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

Diff of /Sprout/Sprout.pm

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

revision 1.12, Wed May 4 03:24:43 2005 UTC revision 1.117, Tue Sep 16 18:57:59 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 BioWords;
20        use base qw(ERDB);
21    
22  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
23    
# Line 25  Line 30 
30  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>
31  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>.
32    
33  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' });
34    
35  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
36  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
37  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
38  L</dna_seq> returns the DNA sequence for a specified genome location.  L</DNASeq> returns the DNA sequence for a specified genome location.
39    
40    The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.
41    
42  =cut  =cut
43    
# Line 40  Line 47 
47    
48  =head3 new  =head3 new
49    
50  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
51    
52  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
53  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 62  Line 69 
69    
70  * 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>)
71    
72  * 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)
73    
74  * B<port> connection port (default C<0>)  * B<port> connection port (default C<0>)
75    
76    * B<sock> connection socket (default same as SEED)
77    
78  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)
79    
80  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
81    
82    * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
83    
84    * B<host> name of the database host
85    
86  =back  =back
87    
88  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
89  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
90  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
91    
92  C<< my $sprout = Sprout->new('Sprout', { userData =>; 'fig/admin', dataDir => '/usr/fig/SproutData' }); >>      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });
93    
94  =cut  =cut
95    
96  sub new {  sub new {
97          # Get the parameters.          # Get the parameters.
98          my ($class, $dbName, $options) = @_;          my ($class, $dbName, $options) = @_;
99        # Compute the DBD directory.
100        my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
101                                                      $FIG_Config::fig );
102          # 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
103          # the incoming data.          # the incoming data.
104          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
105                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
106                                             dataDir              => 'Data',                      # data file directory                                                          # database type
107                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
108                                             userData             => 'root/',                     # user name and password                                                          # data file directory
109                                             port                 => 0,                           # database connection port                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
110                                                            # database definition file name
111                           userData     => "$FIG_Config::sproutUser/$FIG_Config::sproutPass",
112                                                            # user name and password
113                           port         => $FIG_Config::sproutPort,
114                                                            # database connection port
115                           sock         => $FIG_Config::sproutSock,
116                           host         => $FIG_Config::sprout_host,
117                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
118                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
119                           noDBOpen     => 0,               # 1 to suppress the database open
120                                            }, $options);                                            }, $options);
121          # Get the data directory.          # Get the data directory.
122          my $dataDir = $optionTable->{dataDir};          my $dataDir = $optionTable->{dataDir};
# Line 100  Line 124 
124          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
125          my ($userName, $password) = ($1, $2);          my ($userName, $password) = ($1, $2);
126          # Connect to the database.          # Connect to the database.
127          my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
128        if (! $optionTable->{noDBOpen}) {
129            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
130            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
131                                    $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
132        }
133          # Create the ERDB object.          # Create the ERDB object.
134          my $xmlFileName = "$optionTable->{xmlFileName}";          my $xmlFileName = "$optionTable->{xmlFileName}";
135          my $erdb = ERDB->new($dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName);
136          # Create this object.      # Add the option table and XML file name.
137          my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName };      $retVal->{_options} = $optionTable;
138          # Bless and return it.      $retVal->{_xmlName} = $xmlFileName;
139          bless $self;      # Set up space for the group file data.
140          return $self;      $retVal->{groupHash} = undef;
141        # Set up space for the genome hash. We use this to identify NMPDR genomes.
142        $retVal->{genomeHash} = undef;
143        # Connect to the attributes.
144        if ($FIG_Config::attrURL) {
145            Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
146            $retVal->{_ca} = RemoteCustomAttributes->new($FIG_Config::attrURL);
147        } elsif ($FIG_Config::attrDbName) {
148            Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
149            my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
150            $retVal->{_ca} = CustomAttributes->new(user => $user);
151        }
152        # Return it.
153        return $retVal;
154    }
155    
156    =head3 CoreGenomes
157    
158        my @genomes = $sprout->CoreGenomes($scope);
159    
160    Return the IDs of NMPDR genomes in the specified scope.
161    
162    =over 4
163    
164    =item scope
165    
166    Scope of the desired genomes. C<core> covers the original core genomes,
167    C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
168    genomes in the system.
169    
170    =item RETURN
171    
172    Returns a list of the IDs for the genomes in the specified scope.
173    
174    =back
175    
176    =cut
177    
178    sub CoreGenomes {
179        # Get the parameters.
180        my ($self, $scope) = @_;
181        # Declare the return variable.
182        my @retVal = ();
183        # If we want all genomes, then this is easy.
184        if ($scope eq 'all') {
185            @retVal = $self->Genomes();
186        } else {
187            # Here we're dealing with groups. Get the hash of all the
188            # genome groups.
189            my %groups = $self->GetGroups();
190            # Loop through the groups, keeping the ones that we want.
191            for my $group (keys %groups) {
192                # Decide if we want to keep this group.
193                my $keepGroup = 0;
194                if ($scope eq 'nmpdr') {
195                    # NMPDR mode: keep all groups.
196                    $keepGroup = 1;
197                } elsif ($scope eq 'core') {
198                    # CORE mode. Only keep real core groups.
199                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
200                        $keepGroup = 1;
201                    }
202                }
203                # Add this group if we're keeping it.
204                if ($keepGroup) {
205                    push @retVal, @{$groups{$group}};
206                }
207            }
208        }
209        # Return the result.
210        return @retVal;
211    }
212    
213    =head3 SuperGroup
214    
215        my $superGroup = $sprout->SuperGroup($groupName);
216    
217    Return the name of the super-group containing the specified NMPDR genome
218    group. If no appropriate super-group can be found, an error will be
219    thrown.
220    
221    =over 4
222    
223    =item groupName
224    
225    Name of the group whose super-group is desired.
226    
227    =item RETURN
228    
229    Returns the name of the super-group containing the incoming group.
230    
231    =back
232    
233    =cut
234    
235    sub SuperGroup {
236        # Get the parameters.
237        my ($self, $groupName) = @_;
238        # Declare the return variable.
239        my $retVal;
240        # Get the group hash.
241        my %groupHash = $self->CheckGroupFile();
242        # Find the super-group genus.
243        $groupName =~ /([A-Z]\w+)/;
244        my $nameThing = $1;
245        # See if it's directly in the group hash.
246        if (exists $groupHash{$nameThing}) {
247            # Yes, then it's our result.
248            $retVal = $nameThing;
249        } else {
250            # No, so we have to search.
251            for my $superGroup (keys %groupHash) {
252                # Get this super-group's item list.
253                my $list = $groupHash{$superGroup}->{contents};
254                # Search it.
255                if (grep { $_->[0] eq $nameThing } @{$list}) {
256                    $retVal = $superGroup;
257                }
258            }
259            # Make sure we found something.
260            if (! $retVal) {
261                Confess("No super-group found for \"$groupName\".");
262            }
263        }
264        # Return the result.
265        return $retVal;
266  }  }
267    
268  =head3 MaxSegment  =head3 MaxSegment
269    
270  C<< my $length = $sprout->MaxSegment(); >>      my $length = $sprout->MaxSegment();
271    
272  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
273  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 130  Line 284 
284    
285  =head3 MaxSequence  =head3 MaxSequence
286    
287  C<< my $length = $sprout->MaxSequence(); >>      my $length = $sprout->MaxSequence();
288    
289  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
290  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 143  Line 297 
297          return $self->{_options}->{maxSequenceLength};          return $self->{_options}->{maxSequenceLength};
298  }  }
299    
300  =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.  
301    
302  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>      $sprout->Load($rebuild);;
303    
304  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  
305    
306  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
307    re-created. The data is loaded into the relations from files in the data directory either having the
308    same name as the target relation with no extension or with an extension of C<.dtx>. Files without an
309    extension are used in preference to the files with an extension.
310    
311  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
312  characters inside the variable C<$genus>.  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside
313    fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must
314    be presented in the order given in the relation tables produced by the L</ShowMetaData> method.
315    
316  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.  
317    
318  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,  
319    
320  C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>  TRUE if the data tables need to be created or re-created, else FALSE
321    
322  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.  
323    
324  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,
325  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.  
326    
327  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ? ORDER BY Genome(species)", [$genus]); >>  =back
328    
329  It is also permissible to specify I<only> an ORDER BY clause. For example, the following invocation gets  =cut
330  all genomes ordered by genus and species.  #: Return Type %;
331    sub Load {
332        # Get the parameters.
333        my ($self, $rebuild) = @_;
334        # Load the tables from the data directory.
335        my $retVal = $self->LoadTables($self->{_options}->{dataDir}, $rebuild);
336        # Return the statistics.
337        return $retVal;
338    }
339    
340  C<< $query = $sprout->Get(['Genome'], "ORDER BY Genome(genus), Genome(species)"); >>  =head3 LoadUpdate
341    
342  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.  
343    
344  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
345  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
346  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,
347  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
348  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
349  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.  
350    
351  =over 4  =over 4
352    
353  =item objectNames  =item truncateFlag
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
354    
355  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
356  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
357  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.  
358    
359  =item parameterList  =item tableList
360    
361  List of the parameters to be substituted in for the parameters marks in the filter clause.  List of the tables to be updated.
362    
363  =item RETURN  =item RETURN
364    
365  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,
366    the number of errors encountered, and a list of error messages.
367    
368  =back  =back
369    
370  =cut  =cut
371    #: Return Type $%;
372  sub Get {  sub LoadUpdate {
373          # Get the parameters.          # Get the parameters.
374          my ($self, $objectNames, $filterClause, $parameterList) = @_;      my ($self, $truncateFlag, $tableList) = @_;
375          # We differ from the ERDB Get method in that the parameter list is passed in as a list reference      # Declare the return value.
376          # rather than a list of parameters. The next step is to convert the parameters from a reference      my $retVal = Stats->new();
377          # to a real list. We can only do this if the parameters have been specified.      # Get the data directory.
378          my @parameters;      my $optionTable = $self->{_options};
379          if ($parameterList) { @parameters = @{$parameterList}; }      my $dataDir = $optionTable->{dataDir};
380          return $self->{_erdb}->Get($objectNames, $filterClause, @parameters);      # Loop through the incoming table names.
381        for my $tableName (@{$tableList}) {
382            # Find the table's file.
383            my $fileName = LoadFileName($dataDir, $tableName);
384            if (! $fileName) {
385                Trace("No load file found for $tableName in $dataDir.") if T(0);
386            } else {
387                # Attempt to load this table.
388                my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
389                # Accumulate the resulting statistics.
390                $retVal->Accumulate($result);
391            }
392        }
393        # Return the statistics.
394        return $retVal;
395  }  }
396    
397  =head3 GetEntity  =head3 GenomeCounts
398    
399  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>      my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
400    
401  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
402    genomes will be included in the counts.
403    
404  =over 4  =over 4
405    
406  =item entityType  =item complete
   
 Entity type name.  
   
 =item ID  
407    
408  ID of the desired entity.  TRUE if only complete genomes are to be counted, FALSE if all genomes are to be
409    counted
410    
411  =item RETURN  =item RETURN
412    
413  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--
414  instance is found with the specified key.  Archaea, Bacteria, Eukaryota, Viral, Environmental, and Unknown, respectively.
415    
416  =back  =back
417    
418  =cut  =cut
419    
420  sub GetEntity {  sub GenomeCounts {
421          # Get the parameters.          # Get the parameters.
422          my ($self, $entityType, $ID) = @_;      my ($self, $complete) = @_;
423          # Call the ERDB method.      # Set the filter based on the completeness flag.
424          return $self->{_erdb}->GetEntity($entityType, $ID);      my $filter = ($complete ? "Genome(complete) = 1" : "");
425        # Get all the genomes and the related taxonomy information.
426        my @genomes = $self->GetAll(['Genome'], $filter, [], ['Genome(id)', 'Genome(taxonomy)']);
427        # Clear the counters.
428        my ($arch, $bact, $euk, $vir, $env, $unk) = (0, 0, 0, 0, 0, 0);
429        # Loop through, counting the domains.
430        for my $genome (@genomes) {
431            if    ($genome->[1] =~ /^archaea/i)  { ++$arch }
432            elsif ($genome->[1] =~ /^bacter/i)   { ++$bact }
433            elsif ($genome->[1] =~ /^eukar/i)    { ++$euk }
434            elsif ($genome->[1] =~ /^vir/i)      { ++$vir }
435            elsif ($genome->[1] =~ /^env/i)      { ++$env }
436            else  { ++$unk }
437        }
438        # Return the counts.
439        return ($arch, $bact, $euk, $vir, $env, $unk);
440  }  }
441    
442  =head3 GetEntityValues  =head3 ContigCount
443    
444  C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>      my $count = $sprout->ContigCount($genomeID);
445    
446  Return a list of values from a specified entity instance.  Return the number of contigs for the specified genome ID.
447    
448  =over 4  =over 4
449    
450  =item entityType  =item genomeID
   
 Entity type name.  
   
 =item ID  
   
 ID of the desired entity.  
   
