
1389    
1390        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1391    
1392    List the features which overlap a specified region in a contig.
1393    
1394    =over 4
1395    
1396    =item contigID
1397    
1398    ID of the contig containing the region of interest.
1399    
1400    =item start
1401    
1402    Offset of the first residue in the region of interest.
1403    
1404    =item stop
1405    
1406    Offset of the last residue in the region of interest.
1407    
1408    =item RETURN
1409    
1410    Returns a list of B<ERDBObjects> for the desired features. Each object will
1411    contain a B<Feature> record.
1412    
1413    =back
1414    
1415    =cut
1416    
1417    sub GeneDataInRegion {
1418        # Get the parameters.
1419        my ($self, $contigID, $start, $stop) = @_;
1420          # Get the maximum segment length.          # Get the maximum segment length.
1421          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
1422          # Create a hash to receive the feature list. We use a hash so that we can eliminate          # Create a hash to receive the feature list. We use a hash so that we can eliminate
1423          # duplicates easily.      # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1424        # ERDBObject from the query.
1425          my %featuresFound = ();          my %featuresFound = ();
1426          # Prime the values we'll use for the returned beginning and end.      # Create a table of parameters for the queries. Each query looks for features travelling in
         my ($min, $max) = ($self->ContigLength($contigID), 0);  
         # Create a table of parameters for each query. Each query looks for features travelling in  
1427          # a particular direction. The query parameters include the contig ID, the feature direction,          # a particular direction. The query parameters include the contig ID, the feature direction,
1428          # the lowest possible start position, and the highest possible start position. This works          # the lowest possible start position, and the highest possible start position. This works
1429          # because each feature segment length must be no greater than the maximum segment length.          # because each feature segment length must be no greater than the maximum segment length.
# Line 879  Line 1432 
1432          # Loop through the query parameters.          # Loop through the query parameters.
1433          for my $parms (values %queryParms) {          for my $parms (values %queryParms) {
1434                  # Create the query.                  # Create the query.
1435                  my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1436                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1437                          $parms);                          $parms);
1438                  # Loop through the feature segments found.                  # Loop through the feature segments found.
1439                  while (my $segment = $query->Fetch) {                  while (my $segment = $query->Fetch) {
1440                          # Get the data about this segment.                          # Get the data about this segment.
1441                          my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1442                                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1443                          # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1444                          # this will be the case if the segment is the maximum length, so to fine-tune                          # this will be the case if the segment is the maximum length, so to fine-tune
1445                          # the results we insure that the inequality from the query holds using the actual                          # the results we insure that the inequality from the query holds using the actual
1446                          # length.                          # length.
1447                          my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1448                          if ($dir eq '+') {              my $found = $loc->Overlap($start, $stop);
                                 $end = $beg + $len;  
                                 if ($end >= $start) {  
                                         # Denote we found a useful feature.  
                                         $found = 1;  
                                 }  
                         } elsif ($dir eq '-') {  
                                 $end = $beg - $len;  
                                 if ($end <= $stop) {  
                                         # Denote we found a useful feature.  
                                         $found = 1;  
                                 }  
                         }  
1449                          if ($found) {                          if ($found) {
1450                                  # Here we need to record the feature and update the minimum and maximum.                  # Save this feature in the result list.
1451                                  $featuresFound{$featureID} = 1;                  $featuresFound{$featureID} = $segment;
                                 if ($beg < $min) { $min = $beg; }  
                                 if ($end < $min) { $min = $end; }  
                                 if ($beg > $max) { $max = $beg; }  
                                 if ($end > $max) { $max = $end; }  
1452                          }                          }
1453                  }                  }
1454          }          }
1455          # Compute a list of the IDs for the features found.      # Return the ERDB objects for the features found.
1456          my @list = (sort (keys %featuresFound));      return values %featuresFound;
         # Return it along with the min and max.  
         return (\@list, $min, $max);  
1457  }  }
1458    
1459  =head3 FType  =head3 FType
1460    
1461  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1462    
1463  Return the type of a feature.  Return the type of a feature.
1464    
# Line 944  Line 1479 
1479  #: Return Type $;  #: Return Type $;
1480  sub FType {  sub FType {
1481          # Get the parameters.          # Get the parameters.
1482          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1483          # Get the specified feature's type.          # Get the specified feature's type.
1484          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1485          # Return the result.          # Return the result.
# Line 954  Line 1488 
1488    
1489  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1490    
1491  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1492    
1493  Return the annotations of a feature.  Return the annotations of a feature.
1494    
# Line 964  Line 1498 
1498    
1499  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1500    
1501    =item rawFlag
1502    
1503    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1504    will be returned in human-readable form.
1505    
1506  =item RETURN  =item RETURN
1507    
1508  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1509    
1510  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1511    
1512  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1513    
1514  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1515    
# Line 982  Line 1521 
1521  #: Return Type @%;  #: Return Type @%;
1522  sub FeatureAnnotations {  sub FeatureAnnotations {
1523          # Get the parameters.          # Get the parameters.
1524          my $self = shift @_;      my ($self, $featureID, $rawFlag) = @_;
         my ($featureID) = @_;  
1525          # Create a query to get the feature's annotations and the associated users.          # Create a query to get the feature's annotations and the associated users.
1526          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1527                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 996  Line 1534 
1534                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1535                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1536                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1537            # Convert the time, if necessary.
1538            if (! $rawFlag) {
1539                $timeStamp = FriendlyTimestamp($timeStamp);
1540            }
1541                  # Assemble them into a hash.                  # Assemble them into a hash.
1542          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1543                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1544                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1545                  # Add it to the return list.                  # Add it to the return list.
1546                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1009  Line 1551 
1551    
1552  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1553    
1554  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1555    
1556  Return all of the functional assignments for a particular feature. The data is returned as a  Return all of the functional assignments for a particular feature. The data is returned as a
1557  hash of functional assignments to user IDs. A functional assignment is a type of annotation.  hash of functional assignments to user IDs. A functional assignment is a type of annotation,
1558  It has the format "XXXX\nset XXXX function to\nYYYYY". In this instance, XXXX is the user ID  Functional assignments are described in the L</ParseAssignment> function. Its worth noting that
1559  and YYYYY is the functional assignment text. Its worth noting that we cannot filter on the content  we cannot filter on the content of the annotation itself because it's a text field; however,
1560  of the annotation itself because it's a text field; however, this is not a big problem because most  this is not a big problem because most features only have a small number of annotations.
1561  features only have a small number of annotations.  Finally, if a single user has multiple functional assignments, we will only keep the most
1562    recent one.
1563    
1564  =over 4  =over 4
1565    
# Line 1026  Line 1569 
1569    
1570  =item RETURN  =item RETURN
1571    
1572  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1573    
1574  =back  =back
1575    
# Line 1034  Line 1577 
1577  #: Return Type %;  #: Return Type %;
1578  sub AllFunctionsOf {  sub AllFunctionsOf {
1579          # Get the parameters.          # Get the parameters.
1580          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1581          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1582          my @query = $self->GetFlat(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1583                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1584                                                          [$featureID], 'Annotation(annotation)');                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1585                                               'MadeAnnotation(from-link)']);
1586          # Declare the return hash.          # Declare the return hash.
1587          my %retVal;          my %retVal;
1588        # Now we sort the assignments by timestamp in reverse.
1589        my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1590          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1591          for my $text (@query) {      for my $annotation (@sortedQuery) {
1592            # Get the annotation fields.
1593            my ($timeStamp, $text, $user) = @{$annotation};
1594                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1595                  my ($user, $function) = ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1596                  if ($user) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1597                          # Here it is, so stuff it in the return hash.              # Here it is a functional assignment and there has been no
1598                          $retVal{$function} = $user;              # previous assignment for this user, so we stuff it in the
1599                # return hash.
1600                $retVal{$actualUser} = $function;
1601                  }                  }
1602          }          }
1603          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1057  Line 1606 
1606    
1607  =head3 FunctionOf  =head3 FunctionOf
1608    
1609  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1610    
1611  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1612    
1613  The functional assignment is handled differently depending on the type of feature. If  The functional assignment is handled differently depending on the type of feature. If
1614  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional  the feature is identified by a FIG ID (begins with the string C<fig|>), then the functional
1615  assignment is a type of annotation. It has the format "XXXX\nset XXXX function to\nYYYYY". In this  assignment is taken from the B<Feature> or C<Annotation> table, depending.
 instance, XXXX is the user ID and YYYYY is the functional assignment text. Its worth noting that  
 we cannot filter on the content of the annotation itself because it's a text field; however, this  
 is not a big problem because most features only have a small number of annotations.  
1616    
1617  Each user has an associated list of trusted users. The assignment returned will be the most  Each user has an associated list of trusted users. The assignment returned will be the most
1618  recent one by at least one of the trusted users. If no trusted user list is available, then  recent one by at least one of the trusted users. If no trusted user list is available, then
# Line 1085  Line 1631 
1631    
1632  =item userID (optional)  =item userID (optional)
1633    
1634  ID of the user whose function determination is desired. If omitted, only the latest  ID of the user whose function determination is desired. If omitted, the primary
1635  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1636    
1637  =item RETURN  =item RETURN
1638    
# Line 1098  Line 1644 
1644  #: Return Type $;  #: Return Type $;
1645  sub FunctionOf {  sub FunctionOf {
1646          # Get the parameters.          # Get the parameters.
1647          my $self = shift @_;      my ($self, $featureID, $userID) = @_;
         my ($featureID, $userID) = @_;  
1648      # Declare the return value.      # Declare the return value.
1649      my $retVal;      my $retVal;
1650      # Determine the ID type.      # Determine the ID type.
1651      if ($featureID =~ m/^fig\|/) {      if ($featureID =~ m/^fig\|/) {
1652          # Here we have a FIG feature ID. We must build the list of trusted          # Here we have a FIG feature ID.
1653          # users.          if (!$userID) {
1654                # Use the primary assignment.
1655                ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);
1656            } else {
1657                # We must build the list of trusted users.
1658          my %trusteeTable = ();          my %trusteeTable = ();
1659          # Check the user ID.          # Check the user ID.
1660          if (!$userID) {          if (!$userID) {
# Line 1127  Line 1676 
1676              }              }
1677          }          }
1678          # Build a query for all of the feature's annotations, sorted by date.          # Build a query for all of the feature's annotations, sorted by date.
1679          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1680                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1681                                 [$featureID]);                                 [$featureID]);
1682          my $timeSelected = 0;          my $timeSelected = 0;
1683          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1684          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1685              # Get the annotation text.              # Get the annotation text.
1686              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);                  my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1687                                                             'Annotation(time)', 'MadeAnnotation(from-link)']);
1688              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1689              my ($user, $type, $function) = split(/\n/, $text);                  my ($actualUser, $function) = _ParseAssignment($user, $text);
1690              if ($type =~ m/^set $user function to$/i) {                  Trace("Assignment user is $actualUser, text is $function.") if T(4);
1691                    if ($actualUser) {
1692                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1693                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1694                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                      if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1695                      $retVal = $function;                      $retVal = $function;
1696                      $timeSelected = $time;                      $timeSelected = $time;
1697                  }                  }
1698              }              }
1699          }          }
1700            }
