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

Diff of /Sprout/Sprout.pm

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

revision 1.33, Wed Sep 14 13:26:27 2005 UTC revision 1.110, Tue Apr 29 20:54:51 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 base qw(ERDB);
19    
20  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
21    
# Line 25  Line 28 
28  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>
29  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>.
30    
31  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' });
32    
33  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
34  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
35  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
36  L</dna_seq> returns the DNA sequence for a specified genome location.  L</DNASeq> returns the DNA sequence for a specified genome location.
37    
38    The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.
39    
40  =cut  =cut
41    
# Line 40  Line 45 
45    
46  =head3 new  =head3 new
47    
48  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
49    
50  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
51  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 67 
67    
68  * 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>)
69    
70  * 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)
71    
72  * B<port> connection port (default C<0>)  * B<port> connection port (default C<0>)
73    
74    * B<sock> connection socket (default same as SEED)
75    
76  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)
77    
78  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
79    
80  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
81    
82    * B<host> name of the database host
83    
84  =back  =back
85    
86  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
87  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
88  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
89    
90  C<< my $sprout = Sprout->new('Sprout', { userData =>; 'fig/admin', dataDir => '/usr/fig/SproutData' }); >>      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });
91    
92  =cut  =cut
93    
94  sub new {  sub new {
95      # Get the parameters.      # Get the parameters.
96      my ($class, $dbName, $options) = @_;      my ($class, $dbName, $options) = @_;
97        # Compute the DBD directory.
98        my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
99                                                      $FIG_Config::fig );
100      # 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
101      # the incoming data.      # the incoming data.
102      my $optionTable = Tracer::GetOptions({      my $optionTable = Tracer::GetOptions({
# Line 92  Line 104 
104                                                          # database type                                                          # database type
105                         dataDir      => $FIG_Config::sproutData,                         dataDir      => $FIG_Config::sproutData,
106                                                          # data file directory                                                          # data file directory
107                         xmlFileName  => "$FIG_Config::sproutData/SproutDBD.xml",                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
108                                                          # database definition file name                                                          # database definition file name
109                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
110                                                          # user name and password                                                          # user name and password
111                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::dbport,
112                                                          # database connection port                                                          # database connection port
113                           sock         => $FIG_Config::dbsock,
114                           host         => $FIG_Config::sprout_host,
115                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
116                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
117                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
# Line 110  Line 124 
124      # Connect to the database.      # Connect to the database.
125      my $dbh;      my $dbh;
126      if (! $optionTable->{noDBOpen}) {      if (! $optionTable->{noDBOpen}) {
127            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
128          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
129                                  $password, $optionTable->{port});                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
130      }      }
131      # Create the ERDB object.      # Create the ERDB object.
132      my $xmlFileName = "$optionTable->{xmlFileName}";      my $xmlFileName = "$optionTable->{xmlFileName}";
133      my $erdb = ERDB->new($dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName);
134      # Create this object.      # Add the option table and XML file name.
135      my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName };      $retVal->{_options} = $optionTable;
136      # Bless and return it.      $retVal->{_xmlName} = $xmlFileName;
137      bless $self;      # Set up space for the group file data.
138      return $self;      $retVal->{groupHash} = undef;
139  }      # Set up space for the genome hash. We use this to identify NMPDR genomes.
140        $retVal->{genomeHash} = undef;
141  =head3 MaxSegment      # Connect to the attributes.
142        if ($FIG_Config::attrURL) {
143  C<< my $length = $sprout->MaxSegment(); >>          Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
144            $retVal->{_ca} = RemoteCustomAttributes->new($FIG_Config::attrURL);
145  This method returns the maximum permissible length of a feature segment. The length is important      } elsif ($FIG_Config::attrDbName) {
146  because it enables us to make reasonable guesses at how to find features inside a particular          Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
147  contig region. For example, if the maximum length is 4000 and we're looking for a feature that          my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
148  overlaps the region from 6000 to 7000 we know that the starting position must be between 2001          $retVal->{_ca} = CustomAttributes->new(user => $user);
 and 10999.  
   
 =cut  
 #: Return Type $;  
 sub MaxSegment {  
     my ($self) = @_;  
     return $self->{_options}->{maxSegmentLength};  
149  }  }
150        # Return it.
151  =head3 MaxSequence      return $retVal;
   
 C<< my $length = $sprout->MaxSequence(); >>  
   
 This method returns the maximum permissible length of a contig sequence. A contig is broken  
 into sequences in order to save memory resources. In particular, when manipulating features,  
 we generally only need a few sequences in memory rather than the entire contig.  
   
 =cut  
 #: Return Type $;  
 sub MaxSequence {  
     my ($self) = @_;  
     return $self->{_options}->{maxSequenceLength};  
152  }  }
153    
154  =head3 Get  =head3 CoreGenomes
   
 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.  
   
 C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>  
   
 The WHERE clause contains a single question mark, so there is a single additional  
 parameter representing the parameter value. It would also be possible to code  
   
 C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  
   
 however, this version of the call would generate a syntax error if there were any quote  
 characters inside the variable C<$genus>.  
   
 The use of the strange parenthesized notation for field names enables us to distinguish  
 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.  
   
 It is possible to specify multiple entity and relationship names in order to retrieve more than  
 one object's data at the same time, which allows highly complex joined queries. For example,  
   
 C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>  
   
 This query returns all the genomes for a particular genus and allows access to the  
 sources from which they came. The join clauses to go from Genome to Source are generated  
 automatically.  
   