 =item fields  
451    
452  List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.  ID of the genome whose contig count is desired.
453    
454  =item RETURN  =item RETURN
455    
456  Returns a flattened list of the values of the specified fields for the specified entity.  Returns the number of contigs for the specified genome.
457    
458  =back  =back
459    
460  =cut  =cut
461  #: Return Type @;  
462  sub GetEntityValues {  sub ContigCount {
463          # Get the parameters.          # Get the parameters.
464          my ($self, $entityType, $ID, $fields) = @_;      my ($self, $genomeID) = @_;
465          # Call the ERDB method.      # Get the contig count.
466          return $self->{_erdb}->GetEntityValues($entityType, $ID, $fields);      my $retVal = $self->GetCount(['Contig', 'HasContig'], "HasContig(from-link) = ?", [$genomeID]);
467        # Return the result.
468        return $retVal;
469  }  }
470    
471  =head3 ShowMetaData  =head3 GenomeMenu
472    
473  C<< $sprout->ShowMetaData($fileName); >>      my $html = $sprout->GenomeMenu(%options);
474    
475  This method outputs a description of the database to an HTML file in the data directory.  Generate a genome selection control with the specified name and options.
476    This control is almost but not quite the same as the genome control in the
477    B<SearchHelper> class. Eventually, the two will be combined.
478    
479  =over 4  =over 4
480    
481  =item fileName  =item options
482    
483    Optional parameters for the control (see below).
484    
485    =item RETURN
486    
487  Fully-qualified name to give to the output file.  Returns the HTML for a genome selection control on a form (sometimes called a popup menu).
488    
489  =back  =back
490    
491  =cut  The valid options are as follows.
492    
493  sub ShowMetaData {  =over 4
         # Get the parameters.  
         my ($self, $fileName) = @_;  
         # Compute the file name.  
         my $options = $self->{_options};  
         # Call the show method on the underlying ERDB object.  
         $self->{_erdb}->ShowMetaData($fileName);  
 }  
494    
495  =head3 Load  =item name
496    
497  C<< $sprout->Load($rebuild); >>;  Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
498    Terrible things will happen if you have two controls with the same name on the same page.
499    
500  Load the database from files in the data directory, optionally re-creating the tables.  =item filter
501    
502  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
503  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
504  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.  
505    
506  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.  
507    
508  =over 4  If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
509    
510  =item rebuild  =item size
511    
512  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>
513    
514  =item RETURN  =item id
515    
516  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
517  the number of errors, and a list of the error messages.  unless this ID is unique.
518    
519    =item selected
520    
521    A comma-delimited list of selected genomes, or a reference to a list of selected genomes. The
522    default is none.
523    
524    =item class
525    
526    If specified, a style class to assign to the genome control.
527    
528  =back  =back
529    
530  =cut  =cut
531  #: Return Type %;  
532  sub Load {  sub GenomeMenu {
533          # Get the parameters.          # Get the parameters.
534          my ($self, $rebuild) = @_;      my ($self, %options) = @_;
535          # Get the database object.      # Get the control's name and ID.
536          my $erdb = $self->{_erdb};      my $menuName = $options{name} || $options{id} || 'myGenomeControl';
537          # Load the tables from the data directory.      my $menuID = $options{id} || $menuName;
538          my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild);      Trace("Genome menu name = $menuName with ID $menuID.") if T(3);
539          # Return the statistics.      # Compute the IDs for the status display.
540        my $divID = "${menuID}_status";
541        my $urlID = "${menuID}_url";
542        # Compute the code to show selected genomes in the status area.
543        my $showSelect = "showSelected('$menuID', '$divID', '$urlID', 1000)";
544        # Check for single-select or multi-select.
545        my $multiSelect = $options{multiSelect} || 0;
546        # Get the style data.
547        my $class = $options{class} || '';
548        # Get the list of pre-selected items.
549        my $selections = $options{selected} || [];
550        if (ref $selections ne 'ARRAY') {
551            $selections = [ split /\s*,\s*/, $selections ];
552        }
553        my %selected = map { $_ => 1 } @{$selections};
554        # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
555        # string or a list reference.
556        my $filterParms = $options{filter} || "";
557        if (! ref $filterParms) {
558            $filterParms = [split /\t|\\t/, $filterParms];
559        }
560        my $filterString = shift @{$filterParms};
561        # Get a list of all the genomes in group order. In fact, we only need them ordered
562        # by name (genus,species,strain), but putting primary-group in front enables us to
563        # take advantage of an existing index.
564        my @genomeList = $self->GetAll(['Genome'], "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
565                                       $filterParms,
566                                       [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
567        # Create a hash to organize the genomes by group. Each group will contain a list of
568        # 2-tuples, the first element being the genome ID and the second being the genome
569        # name.
570        my %gHash = ();
571        for my $genome (@genomeList) {
572            # Get the genome data.
573            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
574            # Compute its name. This is the genus, species, strain (if any), and the contig count.
575            my $name = "$genus $species ";
576            $name .= "$strain " if $strain;
577            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
578            # Now we get the domain. The domain tells us the display style of the organism.
579            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
580            # Now compute the display group. This is normally the primary group, but if the
581            # organism is supporting, we blank it out.
582            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
583            # Push the genome into the group's list. Note that we use the real group
584            # name for the hash key here, not the display group name.
585            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
586        }
587        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
588        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
589        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
590        # that aren't "other". At some point, we will want to make this less complicated.
591        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
592                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
593        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
594        # Remember the number of NMPDR groups.
595        my $nmpdrGroupCount = scalar @groups;
596        # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
597        # of the domains found.
598        my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
599        my @domains = ();
600        for my $genomeData (@otherGenomes) {
601            my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
602            if (exists $gHash{$domain}) {
603                push @{$gHash{$domain}}, $genomeData;
604            } else {
605                $gHash{$domain} = [$genomeData];
606                push @domains, $domain;
607            }
608        }
609        # Add the domain groups at the end of the main group list. The main group list will now
610        # contain all the categories we need to display the genomes.
611        push @groups, sort @domains;
612        # Delete the supporting group.
613        delete $gHash{$FIG_Config::otherGroup};
614        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
615        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
616        # and use that to make the selections.
617        my $nmpdrCount = 0;
618        # Create the type counters.
619        my $groupCount = 1;
620        # Get the number of rows to display.
621        my $rows = $options{size} || 10;
622        # If we're multi-row, create an onChange event.
623        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
624        # Set up the multiple-select flag.
625        my $multipleTag = ($multiSelect ? " multiple" : "" );
626        # Set up the style class.
627        my $classTag = ($class ? " class=\"$class\"" : "" );
628        # Create the SELECT tag and stuff it into the output array.
629        my @lines = ("<SELECT name=\"$menuName\" id=\"$menuID\" $onChangeTag$multipleTag$classTag size=\"$rows\">");
630        # Loop through the groups.
631        for my $group (@groups) {
632            # Get the genomes in the group.
633            for my $genome (@{$gHash{$group}}) {
634                # If this is an NMPDR organism, we add an extra style and count it.
635                my $nmpdrStyle = "";
636                if ($nmpdrGroupCount > 0) {
637                    $nmpdrCount++;
638                    $nmpdrStyle = " Core";
639                }
640                # Get the organism ID, name, contig count, and domain.
641                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
642                # See if we're pre-selected.
643                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
644                # Compute the display name.
645                my $nameString = "$name ($genomeID$contigCount)";
646                # Generate the option tag.
647                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
648                push @lines, "    $optionTag";
649            }
650            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
651            # groups.
652            $nmpdrGroupCount--;
653        }
654        # Close the SELECT tag.
655        push @lines, "</SELECT>";
656        if ($rows > 1) {
657            # We're in a non-compact mode, so we need to add some selection helpers. First is
658            # the search box. This allows the user to type text and change which genomes are
659            # displayed. For multiple-select mode, we include a button that selects the displayed
660            # genes. For single-select mode, we use a plain label instead.
661            my $searchThingName = "${menuID}_SearchThing";
662            my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"
663                                                 : "Show genomes containing");
664            push @lines, "<br />$searchThingLabel&nbsp;" .
665                         "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />" .
666                         Hint("GenomeControl", "Type here to filter the genomes displayed.") . "<br />";
667            # For multi-select mode, we also have buttons to set and clear selections.
668            if ($multiSelect) {
669                push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll('$menuID'); $showSelect\" />";
670                push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll('$menuID'); $showSelect\" />";
671                push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome('$menuID', $nmpdrCount, true); $showSelect;\" />";
672            }
673            # Add a hidden field we can use to generate organism page hyperlinks.
674            push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/wiki/rest.cgi/NmpdrPlugin/SeedViewer?page=Organism;organism=\" />";
675            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
676            push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";
677        }
678        # Assemble all the lines into a string.
679        my $retVal = join("\n", @lines, "");
680        # Return the result.
681          return $retVal;          return $retVal;
682  }  }
683    
 =head3 LoadUpdate  
   