1701      } else {      } else {
1702          # Here we have a non-FIG feature ID. In this case the user ID does not          # Here we have a non-FIG feature ID. In this case the user ID does not
1703          # matter. We simply get the information from the External Alias Function          # matter. We simply get the information from the External Alias Function
# Line 1156  Line 1708 
1708          return $retVal;          return $retVal;
1709  }  }
1710    
1711    =head3 FunctionsOf
1712    
1713        my @functionList = $sprout->FunctionOf($featureID, $userID);
1714    
1715    Return the functional assignments of a particular feature.
1716    
1717    The functional assignment is handled differently depending on the type of feature. If
1718    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1719    assignment is a type of annotation. The format of an assignment is described in
1720    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1721    annotation itself because it's a text field; however, this is not a big problem because
1722    most features only have a small number of annotations.
1723    
1724    If the feature is B<not> identified by a FIG ID, then the functional assignment
1725    information is taken from the B<ExternalAliasFunc> table. If the table does
1726    not contain an entry for the feature, an empty list is returned.
1727    
1728    =over 4
1729    
1730    =item featureID
1731    
1732    ID of the feature whose functional assignments are desired.
1733    
1734    =item RETURN
1735    
1736    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1737    that user.
1738    
1739    =back
1740    
1741    =cut
1742    #: Return Type @@;
1743    sub FunctionsOf {
1744        # Get the parameters.
1745        my ($self, $featureID) = @_;
1746        # Declare the return value.
1747        my @retVal = ();
1748        # Determine the ID type.
1749        if ($featureID =~ m/^fig\|/) {
1750            # Here we have a FIG feature ID. We must build the list of trusted
1751            # users.
1752            my %trusteeTable = ();
1753            # Build a query for all of the feature's annotations, sorted by date.
1754            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1755                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1756                                   [$featureID]);
1757            my $timeSelected = 0;
1758            # Loop until we run out of annotations.
1759            while (my $annotation = $query->Fetch()) {
1760                # Get the annotation text.
1761                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1762                                                                'Annotation(time)',
1763                                                                'MadeAnnotation(user)']);
1764                # Check to see if this is a functional assignment for a trusted user.
1765                my ($actualUser, $function) = _ParseAssignment($user, $text);
1766                if ($actualUser) {
1767                    # Here it is a functional assignment.
1768                    push @retVal, [$actualUser, $function];
1769                }
1770            }
1771        } else {
1772            # Here we have a non-FIG feature ID. In this case the user ID does not
1773            # matter. We simply get the information from the External Alias Function
1774            # table.
1775            my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1776                                                     ['ExternalAliasFunc(func)']);
1777            push @retVal, map { ['master', $_] } @assignments;
1778        }
1779        # Return the assignments found.
1780        return @retVal;
1781    }
1782    
1783  =head3 BBHList  =head3 BBHList
1784    
1785  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1786    
1787  Return a hash mapping the features in a specified list to their bidirectional best hits  Return a hash mapping the features in a specified list to their bidirectional best hits
1788  on a specified target genome.  on a specified target genome.
# Line 1175  Line 1799 
1799    
1800  =item RETURN  =item RETURN
1801    
1802  Returns a reference to a hash that maps the IDs of the incoming features to the IDs of  Returns a reference to a hash that maps the IDs of the incoming features to the best hits
1803  their best hits.  on the target genome.
1804    
1805  =back  =back
1806    
# Line 1184  Line 1808 
1808  #: Return Type %;  #: Return Type %;
1809  sub BBHList {  sub BBHList {
1810          # Get the parameters.          # Get the parameters.
1811          my $self = shift @_;      my ($self, $genomeID, $featureList) = @_;
         my ($genomeID, $featureList) = @_;  
1812          # Create the return structure.          # Create the return structure.
1813          my %retVal = ();          my %retVal = ();
1814          # Loop through the incoming features.          # Loop through the incoming features.
1815          for my $featureID (@{$featureList}) {          for my $featureID (@{$featureList}) {
1816                  # Create a query to get the feature's best hit.          # Ask the server for the feature's best hit.
1817                  my $query = $self->Get(['IsBidirectionalBestHitOf'],          my @bbhData = FIGRules::BBHData($featureID);
1818                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",          # Peel off the BBHs found.
1819                                                             [$featureID, $genomeID]);          my @found = ();
1820                  # Look for the best hit.          for my $bbh (@bbhData) {
1821                  my $bbh = $query->Fetch;              my $fid = $bbh->[0];
1822                  if ($bbh) {              my $bbGenome = $self->GenomeOf($fid);
1823                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              if ($bbGenome eq $genomeID) {
1824                          $retVal{$featureID} = $targetFeature;                  push @found, $fid;
1825                }
1826                  }                  }
1827            $retVal{$featureID} = \@found;
1828          }          }
1829          # Return the mapping.          # Return the mapping.
1830          return \%retVal;          return \%retVal;
1831  }  }
1832    
1833    =head3 SimList
1834    
1835        my %similarities = $sprout->SimList($featureID, $count);
1836    
1837    Return a list of the similarities to the specified feature.
1838    
1839    This method just returns the bidirectional best hits for performance reasons.
1840    
1841    =over 4
1842    
1843    =item featureID
1844    
1845    ID of the feature whose similarities are desired.
1846    
1847    =item count
1848    
1849    Maximum number of similar features to be returned, or C<0> to return them all.
1850    
1851    =back
1852    
1853    =cut
1854    #: Return Type %;
1855    sub SimList {
1856        # Get the parameters.
1857        my ($self, $featureID, $count) = @_;
1858        # Ask for the best hits.
1859        my @lists = FIGRules::BBHData($featureID);
1860        # Create the return value.
1861        my %retVal = ();
1862        for my $tuple (@lists) {
1863            $retVal{$tuple->[0]} = $tuple->[1];
1864        }
1865        # Return the result.
1866        return %retVal;
1867    }
1868    
1869    =head3 IsComplete
1870    
1871        my $flag = $sprout->IsComplete($genomeID);
1872    
1873    Return TRUE if the specified genome is complete, else FALSE.
1874    
1875    =over 4
1876    
1877    =item genomeID
1878    
1879    ID of the genome whose completeness status is desired.
1880    
1881    =item RETURN
1882    
1883    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1884    not found.
1885    
1886    =back
1887    
1888    =cut
1889    #: Return Type $;
1890    sub IsComplete {
1891        # Get the parameters.
1892        my ($self, $genomeID) = @_;
1893        # Declare the return variable.
1894        my $retVal;
1895        # Get the genome's data.
1896        my $genomeData = $self->GetEntity('Genome', $genomeID);
1897        if ($genomeData) {
1898            # The genome exists, so get the completeness flag.
1899            $retVal = $genomeData->PrimaryValue('Genome(complete)');
1900        }
1901        # Return the result.
1902        return $retVal;
1903    }
1904    
1905  =head3 FeatureAliases  =head3 FeatureAliases
1906    
1907  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1908    
1909  Return a list of the aliases for a specified feature.  Return a list of the aliases for a specified feature.
1910    
# Line 1228  Line 1925 
1925  #: Return Type @;  #: Return Type @;
1926  sub FeatureAliases {  sub FeatureAliases {
1927          # Get the parameters.          # Get the parameters.
1928          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1929          # Get the desired feature's aliases          # Get the desired feature's aliases
1930          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
1931          # Return the result.          # Return the result.
1932          return @retVal;          return @retVal;
1933  }  }
1934    
1935  =head3 GenomeOf  =head3 GenomeOf
1936    
1937  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $genomeID = $sprout->GenomeOf($featureID);
1938    
1939  Return the genome that contains a specified feature.  Return the genome that contains a specified feature or contig.
1940    
1941  =over 4  =over 4
1942    
1943  =item featureID  =item featureID
1944    
1945  ID of the feature whose genome is desired.  ID of the feature or contig whose genome is desired.
1946    
1947  =item RETURN  =item RETURN
1948    
1949  Returns the ID of the genome for the specified feature. If the feature is not found, returns  Returns the ID of the genome for the specified feature or contig. If the feature or contig is not
1950  an undefined value.  found, returns an undefined value.
1951    
1952  =back  =back
1953    
# Line 1259  Line 1955 
1955  #: Return Type $;  #: Return Type $;
1956  sub GenomeOf {  sub GenomeOf {
1957          # Get the parameters.          # Get the parameters.
1958          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
         # Create a query to find the genome associated with the feature.  
         my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);  
1959          # Declare the return value.          # Declare the return value.
1960          my $retVal;          my $retVal;
1961          # Get the genome ID.      # Parse the genome ID from the feature ID.
1962          if (my $relationship = $query->Fetch()) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
1963                  ($retVal) = $relationship->Value('HasContig(from-link)');          $retVal = $1;
1964        } else {
1965            # Find the feature by alias.
1966            my ($realFeatureID) = $self->FeaturesByAlias($featureID);
1967            if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {
1968                $retVal = $1;
1969            } else {
1970                # Use the external table.
1971                my ($org) = $self->GetFlat(['ExternalAliasOrg'], "ExternalAliasOrg(id) = ?",
1972                                           [$featureID], "ExternalAliasOrg(org)");
1973                if ($org) {
1974                    $retVal = $org;
1975                } else {
1976                    Confess("Invalid feature ID $featureID.");
1977                }
1978            }
1979          }          }
1980          # Return the value found.          # Return the value found.
1981          return $retVal;          return $retVal;
# Line 1275  Line 1983 
1983    
1984  =head3 CoupledFeatures  =head3 CoupledFeatures
1985    
1986  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
1987    
1988  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
1989  functionally coupled if they tend to be clustered on the same chromosome.  functionally coupled if they tend to be clustered on the same chromosome.
# Line 1296  Line 2004 
2004  #: Return Type %;  #: Return Type %;
2005  sub CoupledFeatures {  sub CoupledFeatures {
2006          # Get the parameters.          # Get the parameters.
2007          my $self = shift @_;      my ($self, $featureID) = @_;
2008          my ($featureID) = @_;      # Ask the coupling server for the data.
2009          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
2010          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
2011          # (B,A) will also be found.      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
2012          my $query = $self->Get(['IsClusteredOnChromosomeWith'],      # Form them into a hash.
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
         # This value will be set to TRUE if we find at least one coupled feature.  
         my $found = 0;  
         # Create the return hash.  
2013          my %retVal = ();          my %retVal = ();
2014          # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
2015          while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
2016                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          my ($featureID2, $score) = @{$pair};
2017                                                                      'IsClusteredOnChromosomeWith(score)']);          # Only proceed if the feature is in NMPDR.
2018                  $retVal{$otherFeatureID} = $score;          if ($self->_CheckFeature($featureID2)) {
2019                  $found = 1;              $retVal{$featureID2} = $score;
2020            }
2021          }          }
2022          # Functional coupling is reflexive. If we found at least one coupled feature, we must add          # Functional coupling is reflexive. If we found at least one coupled feature, we must add
2023          # the incoming feature as well.          # the incoming feature as well.
2024          if ($found) {      if (keys %retVal) {
2025                  $retVal{$featureID} = 9999;                  $retVal{$featureID} = 9999;
2026      }      }
2027          # Return the hash.          # Return the hash.
2028          return %retVal;          return %retVal;
2029  }  }
2030    
2031  =head3 GetEntityTypes  =head3 CouplingEvidence
2032    
2033  C<< my @entityList = $sprout->GetEntityTypes(); >>      my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
2034    
2035  Return the list of supported entity types.  Return the evidence for a functional coupling.
2036    
2037  =cut  A pair of features is considered evidence of a coupling between two other
2038  #: Return Type @;  features if they occur close together on a contig and both are similar to
2039  sub GetEntityTypes {  the coupled features. So, if B<A1> and B<A2> are close together on a contig,
2040          # Get the parameters.  B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
2041          my $self = shift @_;  B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
2042          # Get the underlying database object.  similar to B<A2>.
         my $erdb = $self->{_erdb};  
         # Get its entity type list.  
         my @retVal = $erdb->GetEntityTypes();  
 }  
2043    
2044  =head3 ReadFasta  The score of a coupling is determined by the number of pieces of evidence
2045    that are considered I<representative>. If several evidence items belong to
2046    a group of genomes that are close to each other, only one of those items
2047    is considered representative. The other evidence items are presumed to be
2048    there because of the relationship between the genomes rather than because
2049    the two proteins generated by the features have a related functionality.
2050    
2051  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>  Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
2052    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
2053    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
2054    and FALSE otherwise.
2055    
2056    =over 4
2057    
2058    =item peg1
2059    
2060    ID of the feature of interest.
2061    
2062    =item peg2
2063    
2064    ID of a feature functionally coupled to the feature of interest.
2065    
2066    =item RETURN
2067    
2068    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
2069    of interest, a feature similar to the functionally coupled feature, and a flag
2070    that is TRUE for a representative piece of evidence and FALSE otherwise.
2071    
2072    =back
2073    
2074    =cut
2075    #: Return Type @@;
2076    sub CouplingEvidence {
2077        # Get the parameters.
2078        my ($self, $peg1, $peg2) = @_;
2079        # Declare the return variable.
2080        my @retVal = ();
2081        # Get the coupling and evidence data.
2082        my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
2083        # Loop through the raw data, saving the ones that are in NMPDR genomes.
2084        for my $rawTuple (@rawData) {
2085            if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
2086                push @retVal, $rawTuple;
2087            }
2088        }
2089        # Return the result.
2090        return @retVal;
2091    }
2092    
2093    =head3 GetSynonymGroup
2094    
2095        my $id = $sprout->GetSynonymGroup($fid);
2096    