 Finally, the filter clause can contain sort information. To do this, simply put an C<ORDER BY>  
 clause at the end of the filter. Field references in the ORDER BY section follow the same rules  
 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.  
   
 C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ? ORDER BY Genome(species)", [$genus]); >>  
   
 It is also permissible to specify I<only> an ORDER BY clause. For example, the following invocation gets  
 all genomes ordered by genus and species.  
155    
156  C<< $query = $sprout->Get(['Genome'], "ORDER BY Genome(genus), Genome(species)"); >>      my @genomes = $sprout->CoreGenomes($scope);
157    
158  Odd things may happen if one of the ORDER BY fields is in a secondary relation. So, for example, an  Return the IDs of NMPDR genomes in the specified scope.
 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.  
   
 If multiple names are specified, then the query processor will automatically determine a  
 join path between the entities and relationships. The algorithm used is very simplistic.  
 In particular, you can't specify any entity or relationship more than once, and if a  
 relationship is recursive, the path is determined by the order in which the entity  
 and the relationship appear. For example, consider a recursive relationship B<IsParentOf>  
 which relates B<People> objects to other B<People> objects. If the join path is  
 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.  
159    
160  =over 4  =over 4
161    
162  =item objectNames  =item scope
   
 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.  
163    
164  =item parameterList  Scope of the desired genomes. C<core> covers the original core genomes,
165    C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
166  List of the parameters to be substituted in for the parameters marks in the filter clause.  genomes in the system.
167    
168  =item RETURN  =item RETURN
169    
170  Returns a B<DBQuery> that can be used to iterate through all of the results.  Returns a list of the IDs for the genomes in the specified scope.
171    
172  =back  =back
173    
174  =cut  =cut
175    
176  sub Get {  sub CoreGenomes {
177      # Get the parameters.      # Get the parameters.
178      my ($self, $objectNames, $filterClause, $parameterList) = @_;      my ($self, $scope) = @_;
179      # We differ from the ERDB Get method in that the parameter list is passed in as a list reference      # Declare the return variable.
180      # rather than a list of parameters. The next step is to convert the parameters from a reference      my @retVal = ();
181      # to a real list. We can only do this if the parameters have been specified.      # If we want all genomes, then this is easy.
182      my @parameters;      if ($scope eq 'all') {
183      if ($parameterList) { @parameters = @{$parameterList}; }          @retVal = $self->Genomes();
184      return $self->{_erdb}->Get($objectNames, $filterClause, @parameters);      } else {
185            # Here we're dealing with groups. Get the hash of all the
186            # genome groups.
187            my %groups = $self->GetGroups();
188            # Loop through the groups, keeping the ones that we want.
189            for my $group (keys %groups) {
190                # Decide if we want to keep this group.
191                my $keepGroup = 0;
192                if ($scope eq 'nmpdr') {
193                    # NMPDR mode: keep all groups.
194                    $keepGroup = 1;
195                } elsif ($scope eq 'core') {
196                    # CORE mode. Only keep real core groups.
197                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
198                        $keepGroup = 1;
199                    }
200                }
201                # Add this group if we're keeping it.
202                if ($keepGroup) {
203                    push @retVal, @{$groups{$group}};
204                }
205            }
206        }
207        # Return the result.
208        return @retVal;
209  }  }
210    
211  =head3 GetEntity  =head3 SuperGroup
212    
213  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>      my $superGroup = $sprout->SuperGroup($groupName);
214    
215  Return an object describing the entity instance with a specified ID.  Return the name of the super-group containing the specified NMPDR genome
216    group. If no appropriate super-group can be found, an error will be
217    thrown.
218    
219  =over 4  =over 4
220    
221  =item entityType  =item groupName
   
 Entity type name.  
222    
223  =item ID  Name of the group whose super-group is desired.
   
 ID of the desired entity.  
224    
225  =item RETURN  =item RETURN
226    
227  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Returns the name of the super-group containing the incoming group.
 instance is found with the specified key.  
228    
229  =back  =back
230    
231  =cut  =cut
232    
233  sub GetEntity {  sub SuperGroup {
234      # Get the parameters.      # Get the parameters.
235      my ($self, $entityType, $ID) = @_;      my ($self, $groupName) = @_;
236      # Call the ERDB method.      # Declare the return variable.
237      return $self->{_erdb}->GetEntity($entityType, $ID);      my $retVal;
238        # Get the group hash.
239        my %groupHash = $self->CheckGroupFile();
240        # Find the super-group genus.
241        $groupName =~ /([A-Z]\w+)/;
242        my $nameThing = $1;
243        # See if it's directly in the group hash.
244        if (exists $groupHash{$nameThing}) {
245            # Yes, then it's our result.
246            $retVal = $nameThing;
247        } else {
248            # No, so we have to search.
249            for my $superGroup (keys %groupHash) {
250                # Get this super-group's item list.
251                my $list = $groupHash{$superGroup}->{contents};
252                # Search it.
253                if (grep { $_->[0] eq $nameThing } @{$list}) {
254                    $retVal = $superGroup;
255                }
256            }
257            # Make sure we found something.
258            if (! $retVal) {
259                Confess("No super-group found for \"$groupName\".");
260            }
261        }
262        # Return the result.
263        return $retVal;
264  }  }
265    
266  =head3 GetEntityValues  =head3 MaxSegment
   
 C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>  
   
 Return a list of values from a specified entity instance.  
   