 C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>  
684    
685  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.  
686    
687  =over 4      my $stem = $sprout->Stem($word);
688    
689  =item truncateFlag  Return the stem of the specified word, or C<undef> if the word is not
690    stemmable. Note that even if the word is stemmable, the stem may be
691    the same as the original word.
692    
693  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.  
694    
695  =item tableList  =item word
696    
697  List of the tables to be updated.  Word to convert into a stem.
698    
699  =item RETURN  =item RETURN
700    
701  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
702  the number of errors encountered, and a list of error messages.  the word is not stemmable.
703    
704  =back  =back
705    
706  =cut  =cut
707  #: Return Type $%;  
708  sub LoadUpdate {  sub Stem {
709          # Get the parameters.          # Get the parameters.
710          my ($self, $truncateFlag, $tableList) = @_;      my ($self, $word) = @_;
711          # Get the database object.      # Get the stemmer object.
712          my $erdb = $self->{_erdb};      my $stemmer = $self->{stemmer};
713          # Declare the return value.      if (! defined $stemmer) {
714          my $retVal = Stats->new();          # We don't have one pre-built, so we build and save it now.
715          # Get the data directory.          $stemmer = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
716          my $optionTable = $self->{_options};                                   stops => "$FIG_Config::sproutData/StopWords.txt",
717          my $dataDir = $optionTable->{dataDir};                                   cache => 1);
718          # Loop through the incoming table names.          $self->{stemmer} = $stemmer;
         for my $tableName (@{$tableList}) {  
                 # Find the table's file.  
                 my $fileName = "$dataDir/$tableName";  
                 if (! -e $fileName) {  
                         $fileName = "$fileName.dtx";  
                 }  
                 # Attempt to load this table.  
                 my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);  
                 # Accumulate the resulting statistics.  
                 $retVal->Accumulate($result);  
719          }          }
720          # Return the statistics.      # Try to stem the word.
721        my $retVal = $stemmer->Process($word);
722        # Return the result.
723          return $retVal;          return $retVal;
724  }  }
725    
726    
727  =head3 Build  =head3 Build
728    
729  C<< $sprout->Build(); >>      $sprout->Build();
730    
731  Build the database. The database will be cleared and the tables re-created from the metadata.  Build the database. The database will be cleared and the tables re-created from the metadata.
732  This method is useful when a database is brand new or when the database definition has  This method is useful when a database is brand new or when the database definition has
# Line 447  Line 738 
738          # Get the parameters.          # Get the parameters.
739          my ($self) = @_;          my ($self) = @_;
740          # Create the tables.          # Create the tables.
741          $self->{_erdb}->CreateTables;      $self->CreateTables();
742  }  }
743    
744  =head3 Genomes  =head3 Genomes
745    
746  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
747    
748  Return a list of all the genome IDs.  Return a list of all the genome IDs.
749    
# Line 469  Line 760 
760    
761  =head3 GenusSpecies  =head3 GenusSpecies
762    
763  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
764    
765  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
766    
# Line 501  Line 792 
792    
793  =head3 FeaturesOf  =head3 FeaturesOf
794    
795  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
796    
797  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
798    
# Line 546  Line 837 
837    
838  =head3 FeatureLocation  =head3 FeatureLocation
839    
840  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
841    
842  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
843  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 570  Line 861 
861  =item RETURN  =item RETURN
862    
863  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
864  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
865    wasn't found.
866    
867  =back  =back
868    
869  =cut  =cut
870  #: Return Type @;  
 #: Return Type $;  
871  sub FeatureLocation {  sub FeatureLocation {
872          # Get the parameters.          # Get the parameters.
873          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
874          # Create a query for the feature locations.      # Declare the return variable.
         my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",  
                                                    [$featureID]);  
         # Create the return list.  
875          my @retVal = ();          my @retVal = ();
876          # Set up the variables used to determine if we have adjacent segments. This initial setup will      # Get the feature record.
877          # not match anything.      my $object = $self->GetEntity('Feature', $featureID);
878          my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);      # Only proceed if we found it.
879          # Loop through the query results, creating location specifiers.      if (defined $object) {
880          while (my $location = $query->Fetch()) {          # Get the location string.
881                  # Get the location parameters.          my $locString = $object->PrimaryValue('Feature(location-string)');
882                  my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',          # Create the return list.
883                          '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$len";  
884          }          }
885          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
886          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
887  }  }
888    
889  =head3 ParseLocation  =head3 ParseLocation
890    
891  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
892    
893  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
894  length.  length.
# Line 637  Line 907 
907  =back  =back
908    
909  =cut  =cut
910  #: Return Type @;  
911  sub ParseLocation {  sub ParseLocation {
912          # Get the parameter. Note that if we're called as an instance method, we ignore          # Get the parameter. Note that if we're called as an instance method, we ignore
913      # the first parameter.      # the first parameter.
914      shift if UNIVERSAL::isa($_[0],__PACKAGE__);      shift if UNIVERSAL::isa($_[0],__PACKAGE__);
915          my ($location) = @_;          my ($location) = @_;
916          # Parse it into segments.          # Parse it into segments.
917          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
918          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
919          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
920          if ($dir eq "_") {          if ($dir eq "_") {
# Line 660  Line 930 
930          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
931  }  }
932    
933    
934    
935  =head3 PointLocation  =head3 PointLocation
936    
937  C<< my $found = Sprout::PointLocation($location, $point); >>      my $found = Sprout::PointLocation($location, $point);
938    
939  Return the offset into the specified location of the specified point on the contig. If  Return the offset into the specified location of the specified point on the contig. If
940  the specified point is before the location, a negative value will be returned. If it is  the specified point is before the location, a negative value will be returned. If it is
# Line 691  Line 963 
963  =back  =back
964    
965  =cut  =cut
966  #: Return Type $;  
967  sub PointLocation {  sub PointLocation {
968          # Get the parameter. Note that if we're called as an instance method, we ignore          # Get the parameter. Note that if we're called as an instance method, we ignore
969      # the first parameter.      # the first parameter.
# Line 714  Line 986 
986    
987  =head3 DNASeq  =head3 DNASeq
988    
989  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
990    
991  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
992  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,
993  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>.
994    
995    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
996    between positions 1401 and 1532, inclusive.
997    
998        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
999    
1000  =over 4  =over 4
1001    
1002  =item locationList  =item locationList
1003    
1004  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
1005  L</FeatureLocation> for more about this format).  I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
1006    
1007  =item RETURN  =item RETURN
1008    
# Line 752  Line 1029 
1029                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
1030                  # before putting it in the return value.                  # before putting it in the return value.
1031                  my ($start, $stop);                  my ($start, $stop);
1032            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
1033                  if ($dir eq "+") {                  if ($dir eq "+") {
1034                          $start = $beg;                          $start = $beg;
1035                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
1036                  } else {                  } else {
1037                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
1038                          $stop = $beg;                          $stop = $beg;
1039                  }                  }
1040            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
1041                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
1042                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
1043                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 770  Line 1049 
1049                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
1050                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
1051                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
1052                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
1053                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
1054                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
1055                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
1056                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
1057                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
1058                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
1059                  }                  }
1060                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
1061                  if ($dir eq '+') {                  if ($dir eq '+') {
1062                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
1063                  } else {                  } else {
1064                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
1065                  }                  }
1066          }          }
1067          # Return the result.          # Return the result.
# Line 790  Line 1070 
1070    
1071  =head3 AllContigs  =head3 AllContigs
1072    
1073  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1074    
1075  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1076    
# Line 818  Line 1098 
1098          return @retVal;          return @retVal;
1099  }  }
1100    
1101  =head3 ContigLength  =head3 GenomeLength
1102    
1103  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->GenomeLength($genomeID);
1104    
1105  Compute the length of a contig.  Return the length of the specified genome in base pairs.
1106    
1107  =over 4  =over 4
1108    
1109  =item contigID  =item genomeID
1110    
1111  ID of the contig whose length is desired.  ID of the genome whose base pair count is desired.
1112    
1113  =item RETURN  =item RETURN
1114    
1115  Returns the number of positions in the contig.  Returns the number of base pairs in all the contigs of the specified
1116    genome.
1117    
1118  =back  =back
1119    
1120  =cut  =cut
1121  #: Return Type $;  
1122  sub ContigLength {  sub GenomeLength {
1123          # Get the parameters.          # Get the parameters.
1124          my ($self, $contigID) = @_;      my ($self, $genomeID) = @_;
1125          # Get the contig's last sequence.      # Declare the return variable.
         my $query = $self->Get(['IsMadeUpOf'],  
                 "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",  
                 [$contigID]);  
         my $sequence = $query->Fetch();  
         # Declare the return value.  
1126          my $retVal = 0;          my $retVal = 0;
1127          # Set it from the sequence data, if any.      # Get the genome's contig sequence lengths.
1128          if ($sequence) {      my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',
1129                           [$genomeID], 'IsMadeUpOf(len)');
1130        # Sum the lengths.
1131        map { $retVal += $_ } @lens;
1132        # Return the result.
1133        return $retVal;
1134    }
1135    
1136    =head3 FeatureCount
1137    
1138        my $count = $sprout->FeatureCount($genomeID, $type);
1139    
1140    Return the number of features of the specified type in the specified genome.
1141    
1142    =over 4
1143    
1144    =item genomeID
1145    
1146    ID of the genome whose feature count is desired.
1147    
1148    =item type
1149    
1150    Type of feature to count (eg. C<peg>, C<rna>, etc.).
1151    
1152    =item RETURN
1153    
1154    Returns the number of features of the specified type for the specified genome.
1155    
1156    =back
1157    
1158    =cut
1159    
1160    sub FeatureCount {
1161        # Get the parameters.
1162        my ($self, $genomeID, $type) = @_;
1163        # Compute the count.
1164        my $retVal = $self->GetCount(['HasFeature', 'Feature'],
1165                                    "HasFeature(from-link) = ? AND Feature(feature-type) = ?",
1166                                    [$genomeID, $type]);
1167        # Return the result.
1168        return $retVal;
1169    }
1170    
1171    =head3 GenomeAssignments
1172    
1173        my $fidHash = $sprout->GenomeAssignments($genomeID);
1174    
1175    Return a list of a genome's assigned features. The return hash will contain each
1176    assigned feature of the genome mapped to the text of its most recent functional
1177    assignment.
1178    
1179    =over 4
1180    
1181    =item genomeID
1182    
1183    ID of the genome whose functional assignments are desired.
1184    
1185    =item RETURN
1186    
1187    Returns a reference to a hash which maps each feature to its most recent
1188    functional assignment.
1189    
1190    =back
1191    
1192    =cut
1193    
1194    sub GenomeAssignments {
1195        # Get the parameters.
1196        my ($self, $genomeID) = @_;
1197        # Declare the return variable.
1198        my $retVal = {};
1199        # Query the genome's features.
1200        my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?",
1201                               [$genomeID]);
1202        # Loop through the features.
1203        while (my $data = $query->Fetch) {
1204            # Get the feature ID and assignment.
1205            my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
1206            if ($assignment) {
1207                $retVal->{$fid} = $assignment;
1208            }
1209        }
1210        # Return the result.
1211        return $retVal;
1212    }
1213    
1214    =head3 ContigLength
1215    
1216        my $length = $sprout->ContigLength($contigID);
1217    
1218    Compute the length of a contig.
1219    
1220    =over 4
1221    
1222    =item contigID
1223    
1224    ID of the contig whose length is desired.
1225    
1226    =item RETURN
1227    
1228    Returns the number of positions in the contig.
1229    
1230    =back
1231    
1232    =cut
1233    #: Return Type $;
1234    sub ContigLength {
1235        # Get the parameters.
1236        my ($self, $contigID) = @_;
1237        # Get the contig's last sequence.
1238        my $query = $self->Get(['IsMadeUpOf'],
1239            "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
1240            [$contigID]);
1241        my $sequence = $query->Fetch();
1242        # Declare the return value.
1243        my $retVal = 0;
1244        # Set it from the sequence data, if any.
1245        if ($sequence) {
1246                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
1247                  $retVal = $start + $len;          $retVal = $start + $len - 1;
1248        }
1249        # Return the result.
1250        return $retVal;
1251    }
1252    
1253    =head3 ClusterPEGs
1254    
1255        my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1256    
1257    Cluster the PEGs in a list according to the cluster coding scheme of the specified
1258    subsystem. In order for this to work properly, the subsystem object must have
1259    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> or
1260    B<get_row> methods. This causes the cluster numbers to be pulled into the
1261    subsystem's color hash. If a PEG is not found in the color hash, it will not
1262    appear in the output sequence.
1263    
1264    =over 4
1265    
1266    =item sub
1267    
1268    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
1269    method.
1270    
1271    =item pegs
1272    
1273    Reference to the list of PEGs to be clustered.
1274    
1275    =item RETURN
1276    
1277    Returns a list of the PEGs, grouped into smaller lists by cluster number.
1278    
1279    =back
1280    
1281    =cut
1282    #: Return Type $@@;
1283    sub ClusterPEGs {
1284        # Get the parameters.
1285        my ($self, $sub, $pegs) = @_;
1286        # Declare the return variable.
1287        my $retVal = [];
1288        # Loop through the PEGs, creating arrays for each cluster.
1289        for my $pegID (@{$pegs}) {
1290            my $clusterNumber = $sub->get_cluster_number($pegID);
1291            # Only proceed if the PEG is in a cluster.
1292            if ($clusterNumber >= 0) {
1293                # Push this PEG onto the sub-list for the specified cluster number.
1294                push @{$retVal->[$clusterNumber]}, $pegID;
1295            }
1296          }          }
1297          # Return the result.          # Return the result.
1298          return $retVal;          return $retVal;
# Line 859  Line 1300 
1300    
1301  =head3 GenesInRegion  =head3 GenesInRegion
1302    
1303  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1304    
1305  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1306    
# Line 888  Line 1329 
1329  =back  =back
1330    
1331  =cut  =cut
1332  #: Return Type @@;  
1333  sub GenesInRegion {  sub GenesInRegion {
1334          # Get the parameters.          # Get the parameters.
1335          my ($self, $contigID, $start, $stop) = @_;          my ($self, $contigID, $start, $stop) = @_;
1336          # Get the maximum segment length.          # Get the maximum segment length.
1337          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
         # Create a hash to receive the feature list. We use a hash so that we can eliminate  
         # duplicates easily. The hash key will be the feature ID. The value will be a two-element  
         # containing the minimum and maximum offsets. We will use the offsets to sort the results  
         # when we're building the result set.  
         my %featuresFound = ();  
1338          # Prime the values we'll use for the returned beginning and end.          # Prime the values we'll use for the returned beginning and end.
1339          my @initialMinMax = ($self->ContigLength($contigID), 0);          my @initialMinMax = ($self->ContigLength($contigID), 0);
1340          my ($min, $max) = @initialMinMax;          my ($min, $max) = @initialMinMax;
1341          # Create a table of parameters for each query. Each query looks for features travelling in      # Get the overlapping features.
1342        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1343        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1344        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1345        # of the feature's locations.
1346        my %featureMap = ();
1347        # Loop through them to do the begin/end analysis.
1348        for my $featureObject (@featureObjects) {
1349            # Get the feature's location string. This may contain multiple actual locations.
1350            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1351            my @locationSegments = split /\s*,\s*/, $locations;
1352            # Loop through the locations.
1353            for my $locationSegment (@locationSegments) {
1354                # Construct an object for the location.
1355                my $locationObject = BasicLocation->new($locationSegment);
1356                # Merge the current segment's begin and end into the min and max.
1357                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1358                my ($beg, $end);
1359                if (exists $featureMap{$fid}) {
1360                    ($beg, $end) = @{$featureMap{$fid}};
1361                    $beg = $left if $left < $beg;
1362                    $end = $right if $right > $end;
1363                } else {
1364                    ($beg, $end) = ($left, $right);
1365                }
1366                $min = $beg if $beg < $min;
1367                $max = $end if $end > $max;
1368                # Store the feature's new extent back into the hash table.
1369                $featureMap{$fid} = [$beg, $end];
1370            }
1371        }