2097    Return the synonym group name for the specified feature.
2098    
2099    =over 4
2100    
2101    =item fid
2102    
2103    ID of the feature whose synonym group is desired.
2104    
2105    =item RETURN
2106    
2107    The name of the synonym group to which the feature belongs. If the feature does
2108    not belong to a synonym group, the feature ID itself is returned.
2109    
2110    =back
2111    
2112    =cut
2113    
2114    sub GetSynonymGroup {
2115        # Get the parameters.
2116        my ($self, $fid) = @_;
2117        # Declare the return variable.
2118        my $retVal;
2119        # Find the synonym group.
2120        my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?",
2121                                       [$fid], 'IsSynonymGroupFor(from-link)');
2122        # Check to see if we found anything.
2123        if (@groups) {
2124            $retVal = $groups[0];
2125        } else {
2126            $retVal = $fid;
2127        }
2128        # Return the result.
2129        return $retVal;
2130    }
2131    
2132    =head3 GetBoundaries
2133    
2134        my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2135    
2136    Determine the begin and end boundaries for the locations in a list. All of the
2137    locations must belong to the same contig and have mostly the same direction in
2138    order for this method to produce a meaningful result. The resulting
2139    begin/end pair will contain all of the bases in any of the locations.
2140    
2141    =over 4
2142    
2143    =item locList
2144    
2145    List of locations to process.
2146    
2147    =item RETURN
2148    
2149    Returns a 3-tuple consisting of the contig ID, the beginning boundary,
2150    and the ending boundary. The beginning boundary will be left of the
2151    end for mostly-forward locations and right of the end for mostly-backward
2152    locations.
2153    
2154    =back
2155    
2156    =cut
2157    
2158    sub GetBoundaries {
2159        # Get the parameters.
2160        my ($self, @locList) = @_;
2161        # Set up the counters used to determine the most popular direction.
2162        my %counts = ( '+' => 0, '-' => 0 );
2163        # Get the last location and parse it.
2164        my $locObject = BasicLocation->new(pop @locList);
2165        # Prime the loop with its data.
2166        my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right);
2167        # Count its direction.
2168        $counts{$locObject->Dir}++;
2169        # Loop through the remaining locations. Note that in most situations, this loop
2170        # will not iterate at all, because most of the time we will be dealing with a
2171        # singleton list.
2172        for my $loc (@locList) {
2173            # Create a location object.
2174            my $locObject = BasicLocation->new($loc);
2175            # Count the direction.
2176            $counts{$locObject->Dir}++;
2177            # Get the left end and the right end.
2178            my $left = $locObject->Left;
2179            my $right = $locObject->Right;
2180            # Merge them into the return variables.
2181            if ($left < $beg) {
2182                $beg = $left;
2183            }
2184            if ($right > $end) {
2185                $end = $right;
2186            }
2187        }
2188        # If the most common direction is reverse, flip the begin and end markers.
2189        if ($counts{'-'} > $counts{'+'}) {
2190            ($beg, $end) = ($end, $beg);
2191        }
2192        # Return the result.
2193        return ($contig, $beg, $end);
2194    }
2195    
2196    =head3 ReadFasta
2197    
2198        my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2199    
2200  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
2201  one or more lines of data. The first line begins with a > character and contains an ID.  one or more lines of data. The first line begins with a > character and contains an ID.
# Line 1384  Line 2237 
2237                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
2238                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
2239                          if ($id) {                          if ($id) {
2240                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
2241                          }                          }
2242                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
2243                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
2244                  } else {                  } else {
2245                          # Here we have a data line, so we add it to the sequence accumulator.                          # Here we have a data line, so we add it to the sequence accumulator.
2246                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
2247                # case.
2248                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
2249                          $sequence .= $1;                          $sequence .= $1;
2250                  }                  }
2251          }          }
2252          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
2253          if ($sequence) {          if ($sequence) {
2254                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
2255          }          }
2256        # Close the file.
2257        close FASTAFILE;
2258          # Return the hash constructed from the file.          # Return the hash constructed from the file.
2259          return %retVal;          return %retVal;
2260  }  }
2261    
2262  =head3 FormatLocations  =head3 FormatLocations
2263    
2264  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2265    
2266  Insure that a list of feature locations is in the Sprout format. The Sprout feature location  Insure that a list of feature locations is in the Sprout format. The Sprout feature location
2267  format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward  format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward
2268  gene. The old format is I<contig>_I<beg>_I<end>.  gene. The old format is I<contig>_I<beg>_I<end>. If a feature is in the new format already,
2269    it will not be changed; otherwise, it will be converted. This method can also be used to
2270    perform the reverse task-- insuring that all the locations are in the old format.
2271    
2272  =over 4  =over 4
2273    
# Line 1436  Line 2294 
2294  #: Return Type @;  #: Return Type @;
2295  sub FormatLocations {  sub FormatLocations {
2296          # Get the parameters.          # Get the parameters.
2297          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
2298          # Create the return list.          # Create the return list.
2299          my @retVal = ();          my @retVal = ();
2300          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
2301          if ($locations eq '') {          if ($locations eq '') {
2302              confess "No locations specified.";          Confess("No locations specified.");
2303          } else {          } else {
2304                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
2305                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1469  Line 2326 
2326    
2327  =head3 DumpData  =head3 DumpData
2328    
2329  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2330    
2331  Dump all the tables to tab-delimited DTX files. The files will be stored in the data directory.  Dump all the tables to tab-delimited DTX files. The files will be stored in the data directory.
2332    
# Line 1477  Line 2334 
2334    
2335  sub DumpData {  sub DumpData {
2336          # Get the parameters.          # Get the parameters.
2337          my $self = shift @_;      my ($self) = @_;
2338          # Get the data directory name.          # Get the data directory name.
2339          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
2340          # Dump the relations.          # Dump the relations.
2341          $self->{_erdb}->DumpRelations($outputDirectory);      $self->DumpRelations($outputDirectory);
2342  }  }
2343    
2344  =head3 XMLFileName  =head3 XMLFileName
2345    
2346  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2347    
2348  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2349    
2350  =cut  =cut
2351  #: Return Type $;  #: Return Type $;
2352  sub XMLFileName {  sub XMLFileName {
2353          my $self = shift @_;      my ($self) = @_;
2354          return $self->{_xmlName};          return $self->{_xmlName};
2355  }  }
2356    
2357    =head3 GetGenomeNameData
2358    
2359        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2360    
2361    Return the genus, species, and unique characterization for a genome. This
2362    is similar to L</GenusSpecies>, with the exception that it returns the
2363    values in three seperate fields.
2364    
2365    =over 4
2366    
2367    =item genomeID
2368    
2369    ID of the genome whose name data is desired.
2370    
2371    =item RETURN
2372    
2373    Returns a three-element list, consisting of the genus, species, and strain
2374    of the specified genome. If the genome is not found, an error occurs.
2375    
2376    =back
2377    
2378    =cut
2379    
2380    sub GetGenomeNameData {
2381        # Get the parameters.
2382        my ($self, $genomeID) = @_;
2383        # Get the desired values.
2384        my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>
2385                                                                [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);
2386        # Throw an error if they were not found.
2387        if (! defined $genus) {
2388            Confess("Genome $genomeID not found in database.");
2389        }
2390        # Return the results.
2391        return ($genus, $species, $strain);
2392    }
2393    
2394    =head3 GetGenomeByNameData
2395    
2396        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2397    
2398    Return a list of the IDs of the genomes with the specified genus,
2399    species, and strain. In almost every case, there will be either zero or
2400    one IDs returned; however, two or more IDs could be returned if there are
2401    multiple versions of the genome in the database.
2402    
2403    =over 4
2404    
2405    =item genus
2406    
2407    Genus of the desired genome.
2408    
2409    =item species
2410    
2411    Species of the desired genome.
2412    
2413    =item strain
2414    
2415    Strain (unique characterization) of the desired genome. This may be an empty
2416    string, in which case it is presumed that the desired genome has no strain
2417    specified.
2418    
2419    =item RETURN
2420    
2421    Returns a list of the IDs of the genomes having the specified genus, species, and
2422    strain.
2423    
2424    =back
2425    
2426    =cut
2427    
2428    sub GetGenomeByNameData {
2429        # Get the parameters.
2430        my ($self, $genus, $species, $strain) = @_;
2431        # Try to find the genomes.
2432        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2433                                    [$genus, $species, $strain], 'Genome(id)');
2434        # Return the result.
2435        return @retVal;
2436    }
2437    
2438  =head3 Insert  =head3 Insert
2439    
2440  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2441    
2442  Insert an entity or relationship instance into the database. The entity or relationship of interest  Insert an entity or relationship instance into the database. The entity or relationship of interest
2443  is defined by a type name and then a hash of field names to values. Field values in the primary  is defined by a type name and then a hash of field names to values. Field values in the primary
# Line 1508  Line 2446 
2446  list references. For example, the following line inserts an inactive PEG feature named  list references. For example, the following line inserts an inactive PEG feature named
2447  C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.  C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.
2448    
2449  C<< $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>      $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']});
2450    
2451  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2452  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2453    
2454  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>      $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2455    
2456  =over 4  =over 4
2457    
# Line 1531  Line 2469 
2469  #: Return Type ;  #: Return Type ;
2470  sub Insert {  sub Insert {
2471          # Get the parameters.          # Get the parameters.
2472          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
2473          # Call the underlying method.          # Call the underlying method.
2474          $self->{_erdb}->InsertObject($objectType, $fieldHash);      $self->InsertObject($objectType, $fieldHash);
2475  }  }
2476    
2477  =head3 Annotate  =head3 Annotate
2478    
2479  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2480    
2481  Annotate a feature. This inserts an Annotation record into the database and links it to the  Annotate a feature. This inserts an Annotation record into the database and links it to the
2482  specified feature and user.  specified feature and user.
# Line 1573  Line 2510 
2510  #: Return Type $;  #: Return Type $;
2511  sub Annotate {  sub Annotate {
2512          # Get the parameters.          # Get the parameters.
2513          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
2514          # Create the annotation ID.          # Create the annotation ID.
2515          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
2516          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1594  Line 2530 
2530    
2531  =head3 AssignFunction  =head3 AssignFunction
2532    
2533  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2534    
2535  This method assigns a function to a feature. Functions are a special type of annotation. The general  This method assigns a function to a feature. Functions are a special type of annotation. The general
2536  format is "XXXX\nset XXXX function to\nYYYYY" where XXXX is the feature type and YYYY is the functional  format is described in L</ParseAssignment>.
 assignment text.  
2537    
2538  =over 4  =over 4
2539    
# Line 1608  Line 2543 
2543    
2544  =item user  =item user
2545    
2546  Name of the user making the assignment. This is frequently a group name, like C<kegg> or C<fig>.  Name of the user group making the assignment, such as C<kegg> or C<fig>.
2547    
2548  =item function  =item function
2549    
2550  Text of the function being assigned.  Text of the function being assigned.
2551    
2552    =item assigningUser (optional)
2553    
2554    Name of the individual user making the assignment. If omitted, defaults to the user group.
2555    
2556  =item RETURN  =item RETURN
2557    
2558  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1624  Line 2563 
2563  #: Return Type $;  #: Return Type $;
2564  sub AssignFunction {  sub AssignFunction {
2565          # Get the parameters.          # Get the parameters.
2566          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
2567          my ($featureID, $user, $function) = @_;      # Default the assigning user.
2568        if (! $assigningUser) {
2569            $assigningUser = $user;
2570        }
2571          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
2572          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
2573          # Get the current time.          # Get the current time.
2574          my $now = time;          my $now = time;
2575          # Declare the return variable.          # Declare the return variable.
# Line 1648  Line 2590 
2590    
2591  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2592    
2593  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2594    
2595  Returns a list of features with the specified alias. The alias is parsed to determine  Returns a list of features with the specified alias. The alias is parsed to determine
2596  the type of the alias. A string of digits is a GenBack ID and a string of exactly 6  the type of the alias. A string of digits is a GenBack ID and a string of exactly 6
# Line 1672  Line 2614 
2614  #: Return Type @;  #: Return Type @;
2615  sub FeaturesByAlias {  sub FeaturesByAlias {
2616          # Get the parameters.          # Get the parameters.
2617          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
2618          # Declare the return variable.          # Declare the return variable.
2619          my @retVal = ();          my @retVal = ();
2620          # Parse the alias.          # Parse the alias.
# Line 1683  Line 2624 
2624                  push @retVal, $mappedAlias;                  push @retVal, $mappedAlias;
2625          } else {          } else {
2626                  # Here we have a non-FIG alias. Get the features with the normalized alias.                  # Here we have a non-FIG alias. Get the features with the normalized alias.
2627                  @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2628          }          }
2629          # Return the result.          # Return the result.
2630          return @retVal;          return @retVal;
2631  }  }
2632    
 =head3 Exists  
   