 =over 4  
   
 =item entityType  
   
 Entity type name.  
   
 =item ID  
   
 ID of the desired entity.  
   
 =item fields  
   
 List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.  
   
 =item RETURN  
267    
268  Returns a flattened list of the values of the specified fields for the specified entity.      my $length = $sprout->MaxSegment();
269    
270  =back  This method returns the maximum permissible length of a feature segment. The length is important
271    because it enables us to make reasonable guesses at how to find features inside a particular
272    contig region. For example, if the maximum length is 4000 and we're looking for a feature that
273    overlaps the region from 6000 to 7000 we know that the starting position must be between 2001
274    and 10999.
275    
276  =cut  =cut
277  #: Return Type @;  #: Return Type $;
278  sub GetEntityValues {  sub MaxSegment {
279      # Get the parameters.      my ($self) = @_;
280      my ($self, $entityType, $ID, $fields) = @_;      return $self->{_options}->{maxSegmentLength};
     # Call the ERDB method.  
     return $self->{_erdb}->GetEntityValues($entityType, $ID, $fields);  
281  }  }
282    
283  =head3 ShowMetaData  =head3 MaxSequence
   
 C<< $sprout->ShowMetaData($fileName); >>  
   
 This method outputs a description of the database to an HTML file in the data directory.  
   