1372        # Now we must compute the list of the IDs for the features found. We start with a list
1373        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1374        # but the result of the sort will be the same.)
1375        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1376        # Now we sort by midpoint and yank out the feature IDs.
1377        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1378        # Return it along with the min and max.
1379        return (\@retVal, $min, $max);
1380    }
1381    
1382    =head3 GeneDataInRegion
1383    
1384        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1385    
1386    List the features which overlap a specified region in a contig.
1387    
1388    =over 4
1389    
1390    =item contigID
1391    
1392    ID of the contig containing the region of interest.
1393    
1394    =item start
1395    
1396    Offset of the first residue in the region of interest.
1397    
1398    =item stop
1399    
1400    Offset of the last residue in the region of interest.
1401    
1402    =item RETURN
1403    
1404    Returns a list of B<ERDBObjects> for the desired features. Each object will
1405    contain a B<Feature> record.
1406    
1407    =back
1408    
1409    =cut
1410    
1411    sub GeneDataInRegion {
1412        # Get the parameters.
1413        my ($self, $contigID, $start, $stop) = @_;
1414        # Get the maximum segment length.
1415        my $maximumSegmentLength = $self->MaxSegment;
1416        # Create a hash to receive the feature list. We use a hash so that we can eliminate
1417        # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1418        # ERDBObject from the query.
1419        my %featuresFound = ();
1420        # Create a table of parameters for the queries. Each query looks for features travelling in
1421          # 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,
1422          # 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
1423          # 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 911  Line 1426 
1426          # Loop through the query parameters.          # Loop through the query parameters.
1427          for my $parms (values %queryParms) {          for my $parms (values %queryParms) {
1428                  # Create the query.                  # Create the query.
1429                  my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1430                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1431                          $parms);                          $parms);
1432                  # Loop through the feature segments found.                  # Loop through the feature segments found.
1433                  while (my $segment = $query->Fetch) {                  while (my $segment = $query->Fetch) {
1434                          # Get the data about this segment.                          # Get the data about this segment.
1435                          my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1436                                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1437                          # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1438                          # this will be the case if the segment is the maximum length, so to fine-tune                          # this will be the case if the segment is the maximum length, so to fine-tune
1439                          # the results we insure that the inequality from the query holds using the actual                          # the results we insure that the inequality from the query holds using the actual
1440                          # length.                          # length.
1441                          my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1442                          if ($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 '-') {  
                                 # Note we switch things around so that the beginning is to the left of the  
                                 # ending.  
                                 ($beg, $end) = ($beg - $len, $beg);  
                                 if ($beg <= $stop) {  
                                         # Denote we found a useful feature.  
                                         $found = 1;  
                                 }  
                         }  
1443                          if ($found) {                          if ($found) {
1444                                  # Here we need to record the feature and update the minima and maxima. First,                  # Save this feature in the result list.
1445                                  # get the current entry for the specified feature.                  $featuresFound{$featureID} = $segment;
                                 my ($loc1, $loc2) = (exists $featuresFound{$featureID} ? @{$featuresFound{$featureID}} :  
                                                                          @initialMinMax);  
                                 # Merge the current segment's begin and end into the feature begin and end and the  
                                 # global min and max.  
                                 if ($beg < $loc1) {  
                                         $loc1 = $beg;  
                                         $min = $beg if $beg < $min;  
1446                                  }                                  }
                                 if ($end > $loc2) {  
                                         $loc2 = $end;  
                                         $max = $end if $end > $max;  
                                 }  
                                 # Store the entry back into the hash table.  
                                 $featuresFound{$featureID} = [$loc1, $loc2];  
1447                          }                          }
1448                  }                  }
1449          }      # Return the ERDB objects for the features found.
1450          # Now we must compute the list of the IDs for the features found. We start with a list      return values %featuresFound;
         # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,  
         # but the result of the sort will be the same.)  
         my @list = map { [$featuresFound{$_}->[0] + $featuresFound{$_}->[1], $_] } keys %featuresFound;  
         # Now we sort by midpoint and yank out the feature IDs.  
         my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;  
         # Return it along with the min and max.  
         return (\@retVal, $min, $max);  
1451  }  }
1452    
1453  =head3 FType  =head3 FType
1454    
1455  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1456    
1457  Return the type of a feature.  Return the type of a feature.
1458    
# Line 1001  Line 1482 
1482    
1483  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1484    
1485  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1486    
1487  Return the annotations of a feature.  Return the annotations of a feature.
1488    
# Line 1011  Line 1492 
1492    
1493  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1494    
1495    =item rawFlag
1496    
1497    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1498    will be returned in human-readable form.
1499    
1500  =item RETURN  =item RETURN
1501    
1502  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1503    
1504  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1505    
1506  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1507    
1508  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1509    
# Line 1029  Line 1515 
1515  #: Return Type @%;  #: Return Type @%;
1516  sub FeatureAnnotations {  sub FeatureAnnotations {
1517          # Get the parameters.          # Get the parameters.
1518          my ($self, $featureID) = @_;      my ($self, $featureID, $rawFlag) = @_;
1519          # 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.
1520          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1521                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1042  Line 1528 
1528                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1529                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1530                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1531            # Convert the time, if necessary.
1532            if (! $rawFlag) {
1533                $timeStamp = FriendlyTimestamp($timeStamp);
1534            }
1535                  # Assemble them into a hash.                  # Assemble them into a hash.
1536          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1537                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1538                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1539                  # Add it to the return list.                  # Add it to the return list.
1540                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1055  Line 1545 
1545    
1546  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1547    
1548  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1549    
1550  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
1551  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,
# Line 1073  Line 1563 
1563    
1564  =item RETURN  =item RETURN
1565    
1566  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1567    
1568  =back  =back
1569    
# Line 1083  Line 1573 
1573          # Get the parameters.          # Get the parameters.
1574          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1575          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1576      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1577                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1578                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1579                                               'MadeAnnotation(from-link)']);
1580          # Declare the return hash.          # Declare the return hash.
1581          my %retVal;          my %retVal;
     # Declare a hash for insuring we only make one assignment per user.  
     my %timeHash = ();  
1582      # Now we sort the assignments by timestamp in reverse.      # Now we sort the assignments by timestamp in reverse.
1583      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1584          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1585      for my $annotation (@sortedQuery) {      for my $annotation (@sortedQuery) {
1586          # Get the annotation fields.          # Get the annotation fields.
1587          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text, $user) = @{$annotation};
1588                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1589                  my ($user, $function) = _ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1590          if ($user && ! exists $timeHash{$user}) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1591              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1592              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
1593              # return hash.              # return hash.
1594                          $retVal{$function} = $user;              $retVal{$actualUser} = $function;
             # Insure we don't assign to this user again.  
             $timeHash{$user} = 1;  
1595                  }                  }
1596          }          }
1597          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1113  Line 1600 
1600    
1601  =head3 FunctionOf  =head3 FunctionOf
1602    
1603  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1604    
1605  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1606    
1607  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
1608  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
1609  assignment is a type of annotation. The format of an assignment is described in  assignment is taken from the B<Feature> or C<Annotation> table, depending.
 L</ParseLocation>. 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.  
1610    
1611  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
1612  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
1613  the specified user and FIG are considered trusted. If the user ID is omitted, only FIG  the specified user and FIG are considered trusted. If the user ID is omitted, only FIG
1614  is trusted.  is trusted.
1615    
1616  If the feature is B<not> identified by a FIG ID, then the functional assignment  If the feature is B<not> identified by a FIG ID, then we search the aliases for it.
1617  information is taken from the B<ExternalAliasFunc> table. If the table does  If no matching alias is found, we return an undefined value.
 not contain an entry for the feature, an undefined value is returned.  
1618    
1619  =over 4  =over 4
1620    
# Line 1141  Line 1624 
1624    
1625  =item userID (optional)  =item userID (optional)
1626    
1627  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
1628  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1629    
1630  =item RETURN  =item RETURN
1631    
# Line 1157  Line 1640 
1640          my ($self, $featureID, $userID) = @_;          my ($self, $featureID, $userID) = @_;
1641      # Declare the return value.      # Declare the return value.
1642      my $retVal;      my $retVal;
1643      # Determine the ID type.      # Find a FIG ID for this feature.
1644      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1645          # Here we have a FIG feature ID. We must build the list of trusted      # Only proceed if we have an ID.
1646          # users.      if ($fid) {
1647            # Here we have a FIG feature ID.
1648            if (!$userID) {
1649                # Use the primary assignment.
1650                ($retVal) = $self->GetEntityValues('Feature', $fid, ['Feature(assignment)']);
1651            } else {
1652                # We must build the list of trusted users.
1653          my %trusteeTable = ();          my %trusteeTable = ();
1654          # Check the user ID.          # Check the user ID.
1655          if (!$userID) {          if (!$userID) {
# Line 1182  Line 1671 
1671              }              }
1672          }          }
1673          # 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.
1674          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1675                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1676                                 [$featureID]);                                     [$fid]);
1677          my $timeSelected = 0;          my $timeSelected = 0;
1678          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1679          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1680              # Get the annotation text.              # Get the annotation text.
1681              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);                  my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1682                                                             'Annotation(time)', 'MadeAnnotation(from-link)']);
1683              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1684              my ($user, $function) = _ParseAssignment($text);                  my ($actualUser, $function) = _ParseAssignment($user, $text);
1685              if ($user) {                  Trace("Assignment user is $actualUser, text is $function.") if T(4);
1686                    if ($actualUser) {
1687                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1688                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1689                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                      if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1690                      $retVal = $function;                      $retVal = $function;
1691                      $timeSelected = $time;                      $timeSelected = $time;
1692                  }                  }
1693              }              }
1694          }          }
1695      } else {          }
         # Here we have a non-FIG feature ID. In this case the user ID does not  
         # matter. We simply get the information from the External Alias Function  
         # table.  
         ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);  
1696      }      }
1697          # Return the assignment found.          # Return the assignment found.
1698          return $retVal;          return $retVal;
1699  }  }
1700    
1701    =head3 FunctionsOf
1702    
1703        my @functionList = $sprout->FunctionOf($featureID, $userID);
1704    
1705    Return the functional assignments of a particular feature.
1706    
1707    The functional assignment is handled differently depending on the type of feature. If
1708    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1709    assignment is a type of annotation. The format of an assignment is described in
1710    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1711    annotation itself because it's a text field; however, this is not a big problem because
1712    most features only have a small number of annotations.
1713    
1714    =over 4
1715    
1716    =item featureID
1717    
1718    ID of the feature whose functional assignments are desired.
1719    
1720    =item RETURN
1721    
1722    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1723    that user.
1724    
1725    =back
1726    
1727    =cut
1728    #: Return Type @@;
1729    sub FunctionsOf {
1730        # Get the parameters.
1731        my ($self, $featureID) = @_;
1732        # Declare the return value.
1733        my @retVal = ();
1734        # Convert to a FIG ID.
1735        my ($fid) = $self->FeaturesByAlias($featureID);
1736        # Only proceed if we found one.
1737        if ($fid) {
1738            # Here we have a FIG feature ID. We must build the list of trusted
1739            # users.
1740            my %trusteeTable = ();
1741            # Build a query for all of the feature's annotations, sorted by date.
1742            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1743                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1744                                   [$fid]);
1745            my $timeSelected = 0;
1746            # Loop until we run out of annotations.
1747            while (my $annotation = $query->Fetch()) {
1748                # Get the annotation text.
1749                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1750                                                                'Annotation(time)',
1751                                                                'MadeAnnotation(user)']);
1752                # Check to see if this is a functional assignment for a trusted user.
1753                my ($actualUser, $function) = _ParseAssignment($user, $text);
1754                if ($actualUser) {
1755                    # Here it is a functional assignment.
1756                    push @retVal, [$actualUser, $function];
1757                }
1758            }
1759        }
1760        # Return the assignments found.
1761        return @retVal;
1762    }
1763    
1764  =head3 BBHList  =head3 BBHList
1765    
1766  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1767    
1768  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
1769  on a specified target genome.  on a specified target genome.
# Line 1230  Line 1780 
1780    
1781  =item RETURN  =item RETURN
1782    
1783  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
1784  their best hits.  on the target genome.
1785    
1786  =back  =back
1787    
# Line 1244  Line 1794 
1794          my %retVal = ();          my %retVal = ();
1795          # Loop through the incoming features.          # Loop through the incoming features.
1796          for my $featureID (@{$featureList}) {          for my $featureID (@{$featureList}) {
1797                  # Create a query to get the feature's best hit.          # Ask the server for the feature's best hit.
1798                  my $query = $self->Get(['IsBidirectionalBestHitOf'],          my @bbhData = FIGRules::BBHData($featureID);
1799                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",          # Peel off the BBHs found.
1800                                                             [$featureID, $genomeID]);          my @found = ();
1801                  # Look for the best hit.          for my $bbh (@bbhData) {
1802                  my $bbh = $query->Fetch;              my $fid = $bbh->[0];
1803                  if ($bbh) {              my $bbGenome = $self->GenomeOf($fid);
1804                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              if ($bbGenome eq $genomeID) {
1805                          $retVal{$featureID} = $targetFeature;                  push @found, $fid;
1806                  }                  }
1807          }          }
1808            $retVal{$featureID} = \@found;
1809        }
1810          # Return the mapping.          # Return the mapping.
1811          return \%retVal;          return \%retVal;
1812  }  }
1813    
1814  =head3 FeatureAliases  =head3 SimList
1815    
1816  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my %similarities = $sprout->SimList($featureID, $count);
1817    
1818  Return a list of the aliases for a specified feature.  Return a list of the similarities to the specified feature.
1819    
1820    This method just returns the bidirectional best hits for performance reasons.
1821    
1822  =over 4  =over 4
1823    
1824  =item featureID  =item featureID
1825    
1826  ID of the feature whose aliases are desired.  ID of the feature whose similarities are desired.
1827    
1828  =item RETURN  =item count
1829    
1830  Returns a list of the feature's aliases. If the feature is not found or has no aliases, it will  Maximum number of similar features to be returned, or C<0> to return them all.
 return an empty list.  
1831    
1832  =back  =back
1833    
1834  =cut  =cut
1835  #: Return Type @;  #: Return Type %;
1836  sub FeatureAliases {  sub SimList {
1837          # Get the parameters.          # Get the parameters.