 C<< my $found = $sprout->Exists($entityName, $entityID); >>  
   
 Return TRUE if an entity exists, else FALSE.  
   
 =over 4  
   
 =item entityName  
   
 Name of the entity type (e.g. C<Feature>) relevant to the existence check.  
   
 =item entityID  
   
 ID of the entity instance whose existence is to be checked.  
   
 =item RETURN  
   
 Returns TRUE if the entity instance exists, else FALSE.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub Exists {  
         # Get the parameters.  
         my $self = shift @_;  
         my ($entityName, $entityID) = @_;  
         # Check for the entity instance.  
         my $testInstance = $self->GetEntity($entityName, $entityID);  
         # Return an existence indicator.  
         my $retVal = ($testInstance ? 1 : 0);  
         return $retVal;  
 }  
   
2633  =head3 FeatureTranslation  =head3 FeatureTranslation
2634    
2635  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2636    
2637  Return the translation of a feature.  Return the translation of a feature.
2638    
# Line 1746  Line 2652 
2652  #: Return Type $;  #: Return Type $;
2653  sub FeatureTranslation {  sub FeatureTranslation {
2654          # Get the parameters.          # Get the parameters.
2655          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2656          # Get the specified feature's translation.          # Get the specified feature's translation.
2657          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2658          return $retVal;          return $retVal;
# Line 1755  Line 2660 
2660    
2661  =head3 Taxonomy  =head3 Taxonomy
2662    
2663  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2664    
2665  Return the taxonomy of the specified genome. This will be in the form of a list  Return the taxonomy of the specified genome. This will be in the form of a list
2666  containing the various classifications in order from domain (eg. C<Bacteria>, C<Archaea>,  containing the various classifications in order from domain (eg. C<Bacteria>, C<Archaea>,
2667  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2668    
2669  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2670    
2671  =over 4  =over 4
2672    
# Line 1779  Line 2684 
2684  #: Return Type @;  #: Return Type @;
2685  sub Taxonomy {  sub Taxonomy {
2686          # Get the parameters.          # Get the parameters.
2687          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
2688          # Find the specified genome's taxonomy string.          # Find the specified genome's taxonomy string.
2689          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);
2690          # Declare the return variable.          # Declare the return variable.
# Line 1797  Line 2701 
2701    
2702  =head3 CrudeDistance  =head3 CrudeDistance
2703    
2704  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2705    
2706  Returns a crude estimate of the distance between two genomes. The distance is construed so  Returns a crude estimate of the distance between two genomes. The distance is construed so
2707  that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.  that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.
# Line 1823  Line 2727 
2727  #: Return Type $;  #: Return Type $;
2728  sub CrudeDistance {  sub CrudeDistance {
2729          # Get the parameters.          # Get the parameters.
2730          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2731          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2732          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2733          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1850  Line 2753 
2753    
2754  =head3 RoleName  =head3 RoleName
2755    
2756  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2757    
2758  Return the descriptive name of the role with the specified ID. In general, a role  Return the descriptive name of the role with the specified ID. In general, a role
2759  will only have a descriptive name if it is coded as an EC number.  will only have a descriptive name if it is coded as an EC number.
# Line 1871  Line 2774 
2774  #: Return Type $;  #: Return Type $;
2775  sub RoleName {  sub RoleName {
2776          # Get the parameters.          # Get the parameters.
2777          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2778          # Get the specified role's name.          # Get the specified role's name.
2779          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2780          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1885  Line 2787 
2787    
2788  =head3 RoleDiagrams  =head3 RoleDiagrams
2789    
2790  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2791    
2792  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2793    
# Line 1905  Line 2807 
2807  #: Return Type @;  #: Return Type @;
2808  sub RoleDiagrams {  sub RoleDiagrams {
2809          # Get the parameters.          # Get the parameters.
2810          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2811          # Query for the diagrams.          # Query for the diagrams.
2812          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2813                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1914  Line 2815 
2815          return @retVal;          return @retVal;
2816  }  }
2817    
2818    =head3 GetProperties
2819    
2820        my @list = $sprout->GetProperties($fid, $key, $value, $url);
2821    
2822    Return a list of the properties with the specified characteristics.
2823    
2824    Properties are the Sprout analog of the FIG attributes. The call is
2825    passed directly to the CustomAttributes or RemoteCustomAttributes object
2826    contained in this object.
2827    
2828    This method returns a series of tuples that match the specified criteria. Each tuple
2829    will contain an object ID, a key, and one or more values. The parameters to this
2830    method therefore correspond structurally to the values expected in each tuple. In
2831    addition, you can ask for a generic search by suffixing a percent sign (C<%>) to any
2832    of the parameters. So, for example,
2833    
2834        my @attributeList = $sprout->GetProperties('fig|100226.1.peg.1004', 'structure%', 1, 2);
2835    
2836    would return something like
2837    
2838        ['fig}100226.1.peg.1004', 'structure', 1, 2]
2839        ['fig}100226.1.peg.1004', 'structure1', 1, 2]
2840        ['fig}100226.1.peg.1004', 'structure2', 1, 2]
2841        ['fig}100226.1.peg.1004', 'structureA', 1, 2]
2842    
2843    Use of C<undef> in any position acts as a wild card (all values). You can also specify
2844    a list reference in the ID column. Thus,
2845    
2846        my @attributeList = $sprout->GetProperties(['100226.1', 'fig|100226.1.%'], 'PUBMED');
2847    
2848    would get the PUBMED attribute data for Streptomyces coelicolor A3(2) and all its
2849    features.
2850    
2851    In addition to values in multiple sections, a single attribute key can have multiple
2852    values, so even
2853    
2854        my @attributeList = $sprout->GetProperties($peg, 'virulent');
2855    
2856    which has no wildcard in the key or the object ID, may return multiple tuples.
2857    
2858    =over 4
2859    
2860    =item objectID
2861    
2862    ID of object whose attributes are desired. If the attributes are desired for multiple
2863    objects, this parameter can be specified as a list reference. If the attributes are
2864    desired for all objects, specify C<undef> or an empty string. Finally, you can specify
2865    attributes for a range of object IDs by putting a percent sign (C<%>) at the end.
2866    
2867    =item key
2868    
2869    Attribute key name. A value of C<undef> or an empty string will match all
2870    attribute keys. If the values are desired for multiple keys, this parameter can be
2871    specified as a list reference. Finally, you can specify attributes for a range of
2872    keys by putting a percent sign (C<%>) at the end.
2873    
2874    =item values
2875    
2876    List of the desired attribute values, section by section. If C<undef>
2877    or an empty string is specified, all values in that section will match. A
2878    generic match can be requested by placing a percent sign (C<%>) at the end.
2879    In that case, all values that match up to and not including the percent sign
2880    will match. You may also specify a regular expression enclosed
2881    in slashes. All values that match the regular expression will be returned. For
2882    performance reasons, only values have this extra capability.
2883    
2884    =item RETURN
2885    
2886    Returns a list of tuples. The first element in the tuple is an object ID, the
2887    second is an attribute key, and the remaining elements are the sections of
2888    the attribute value. All of the tuples will match the criteria set forth in
2889    the parameter list.
2890    
2891    =back
2892    
2893    =cut
2894    
2895    sub GetProperties {
2896        # Get the parameters.
2897        my ($self, @parms) = @_;
2898        # Declare the return variable.
2899        my @retVal = $self->{_ca}->GetAttributes(@parms);
2900        # Return the result.
2901        return @retVal;
2902    }
2903    
2904  =head3 FeatureProperties  =head3 FeatureProperties
2905    
2906  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2907    
2908  Return a list of the properties for the specified feature. Properties are key-value pairs  Return a list of the properties for the specified feature. Properties are key-value pairs
2909  that specify special characteristics of the feature. For example, a property could indicate  that specify special characteristics of the feature. For example, a property could indicate
2910  that a feature is essential to the survival of the organism or that it has benign influence  that a feature is essential to the survival of the organism or that it has benign influence
2911  on the activities of a pathogen. Each property is returned as a triple of the form  on the activities of a pathogen. Each property is returned as a triple of the form
2912  C<($key,$value,$url)>, where C<$key> is the property name, C<$value> is its value (commonly  C<($key,@values)>, where C<$key> is the property name and  C<@values> are its values.
 a 1 or a 0, but possibly a string or a floating-point value), and C<$url> is a string describing  
 the web address or citation in which the property's value for the feature was identified.  
2913    
2914  =over 4  =over 4
2915    
# Line 1934  Line 2919 
2919    
2920  =item RETURN  =item RETURN
2921    
2922  Returns a list of triples, each triple containing the property name, its value, and a URL or  Returns a list of tuples, each tuple containing the property name and its values.
 citation.  
2923    
2924  =back  =back
2925    
# Line 1943  Line 2927 
2927  #: Return Type @@;  #: Return Type @@;
2928  sub FeatureProperties {  sub FeatureProperties {
2929          # Get the parameters.          # Get the parameters.
2930          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2931          # Get the properties.          # Get the properties.
2932          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->{_ca}->GetAttributes($featureID);
2933                                                          ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2934                                                           'HasProperty(evidence)']);      my @retVal = ();
2935        for my $attributeRow (@attributes) {
2936            shift @{$attributeRow};
2937            push @retVal, $attributeRow;
2938        }
2939          # Return the resulting list.          # Return the resulting list.
2940          return @retVal;          return @retVal;
2941  }  }
2942    
2943  =head3 DiagramName  =head3 DiagramName
2944    
2945  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2946    
2947  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2948    
# Line 1975  Line 2962 
2962  #: Return Type $;  #: Return Type $;
2963  sub DiagramName {  sub DiagramName {
2964          # Get the parameters.          # Get the parameters.
2965          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2966          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2967          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2968          return $retVal;          return $retVal;
2969  }  }
2970    
2971    =head3 PropertyID
2972    
2973        my $id = $sprout->PropertyID($propName, $propValue);
2974    
2975    Return the ID of the specified property name and value pair, if the
2976    pair exists. Only a small subset of the FIG attributes are stored as
2977    Sprout properties, mostly for use in search optimization.
2978    
2979    =over 4
2980    
2981    =item propName
2982    
2983    Name of the desired property.
2984    
2985    =item propValue
2986    
2987    Value expected for the desired property.
2988    
2989    =item RETURN
2990    
2991    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2992    