 =over 4  
   
 =item fileName  
284    
285  Fully-qualified name to give to the output file.      my $length = $sprout->MaxSequence();
286    
287  =back  This method returns the maximum permissible length of a contig sequence. A contig is broken
288    into sequences in order to save memory resources. In particular, when manipulating features,
289    we generally only need a few sequences in memory rather than the entire contig.
290    
291  =cut  =cut
292    #: Return Type $;
293  sub ShowMetaData {  sub MaxSequence {
294      # Get the parameters.      my ($self) = @_;
295      my ($self, $fileName) = @_;      return $self->{_options}->{maxSequenceLength};
     # Compute the file name.  
     my $options = $self->{_options};  
     # Call the show method on the underlying ERDB object.  
     $self->{_erdb}->ShowMetaData($fileName);  
296  }  }
297    
298  =head3 Load  =head3 Load
299    
300  C<< $sprout->Load($rebuild); >>;      $sprout->Load($rebuild);;
301    
302  Load the database from files in the data directory, optionally re-creating the tables.  Load the database from files in the data directory, optionally re-creating the tables.
303    
# Line 379  Line 329 
329  sub Load {  sub Load {
330      # Get the parameters.      # Get the parameters.
331      my ($self, $rebuild) = @_;      my ($self, $rebuild) = @_;
     # Get the database object.  
     my $erdb = $self->{_erdb};  
332      # Load the tables from the data directory.      # Load the tables from the data directory.
333      my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild);      my $retVal = $self->LoadTables($self->{_options}->{dataDir}, $rebuild);
334      # Return the statistics.      # Return the statistics.
335      return $retVal;      return $retVal;
336  }  }
337    
338  =head3 LoadUpdate  =head3 LoadUpdate
339    
340  C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
341    
342  Load updates to one or more database tables. This method enables the client to make changes to one  Load updates to one or more database tables. This method enables the client to make changes to one
343  or two tables without reloading the whole database. For each table, there must be a corresponding  or two tables without reloading the whole database. For each table, there must be a corresponding
# Line 422  Line 370 
370  sub LoadUpdate {  sub LoadUpdate {
371      # Get the parameters.      # Get the parameters.
372      my ($self, $truncateFlag, $tableList) = @_;      my ($self, $truncateFlag, $tableList) = @_;
     # Get the database object.  
     my $erdb = $self->{_erdb};  
373      # Declare the return value.      # Declare the return value.
374      my $retVal = Stats->new();      my $retVal = Stats->new();
375      # Get the data directory.      # Get the data directory.
# Line 437  Line 383 
383              Trace("No load file found for $tableName in $dataDir.") if T(0);              Trace("No load file found for $tableName in $dataDir.") if T(0);
384          } else {          } else {
385              # Attempt to load this table.              # Attempt to load this table.
386              my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
387              # Accumulate the resulting statistics.              # Accumulate the resulting statistics.
388              $retVal->Accumulate($result);              $retVal->Accumulate($result);
389          }          }
# Line 446  Line 392 
392      return $retVal;      return $retVal;
393  }  }
394    
395    =head3 GenomeCounts
396    
397        my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
398    
399    Count the number of genomes in each domain. If I<$complete> is TRUE, only complete
400    genomes will be included in the counts.
401    
402    =over 4
403    
404    =item complete
405    
406    TRUE if only complete genomes are to be counted, FALSE if all genomes are to be
407    counted
408    
409    =item RETURN
410    
411    A six-element list containing the number of genomes in each of six categories--
412    Archaea, Bacteria, Eukaryota, Viral, Environmental, and Unknown, respectively.
413    
414    =back
415    
416    =cut
417    
418    sub GenomeCounts {
419        # Get the parameters.
420        my ($self, $complete) = @_;
421        # Set the filter based on the completeness flag.
422        my $filter = ($complete ? "Genome(complete) = 1" : "");
423        # Get all the genomes and the related taxonomy information.
424        my @genomes = $self->GetAll(['Genome'], $filter, [], ['Genome(id)', 'Genome(taxonomy)']);
425        # Clear the counters.
426        my ($arch, $bact, $euk, $vir, $env, $unk) = (0, 0, 0, 0, 0, 0);
427        # Loop through, counting the domains.
428        for my $genome (@genomes) {
429            if    ($genome->[1] =~ /^archaea/i)  { ++$arch }
430            elsif ($genome->[1] =~ /^bacter/i)   { ++$bact }
431            elsif ($genome->[1] =~ /^eukar/i)    { ++$euk }
432            elsif ($genome->[1] =~ /^vir/i)      { ++$vir }
433            elsif ($genome->[1] =~ /^env/i)      { ++$env }
434            else  { ++$unk }
435        }
436        # Return the counts.
437        return ($arch, $bact, $euk, $vir, $env, $unk);
438    }
439    
440    =head3 ContigCount
441    
442        my $count = $sprout->ContigCount($genomeID);
443    
444    Return the number of contigs for the specified genome ID.
445    
446    =over 4
447    
448    =item genomeID
449    
450    ID of the genome whose contig count is desired.
451    
452    =item RETURN
453    
454    Returns the number of contigs for the specified genome.
455    
456    =back
457    
458    =cut
459    
460    sub ContigCount {
461        # Get the parameters.
462        my ($self, $genomeID) = @_;
463        # Get the contig count.
464        my $retVal = $self->GetCount(['Contig', 'HasContig'], "HasContig(from-link) = ?", [$genomeID]);
465        # Return the result.
466        return $retVal;
467    }
468    
469    =head3 GenomeMenu
470    
471        my $html = $sprout->GenomeMenu(%options);
472    
473    Generate a genome selection control with the specified name and options.
474    This control is almost but not quite the same as the genome control in the
475    B<SearchHelper> class. Eventually, the two will be combined.
476    
477    =over 4
478    
479    =item options
480    
481    Optional parameters for the control (see below).
482    
483    =item RETURN
484    
485    Returns the HTML for a genome selection control on a form (sometimes called a popup menu).
486    
487    =back
488    
489    The valid options are as follows.
490    
491    =over 4
492    
493    =item name
494    
495    Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
496    Terrible things will happen if you have two controls with the same name on the same page.
497    
498    =item filter
499    
500    If specified, a filter for the list of genomes to display. The filter should be in the form of a
501    list reference. The first element of the list should be the filter string, and the remaining elements
502    the filter parameters.
503    
504    =item multiSelect
505    
506    If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
507    
508    =item size
509    
510    Number of rows to display in the control. The default is C<10>
511    
512    =item id
513    
514    ID to give this control. The default is the value of the C<name> option. Nothing will work correctly
515    unless this ID is unique.
516    
517    =item selected
518    
519    A comma-delimited list of selected genomes, or a reference to a list of selected genomes. The
520    default is none.
521    
522    =item class
523    
524    If specified, a style class to assign to the genome control.
525    
526    =back
527    
528    =cut
529    
530    sub GenomeMenu {
531        # Get the parameters.
532        my ($self, %options) = @_;
533        # Get the control's name and ID.
534        my $menuName = $options{name} || 'myGenomeControl';
535        my $menuID = $options{id} || $menuName;
536        # Compute the IDs for the status display.
537        my $divID = "${menuID}_status";
538        my $urlID = "${menuID}_url";
539        # Compute the code to show selected genomes in the status area.
540        my $showSelect = "showSelected('$menuID', '$divID', '$urlID', 1000)";
541        # Check for single-select or multi-select.
542        my $multiSelect = $options{multiSelect} || 0;
543        # Get the style data.
544        my $class = $options{class} || '';
545        # Get the list of pre-selected items.
546        my $selections = $options{selected} || [];
547        if (ref $selections ne 'ARRAY') {
548            $selections = [ split /\s*,\s*/, $selections ];
549        }
550        my %selected = map { $_ => } @{$selections};