1838          my ($self, $featureID) = @_;      my ($self, $featureID, $count) = @_;
1839          # Get the desired feature's aliases      # Ask for the best hits.
1840          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      my @lists = FIGRules::BBHData($featureID);
1841        # Create the return value.
1842        my %retVal = ();
1843        for my $tuple (@lists) {
1844            $retVal{$tuple->[0]} = $tuple->[1];
1845        }
1846          # Return the result.          # Return the result.
1847          return @retVal;      return %retVal;
1848  }  }
1849    
1850  =head3 GenomeOf  =head3 IsComplete
1851    
1852  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $flag = $sprout->IsComplete($genomeID);
1853    
1854  Return the genome that contains a specified feature.  Return TRUE if the specified genome is complete, else FALSE.
1855    
1856  =over 4  =over 4
1857    
1858  =item featureID  =item genomeID
1859    
1860  ID of the feature whose genome is desired.  ID of the genome whose completeness status is desired.
1861    
1862  =item RETURN  =item RETURN
1863    
1864  Returns the ID of the genome for the specified feature. If the feature is not found, returns  Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1865  an undefined value.  not found.
1866    
1867  =back  =back
1868    
1869  =cut  =cut
1870  #: Return Type $;  #: Return Type $;
1871  sub GenomeOf {  sub IsComplete {
1872          # Get the parameters.          # Get the parameters.
1873          my ($self, $featureID) = @_;      my ($self, $genomeID) = @_;
1874          # Create a query to find the genome associated with the feature.      # Declare the return variable.
         my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);  
         # Declare the return value.  
1875          my $retVal;          my $retVal;
1876          # Get the genome ID.      # Get the genome's data.
1877          if (my $relationship = $query->Fetch()) {      my $genomeData = $self->GetEntity('Genome', $genomeID);
1878                  ($retVal) = $relationship->Value('HasContig(from-link)');      if ($genomeData) {
1879            # The genome exists, so get the completeness flag.
1880            $retVal = $genomeData->PrimaryValue('Genome(complete)');
1881          }          }
1882          # Return the value found.      # Return the result.
1883        return $retVal;
1884    }
1885    
1886    =head3 FeatureAliases
1887    
1888        my @aliasList = $sprout->FeatureAliases($featureID);
1889    
1890    Return a list of the aliases for a specified feature.
1891    
1892    =over 4
1893    
1894    =item featureID
1895    
1896    ID of the feature whose aliases are desired.
1897    
1898    =item RETURN
1899    
1900    Returns a list of the feature's aliases. If the feature is not found or has no aliases, it will
1901    return an empty list.
1902    
1903    =back
1904    
1905    =cut
1906    #: Return Type @;
1907    sub FeatureAliases {
1908        # Get the parameters.
1909        my ($self, $featureID) = @_;
1910        # Get the desired feature's aliases
1911        my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
1912        # Return the result.
1913        return @retVal;
1914    }
1915    
1916    =head3 GenomeOf
1917    
1918        my $genomeID = $sprout->GenomeOf($featureID);
1919    
1920    Return the genome that contains a specified feature or contig.
1921    
1922    =over 4
1923    
1924    =item featureID
1925    
1926    ID of the feature or contig whose genome is desired.
1927    
1928    =item RETURN
1929    
1930    Returns the ID of the genome for the specified feature or contig. If the feature or contig is not
1931    found, returns an undefined value.
1932    
1933    =back
1934    
1935    =cut
1936    #: Return Type $;
1937    sub GenomeOf {
1938        # Get the parameters.
1939        my ($self, $featureID) = @_;
1940        # Declare the return value.
1941        my $retVal;
1942        # Parse the genome ID from the feature ID.
1943        if ($featureID =~ /^fig\|(\d+\.\d+)/) {
1944            $retVal = $1;
1945        } else {
1946            # Find the feature by alias.
1947            my ($realFeatureID) = $self->FeaturesByAlias($featureID);
1948            if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {
1949                $retVal = $1;
1950            }
1951        }
1952        # Return the value found.
1953          return $retVal;          return $retVal;
1954  }  }
1955    
1956  =head3 CoupledFeatures  =head3 CoupledFeatures
1957    
1958  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
1959    
1960  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
1961  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 1349  Line 1977 
1977  sub CoupledFeatures {  sub CoupledFeatures {
1978          # Get the parameters.          # Get the parameters.
1979          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1980          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      # Ask the coupling server for the data.
1981          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
1982          # (B,A) will also be found.      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
1983          my $query = $self->Get(['IsClusteredOnChromosomeWith'],      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
1984                                                     "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);      # Form them into a hash.
         # This value will be set to TRUE if we find at least one coupled feature.  
         my $found = 0;  
         # Create the return hash.  
1985          my %retVal = ();          my %retVal = ();
1986          # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
1987          while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
1988                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          my ($featureID2, $score) = @{$pair};
1989                                                                      'IsClusteredOnChromosomeWith(score)']);          # Only proceed if the feature is in NMPDR.
1990                  $retVal{$otherFeatureID} = $score;          if ($self->_CheckFeature($featureID2)) {
1991                  $found = 1;              $retVal{$featureID2} = $score;
1992            }
1993          }          }
1994          # Functional coupling is reflexive. If we found at least one coupled feature, we must add          # Functional coupling is reflexive. If we found at least one coupled feature, we must add
1995          # the incoming feature as well.          # the incoming feature as well.
1996          if ($found) {      if (keys %retVal) {
1997                  $retVal{$featureID} = 9999;                  $retVal{$featureID} = 9999;
1998      }      }
1999          # Return the hash.          # Return the hash.
2000          return %retVal;          return %retVal;
2001  }  }
2002    
2003  =head3 GetEntityTypes  =head3 CouplingEvidence
2004    
2005        my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
2006    
2007    Return the evidence for a functional coupling.
2008    
2009    A pair of features is considered evidence of a coupling between two other
2010    features if they occur close together on a contig and both are similar to
2011    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
2012    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
2013    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
2014    similar to B<A2>.
2015    
2016    The score of a coupling is determined by the number of pieces of evidence
2017    that are considered I<representative>. If several evidence items belong to
2018    a group of genomes that are close to each other, only one of those items
2019    is considered representative. The other evidence items are presumed to be
2020    there because of the relationship between the genomes rather than because
2021    the two proteins generated by the features have a related functionality.
2022    
2023    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
2024    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
2025    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
2026    and FALSE otherwise.
2027    
2028    =over 4
2029    
2030    =item peg1
2031    
2032    ID of the feature of interest.
2033    
2034    =item peg2
2035    
2036    ID of a feature functionally coupled to the feature of interest.
2037    
2038    =item RETURN
2039    
2040    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
2041    of interest, a feature similar to the functionally coupled feature, and a flag
2042    that is TRUE for a representative piece of evidence and FALSE otherwise.
2043    
2044    =back
2045    
2046    =cut
2047    #: Return Type @@;
2048    sub CouplingEvidence {
2049        # Get the parameters.
2050        my ($self, $peg1, $peg2) = @_;
2051        # Declare the return variable.
2052        my @retVal = ();
2053        # Get the coupling and evidence data.
2054        my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
2055        # Loop through the raw data, saving the ones that are in NMPDR genomes.
2056        for my $rawTuple (@rawData) {
2057            if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
2058                push @retVal, $rawTuple;
2059            }
2060        }
2061        # Return the result.
2062        return @retVal;
2063    }
2064    
2065    =head3 GetSynonymGroup
2066    
2067        my $id = $sprout->GetSynonymGroup($fid);
2068    
2069    Return the synonym group name for the specified feature.
2070    
2071    =over 4
2072    
2073    =item fid
2074    
2075    ID of the feature whose synonym group is desired.
2076    
2077    =item RETURN
2078    
2079    The name of the synonym group to which the feature belongs. If the feature does
2080    not belong to a synonym group, the feature ID itself is returned.
2081    
2082    =back
2083    
2084    =cut
2085    
2086    sub GetSynonymGroup {
2087        # Get the parameters.
2088        my ($self, $fid) = @_;
2089        # Declare the return variable.
2090        my $retVal;
2091        # Find the synonym group.
2092        my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?",
2093                                       [$fid], 'IsSynonymGroupFor(from-link)');
2094        # Check to see if we found anything.
2095        if (@groups) {
2096            $retVal = $groups[0];
2097        } else {
2098            $retVal = $fid;
2099        }
2100        # Return the result.
2101        return $retVal;
2102    }
2103    
2104    =head3 GetBoundaries
2105    
2106  C<< my @entityList = $sprout->GetEntityTypes(); >>      my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2107    
2108  Return the list of supported entity types.  Determine the begin and end boundaries for the locations in a list. All of the
2109    locations must belong to the same contig and have mostly the same direction in
2110    order for this method to produce a meaningful result. The resulting
2111    begin/end pair will contain all of the bases in any of the locations.
2112    
2113    =over 4
2114    
2115    =item locList
2116    
2117    List of locations to process.
2118    
2119    =item RETURN
2120    
2121    Returns a 3-tuple consisting of the contig ID, the beginning boundary,
2122    and the ending boundary. The beginning boundary will be left of the
2123    end for mostly-forward locations and right of the end for mostly-backward
2124    locations.
2125    
2126    =back
2127    
2128  =cut  =cut
2129  #: Return Type @;  
2130  sub GetEntityTypes {  sub GetBoundaries {
2131          # Get the parameters.          # Get the parameters.
2132          my ($self) = @_;      my ($self, @locList) = @_;
2133          # Get the underlying database object.      # Set up the counters used to determine the most popular direction.
2134          my $erdb = $self->{_erdb};      my %counts = ( '+' => 0, '-' => 0 );
2135          # Get its entity type list.      # Get the last location and parse it.
2136          my @retVal = $erdb->GetEntityTypes();      my $locObject = BasicLocation->new(pop @locList);
2137        # Prime the loop with its data.
2138        my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right);
2139        # Count its direction.
2140        $counts{$locObject->Dir}++;
2141        # Loop through the remaining locations. Note that in most situations, this loop
2142        # will not iterate at all, because most of the time we will be dealing with a
2143        # singleton list.
2144        for my $loc (@locList) {
2145            # Create a location object.
2146            my $locObject = BasicLocation->new($loc);
2147            # Count the direction.
2148            $counts{$locObject->Dir}++;
2149            # Get the left end and the right end.
2150            my $left = $locObject->Left;
2151            my $right = $locObject->Right;
2152            # Merge them into the return variables.
2153            if ($left < $beg) {
2154                $beg = $left;
2155            }
2156            if ($right > $end) {
2157                $end = $right;
2158            }
2159        }
2160        # If the most common direction is reverse, flip the begin and end markers.
2161        if ($counts{'-'} > $counts{'+'}) {
2162            ($beg, $end) = ($end, $beg);
2163        }
2164        # Return the result.
2165        return ($contig, $beg, $end);
2166  }  }
2167    
2168  =head3 ReadFasta  =head3 ReadFasta
2169    
2170  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2171    
2172  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
2173  one or more lines of data. The first line begins with a > character and contains an ID.  one or more lines of data. The first line begins with a > character and contains an ID.
# Line 1435  Line 2209 
2209                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
2210                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
2211                          if ($id) {                          if ($id) {
2212                                  $retVal{$id} = uc $sequence;                  $retVal{$id} = lc $sequence;
2213                          }                          }
2214                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
2215                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
2216                  } else {                  } else {
2217                          # 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.
2218                          # First, we get the actual data out. Note that we normalize to upper              # First, we get the actual data out. Note that we normalize to lower
2219                          # case.                          # case.
2220                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
2221                          $sequence .= $1;                          $sequence .= $1;
# Line 1449  Line 2223 
2223          }          }
2224          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
2225          if ($sequence) {          if ($sequence) {
2226                  $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
2227          }          }
2228          # Close the file.          # Close the file.
2229          close FASTAFILE;          close FASTAFILE;
# Line 1459  Line 2233 
2233    
2234  =head3 FormatLocations  =head3 FormatLocations
2235    
2236  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2237    
2238  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
2239  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
# Line 1524  Line 2298 
2298    
2299  =head3 DumpData  =head3 DumpData
2300    
2301  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2302    
2303  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.
2304    
# Line 1536  Line 2310 
2310          # Get the data directory name.          # Get the data directory name.
2311          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
2312          # Dump the relations.          # Dump the relations.
2313          $self->{_erdb}->DumpRelations($outputDirectory);      $self->DumpRelations($outputDirectory);
2314  }  }
2315    
2316  =head3 XMLFileName  =head3 XMLFileName
2317    
2318  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2319    
2320  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2321    
# Line 1552  Line 2326 
2326          return $self->{_xmlName};          return $self->{_xmlName};
2327  }  }
2328    
2329    =head3 GetGenomeNameData
2330    
2331        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2332    
2333    Return the genus, species, and unique characterization for a genome. This
2334    is similar to L</GenusSpecies>, with the exception that it returns the
2335    values in three seperate fields.
2336    
2337    =over 4
2338    
2339    =item genomeID
2340    
2341    ID of the genome whose name data is desired.
2342    
2343    =item RETURN
2344    
2345    Returns a three-element list, consisting of the genus, species, and strain
2346    of the specified genome. If the genome is not found, an error occurs.
2347    
2348    =back
2349    
2350    =cut
2351    
2352    sub GetGenomeNameData {
2353        # Get the parameters.
2354        my ($self, $genomeID) = @_;
2355        # Get the desired values.
2356        my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>
2357                                                                [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);
2358        # Throw an error if they were not found.
2359        if (! defined $genus) {
2360            Confess("Genome $genomeID not found in database.");
2361        }
2362        # Return the results.
2363        return ($genus, $species, $strain);
2364    }
2365    
2366    =head3 GetGenomeByNameData
2367    
2368        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2369    
2370    Return a list of the IDs of the genomes with the specified genus,
2371    species, and strain. In almost every case, there will be either zero or
2372    one IDs returned; however, two or more IDs could be returned if there are
2373    multiple versions of the genome in the database.
2374    
2375    =over 4
2376    
2377    =item genus
2378    
2379    Genus of the desired genome.
2380    
2381    =item species
2382    
2383    Species of the desired genome.
2384    
2385    =item strain
2386    
2387    Strain (unique characterization) of the desired genome. This may be an empty
2388    string, in which case it is presumed that the desired genome has no strain
2389    specified.
2390    
2391    =item RETURN
2392    
2393    Returns a list of the IDs of the genomes having the specified genus, species, and
2394    strain.
2395    
2396    =back
2397    
2398    =cut
2399    
2400    sub GetGenomeByNameData {
2401        # Get the parameters.
2402        my ($self, $genus, $species, $strain) = @_;
2403        # Try to find the genomes.
2404        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2405                                    [$genus, $species, $strain], 'Genome(id)');
2406        # Return the result.
2407        return @retVal;
2408    }
2409    
2410  =head3 Insert  =head3 Insert
2411    
2412  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2413    
2414  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
2415  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 1563  Line 2418 
2418  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
2419  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>.
2420    
2421  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']});
2422    
2423  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
2424  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>.
2425    
2426  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>      $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2427    
2428  =over 4  =over 4
2429    
# Line 1588  Line 2443 
2443          # Get the parameters.          # Get the parameters.
2444          my ($self, $objectType, $fieldHash) = @_;          my ($self, $objectType, $fieldHash) = @_;
2445          # Call the underlying method.          # Call the underlying method.
2446          $self->{_erdb}->InsertObject($objectType, $fieldHash);      $self->InsertObject($objectType, $fieldHash);
2447  }  }
2448    
2449  =head3 Annotate  =head3 Annotate
2450    
2451  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2452    
2453  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
2454  specified feature and user.  specified feature and user.
# Line 1647  Line 2502 
2502    
2503  =head3 AssignFunction  =head3 AssignFunction
2504    
2505  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2506    
2507  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
2508  format is described in L</ParseAssignment>.  format is described in L</ParseAssignment>.
# Line 1707  Line 2562 
2562    
2563  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2564    
2565  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2566    
2567  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
2568  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 1741  Line 2596 
2596                  push @retVal, $mappedAlias;                  push @retVal, $mappedAlias;
2597          } else {          } else {
2598                  # 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.
2599                  @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2600          }          }
2601          # Return the result.          # Return the result.
2602          return @retVal;          return @retVal;
2603  }  }
2604    
 =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, $entityName, $entityID) = @_;  
         # Check for the entity instance.  
         my $testInstance = $self->GetEntity($entityName, $entityID);  
         # Return an existence indicator.  
         my $retVal = ($testInstance ? 1 : 0);  
         return $retVal;  
 }  
   