2993    =back
2994    
2995    =cut
2996    
2997    sub PropertyID {
2998        # Get the parameters.
2999        my ($self, $propName, $propValue) = @_;
3000        # Try to find the ID.
3001        my ($retVal) = $self->GetFlat(['Property'],
3002                                      "Property(property-name) = ? AND Property(property-value) = ?",
3003                                      [$propName, $propValue], 'Property(id)');
3004        # Return the result.
3005        return $retVal;
3006    }
3007    
3008  =head3 MergedAnnotations  =head3 MergedAnnotations
3009    
3010  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
3011    
3012  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
3013  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2008  Line 3031 
3031  #: Return Type @;  #: Return Type @;
3032  sub MergedAnnotations {  sub MergedAnnotations {
3033          # Get the parameters.          # Get the parameters.
3034          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
3035          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
3036          my @tuples = ();          my @tuples = ();
3037          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 2034  Line 3056 
3056    
3057  =head3 RoleNeighbors  =head3 RoleNeighbors
3058    
3059  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
3060    
3061  Returns a list of the roles that occur in the same diagram as the specified role. Because  Returns a list of the roles that occur in the same diagram as the specified role. Because
3062  diagrams and roles are in a many-to-many relationship with each other, the list is  diagrams and roles are in a many-to-many relationship with each other, the list is
# Line 2057  Line 3079 
3079  #: Return Type @;  #: Return Type @;
3080  sub RoleNeighbors {  sub RoleNeighbors {
3081          # Get the parameters.          # Get the parameters.
3082          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
3083          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
3084          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
3085                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2078  Line 3099 
3099    
3100  =head3 FeatureLinks  =head3 FeatureLinks
3101    
3102  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
3103    
3104  Return a list of the web hyperlinks associated with a feature. The web hyperlinks are  Return a list of the web hyperlinks associated with a feature. The web hyperlinks are
3105  to external websites describing either the feature itself or the organism containing it  to external websites describing either the feature itself or the organism containing it
# Line 2100  Line 3121 
3121  #: Return Type @;  #: Return Type @;
3122  sub FeatureLinks {  sub FeatureLinks {
3123          # Get the parameters.          # Get the parameters.
3124          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
3125          # Get the feature's links.          # Get the feature's links.
3126          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
3127          # Return the feature's links.          # Return the feature's links.
# Line 2110  Line 3130 
3130    
3131  =head3 SubsystemsOf  =head3 SubsystemsOf
3132    
3133  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3134    
3135  Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped  Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped
3136  to the role the feature performs.  to the roles the feature performs.
3137    
3138  =over 4  =over 4
3139    
# Line 2123  Line 3143 
3143    
3144  =item RETURN  =item RETURN
3145    
3146  Returns a hash mapping all the feature's subsystems to the feature's role.  Returns a hash mapping all the feature's subsystems to a list of the feature's roles.
3147    
3148  =back  =back
3149    
3150  =cut  =cut
3151  #: Return Type %;  #: Return Type %@;
3152  sub SubsystemsOf {  sub SubsystemsOf {
3153          # Get the parameters.          # Get the parameters.
3154          my $self = shift @_;      my ($self, $featureID) = @_;
3155          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
3156          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
3157                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
3158                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
3159          # Create the return value.          # Create the return value.
3160          my %retVal = ();          my %retVal = ();
3161        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
3162        # in two spreadsheet cells.
3163        my %dupHash = ();
3164          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
3165          for my $record (@subsystems) {          for my $record (@subsystems) {
3166                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
3167            my ($subsys, $role) = @{$record};
3168            # Insure it's the first time for both.
3169            my $dupKey = "$subsys\n$role";
3170            if (! exists $dupHash{"$subsys\n$role"}) {
3171                $dupHash{$dupKey} = 1;
3172                push @{$retVal{$subsys}}, $role;
3173            }
3174          }          }
3175          # Return the hash.          # Return the hash.
3176          return %retVal;          return %retVal;
3177  }  }
3178    
3179    =head3 SubsystemList
3180    
3181        my @subsystems = $sprout->SubsystemList($featureID);
3182    
3183    Return a list containing the names of the subsystems in which the specified
3184    feature participates. Unlike L</SubsystemsOf>, this method only returns the
3185    subsystem names, not the roles.
3186    
3187    =over 4
3188    
3189    =item featureID
3190    
3191    ID of the feature whose subsystem names are desired.
3192    
3193    =item RETURN
3194    
3195    Returns a list of the names of the subsystems in which the feature participates.
3196    
3197    =back
3198    
3199    =cut
3200    #: Return Type @;
3201    sub SubsystemList {
3202        # Get the parameters.
3203        my ($self, $featureID) = @_;
3204        # Get the list of names.
3205        my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?",
3206                                    [$featureID], 'HasRoleInSubsystem(to-link)');
3207        # Return the result, sorted.
3208        return sort @retVal;
3209    }
3210    
3211    =head3 GenomeSubsystemData
3212    
3213        my %featureData = $sprout->GenomeSubsystemData($genomeID);
3214    
3215    Return a hash mapping genome features to their subsystem roles.
3216    
3217    =over 4
3218    
3219    =item genomeID
3220    
3221    ID of the genome whose subsystem feature map is desired.
3222    
3223    =item RETURN
3224    
3225    Returns a hash mapping each feature of the genome to a list of 2-tuples. Eacb
3226    2-tuple contains a subsystem name followed by a role ID.
3227    
3228    =back
3229    
3230    =cut
3231    
3232    sub GenomeSubsystemData {
3233        # Get the parameters.
3234        my ($self, $genomeID) = @_;
3235        # Declare the return variable.
3236        my %retVal = ();
3237        # Get a list of the genome features that participate in subsystems. For each
3238        # feature we get its spreadsheet cells and the corresponding roles.
3239        my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'],
3240                                 "HasFeature(from-link) = ?", [$genomeID],
3241                                 ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']);
3242        # Now we get a list of the spreadsheet cells and their associated subsystems. Subsystems
3243        # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the
3244        # list. We use it at the beginning to get all the spreadsheet cells for the genome and
3245        # again at the end to filter out participation in subsystems with a negative variant code.
3246        my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'],
3247                                     "IsGenomeOf(from-link) = ? AND ParticipatesIn(variant-code) >= 0 AND ParticipatesIn(from-link) = ?",
3248                                     [$genomeID, $genomeID], ['HasSSCell(to-link)', 'HasSSCell(from-link)']);
3249        # Now "@roleData" lists the spreadsheet cell and role for each of the genome's features.
3250        # "@cellData" lists the subsystem name for each of the genome's spreadsheet cells. We
3251        # link these two lists together to create the result. First, we want a hash mapping
3252        # spreadsheet cells to subsystem names.
3253        my %subHash = map { $_->[0] => $_->[1] } @cellData;
3254        # We loop through @cellData to build the hash.
3255        for my $roleEntry (@roleData) {
3256            # Get the data for this feature and cell.
3257            my ($fid, $cellID, $role) = @{$roleEntry};
3258            # Check for a subsystem name.
3259            my $subsys = $subHash{$cellID};
3260            if ($subsys) {
3261                # Insure this feature has an entry in the return hash.
3262                if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3263                # Merge in this new data.
3264                push @{$retVal{$fid}}, [$subsys, $role];
3265            }
3266        }
3267        # Return the result.
3268        return %retVal;
3269    }
3270    
3271  =head3 RelatedFeatures  =head3 RelatedFeatures
3272    
3273  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
3274    
3275  Return a list of the features which are bi-directional best hits of the specified feature and  Return a list of the features which are bi-directional best hits of the specified feature and
3276  have been assigned the specified function by the specified user. If no such features exists,  have been assigned the specified function by the specified user. If no such features exists,
# Line 2180  Line 3301 
3301  #: Return Type @;  #: Return Type @;
3302  sub RelatedFeatures {  sub RelatedFeatures {
3303          # Get the parameters.          # Get the parameters.
3304          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
         my ($featureID, $function, $userID) = @_;  
3305          # Get a list of the features that are BBHs of the incoming feature.          # Get a list of the features that are BBHs of the incoming feature.
3306          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);
                                                                          "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],  
                                                                          'IsBidirectionalBestHitOf(to-link)');  
3307          # Now we loop through the features, pulling out the ones that have the correct          # Now we loop through the features, pulling out the ones that have the correct
3308          # functional assignment.          # functional assignment.
3309          my @retVal = ();          my @retVal = ();
# Line 2203  Line 3321 
3321    
3322  =head3 TaxonomySort  =head3 TaxonomySort
3323    
3324  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3325    
3326  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a list formed by sorting the specified features by the taxonomy of the containing
3327  genome. This will cause genomes from similar organisms to float close to each other.  genome. This will cause genomes from similar organisms to float close to each other.
# Line 2229  Line 3347 
3347  #: Return Type @;  #: Return Type @;
3348  sub TaxonomySort {  sub TaxonomySort {
3349          # Get the parameters.          # Get the parameters.
3350          my $self = shift @_;      my ($self, $featureIDs) = @_;
         my ($featureIDs) = @_;  
3351          # Create the working hash table.          # Create the working hash table.
3352          my %hashBuffer = ();          my %hashBuffer = ();
3353          # Loop through the features.          # Loop through the features.
# Line 2239  Line 3356 
3356                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3357                                                                                  [$fid], 'Genome(taxonomy)');                                                                                  [$fid], 'Genome(taxonomy)');
3358                  # Add this feature to the hash buffer.                  # Add this feature to the hash buffer.
                 if (exists $hashBuffer{$taxonomy}) {  
3359                          push @{$hashBuffer{$taxonomy}}, $fid;                          push @{$hashBuffer{$taxonomy}}, $fid;
                 } else {  
                         $hashBuffer{$taxonomy} = [$fid];  
                 }  
3360          }          }
3361          # Sort the keys and get the elements.          # Sort the keys and get the elements.
3362          my @retVal = ();          my @retVal = ();
# Line 2254  Line 3367 
3367          return @retVal;          return @retVal;
3368  }  }
3369    
3370  =head3 GetAll  =head3 Protein
   