551        # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
552        # string or a list reference.
553        my $filterParms = $options{filter} || "";
554        if (! ref $filterParms) {
555            $filterParms = [split /\t|\\t/, $filterParms];
556        }
557        my $filterString = shift @{$filterParms};
558        # Get a list of all the genomes in group order. In fact, we only need them ordered
559        # by name (genus,species,strain), but putting primary-group in front enables us to
560        # take advantage of an existing index.
561        my @genomeList = $self->GetAll(['Genome'], "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
562                                       $filterParms,
563                                       [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
564        # Create a hash to organize the genomes by group. Each group will contain a list of
565        # 2-tuples, the first element being the genome ID and the second being the genome
566        # name.
567        my %gHash = ();
568        for my $genome (@genomeList) {
569            # Get the genome data.
570            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
571            # Compute its name. This is the genus, species, strain (if any), and the contig count.
572            my $name = "$genus $species ";
573            $name .= "$strain " if $strain;
574            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
575            # Now we get the domain. The domain tells us the display style of the organism.
576            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
577            # Now compute the display group. This is normally the primary group, but if the
578            # organism is supporting, we blank it out.
579            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
580            # Push the genome into the group's list. Note that we use the real group
581            # name for the hash key here, not the display group name.
582            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
583        }
584        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
585        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
586        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
587        # that aren't "other". At some point, we will want to make this less complicated.
588        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
589                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
590        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
591        # Remember the number of NMPDR groups.
592        my $nmpdrGroupCount = scalar @groups;
593        # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
594        # of the domains found.
595        my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
596        my @domains = ();
597        for my $genomeData (@otherGenomes) {
598            my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
599            if (exists $gHash{$domain}) {
600                push @{$gHash{$domain}}, $genomeData;
601            } else {
602                $gHash{$domain} = [$genomeData];
603                push @domains, $domain;
604            }
605        }
606        # Add the domain groups at the end of the main group list. The main group list will now
607        # contain all the categories we need to display the genomes.
608        push @groups, sort @domains;
609        # Delete the supporting group.
610        delete $gHash{$FIG_Config::otherGroup};
611        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
612        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
613        # and use that to make the selections.
614        my $nmpdrCount = 0;
615        # Create the type counters.
616        my $groupCount = 1;
617        # Get the number of rows to display.
618        my $rows = $options{size} || 10;
619        # If we're multi-row, create an onChange event.
620        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
621        # Set up the multiple-select flag.
622        my $multipleTag = ($multiSelect ? " multiple" : "" );
623        # Set up the style class.
624        my $classTag = ($class ? " class=\"$class\"" : "" );
625        # Create the SELECT tag and stuff it into the output array.
626        my @lines = ("<SELECT name=\"$menuID\" id=\"$menuID\" $onChangeTag$multipleTag$classTag size=\"$rows\">");
627        # Loop through the groups.
628        for my $group (@groups) {
629            # Get the genomes in the group.
630            for my $genome (@{$gHash{$group}}) {
631                # If this is an NMPDR organism, we add an extra style and count it.
632                my $nmpdrStyle = "";
633                if ($nmpdrGroupCount > 0) {
634                    $nmpdrCount++;
635                    $nmpdrStyle = " Core";
636                }
637                # Get the organism ID, name, contig count, and domain.
638                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
639                # See if we're pre-selected.
640                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
641                # Compute the display name.
642                my $nameString = "$name ($genomeID$contigCount)";
643                # Generate the option tag.
644                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
645                push @lines, "    $optionTag";
646            }
647            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
648            # groups.
649            $nmpdrGroupCount--;
650        }
651        # Close the SELECT tag.
652        push @lines, "</SELECT>";
653        if ($rows > 1) {
654            # We're in a non-compact mode, so we need to add some selection helpers. First is
655            # the search box. This allows the user to type text and change which genomes are
656            # displayed. For multiple-select mode, we include a button that selects the displayed
657            # genes. For single-select mode, we use a plain label instead.
658            my $searchThingName = "${menuID}_SearchThing";
659            my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"
660                                                 : "Show genomes containing");
661            push @lines, "<br />$searchThingLabel&nbsp;" .
662                         "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />";
663            # For multi-select mode, we also have buttons to set and clear selections.
664            if ($multiSelect) {
665                push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll('$menuID'); $showSelect\" />";
666                push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll('$menuID'); $showSelect\" />";
667                push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome('$menuID', $nmpdrCount, true); $showSelect;\" />";
668            }
669            # Add a hidden field we can use to generate organism page hyperlinks.
670            push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/seedviewer.cgi?page=Organism;organism=\" />";
671            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
672            push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";
673        }
674        # Assemble all the lines into a string.
675        my $retVal = join("\n", @lines, "");
676        # Return the result.
677        return $retVal;
678    }
679    
680    
681  =head3 Build  =head3 Build
682    
683  C<< $sprout->Build(); >>      $sprout->Build();
684    
685  Build the database. The database will be cleared and the tables re-created from the metadata.  Build the database. The database will be cleared and the tables re-created from the metadata.
686  This method is useful when a database is brand new or when the database definition has  This method is useful when a database is brand new or when the database definition has
# Line 460  Line 692 
692      # Get the parameters.      # Get the parameters.
693      my ($self) = @_;      my ($self) = @_;
694      # Create the tables.      # Create the tables.
695      $self->{_erdb}->CreateTables;      $self->CreateTables();
696  }  }
697    
698  =head3 Genomes  =head3 Genomes
699    
700  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
701    
702  Return a list of all the genome IDs.  Return a list of all the genome IDs.
703    
# Line 482  Line 714 
714    
715  =head3 GenusSpecies  =head3 GenusSpecies
716    
717  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
718    
719  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
720    
# Line 514  Line 746 
746    
747  =head3 FeaturesOf  =head3 FeaturesOf
748    
749  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