2605  =head3 FeatureTranslation  =head3 FeatureTranslation
2606    
2607  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2608    
2609  Return the translation of a feature.  Return the translation of a feature.
2610    
# Line 1811  Line 2632 
2632    
2633  =head3 Taxonomy  =head3 Taxonomy
2634    
2635  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2636    
2637  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
2638  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>,
2639  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2640    
2641  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2642    
2643  =over 4  =over 4
2644    
# Line 1852  Line 2673 
2673    
2674  =head3 CrudeDistance  =head3 CrudeDistance
2675    
2676  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2677    
2678  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
2679  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 1904  Line 2725 
2725    
2726  =head3 RoleName  =head3 RoleName
2727    
2728  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2729    
2730  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
2731  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 1938  Line 2759 
2759    
2760  =head3 RoleDiagrams  =head3 RoleDiagrams
2761    
2762  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2763    
2764  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2765    
# Line 1968  Line 2789 
2789    
2790  =head3 FeatureProperties  =head3 FeatureProperties
2791    
2792  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2793    
2794  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
2795  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
2796  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
2797  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
2798  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.  
2799    
2800  =over 4  =over 4
2801    
# Line 1986  Line 2805 
2805    
2806  =item RETURN  =item RETURN
2807    
2808  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.  
2809    
2810  =back  =back
2811    
# Line 1997  Line 2815 
2815          # Get the parameters.          # Get the parameters.
2816          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2817          # Get the properties.          # Get the properties.
2818          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->{_ca}->GetAttributes($featureID);
2819                                                          ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2820                                                           'HasProperty(evidence)']);      my @retVal = ();
2821        for my $attributeRow (@attributes) {
2822            shift @{$attributeRow};
2823            push @retVal, $attributeRow;
2824        }
2825          # Return the resulting list.          # Return the resulting list.
2826          return @retVal;          return @retVal;
2827  }  }
2828    
2829  =head3 DiagramName  =head3 DiagramName
2830    
2831  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2832    
2833  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2834    
# Line 2032  Line 2854 
2854          return $retVal;          return $retVal;
2855  }  }
2856    
2857    =head3 PropertyID
2858    
2859        my $id = $sprout->PropertyID($propName, $propValue);
2860    
2861    Return the ID of the specified property name and value pair, if the
2862    pair exists. Only a small subset of the FIG attributes are stored as
2863    Sprout properties, mostly for use in search optimization.
2864    
2865    =over 4
2866    
2867    =item propName
2868    
2869    Name of the desired property.
2870    
2871    =item propValue
2872    
2873    Value expected for the desired property.
2874    
2875    =item RETURN
2876    
2877    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2878    
2879    =back
2880    
2881    =cut
2882    
2883    sub PropertyID {
2884        # Get the parameters.
2885        my ($self, $propName, $propValue) = @_;
2886        # Try to find the ID.
2887        my ($retVal) = $self->GetFlat(['Property'],
2888                                      "Property(property-name) = ? AND Property(property-value) = ?",
2889                                      [$propName, $propValue], 'Property(id)');
2890        # Return the result.
2891        return $retVal;
2892    }
2893    
2894  =head3 MergedAnnotations  =head3 MergedAnnotations
2895    
2896  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2897    
2898  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2899  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2083  Line 2942 
2942    
2943  =head3 RoleNeighbors  =head3 RoleNeighbors
2944    
2945  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
2946    
2947  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
2948  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 2126  Line 2985 
2985    
2986  =head3 FeatureLinks  =head3 FeatureLinks
2987    
2988  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
2989    
2990  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
2991  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 2157  Line 3016 
3016    
3017  =head3 SubsystemsOf  =head3 SubsystemsOf
3018    
3019  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3020    
3021  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
3022  to the role the feature performs.  to the roles the feature performs.
3023    
3024  =over 4  =over 4
3025    
# Line 2170  Line 3029 
3029    
3030  =item RETURN  =item RETURN
3031    
3032  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.
3033    
3034  =back  =back
3035    
3036  =cut  =cut
3037  #: Return Type %;  #: Return Type %@;
3038  sub SubsystemsOf {  sub SubsystemsOf {
3039          # Get the parameters.          # Get the parameters.
3040          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
3041          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
3042          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
3043                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
3044                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
3045          # Create the return value.          # Create the return value.
3046          my %retVal = ();          my %retVal = ();
3047        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
3048        # in two spreadsheet cells.
3049        my %dupHash = ();
3050          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
3051          for my $record (@subsystems) {          for my $record (@subsystems) {
3052                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
3053            my ($subsys, $role) = @{$record};
3054            # Insure it's the first time for both.
3055            my $dupKey = "$subsys\n$role";
3056            if (! exists $dupHash{"$subsys\n$role"}) {
3057                $dupHash{$dupKey} = 1;
3058                push @{$retVal{$subsys}}, $role;
3059            }
3060          }          }
3061          # Return the hash.          # Return the hash.
3062          return %retVal;          return %retVal;
3063  }  }
3064    
3065  =head3 RelatedFeatures  =head3 SubsystemList
3066    
3067  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @subsystems = $sprout->SubsystemList($featureID);
3068    
3069  Return a list of the features which are bi-directional best hits of the specified feature and  Return a list containing the names of the subsystems in which the specified
3070  have been assigned the specified function by the specified user. If no such features exists,  feature participates. Unlike L</SubsystemsOf>, this method only returns the
3071  an empty list will be returned.  subsystem names, not the roles.
3072    
3073  =over 4  =over 4
3074    
3075  =item featureID  =item featureID
3076    
3077  ID of the feature to whom the desired features are related.  ID of the feature whose subsystem names are desired.
   