 C<< my @list = $sprout->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>  
   
 Return a list of values taken from the objects returned by a query. The first three  
 parameters correspond to the parameters of the L</Get> method. The final parameter is  
 a list of the fields desired from each record found by the query. The field name  
 syntax is the standard syntax used for fields in the B<ERDB> system--  
 B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity  
 or relationship and I<fieldName> is the name of the field.  
3371    
3372  The list returned will be a list of lists. Each element of the list will contain      my $protein = Sprout::Protein($sequence, $table);
 the values returned for the fields specified in the fourth parameter. If one of the  
 fields specified returns multiple values, they are flattened in with the rest. For  
 example, the following call will return a list of the features in a particular  
 spreadsheet cell, and each feature will be represented by a list containing the  
 feature ID followed by all of its aliases.  
3373    
3374  C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  Translate a DNA sequence into a protein sequence.
3375    
3376  =over 4  =over 4
3377    
3378  =item objectNames  =item sequence
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
3379    
3380  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  DNA sequence to translate.
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
3381    
3382  =item parameterList  =item table (optional)
3383    
3384  List of the parameters to be substituted in for the parameters marks in the filter clause.  Reference to a Hash that translates DNA triples to proteins. A triple that does not
3385    appear in the hash will be translated automatically to C<X>.
3386    
3387  =item fields  =item RETURN
3388    
3389  List of the fields to be returned in each element of the list returned.  Returns the protein sequence that would be created by the DNA sequence.
3390    
3391  =item count  =back
3392    
3393  Maximum number of records to return. If omitted or 0, all available records will be returned.  =cut
   
 =item RETURN  
   
 Returns a list of list references. Each element of the return list contains the values for the  
 fields specified in the B<fields> parameter.  
   
 =back  
   
 =cut  
 #: Return Type @@;  
 sub GetAll {  
         # Get the parameters.  
         my $self = shift @_;  
         my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;  
         # Create the query.  
         my $query = $self->Get($objectNames, $filterClause, $parameterList);  
         # Set up a counter of the number of records read.  
         my $fetched = 0;  
         # Insure the counter has a value.  
         if (!defined $count) {  
                 $count = 0;  
         }  
         # Loop through the records returned, extracting the fields. Note that if the  
         # counter is non-zero, we stop when the number of records read hits the count.  
         my @retVal = ();  
         while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {  
                 my @rowData = $row->Values($fields);  
                 push @retVal, \@rowData;  
                 $fetched++;  
         }  
         # Return the resulting list.  
         return @retVal;  
 }  
   
 =head3 GetFlat  
   
 C<< my @list = $sprout->GetFlat(\@objectNames, $filterClause, $parameterList, $field); >>  
   
 This is a variation of L</GetAll> that asks for only a single field per record and  
 returns a single flattened list.  
   
 =over 4  
   
 =item objectNames  
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
   
 =item field  
   
 Name of the field to be used to get the elements of the list returned.  
   
 =item RETURN  
   
 Returns a list of values.  
   
 =back  
   
 =cut  
 #: Return Type @;  
 sub GetFlat {  
         # Get the parameters.  
         my $self = shift @_;  
         my ($objectNames, $filterClause, $parameterList, $field) = @_;  
         # Construct the query.  
         my $query = $self->Get($objectNames, $filterClause, $parameterList);  
         # Create the result list.  
         my @retVal = ();  
         # Loop through the records, adding the field values found to the result list.  
         while (my $row = $query->Fetch()) {  
                 push @retVal, $row->Value($field);  
         }  
         # Return the list created.  
         return @retVal;  
 }  
   
 =head3 Protein  
   
 C<< my $protein = Sprout::Protein($sequence, $table); >>  
   
 Translate a DNA sequence into a protein sequence.  
   
 =over 4  
   
 =item sequence  
   
 DNA sequence to translate.  
   
 =item table (optional)  
   
 Reference to a Hash that translates DNA triples to proteins. A triple that does not  
 appear in the hash will be translated automatically to C<X>.  
   
 =item RETURN  
   
 Returns the protein sequence that would be created by the DNA sequence.  
   