750    
751  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
752    
# Line 559  Line 791 
791    
792  =head3 FeatureLocation  =head3 FeatureLocation
793    
794  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
795    
796  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
797  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 583  Line 815 
815  =item RETURN  =item RETURN
816    
817  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
818  context and as a comma-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context. An empty list means the feature
819    wasn't found.
820    
821  =back  =back
822    
823  =cut  =cut
824  #: Return Type @;  
 #: Return Type $;  
825  sub FeatureLocation {  sub FeatureLocation {
826      # Get the parameters.      # Get the parameters.
827      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
828      # 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.  
829      my @retVal = ();      my @retVal = ();
830      # Set up the variables used to determine if we have adjacent segments. This initial setup will      # Get the feature record.
831      # not match anything.      my $object = $self->GetEntity('Feature', $featureID);
832      my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);      # Only proceed if we found it.
833      # Loop through the query results, creating location specifiers.      if (defined $object) {
834      while (my $location = $query->Fetch()) {          # Get the location string.
835          # Get the location parameters.          my $locString = $object->PrimaryValue('Feature(location-string)');
836          my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',          # Create the return list.
837              '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);  
         # Compute the initial base pair.  
         my $start = ($dir eq "+" ? $beg : $beg + $len - 1);  
         # Add the specifier to the list.  
         push @retVal, "${contigID}_$start$dir$len";  
838      }      }
839      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
840      return (wantarray ? @retVal : join(',', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
# Line 633  Line 842 
842    
843  =head3 ParseLocation  =head3 ParseLocation
844    
845  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
846    
847  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
848  length.  length.
# Line 652  Line 861 
861  =back  =back
862    
863  =cut  =cut
864  #: Return Type @;  
865  sub ParseLocation {  sub ParseLocation {
866      # 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
867      # the first parameter.      # the first parameter.
868      shift if UNIVERSAL::isa($_[0],__PACKAGE__);      shift if UNIVERSAL::isa($_[0],__PACKAGE__);
869      my ($location) = @_;      my ($location) = @_;
870      # Parse it into segments.      # Parse it into segments.
871      $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
872      my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);      my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
873      # If the direction is an underscore, convert it to a + or -.      # If the direction is an underscore, convert it to a + or -.
874      if ($dir eq "_") {      if ($dir eq "_") {
# Line 675  Line 884 
884      return ($contigID, $start, $dir, $len);      return ($contigID, $start, $dir, $len);
885  }  }
886    
887    
888    
889  =head3 PointLocation  =head3 PointLocation
890    
891  C<< my $found = Sprout::PointLocation($location, $point); >>      my $found = Sprout::PointLocation($location, $point);
892    
893  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
894  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 706  Line 917 
917  =back  =back
918    
919  =cut  =cut
920  #: Return Type $;  
921  sub PointLocation {  sub PointLocation {
922      # 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
923      # the first parameter.      # the first parameter.
# Line 729  Line 940 
940    
941  =head3 DNASeq  =head3 DNASeq
942    
943  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
944    
945  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
946  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,
947  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>.
948    
949    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
950    between positions 1401 and 1532, inclusive.
951    
952        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
953    
954  =over 4  =over 4
955    
956  =item locationList  =item locationList
957    
958  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
959  L</FeatureLocation> for more about this format).  I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
960    
961  =item RETURN  =item RETURN
962    
# Line 767  Line 983 
983          # the start point is the ending. Note that in the latter case we must reverse the DNA string          # the start point is the ending. Note that in the latter case we must reverse the DNA string
984          # before putting it in the return value.          # before putting it in the return value.
985          my ($start, $stop);          my ($start, $stop);
986          Trace("Parsed location is $beg$dir$len.") if T(SDNA => 4);          Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
987          if ($dir eq "+") {          if ($dir eq "+") {
988              $start = $beg;              $start = $beg;
989              $stop = $beg + $len - 1;              $stop = $beg + $len - 1;
# Line 790  Line 1006 
1006              Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);              Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
1007              # Figure out the start point and length of the relevant section.              # Figure out the start point and length of the relevant section.
1008              my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);              my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
1009              my $len1 = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
1010              Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);              Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
1011              # Add the relevant data to the location data.              # Add the relevant data to the location data.
1012              $locationDNA .= substr($sequenceData, $pos1, $len1);              $locationDNA .= substr($sequenceData, $pos1, $len1);
# Line 808  Line 1024 
1024    
1025  =head3 AllContigs  =head3 AllContigs
1026    
1027  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1028    
1029  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1030    
# Line 836  Line 1052 
1052      return @retVal;      return @retVal;
1053  }  }
1054    
1055  =head3 ContigLength  =head3 GenomeLength
1056    
1057  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->GenomeLength($genomeID);
1058    
1059  Compute the length of a contig.  Return the length of the specified genome in base pairs.
1060    
1061  =over 4  =over 4
1062    
1063  =item contigID  =item genomeID
1064    
1065  ID of the contig whose length is desired.  ID of the genome whose base pair count is desired.
1066    
1067  =item RETURN  =item RETURN
1068    
1069  Returns the number of positions in the contig.  Returns the number of base pairs in all the contigs of the specified
1070    genome.
1071    
1072  =back  =back
1073    
1074  =cut  =cut
1075  #: Return Type $;  
1076  sub ContigLength {  sub GenomeLength {
1077      # Get the parameters.      # Get the parameters.
1078      my ($self, $contigID) = @_;      my ($self, $genomeID) = @_;
1079      # 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.  
1080      my $retVal = 0;      my $retVal = 0;
1081      # Set it from the sequence data, if any.      # Get the genome's contig sequence lengths.
1082      if ($sequence) {      my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',
1083          my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                         [$genomeID], 'IsMadeUpOf(len)');
1084          $retVal = $start + $len;      # Sum the lengths.
1085      }      map { $retVal += $_ } @lens;
1086      # Return the result.      # Return the result.
1087      return $retVal;      return $retVal;
1088  }  }
1089    
1090  =head3 GenesInRegion  =head3 FeatureCount
1091    
1092  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my $count = $sprout->FeatureCount($genomeID, $type);
1093    
1094  List the features which overlap a specified region in a contig.  Return the number of features of the specified type in the specified genome.
1095    
1096  =over 4  =over 4
1097    
1098  =item contigID  =item genomeID
   