 =item function  
   
 Functional assignment (as returned by C</FunctionOf>) that is used to determine which related  
 features should be selected.  
   
 =item userID  
   
 ID of the user whose functional assignments are to be used. If omitted, C<FIG> is assumed.  
3078    
3079  =item RETURN  =item RETURN
3080    
3081  Returns a list of the related features with the specified function.  Returns a list of the names of the subsystems in which the feature participates.
3082    
3083  =back  =back
3084    
3085  =cut  =cut
3086  #: Return Type @;  #: Return Type @;
3087  sub RelatedFeatures {  sub SubsystemList {
3088          # Get the parameters.          # Get the parameters.
3089          my ($self, $featureID, $function, $userID) = @_;      my ($self, $featureID) = @_;
3090          # Get a list of the features that are BBHs of the incoming feature.      # Get the list of names. We do a join to the Subsystem table because we have missing subsystems in
3091          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],      # the Sprout database!
3092                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],      my @retVal = $self->GetFlat(['HasRoleInSubsystem', 'Subsystem'], "HasRoleInSubsystem(from-link) = ?",
3093                                                                           'IsBidirectionalBestHitOf(to-link)');                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3094          # Now we loop through the features, pulling out the ones that have the correct      # Return the result, sorted.
3095          # functional assignment.      return sort @retVal;
         my @retVal = ();  
         for my $bbhFeature (@bbhFeatures) {  
                 # Get this feature's functional assignment.  
                 my $newFunction = $self->FunctionOf($bbhFeature, $userID);  
                 # If it matches, add it to the result list.  
                 if ($newFunction eq $function) {  
                         push @retVal, $bbhFeature;  
                 }  
         }  
         # Return the result list.  
         return @retVal;  
3096  }  }
3097    
3098  =head3 TaxonomySort  =head3 GenomeSubsystemData
3099    
3100  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my %featureData = $sprout->GenomeSubsystemData($genomeID);
3101    
3102  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a hash mapping genome features to their subsystem roles.
 genome. This will cause genomes from similar organisms to float close to each other.  
   
 This task could almost be handled by the database; however, the taxonomy string in the  
 database is a text field and can't be indexed. Instead, we create a hash table that maps  
 taxonomy strings to lists of features. We then process the hash table using a key sort  
 and merge the feature lists together to create the output.  
3103    
3104  =over 4  =over 4
3105    
3106  =item $featureIDs  =item genomeID
3107    
3108  List of features to be taxonomically sorted.  ID of the genome whose subsystem feature map is desired.
3109    
3110  =item RETURN  =item RETURN
3111    
3112  Returns the list of features sorted by the taxonomies of the containing genomes.  Returns a hash mapping each feature of the genome to a list of 2-tuples. Eacb
3113    2-tuple contains a subsystem name followed by a role ID.
3114    
3115  =back  =back
3116    
3117  =cut  =cut
3118  #: Return Type @;  
3119  sub TaxonomySort {  sub GenomeSubsystemData {
3120          # Get the parameters.          # Get the parameters.
3121          my ($self, $featureIDs) = @_;      my ($self, $genomeID) = @_;
3122          # Create the working hash table.      # Declare the return variable.
3123          my %hashBuffer = ();      my %retVal = ();
3124          # Loop through the features.      # Get a list of the genome features that participate in subsystems. For each
3125          for my $fid (@{$featureIDs}) {      # feature we get its spreadsheet cells and the corresponding roles.
3126                  # Get the taxonomy of the feature's genome.      my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'],
3127                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                               "HasFeature(from-link) = ?", [$genomeID],
3128                                                                                  [$fid], 'Genome(taxonomy)');                               ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']);
3129                  # Add this feature to the hash buffer.      # Now we get a list of the spreadsheet cells and their associated subsystems. Subsystems
3130          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);      # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the
3131        # list. We use it at the beginning to get all the spreadsheet cells for the genome and
3132        # again at the end to filter out participation in subsystems with a negative variant code.
3133        my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'],
3134                                     "IsGenomeOf(from-link) = ? AND ParticipatesIn(variant-code) >= 0 AND ParticipatesIn(from-link) = ?",
3135                                     [$genomeID, $genomeID], ['HasSSCell(to-link)', 'HasSSCell(from-link)']);
3136        # Now "@roleData" lists the spreadsheet cell and role for each of the genome's features.
3137        # "@cellData" lists the subsystem name for each of the genome's spreadsheet cells. We
3138        # link these two lists together to create the result. First, we want a hash mapping
3139        # spreadsheet cells to subsystem names.
3140        my %subHash = map { $_->[0] => $_->[1] } @cellData;
3141        # We loop through @cellData to build the hash.
3142        for my $roleEntry (@roleData) {
3143            # Get the data for this feature and cell.
3144            my ($fid, $cellID, $role) = @{$roleEntry};
3145            # Check for a subsystem name.
3146            my $subsys = $subHash{$cellID};
3147            if ($subsys) {
3148                # Insure this feature has an entry in the return hash.
3149                if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3150                # Merge in this new data.
3151                push @{$retVal{$fid}}, [$subsys, $role];
3152          }          }
         # Sort the keys and get the elements.  
         my @retVal = ();  
         for my $taxon (sort keys %hashBuffer) {  
                 push @retVal, @{$hashBuffer{$taxon}};  
3153          }          }
3154          # Return the result.          # Return the result.
3155          return @retVal;      return %retVal;
3156  }  }
3157    
3158  =head3 GetAll  =head3 RelatedFeatures
   
 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.  
3159    
3160  The list returned will be a list of lists. Each element of the list will contain      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
 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.  
3161    
3162  C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  Return a list of the features which are bi-directional best hits of the specified feature and
3163    have been assigned the specified function by the specified user. If no such features exists,
3164    an empty list will be returned.
3165    
3166  =over 4  =over 4
3167    
3168  =item objectNames  =item featureID
   
 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  
3169    
3170  List of the parameters to be substituted in for the parameters marks in the filter clause.  ID of the feature to whom the desired features are related.
3171    
3172  =item fields  =item function
3173    
3174  List of the fields to be returned in each element of the list returned.  Functional assignment (as returned by C</FunctionOf>) that is used to determine which related
3175    features should be selected.
3176    
3177  =item count  =item userID
3178    
3179  Maximum number of records to return. If omitted or 0, all available records will be returned.  ID of the user whose functional assignments are to be used. If omitted, C<FIG> is assumed.
3180    
3181  =item RETURN  =item RETURN
3182    
3183  Returns a list of list references. Each element of the return list contains the values for the  Returns a list of the related features with the specified function.
 fields specified in the B<fields> parameter.  
3184    
3185  =back  =back
3186    
3187  =cut  =cut
3188  #: Return Type @@;  #: Return Type @;
3189  sub GetAll {  sub RelatedFeatures {
3190          # Get the parameters.          # Get the parameters.
3191          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;      my ($self, $featureID, $function, $userID) = @_;
3192          # Create the query.      # Get a list of the features that are BBHs of the incoming feature.
3193          my $query = $self->Get($objectNames, $filterClause, $parameterList);      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);
3194          # Set up a counter of the number of records read.      # Now we loop through the features, pulling out the ones that have the correct
3195          my $fetched = 0;      # functional assignment.
         # Insure the counter has a value.  
         if (!defined $count) {  
                 $count = 0;  
         }  
         # Loop through the records returned, extracting the fields. Note that if the  
         # counter is non-zero, we stop when the number of records read hits the count.  
3196          my @retVal = ();          my @retVal = ();
3197          while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {      for my $bbhFeature (@bbhFeatures) {
3198                  my @rowData = $row->Values($fields);          # Get this feature's functional assignment.
3199                  push @retVal, \@rowData;          my $newFunction = $self->FunctionOf($bbhFeature, $userID);
3200                  $fetched++;          # If it matches, add it to the result list.
3201            if ($newFunction eq $function) {
3202                push @retVal, $bbhFeature;
3203          }          }
3204          # Return the resulting list.      }
3205        # Return the result list.
3206          return @retVal;          return @retVal;
3207  }  }
3208    
3209  =head3 GetFlat  =head3 TaxonomySort
   