 =back  
   
 =cut  
3394    
3395  # This is the translation table for protein synthesis.  # This is the translation table for protein synthesis.
3396  my $ProteinTable = { AAA => 'K', AAG => 'K', AAT => 'N', AAC => 'N',  my $ProteinTable = { AAA => 'K', AAG => 'K', AAT => 'N', AAC => 'N',
# Line 2460  Line 3439 
3439          # Loop through the input triples.          # Loop through the input triples.
3440          my $n = length $sequence;          my $n = length $sequence;
3441          for (my $i = 0; $i < $n; $i += 3) {          for (my $i = 0; $i < $n; $i += 3) {
3442                  # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3443                  my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3444            my $triple = uc substr($sequence, $i, 3);
3445                  # Translate it using the table.                  # Translate it using the table.
3446                  my $protein = "X";                  my $protein = "X";
3447                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 2475  Line 3455 
3455    
3456  =head3 LoadInfo  =head3 LoadInfo
3457    
3458  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3459    
3460  Return the name of the directory from which data is to be loaded and a list of the relation  Return the name of the directory from which data is to be loaded and a list of the relation
3461  names. This information is useful when trying to analyze what needs to be put where in order  names. This information is useful when trying to analyze what needs to be put where in order
# Line 2485  Line 3465 
3465  #: Return Type @;  #: Return Type @;
3466  sub LoadInfo {  sub LoadInfo {
3467          # Get the parameters.          # Get the parameters.
3468          my $self = shift @_;      my ($self) = @_;
3469          # Create the return list, priming it with the name of the data directory.          # Create the return list, priming it with the name of the data directory.
3470          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
3471          # Concatenate the table names.          # Concatenate the table names.
3472          push @retVal, $self->{_erdb}->GetTableNames();      push @retVal, $self->GetTableNames();
3473          # Return the result.          # Return the result.
3474          return @retVal;          return @retVal;
3475  }  }
3476    
3477    =head3 BBHMatrix
3478    
3479        my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3480    
3481    Find all the bidirectional best hits for the features of a genome in a
3482    specified list of target genomes. The return value will be a hash mapping
3483    features in the original genome to their bidirectional best hits in the
3484    target genomes.
3485    
3486    =over 4
3487    
3488    =item genomeID
3489    
3490    ID of the genome whose features are to be examined for bidirectional best hits.
3491    
3492    =item cutoff
3493    
3494    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3495    
3496    =item targets
3497    
3498    List of target genomes. Only pairs originating in the original
3499    genome and landing in one of the target genomes will be returned.
3500    
3501    =item RETURN
3502    
3503    Returns a hash mapping each feature in the original genome to a hash mapping its
3504    BBH pegs in the target genomes to their scores.
3505    
3506    =back
3507    
3508    =cut
3509    
3510    sub BBHMatrix {
3511        # Get the parameters.
3512        my ($self, $genomeID, $cutoff, @targets) = @_;
3513        # Declare the return variable.
3514        my %retVal = ();
3515        # Ask for the BBHs.
3516        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3517        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3518        for my $bbhData (@bbhList) {
3519            my ($peg1, $peg2, $score) = @{$bbhData};
3520            if (! exists $retVal{$peg1}) {
3521                $retVal{$peg1} = { $peg2 => $score };
3522            } else {
3523                $retVal{$peg1}->{$peg2} = $score;
3524            }
3525        }
3526        # Return the result.
3527        return %retVal;
3528    }
3529    
3530    
3531    =head3 SimMatrix
3532    
3533        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3534    
3535    Find all the similarities for the features of a genome in a
3536    specified list of target genomes. The return value will be a hash mapping
3537    features in the original genome to their similarites in the
3538    target genomes.
3539    
3540    =over 4
3541    
3542    =item genomeID
3543    
3544    ID of the genome whose features are to be examined for similarities.
3545    
3546    =item cutoff
3547    
3548    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3549    
3550    =item targets
3551    
3552    List of target genomes. Only pairs originating in the original
3553    genome and landing in one of the target genomes will be returned.
3554    
3555    =item RETURN
3556    
3557    Returns a hash mapping each feature in the original genome to a hash mapping its
3558    similar pegs in the target genomes to their scores.
3559    
3560    =back
3561    
3562    =cut
3563    
3564    sub SimMatrix {
3565        # Get the parameters.
3566        my ($self, $genomeID, $cutoff, @targets) = @_;
3567        # Declare the return variable.
3568        my %retVal = ();
3569        # Get the list of features in the source organism.
3570        my @fids = $self->FeaturesOf($genomeID);
3571        # Ask for the sims. We only want similarities to fig features.
3572        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3573        if (! defined $simList) {
3574            Confess("Unable to retrieve similarities from server.");
3575        } else {
3576            Trace("Processing sims.") if T(3);
3577            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3578            # Create a hash for the target genomes.
3579            my %targetHash = map { $_ => 1 } @targets;
3580            for my $simData (@{$simList}) {
3581                # Get the PEGs and the score.
3582                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3583                # Insure the second ID is in the target list.
3584                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3585                if (exists $targetHash{$genome2}) {
3586                    # Here it is. Now we need to add it to the return hash. How we do that depends
3587                    # on whether or not $peg1 is new to us.
3588                    if (! exists $retVal{$peg1}) {
3589                        $retVal{$peg1} = { $peg2 => $score };
3590                    } else {
3591                        $retVal{$peg1}->{$peg2} = $score;
3592                    }
3593                }
3594            }
3595        }
3596        # Return the result.
3597        return %retVal;
3598    }
3599    
3600    
3601  =head3 LowBBHs  =head3 LowBBHs
3602    
3603  C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3604    
3605  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3606  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 2522  Line 3626 
3626  #: Return Type %;  #: Return Type %;
3627  sub LowBBHs {  sub LowBBHs {
3628          # Get the parsameters.          # Get the parsameters.
3629          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
3630          # Create the return hash.          # Create the return hash.
3631          my %retVal = ();          my %retVal = ();
3632          # Create a query to get the desired BBHs.      # Query for the desired BBHs.
3633          my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],      my @bbhList = FIGRules::BBHData($featureID, $cutoff);
                                                                 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',  
                                                                 [$cutoff, $featureID],  
                                                                 ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);  
3634          # Form the results into the return hash.          # Form the results into the return hash.
3635          for my $pair (@bbhList) {          for my $pair (@bbhList) {
3636                  $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3637            if ($self->Exists('Feature', $fid)) {
3638                $retVal{$fid} = $pair->[1];
3639            }
3640        }
3641        # Return the result.
3642        return %retVal;
3643    }
3644    
3645    =head3 Sims
3646    
3647        my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3648    
3649    Get a list of similarities for a specified feature. Similarity information is not kept in the
3650    Sprout database; rather, they are retrieved from a network server. The similarities are
3651    returned as B<Sim> objects. A Sim object is actually a list reference that has been blessed
3652    so that its elements can be accessed by name.
3653    
3654    Similarities can be either raw or expanded. The raw similarities are basic
3655    hits between features with similar DNA. Expanding a raw similarity drags in any
3656    features considered substantially identical. So, for example, if features B<A1>,
3657    B<A2>, and B<A3> are all substantially identical to B<A>, then a raw similarity
3658    B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3659    
3660    =over 4
3661    
3662    =item fid
3663    
3664    ID of the feature whose similarities are desired, or reference to a list of IDs
3665    of features whose similarities are desired.
3666    
3667    =item maxN
3668    
3669    Maximum number of similarities to return.
3670    
3671    =item maxP
3672    
3673    Minumum allowable similarity score.
3674    
3675    =item select
3676    
3677    Selection criterion: C<raw> means only raw similarities are returned; C<fig>
3678    means only similarities to FIG features are returned; C<all> means all expanded
3679    similarities are returned; and C<figx> means similarities are expanded until the
3680    number of FIG features equals the maximum.
3681    
3682    =item max_expand
3683    
3684    The maximum number of features to expand.
3685    
3686    =item filters
3687    
3688    Reference to a hash containing filter information, or a subroutine that can be
3689    used to filter the sims.
3690    
3691    =item RETURN
3692    
3693    Returns a reference to a list of similarity objects, or C<undef> if an error
3694    occurred.
3695    
3696    =back
3697    
3698    =cut
3699    
3700    sub Sims {
3701        # Get the parameters.
3702        my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_;
3703        # Create the shim object to test for deleted FIDs.
3704        my $shim = FidCheck->new($self);
3705        # Ask the network for sims.
3706        my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters);
3707        # Return the result.
3708        return $retVal;
3709    }
3710    
3711    =head3 IsAllGenomes
3712    
3713        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3714    
3715    Return TRUE if all genomes in the second list are represented in the first list at
3716    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3717    compared to a list of all the genomes.
3718    
3719    =over 4
3720    
3721    =item list
3722    
3723    Reference to the list to be compared to the second list.
3724    
3725    =item checkList (optional)
3726    
3727    Reference to the comparison target list. Every genome ID in this list must occur at
3728    least once in the first list. If this parameter is omitted, a list of all the genomes
3729    is used.
3730    
3731    =item RETURN
3732    
3733    Returns TRUE if every item in the second list appears at least once in the
3734    first list, else FALSE.
3735    
3736    =back
3737    
3738    =cut
3739    
3740    sub IsAllGenomes {
3741        # Get the parameters.
3742        my ($self, $list, $checkList) = @_;
3743        # Supply the checklist if it was omitted.
3744        $checkList = [$self->Genomes()] if ! defined($checkList);
3745        # Create a hash of the original list.
3746        my %testList = map { $_ => 1 } @{$list};
3747        # Declare the return variable. We assume that the representation
3748        # is complete and stop at the first failure.
3749        my $retVal = 1;
3750        my $n = scalar @{$checkList};
3751        for (my $i = 0; $retVal && $i < $n; $i++) {
3752            if (! $testList{$checkList->[$i]}) {
3753                $retVal = 0;
3754            }
3755        }
3756        # Return the result.
3757        return $retVal;
3758    }
3759    
3760    =head3 GetGroups
3761    
3762        my %groups = $sprout->GetGroups(\@groupList);
3763    
3764    Return a hash mapping each group to the IDs of the genomes in the group.
3765    A list of groups may be specified, in which case only those groups will be
3766    shown. Alternatively, if no parameter is supplied, all groups will be
3767    included. Genomes that are not in any group are omitted.
3768    
3769    =cut
3770    #: Return Type %@;
3771    sub GetGroups {
3772        # Get the parameters.
3773        my ($self, $groupList) = @_;
3774        # Declare the return value.
3775        my %retVal = ();
3776        # Determine whether we are getting all the groups or just some.
3777        if (defined $groupList) {
3778            # Here we have a group list. Loop through them individually,
3779            # getting a list of the relevant genomes.
3780            for my $group (@{$groupList}) {
3781                my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3782                    [$group], "Genome(id)");
3783                $retVal{$group} = \@genomeIDs;
3784            }
3785        } else {
3786            # Here we need all of the groups. In this case, we run through all
3787            # of the genome records, putting each one found into the appropriate
3788            # group. Note that we use a filter clause to insure that only genomes
3789            # in real NMPDR groups are included in the return set.
3790            my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3791                                        [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3792            # Loop through the genomes found.
3793            for my $genome (@genomes) {
3794                # Get the genome ID and group, and add this genome to the group's list.
3795                my ($genomeID, $group) = @{$genome};
3796                push @{$retVal{$group}}, $genomeID;
3797            }
3798        }
3799        # Return the hash we just built.
3800        return %retVal;
3801    }
3802    