 ID of the contig containing the region of interest.  
   
 =item start  
1099    
1100  Offset of the first residue in the region of interest.  ID of the genome whose feature count is desired.
1101    
1102  =item stop  =item type
1103    
1104  Offset of the last residue in the region of interest.  Type of feature to count (eg. C<peg>, C<rna>, etc.).
1105    
1106  =item RETURN  =item RETURN
1107    
1108  Returns a three-element list. The first element is a list of feature IDs for the features that  Returns the number of features of the specified type for the specified genome.
 overlap the region of interest. The second and third elements are the minimum and maximum  
 locations of the features provided on the specified contig. These may extend outside  
 the start and stop values. The first element (that is, the list of features) is sorted  
 roughly by location.  
1109    
1110  =back  =back
1111    
1112  =cut  =cut
1113  #: Return Type @@;  
1114    sub FeatureCount {
1115        # Get the parameters.
1116        my ($self, $genomeID, $type) = @_;
1117        # Compute the count.
1118        my $retVal = $self->GetCount(['HasFeature', 'Feature'],
1119                                    "HasFeature(from-link) = ? AND Feature(feature-type) = ?",
1120                                    [$genomeID, $type]);
1121        # Return the result.
1122        return $retVal;
1123    }
1124    
1125    =head3 GenomeAssignments
1126    
1127        my $fidHash = $sprout->GenomeAssignments($genomeID);
1128    
1129    Return a list of a genome's assigned features. The return hash will contain each
1130    assigned feature of the genome mapped to the text of its most recent functional
1131    assignment.
1132    
1133    =over 4
1134    
1135    =item genomeID
1136    
1137    ID of the genome whose functional assignments are desired.
1138    
1139    =item RETURN
1140    
1141    Returns a reference to a hash which maps each feature to its most recent
1142    functional assignment.
1143    
1144    =back
1145    
1146    =cut
1147    
1148    sub GenomeAssignments {
1149        # Get the parameters.
1150        my ($self, $genomeID) = @_;
1151        # Declare the return variable.
1152        my $retVal = {};
1153        # Query the genome's features.
1154        my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?",
1155                               [$genomeID]);
1156        # Loop through the features.
1157        while (my $data = $query->Fetch) {
1158            # Get the feature ID and assignment.
1159            my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
1160            if ($assignment) {
1161                $retVal->{$fid} = $assignment;
1162            }
1163        }
1164        # Return the result.
1165        return $retVal;
1166    }
1167    
1168    =head3 ContigLength
1169    
1170        my $length = $sprout->ContigLength($contigID);
1171    
1172    Compute the length of a contig.
1173    
1174    =over 4
1175    
1176    =item contigID
1177    
1178    ID of the contig whose length is desired.
1179    
1180    =item RETURN
1181    
1182    Returns the number of positions in the contig.
1183    
1184    =back
1185    
1186    =cut
1187    #: Return Type $;
1188    sub ContigLength {
1189        # Get the parameters.
1190        my ($self, $contigID) = @_;
1191        # Get the contig's last sequence.
1192        my $query = $self->Get(['IsMadeUpOf'],
1193            "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
1194            [$contigID]);
1195        my $sequence = $query->Fetch();
1196        # Declare the return value.
1197        my $retVal = 0;
1198        # Set it from the sequence data, if any.
1199        if ($sequence) {
1200            my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
1201            $retVal = $start + $len - 1;
1202        }
1203        # Return the result.
1204        return $retVal;
1205    }
1206    
1207    =head3 ClusterPEGs
1208    
1209        my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1210    
1211    Cluster the PEGs in a list according to the cluster coding scheme of the specified
1212    subsystem. In order for this to work properly, the subsystem object must have
1213    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> or
1214    B<get_row> methods. This causes the cluster numbers to be pulled into the
1215    subsystem's color hash. If a PEG is not found in the color hash, it will not
1216    appear in the output sequence.
1217    
1218    =over 4
1219    
1220    =item sub
1221    
1222    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
1223    method.
1224    
1225    =item pegs
1226    
1227    Reference to the list of PEGs to be clustered.
1228    
1229    =item RETURN
1230    
1231    Returns a list of the PEGs, grouped into smaller lists by cluster number.
1232    
1233    =back
1234    
1235    =cut
1236    #: Return Type $@@;
1237    sub ClusterPEGs {
1238        # Get the parameters.
1239        my ($self, $sub, $pegs) = @_;
1240        # Declare the return variable.
1241        my $retVal = [];
1242        # Loop through the PEGs, creating arrays for each cluster.
1243        for my $pegID (@{$pegs}) {
1244            my $clusterNumber = $sub->get_cluster_number($pegID);
1245            # Only proceed if the PEG is in a cluster.
1246            if ($clusterNumber >= 0) {
1247                # Push this PEG onto the sub-list for the specified cluster number.
1248                push @{$retVal->[$clusterNumber]}, $pegID;
1249            }
1250        }
1251        # Return the result.
1252        return $retVal;
1253    }
1254    
1255    =head3 GenesInRegion
1256    
1257        my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1258    
1259    List the features which overlap a specified region in a contig.
1260    
1261    =over 4
1262    
1263    =item contigID
1264    
1265    ID of the contig containing the region of interest.
1266    
1267    =item start
1268    
1269    Offset of the first residue in the region of interest.
1270    
1271    =item stop
1272    
1273    Offset of the last residue in the region of interest.
1274    
1275    =item RETURN
1276    
1277    Returns a three-element list. The first element is a list of feature IDs for the features that
1278    overlap the region of interest. The second and third elements are the minimum and maximum
1279    locations of the features provided on the specified contig. These may extend outside
1280    the start and stop values. The first element (that is, the list of features) is sorted
1281    roughly by location.
1282    
1283    =back
1284    
1285    =cut
1286    
1287  sub GenesInRegion {  sub GenesInRegion {
1288      # Get the parameters.      # Get the parameters.
1289      my ($self, $contigID, $start, $stop) = @_;      my ($self, $contigID, $start, $stop) = @_;