 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.  
3210    
3211  =item filterClause      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3212    
3213  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  Return a list formed by sorting the specified features by the taxonomy of the containing
3214  be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  genome. This will cause genomes from similar organisms to float close to each other.
 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.  
3215    
3216  =item parameterList  This task could almost be handled by the database; however, the taxonomy string in the
3217    database is a text field and can't be indexed. Instead, we create a hash table that maps
3218    taxonomy strings to lists of features. We then process the hash table using a key sort
3219    and merge the feature lists together to create the output.
3220    
3221  List of the parameters to be substituted in for the parameters marks in the filter clause.  =over 4
3222    
3223  =item field  =item $featureIDs
3224    
3225  Name of the field to be used to get the elements of the list returned.  List of features to be taxonomically sorted.
3226    
3227  =item RETURN  =item RETURN
3228    
3229  Returns a list of values.  Returns the list of features sorted by the taxonomies of the containing genomes.
3230    
3231  =back  =back
3232    
3233  =cut  =cut
3234  #: Return Type @;  #: Return Type @;
3235  sub GetFlat {  sub TaxonomySort {
3236          # Get the parameters.          # Get the parameters.
3237          my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;      my ($self, $featureIDs) = @_;
3238          # Construct the query.      # Create the working hash table.
3239          my $query = $self->Get($objectNames, $filterClause, $parameterList);      my %hashBuffer = ();
3240          # Create the result list.      # Loop through the features.
3241        for my $fid (@{$featureIDs}) {
3242            # Get the taxonomy of the feature's genome.
3243            my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3244                                            [$fid], 'Genome(taxonomy)');
3245            # Add this feature to the hash buffer.
3246            push @{$hashBuffer{$taxonomy}}, $fid;
3247        }
3248        # Sort the keys and get the elements.
3249          my @retVal = ();          my @retVal = ();
3250          # Loop through the records, adding the field values found to the result list.      for my $taxon (sort keys %hashBuffer) {
3251          while (my $row = $query->Fetch()) {          push @retVal, @{$hashBuffer{$taxon}};
                 push @retVal, $row->Value($field);  
3252          }          }
3253          # Return the list created.      # Return the result.
3254          return @retVal;          return @retVal;
3255  }  }
3256    
3257  =head3 Protein  =head3 Protein
3258    
3259  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3260    
3261  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3262    
# Line 2498  Line 3326 
3326          # Loop through the input triples.          # Loop through the input triples.
3327          my $n = length $sequence;          my $n = length $sequence;
3328          for (my $i = 0; $i < $n; $i += 3) {          for (my $i = 0; $i < $n; $i += 3) {
3329                  # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3330                  my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3331            my $triple = uc substr($sequence, $i, 3);
3332                  # Translate it using the table.                  # Translate it using the table.
3333                  my $protein = "X";                  my $protein = "X";
3334                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 2513  Line 3342 
3342    
3343  =head3 LoadInfo  =head3 LoadInfo
3344    
3345  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3346    
3347  Return the name of the directory from which data is to be loaded and a list of the relation  Return the name of the directory from which data is to be loaded and a list of the relation
3348  names. This information is useful when trying to analyze what needs to be put where in order  names. This information is useful when trying to analyze what needs to be put where in order
# Line 2527  Line 3356 
3356          # Create the return list, priming it with the name of the data directory.          # Create the return list, priming it with the name of the data directory.
3357          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
3358          # Concatenate the table names.          # Concatenate the table names.
3359          push @retVal, $self->{_erdb}->GetTableNames();      push @retVal, $self->GetTableNames();
3360          # Return the result.          # Return the result.
3361          return @retVal;          return @retVal;
3362  }  }
3363    
3364    =head3 BBHMatrix
3365    
3366        my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3367    
3368    Find all the bidirectional best hits for the features of a genome in a
3369    specified list of target genomes. The return value will be a hash mapping
3370    features in the original genome to their bidirectional best hits in the
3371    target genomes.
3372    
3373    =over 4
3374    
3375    =item genomeID
3376    
3377    ID of the genome whose features are to be examined for bidirectional best hits.
3378    
3379    =item cutoff
3380    
3381    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3382    
3383    =item targets
3384    
3385    List of target genomes. Only pairs originating in the original
3386    genome and landing in one of the target genomes will be returned.
3387    
3388    =item RETURN
3389    
3390    Returns a hash mapping each feature in the original genome to a hash mapping its
3391    BBH pegs in the target genomes to their scores.
3392    
3393    =back
3394    
3395    =cut
3396    
3397    sub BBHMatrix {
3398        # Get the parameters.
3399        my ($self, $genomeID, $cutoff, @targets) = @_;
3400        # Declare the return variable.
3401        my %retVal = ();
3402        # Ask for the BBHs.
3403        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3404        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3405        for my $bbhData (@bbhList) {
3406            my ($peg1, $peg2, $score) = @{$bbhData};
3407            if (! exists $retVal{$peg1}) {
3408                $retVal{$peg1} = { $peg2 => $score };
3409            } else {
3410                $retVal{$peg1}->{$peg2} = $score;
3411            }
3412        }
3413        # Return the result.
3414        return %retVal;
3415    }
3416    
3417    
3418    =head3 SimMatrix
3419    
3420        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3421    
3422    Find all the similarities for the features of a genome in a
3423    specified list of target genomes. The return value will be a hash mapping
3424    features in the original genome to their similarites in the
3425    target genomes.
3426    
3427    =over 4
3428    
3429    =item genomeID
3430    
3431    ID of the genome whose features are to be examined for similarities.
3432    
3433    =item cutoff
3434    
3435    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3436    
3437    =item targets
3438    
3439    List of target genomes. Only pairs originating in the original
3440    genome and landing in one of the target genomes will be returned.
3441    
3442    =item RETURN
3443    
3444    Returns a hash mapping each feature in the original genome to a hash mapping its
3445    similar pegs in the target genomes to their scores.
3446    
3447    =back
3448    
3449    =cut
3450    
3451    sub SimMatrix {
3452        # Get the parameters.
3453        my ($self, $genomeID, $cutoff, @targets) = @_;
3454        # Declare the return variable.
3455        my %retVal = ();
3456        # Get the list of features in the source organism.
3457        my @fids = $self->FeaturesOf($genomeID);
3458        # Ask for the sims. We only want similarities to fig features.
3459        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3460        if (! defined $simList) {
3461            Confess("Unable to retrieve similarities from server.");
3462        } else {
3463            Trace("Processing sims.") if T(3);
3464            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3465            # Create a hash for the target genomes.
3466            my %targetHash = map { $_ => 1 } @targets;
3467            for my $simData (@{$simList}) {
3468                # Get the PEGs and the score.
3469                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3470                # Insure the second ID is in the target list.
3471                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3472                if (exists $targetHash{$genome2}) {
3473                    # Here it is. Now we need to add it to the return hash. How we do that depends
3474                    # on whether or not $peg1 is new to us.
3475                    if (! exists $retVal{$peg1}) {
3476                        $retVal{$peg1} = { $peg2 => $score };
3477                    } else {
3478                        $retVal{$peg1}->{$peg2} = $score;
3479                    }
3480                }
3481            }
3482        }
3483        # Return the result.
3484        return %retVal;
3485    }
3486    
3487    
3488  =head3 LowBBHs  =head3 LowBBHs
3489    
3490  C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3491    
3492  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3493  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 2563  Line 3516 
3516          my ($self, $featureID, $cutoff) = @_;          my ($self, $featureID, $cutoff) = @_;
3517          # Create the return hash.          # Create the return hash.
3518          my %retVal = ();          my %retVal = ();
3519          # Create a query to get the desired BBHs.      # Query for the desired BBHs.
3520          my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],      my @bbhList = FIGRules::BBHData($featureID, $cutoff);
                                                                 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',  
                                                                 [$cutoff, $featureID],  
                                                                 ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);  
3521          # Form the results into the return hash.          # Form the results into the return hash.
3522          for my $pair (@bbhList) {          for my $pair (@bbhList) {
3523                  $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3524            if ($self->Exists('Feature', $fid)) {
3525                $retVal{$fid} = $pair->[1];
3526            }
3527          }          }
3528          # Return the result.          # Return the result.
3529          return %retVal;          return %retVal;
3530  }  }
3531    
3532    =head3 Sims
3533    
3534        my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3535    
3536    Get a list of similarities for a specified feature. Similarity information is not kept in the
3537    Sprout database; rather, they are retrieved from a network server. The similarities are
3538    returned as B<Sim> objects. A Sim object is actually a list reference that has been blessed
3539    so that its elements can be accessed by name.
3540    
3541    Similarities can be either raw or expanded. The raw similarities are basic
3542    hits between features with similar DNA. Expanding a raw similarity drags in any
3543    features considered substantially identical. So, for example, if features B<A1>,
3544    B<A2>, and B<A3> are all substantially identical to B<A>, then a raw similarity
3545    B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3546    
3547    =over 4
3548    
3549    =item fid
3550    
3551    ID of the feature whose similarities are desired, or reference to a list of IDs
3552    of features whose similarities are desired.
3553    
3554    =item maxN
3555    
3556    Maximum number of similarities to return.
3557    
3558    =item maxP
3559    
3560    Minumum allowable similarity score.
3561    
3562    =item select
3563    
3564    Selection criterion: C<raw> means only raw similarities are returned; C<fig>
3565    means only similarities to FIG features are returned; C<all> means all expanded
3566    similarities are returned; and C<figx> means similarities are expanded until the
3567    number of FIG features equals the maximum.
3568    
3569    =item max_expand
3570    
3571    The maximum number of features to expand.
3572    
3573    =item filters
3574    
3575    Reference to a hash containing filter information, or a subroutine that can be
3576    used to filter the sims.
3577    
3578    =item RETURN
3579    
3580    Returns a reference to a list of similarity objects, or C<undef> if an error
3581    occurred.
3582    
3583    =back
3584    
3585    =cut
3586    
3587    sub Sims {
3588        # Get the parameters.
3589        my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_;
3590        # Create the shim object to test for deleted FIDs.
3591        my $shim = FidCheck->new($self);
3592        # Ask the network for sims.
3593        my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters);
3594        # Return the result.
3595        return $retVal;
3596    }
3597    
3598    =head3 IsAllGenomes
3599    
3600        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3601    
3602    Return TRUE if all genomes in the second list are represented in the first list at
3603    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3604    compared to a list of all the genomes.
3605    
3606    =over 4
3607    
3608    =item list
3609    
3610    Reference to the list to be compared to the second list.
3611    
3612    =item checkList (optional)
3613    
3614    Reference to the comparison target list. Every genome ID in this list must occur at
3615    least once in the first list. If this parameter is omitted, a list of all the genomes
3616    is used.
3617    
3618    =item RETURN
3619    
3620    Returns TRUE if every item in the second list appears at least once in the
3621    first list, else FALSE.
3622    
3623    =back
3624    
3625    =cut
3626    
3627    sub IsAllGenomes {
3628        # Get the parameters.
3629        my ($self, $list, $checkList) = @_;
3630        # Supply the checklist if it was omitted.
3631        $checkList = [$self->Genomes()] if ! defined($checkList);
3632        # Create a hash of the original list.
3633        my %testList = map { $_ => 1 } @{$list};
3634        # Declare the return variable. We assume that the representation
3635        # is complete and stop at the first failure.
3636        my $retVal = 1;
3637        my $n = scalar @{$checkList};
3638        for (my $i = 0; $retVal && $i < $n; $i++) {
3639            if (! $testList{$checkList->[$i]}) {
3640                $retVal = 0;
3641            }
3642        }
3643        # Return the result.
3644        return $retVal;
3645    }
3646    
3647  =head3 GetGroups  =head3 GetGroups
3648    
3649  C<< my %groups = $sprout->GetGroups(\@groupList); >>      my %groups = $sprout->GetGroups(\@groupList);
3650    
3651  Return a hash mapping each group to the IDs of the genomes in the group.  Return a hash mapping each group to the IDs of the genomes in the group.
3652  A list of groups may be specified, in which case only those groups will be  A list of groups may be specified, in which case only those groups will be
# Line 2597  Line 3665 
3665          # Here we have a group list. Loop through them individually,          # Here we have a group list. Loop through them individually,
3666          # getting a list of the relevant genomes.          # getting a list of the relevant genomes.
3667          for my $group (@{$groupList}) {          for my $group (@{$groupList}) {
3668              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3669                  [$group], "Genome(id)");                  [$group], "Genome(id)");
3670              $retVal{$group} = \@genomeIDs;              $retVal{$group} = \@genomeIDs;
3671          }          }
# Line 2605  Line 3673 
3673          # Here we need all of the groups. In this case, we run through all          # Here we need all of the groups. In this case, we run through all
3674          # of the genome records, putting each one found into the appropriate          # of the genome records, putting each one found into the appropriate
3675          # group. Note that we use a filter clause to insure that only genomes          # group. Note that we use a filter clause to insure that only genomes
3676          # in groups are included in the return set.          # in real NMPDR groups are included in the return set.
3677          my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],          my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3678                                      ['Genome(id)', 'Genome(group-name)']);                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3679          # Loop through the genomes found.          # Loop through the genomes found.
3680          for my $genome (@genomes) {          for my $genome (@genomes) {
3681              # Pop this genome's ID off the current list.              # Get the genome ID and group, and add this genome to the group's list.
3682              my @groups = @{$genome};              my ($genomeID, $group) = @{$genome};
3683              my $genomeID = shift @groups;              push @{$retVal{$group}}, $genomeID;
             # Loop through the groups, adding the genome ID to each group's  
             # list.  
             for my $group (@groups) {  
                 Tracer::AddToListMap(\%retVal, $group, $genomeID);  
             }  
3684          }          }
3685      }      }
3686      # Return the hash we just built.      # Return the hash we just built.
3687      return %retVal;      return %retVal;
3688  }  }
3689    
3690    =head3 MyGenomes
3691    
3692        my @genomes = Sprout::MyGenomes($dataDir);
3693    
3694    Return a list of the genomes to be included in the Sprout.
3695    
3696    This method is provided for use during the Sprout load. It presumes the Genome load file has
3697    already been created. (It will be in the Sprout data directory and called either C<Genome>
3698    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3699    IDs.
3700    
3701    =over 4
3702    
3703    =item dataDir
3704    
3705    Directory containing the Sprout load files.
3706    
3707    =back
3708    
3709    =cut
3710    #: Return Type @;
3711    sub MyGenomes {
3712        # Get the parameters.
3713        my ($dataDir) = @_;
3714        # Compute the genome file name.
3715        my $genomeFileName = LoadFileName($dataDir, "Genome");
3716        # Extract the genome IDs from the files.
3717        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3718        # Return the result.
3719        return @retVal;
3720    }
3721    
3722    =head3 LoadFileName
3723    
3724        my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3725    
3726    Return the name of the load file for the specified table in the specified data
3727    directory.
3728    
3729    =over 4
3730    
3731    =item dataDir
3732    
3733    Directory containing the Sprout load files.
3734    
3735    =item tableName
3736    
3737    Name of the table whose load file is desired.
3738    
3739    =item RETURN
3740    
3741    Returns the name of the file containing the load data for the specified table, or
3742    C<undef> if no load file is present.
3743    
3744    =back
3745    
3746    =cut
3747    #: Return Type $;
3748    sub LoadFileName {
3749        # Get the parameters.
3750        my ($dataDir, $tableName) = @_;
3751        # Declare the return variable.
3752        my $retVal;
3753        # Check for the various file names.
3754        if (-e "$dataDir/$tableName") {
3755            $retVal = "$dataDir/$tableName";
3756        } elsif (-e "$dataDir/$tableName.dtx") {
3757            $retVal = "$dataDir/$tableName.dtx";
3758        }
3759        # Return the result.
3760        return $retVal;
3761    }
3762    
3763    =head3 DeleteGenome
3764    
3765        my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3766    
3767    Delete a genome from the database.
3768    
3769    =over 4
3770    
3771    =item genomeID
3772    
3773    ID of the genome to delete
3774    
3775    =item testFlag
3776    
3777    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3778    
3779    =item RETURN
3780    
3781    Returns a statistics object describing the rows deleted.
3782    
3783    =back
3784    
3785    =cut
3786    #: Return Type $%;
3787    sub DeleteGenome {
3788        # Get the parameters.
3789        my ($self, $genomeID, $testFlag) = @_;
3790        # Perform the delete for the genome's features.
3791        my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3792        # Perform the delete for the primary genome data.
3793        my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3794        $retVal->Accumulate($stats);
3795        # Return the result.
3796        return $retVal;
3797    }
3798    
3799    =head3 Fix
3800    
3801        my %fixedHash = $sprout->Fix(%groupHash);
3802    
3803    Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3804    The groups will be combined into the appropriate super-groups.
3805    
3806    =over 4
3807    
3808    =item groupHash
3809    
3810    Hash to be fixed up.
3811    
3812    =item RETURN
3813    
3814    Returns a fixed-up version of the hash.
3815    
3816    =back
3817    
3818    =cut
3819    
3820    sub Fix {
3821        # Get the parameters.
3822        my ($self, %groupHash) = @_;
3823        # Create the result hash.
3824        my %retVal = ();
3825        # Copy over the genomes.
3826        for my $groupID (keys %groupHash) {
3827            # Get the super-group name.
3828            my $realGroupID = $self->SuperGroup($groupID);
3829            # Append this group's genomes into the result hash
3830            # using the super-group name.
3831            push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3832        }
3833        # Return the result hash.
3834        return %retVal;
3835    }
3836    
3837    =head3 GroupPageName
3838    
3839        my $name = $sprout->GroupPageName($group);
3840    
3841    Return the name of the page for the specified NMPDR group.
3842    
3843    =over 4
3844    
3845    =item group
3846    
3847    Name of the relevant group.
3848    
3849    =item RETURN
3850    
3851    Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3852    memory it will be read in.
3853    
3854    =back
3855    
3856    =cut
3857    
3858    sub GroupPageName {
3859        # Get the parameters.
3860        my ($self, $group) = @_;
3861        # Check for the group file data.
3862        my %superTable = $self->CheckGroupFile();
3863        # Compute the real group name.
3864        my $realGroup = $self->SuperGroup($group);
3865        # Get the associated page name.
3866        my $retVal = "../content/$superTable{$realGroup}->{page}";
3867        # Return the result.
3868        return $retVal;
3869    }
3870    
3871    
3872    =head3 AddProperty
3873    
3874        $sprout->AddProperty($featureID, $key, @values);
3875    
3876    Add a new attribute value (Property) to a feature.
3877    
3878    =over 4
3879    
3880    =item peg
3881    
3882    ID of the feature to which the attribute is to be added.
3883    
3884    =item key
3885    
3886    Name of the attribute (key).
3887    
3888    =item values
3889    
3890    Values of the attribute.
3891    
3892    =back
3893    
3894    =cut
3895    #: Return Type ;
3896    sub AddProperty {
3897        # Get the parameters.
3898        my ($self, $featureID, $key, @values) = @_;
3899        # Add the property using the attached attributes object.
3900        $self->{_ca}->AddAttribute($featureID, $key, @values);
3901    }
3902    
3903    =head3 CheckGroupFile
3904    
3905        my %groupData = $sprout->CheckGroupFile();
3906    
3907    Get the group file hash. The group file hash describes the relationship
3908    between a group and the super-group to which it belongs for purposes of
3909    display. The super-group name is computed from the first capitalized word
3910    in the actual group name. For each super-group, the group file contains
3911    the page name and a list of the species expected to be in the group.
3912    Each species is specified by a genus and a species name. A species name
3913    of C<0> implies an entire genus.
3914    
3915    This method returns a hash from super-group names to a hash reference. Each
3916    resulting hash reference contains the following fields.
3917    
3918    =over 4
3919    
3920    =item page
3921    
3922    The super-group's web page in the NMPDR.
3923    
3924    =item contents
3925    
3926    A list of 2-tuples, each containing a genus name followed by a species name
3927    (or 0, indicating all species). This list indicates which organisms belong
3928    in the super-group.
3929    
3930    =back
3931    
3932    =cut
3933    
3934    sub CheckGroupFile {
3935        # Get the parameters.
3936        my ($self) = @_;
3937        # Check to see if we already have this hash.
3938        if (! defined $self->{groupHash}) {
3939            # We don't, so we need to read it in.
3940            my %groupHash;
3941            # Read the group file.
3942            my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
3943            # Loop through the list of sort-of groups.
3944            for my $groupLine (@groupLines) {
3945                my ($name, $page, @contents) = split /\t/, $groupLine;
3946                $groupHash{$name} = { page => $page,
3947                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
3948                                    };
3949            }
3950            # Save the hash.
3951            $self->{groupHash} = \%groupHash;
3952        }
3953        # Return the result.
3954        return %{$self->{groupHash}};
3955    }
3956    
3957    =head2 Virtual Methods
3958    
3959    =head3 CleanKeywords
3960    
3961        my $cleanedString = $sprout->CleanKeywords($searchExpression);
3962    
3963    Clean up a search expression or keyword list. This involves converting the periods
3964    in EC numbers to underscores, converting non-leading minus signs to underscores,
3965    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
3966    characters. In addition, any extra spaces are removed.
3967    
3968    =over 4
3969    
3970    =item searchExpression
3971    
3972    Search expression or keyword list to clean. Note that a search expression may
3973    contain boolean operators which need to be preserved. This includes leading
3974    minus signs.
3975    
3976    =item RETURN
3977    
3978    Cleaned expression or keyword list.
3979    
3980    =back
3981    
3982    =cut
3983    
3984    sub CleanKeywords {
3985        # Get the parameters.
3986        my ($self, $searchExpression) = @_;
3987        # Perform the standard cleanup.
3988        my $words = $self->ERDB::CleanKeywords($searchExpression);
3989        # Fix the periods in EC and TC numbers.
3990        $words =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;
3991        # Fix non-trailing periods.
3992        $words =~ s/\.(\w)/_$1/g;
3993        # Fix non-leading minus signs.
3994        $words =~ s/(\w)[\-]/$1_/g;
3995        # Fix the vertical bars and colons
3996        $words =~ s/(\w)[|:](\w)/$1'$2/g;
3997        # Now split up the list so that each keyword is in its own string. We keep the delimiters
3998        # because they may contain boolean expression data.
3999        my @words = split /([^A-Za-z'0-9_]+)/, $words;
4000        # We'll convert the stemmable words into stems and re-assemble the result.
4001        my $retVal = "";
4002        for my $word (@words) {
4003            my $stem = $self->Stem($word);
4004            if (defined $stem) {
4005                $retVal .= $stem;
4006            } else {
4007                $retVal .= $word;
4008            }
4009        }
4010        Trace("Cleaned keyword list for \"$searchExpression\" is \"$retVal\".") if T(3);
4011        # Return the result.
4012        return $retVal;
4013    }
4014    
4015  =head2 Internal Utility Methods  =head2 Internal Utility Methods
4016    
4017  =head3 ParseAssignment  =head3 ParseAssignment
# Line 2634  Line 4022 
4022    
4023  A functional assignment is always of the form  A functional assignment is always of the form
4024    
4025      I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>      set YYYY function to
4026        ZZZZ
4027    
4028  where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the  where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
4029  actual functional role. In most cases, the user and the assigning user will be the  the user and the assigning user (from MadeAnnotation) will be the same, but that is
4030  same, but that is not always the case.  not always the case.
4031    
4032    In addition, the functional role may contain extra data that is stripped, such as
4033    terminating spaces or a comment separated from the rest of the text by a tab.
4034    
4035  This is a static method.  This is a static method.
4036    
4037  =over 4  =over 4
4038    
4039    =item user
4040    
4041    Name of the assigning user.
4042    
4043  =item text  =item text
4044    
4045  Text of the annotation.  Text of the annotation.
# Line 2659  Line 4055 
4055    
4056  sub _ParseAssignment {  sub _ParseAssignment {
4057          # Get the parameters.          # Get the parameters.
4058          my ($text) = @_;      my ($user, $text) = @_;
4059          # Declare the return value.          # Declare the return value.
4060          my @retVal = ();          my @retVal = ();
4061          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
4062          my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
4063          if ($type =~ m/^set ([^ ]+) function to$/i) {      if ($type =~ m/^set function to$/i) {
4064                  # Here it is, so we return the user name (which is in $1), the functional role text,          # Here we have an assignment without a user, so we use the incoming user ID.
4065          # and the assigning user.          @retVal = ($user, $function);
4066                  @retVal = ($1, $function, $user);      } elsif ($type =~ m/^set (\S+) function to$/i) {
4067            # Here we have an assignment with a user that is passed back to the caller.
4068            @retVal = ($1, $function);
4069        }
4070        # If we have an assignment, we need to clean the function text. There may be
4071        # extra junk at the end added as a note from the user.
4072        if (defined( $retVal[1] )) {
4073            $retVal[1] =~ s/(\t\S)?\s*$//;
4074          }          }
4075          # Return the result list.          # Return the result list.
4076          return @retVal;          return @retVal;
4077  }  }
4078    
4079    =head3 _CheckFeature
4080    
4081        my $flag = $sprout->_CheckFeature($fid);
4082    
4083    Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
4084    
4085    =over 4
4086    
4087    =item fid
4088    
4089    Feature ID to check.
4090    
4091    =item RETURN
4092    
4093    Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE.
4094    
4095    =back
4096    
4097    =cut
4098    
4099    sub _CheckFeature {
4100        # Get the parameters.
4101        my ($self, $fid) = @_;
4102        # Insure we have a genome hash.
4103        if (! defined $self->{genomeHash}) {
4104            my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');
4105            $self->{genomeHash} = \%genomeHash;
4106        }
4107        # Get the feature's genome ID.
4108        my ($genomeID) = FIGRules::ParseFeatureID($fid);
4109        # Return an indicator of whether or not the genome ID is in the hash.
4110        return ($self->{genomeHash}->{$genomeID} ? 1 : 0);
4111    }
4112    
4113  =head3 FriendlyTimestamp  =head3 FriendlyTimestamp
4114    
4115  Convert a time number to a user-friendly time stamp for display.  Convert a time number to a user-friendly time stamp for display.
# Line 2695  Line 4132 
4132    
4133  sub FriendlyTimestamp {  sub FriendlyTimestamp {
4134      my ($timeValue) = @_;      my ($timeValue) = @_;
4135      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
4136        return $retVal;
4137    }
4138    
4139    
4140    =head3 Hint
4141    
4142        my $htmlText = SearchHelper::Hint($wikiPage, $hintText);
4143    
4144    Return the HTML for a small question mark that displays the specified hint text when it is clicked.
4145    This HTML can be put in forms to provide a useful hinting mechanism.
4146    
4147    =over 4
4148    
4149    =item wikiPage
4150    
4151    Name of the wiki page to be popped up when the hint mark is clicked.
4152    
4153    =item hintText
4154    
4155    Text to display for the hint. It is raw html, but may not contain any double quotes.
4156    
4157    =item RETURN
4158    
4159    Returns the html for the hint facility. The resulting html shows a small button-like thing that
4160    uses the standard FIG popup technology.
4161    
4162    =back
4163    
4164    =cut
4165    
4166    sub Hint {
4167        # Get the parameters.
4168        my ($wikiPage, $hintText) = @_;
4169        # Escape the single quotes in the hint text.
4170        my $quotedText = $hintText;
4171        $quotedText =~ s/'/\\'/g;
4172        # Convert the wiki page name to a URL.
4173        my $wikiURL = join("", map { ucfirst $_ } split /\s+/, $wikiPage);
4174        $wikiURL = "$FIG_Config::cgi_url/wiki/view.cgi/FIG/$wikiURL";
4175        # Compute the mouseover script.
4176        my $mouseOver = "doTooltip(this, '$quotedText')";
4177        # Create the html.
4178        my $retVal = "&nbsp;<a href=\"$wikiURL\"><img src=\"$FIG_Config::cgi_url/Html/button-h.png\" class=\"helpicon\" onmouseover=\"$mouseOver\"/></a>";
4179        # Return it.
4180      return $retVal;      return $retVal;
4181  }  }
4182    

Legend:
Removed from v.1.12  
changed lines
  Added in v.1.117

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3