3803    =head3 MyGenomes
3804    
3805        my @genomes = Sprout::MyGenomes($dataDir);
3806    
3807    Return a list of the genomes to be included in the Sprout.
3808    
3809    This method is provided for use during the Sprout load. It presumes the Genome load file has
3810    already been created. (It will be in the Sprout data directory and called either C<Genome>
3811    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3812    IDs.
3813    
3814    =over 4
3815    
3816    =item dataDir
3817    
3818    Directory containing the Sprout load files.
3819    
3820    =back
3821    
3822    =cut
3823    #: Return Type @;
3824    sub MyGenomes {
3825        # Get the parameters.
3826        my ($dataDir) = @_;
3827        # Compute the genome file name.
3828        my $genomeFileName = LoadFileName($dataDir, "Genome");
3829        # Extract the genome IDs from the files.
3830        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3831        # Return the result.
3832        return @retVal;
3833    }
3834    
3835    =head3 LoadFileName
3836    
3837        my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3838    
3839    Return the name of the load file for the specified table in the specified data
3840    directory.
3841    
3842    =over 4
3843    
3844    =item dataDir
3845    
3846    Directory containing the Sprout load files.
3847    
3848    =item tableName
3849    
3850    Name of the table whose load file is desired.
3851    
3852    =item RETURN
3853    
3854    Returns the name of the file containing the load data for the specified table, or
3855    C<undef> if no load file is present.
3856    
3857    =back
3858    
3859    =cut
3860    #: Return Type $;
3861    sub LoadFileName {
3862        # Get the parameters.
3863        my ($dataDir, $tableName) = @_;
3864        # Declare the return variable.
3865        my $retVal;
3866        # Check for the various file names.
3867        if (-e "$dataDir/$tableName") {
3868            $retVal = "$dataDir/$tableName";
3869        } elsif (-e "$dataDir/$tableName.dtx") {
3870            $retVal = "$dataDir/$tableName.dtx";
3871          }          }
3872          # Return the result.          # Return the result.
3873        return $retVal;
3874    }
3875    
3876    =head3 DeleteGenome
3877    
3878        my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3879    
3880    Delete a genome from the database.
3881    
3882    =over 4
3883    
3884    =item genomeID
3885    
3886    ID of the genome to delete
3887    
3888    =item testFlag
3889    
3890    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3891    
3892    =item RETURN
3893    
3894    Returns a statistics object describing the rows deleted.
3895    
3896    =back
3897    
3898    =cut
3899    #: Return Type $%;
3900    sub DeleteGenome {
3901        # Get the parameters.
3902        my ($self, $genomeID, $testFlag) = @_;
3903        # Perform the delete for the genome's features.
3904        my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3905        # Perform the delete for the primary genome data.
3906        my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3907        $retVal->Accumulate($stats);
3908        # Return the result.
3909        return $retVal;
3910    }
3911    
3912    =head3 Fix
3913    
3914        my %fixedHash = $sprout->Fix(%groupHash);
3915    
3916    Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3917    The groups will be combined into the appropriate super-groups.
3918    
3919    =over 4
3920    
3921    =item groupHash
3922    
3923    Hash to be fixed up.
3924    
3925    =item RETURN
3926    
3927    Returns a fixed-up version of the hash.
3928    
3929    =back
3930    
3931    =cut
3932    
3933    sub Fix {
3934        # Get the parameters.
3935        my ($self, %groupHash) = @_;
3936        # Create the result hash.
3937        my %retVal = ();
3938        # Copy over the genomes.
3939        for my $groupID (keys %groupHash) {
3940            # Get the super-group name.
3941            my $realGroupID = $self->SuperGroup($groupID);
3942            # Append this group's genomes into the result hash
3943            # using the super-group name.
3944            push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3945        }
3946        # Return the result hash.
3947          return %retVal;          return %retVal;
3948  }  }
3949    
3950    =head3 GroupPageName
3951    
3952        my $name = $sprout->GroupPageName($group);
3953    
3954    Return the name of the page for the specified NMPDR group.
3955    
3956    =over 4
3957    
3958    =item group
3959    
3960    Name of the relevant group.
3961    
3962    =item RETURN
3963    
3964    Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3965    memory it will be read in.
3966    
3967    =back
3968    
3969    =cut
3970    
3971    sub GroupPageName {
3972        # Get the parameters.
3973        my ($self, $group) = @_;
3974        # Check for the group file data.
3975        my %superTable = $self->CheckGroupFile();
3976        # Compute the real group name.
3977        my $realGroup = $self->SuperGroup($group);
3978        # Get the associated page name.
3979        my $retVal = "../content/$superTable{$realGroup}->{page}";
3980        # Return the result.
3981        return $retVal;
3982    }
3983    
3984    
3985    =head3 AddProperty
3986    
3987        $sprout->AddProperty($featureID, $key, @values);
3988    
3989    Add a new attribute value (Property) to a feature.
3990    
3991    =over 4
3992    
3993    =item peg
3994    
3995    ID of the feature to which the attribute is to be added.
3996    
3997    =item key
3998    
3999    Name of the attribute (key).
4000    
4001    =item values
4002    
4003    Values of the attribute.
4004    
4005    =back
4006    
4007    =cut
4008    #: Return Type ;
4009    sub AddProperty {
4010        # Get the parameters.
4011        my ($self, $featureID, $key, @values) = @_;
4012        # Add the property using the attached attributes object.
4013        $self->{_ca}->AddAttribute($featureID, $key, @values);
4014    }
4015    
4016    =head3 CheckGroupFile
4017    
4018        my %groupData = $sprout->CheckGroupFile();
4019    
4020    Get the group file hash. The group file hash describes the relationship
4021    between a group and the super-group to which it belongs for purposes of
4022    display. The super-group name is computed from the first capitalized word
4023    in the actual group name. For each super-group, the group file contains
4024    the page name and a list of the species expected to be in the group.
4025    Each species is specified by a genus and a species name. A species name
4026    of C<0> implies an entire genus.
4027    
4028    This method returns a hash from super-group names to a hash reference. Each
4029    resulting hash reference contains the following fields.
4030    
4031    =over 4
4032    
4033    =item page
4034    
4035    The super-group's web page in the NMPDR.
4036    
4037    =item contents
4038    
4039    A list of 2-tuples, each containing a genus name followed by a species name
4040    (or 0, indicating all species). This list indicates which organisms belong
4041    in the super-group.
4042    
4043    =back
4044    
4045    =cut
4046    
4047    sub CheckGroupFile {
4048        # Get the parameters.
4049        my ($self) = @_;
4050        # Check to see if we already have this hash.
4051        if (! defined $self->{groupHash}) {
4052            # We don't, so we need to read it in.
4053            my %groupHash;
4054            # Read the group file.
4055            my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
4056            # Loop through the list of sort-of groups.
4057            for my $groupLine (@groupLines) {
4058                my ($name, $page, @contents) = split /\t/, $groupLine;
4059                $groupHash{$name} = { page => $page,
4060                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
4061                                    };
4062            }
4063            # Save the hash.
4064            $self->{groupHash} = \%groupHash;
4065        }
4066        # Return the result.
4067        return %{$self->{groupHash}};
4068    }
4069    
4070    =head2 Virtual Methods
4071    
4072    =head3 CleanKeywords
4073    
4074        my $cleanedString = $sprout->CleanKeywords($searchExpression);
4075    
4076    Clean up a search expression or keyword list. This involves converting the periods
4077    in EC numbers to underscores, converting non-leading minus signs to underscores,
4078    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
4079    characters. In addition, any extra spaces are removed.
4080    
4081    =over 4
4082    
4083    =item searchExpression
4084    
4085    Search expression or keyword list to clean. Note that a search expression may
4086    contain boolean operators which need to be preserved. This includes leading
4087    minus signs.
4088    
4089    =item RETURN
4090    
4091    Cleaned expression or keyword list.
4092    
4093    =back
4094    
4095    =cut
4096    
4097    sub CleanKeywords {
4098        # Get the parameters.
4099        my ($self, $searchExpression) = @_;
4100        # Perform the standard cleanup.
4101        my $words = $self->ERDB::CleanKeywords($searchExpression);
4102        # Fix the periods in EC and TC numbers.
4103        $words =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;
4104        # Fix non-trailing periods.
4105        $words =~ s/\.(\w)/_$1/g;
4106        # Fix non-leading minus signs.
4107        $words =~ s/(\w)[\-]/$1_/g;
4108        # Fix the vertical bars and colons
4109        $words =~ s/(\w)[|:](\w)/$1'$2/g;
4110        # Now split up the list so that each keyword is in its own string. We keep the delimiters
4111        # because they may contain boolean expression data.
4112        my @words = split /([^A-Za-z'0-9_]+)/, $words;
4113        # We'll convert the stemmable words into stems and re-assemble the result.
4114        my $retVal = "";
4115        for my $word (@words) {
4116            my $stem = $self->Stem($word);
4117            if (defined $stem) {
4118                $retVal .= $stem;
4119            } else {
4120                $retVal .= $word;
4121            }
4122        }
4123        Trace("Cleaned keyword list for \"$searchExpression\" is \"$retVal\".") if T(3);
4124        # Return the result.
4125        return $retVal;
4126    }
4127    
4128  =head2 Internal Utility Methods  =head2 Internal Utility Methods
4129    
4130  =head3 ParseAssignment  =head3 ParseAssignment
4131    
4132  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
4133  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
4134  will be returned.  isn't, an empty list will be returned.
4135    
4136    A functional assignment is always of the form
4137    
4138        set YYYY function to
4139        ZZZZ
4140    
4141    where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
4142    the user and the assigning user (from MadeAnnotation) will be the same, but that is
4143    not always the case.
4144    
4145    In addition, the functional role may contain extra data that is stripped, such as
4146    terminating spaces or a comment separated from the rest of the text by a tab.
4147    
4148  This is a static method.  This is a static method.
4149    
4150  =over 4  =over 4
4151    
4152    =item user
4153    
4154    Name of the assigning user.
4155    
4156  =item text  =item text
4157    
4158  Text of the annotation.  Text of the annotation.
# Line 2564  Line 4166 
4166    
4167  =cut  =cut
4168    
4169  sub ParseAssignment {  sub _ParseAssignment {
4170          # Get the parameters.          # Get the parameters.
4171          my ($text) = @_;      my ($user, $text) = @_;
4172          # Declare the return value.          # Declare the return value.
4173          my @retVal = ();          my @retVal = ();
4174          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
4175          my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
4176          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set function to$/i) {
4177                  # Here it is, so we return the user name and function text.          # Here we have an assignment without a user, so we use the incoming user ID.
4178                  @retVal = ($user, $function);                  @retVal = ($user, $function);
4179        } elsif ($type =~ m/^set (\S+) function to$/i) {
4180            # Here we have an assignment with a user that is passed back to the caller.
4181            @retVal = ($1, $function);
4182        }
4183        # If we have an assignment, we need to clean the function text. There may be
4184        # extra junk at the end added as a note from the user.
4185        if (defined( $retVal[1] )) {
4186            $retVal[1] =~ s/(\t\S)?\s*$//;
4187          }          }
4188          # Return the result list.          # Return the result list.
4189          return @retVal;          return @retVal;
4190  }  }
4191    
4192    =head3 _CheckFeature
4193    
4194        my $flag = $sprout->_CheckFeature($fid);
4195    
4196    Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
4197    
4198    =over 4
4199    
4200    =item fid
4201    
4202    Feature ID to check.
4203    
4204    =item RETURN
4205    
4206    Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE.
4207    
4208    =back
4209    
4210    =cut
4211    
4212    sub _CheckFeature {
4213        # Get the parameters.
4214        my ($self, $fid) = @_;
4215        # Insure we have a genome hash.
4216        if (! defined $self->{genomeHash}) {
4217            my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');
4218            $self->{genomeHash} = \%genomeHash;
4219        }
4220        # Get the feature's genome ID.
4221        my ($genomeID) = FIGRules::ParseFeatureID($fid);
4222        # Return an indicator of whether or not the genome ID is in the hash.
4223        return ($self->{genomeHash}->{$genomeID} ? 1 : 0);
4224    }
4225    
4226  =head3 FriendlyTimestamp  =head3 FriendlyTimestamp
4227    
4228  Convert a time number to a user-friendly time stamp for display.  Convert a time number to a user-friendly time stamp for display.
# Line 2601  Line 4245 
4245    
4246  sub FriendlyTimestamp {  sub FriendlyTimestamp {
4247      my ($timeValue) = @_;      my ($timeValue) = @_;
4248      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
4249      return $retVal;      return $retVal;
4250  }  }
4251    
4252    
4253  1;  1;

Legend:
Removed from v.1.4  
changed lines
  Added in v.1.113

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3