1290      # Get the maximum segment length.      # Get the maximum segment length.
1291      my $maximumSegmentLength = $self->MaxSegment;      my $maximumSegmentLength = $self->MaxSegment;
     # Create a hash to receive the feature list. We use a hash so that we can eliminate  
     # duplicates easily. The hash key will be the feature ID. The value will be a two-element  
     # containing the minimum and maximum offsets. We will use the offsets to sort the results  
     # when we're building the result set.  
     my %featuresFound = ();  
1292      # Prime the values we'll use for the returned beginning and end.      # Prime the values we'll use for the returned beginning and end.
1293      my @initialMinMax = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
1294      my ($min, $max) = @initialMinMax;      my ($min, $max) = @initialMinMax;
1295      # Create a table of parameters for each query. Each query looks for features travelling in      # Get the overlapping features.
1296        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1297        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1298        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1299        # of the feature's locations.
1300        my %featureMap = ();
1301        # Loop through them to do the begin/end analysis.
1302        for my $featureObject (@featureObjects) {
1303            # Get the feature's location string. This may contain multiple actual locations.
1304            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1305            my @locationSegments = split /\s*,\s*/, $locations;
1306            # Loop through the locations.
1307            for my $locationSegment (@locationSegments) {
1308                # Construct an object for the location.
1309                my $locationObject = BasicLocation->new($locationSegment);
1310                # Merge the current segment's begin and end into the min and max.
1311                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1312                my ($beg, $end);
1313                if (exists $featureMap{$fid}) {
1314                    ($beg, $end) = @{$featureMap{$fid}};
1315                    $beg = $left if $left < $beg;
1316                    $end = $right if $right > $end;
1317                } else {
1318                    ($beg, $end) = ($left, $right);
1319                }
1320                $min = $beg if $beg < $min;
1321                $max = $end if $end > $max;
1322                # Store the feature's new extent back into the hash table.
1323                $featureMap{$fid} = [$beg, $end];
1324            }
1325        }
1326        # Now we must compute the list of the IDs for the features found. We start with a list
1327        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1328        # but the result of the sort will be the same.)
1329        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1330        # Now we sort by midpoint and yank out the feature IDs.
1331        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1332        # Return it along with the min and max.
1333        return (\@retVal, $min, $max);
1334    }
1335    
1336    =head3 GeneDataInRegion
1337    
1338        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1339    
1340    List the features which overlap a specified region in a contig.
1341    
1342    =over 4
1343    
1344    =item contigID
1345    
1346    ID of the contig containing the region of interest.
1347    
1348    =item start
1349    
1350    Offset of the first residue in the region of interest.
1351    
1352    =item stop
1353    
1354    Offset of the last residue in the region of interest.
1355    
1356    =item RETURN
1357    
1358    Returns a list of B<ERDBObjects> for the desired features. Each object will
1359    contain a B<Feature> record.
1360    
1361    =back
1362    
1363    =cut
1364    
1365    sub GeneDataInRegion {
1366        # Get the parameters.
1367        my ($self, $contigID, $start, $stop) = @_;
1368        # Get the maximum segment length.
1369        my $maximumSegmentLength = $self->MaxSegment;
1370        # Create a hash to receive the feature list. We use a hash so that we can eliminate
1371        # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1372        # ERDBObject from the query.
1373        my %featuresFound = ();
1374        # Create a table of parameters for the queries. Each query looks for features travelling in
1375      # 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,
1376      # 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
1377      # 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 929  Line 1380 
1380      # Loop through the query parameters.      # Loop through the query parameters.
1381      for my $parms (values %queryParms) {      for my $parms (values %queryParms) {
1382          # Create the query.          # Create the query.
1383          my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1384              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1385              $parms);              $parms);
1386          # Loop through the feature segments found.          # Loop through the feature segments found.
1387          while (my $segment = $query->Fetch) {          while (my $segment = $query->Fetch) {
1388              # Get the data about this segment.              # Get the data about this segment.
1389              my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1390                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1391              # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1392              # this will be the case if the segment is the maximum length, so to fine-tune              # this will be the case if the segment is the maximum length, so to fine-tune
1393              # the results we insure that the inequality from the query holds using the actual              # the results we insure that the inequality from the query holds using the actual
1394              # length.              # length.
1395              my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1396              if ($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.  
                     $found = 1;  
                 }  
             }  
1397              if ($found) {              if ($found) {
1398                  # Here we need to record the feature and update the minima and maxima. First,                  # Save this feature in the result list.
1399                  # 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 < $min;  
1400                  }                  }
                 if ($end > $loc2) {  
                     $loc2 = $end;  
                     $max = $end if $end > $max;  
                 }  
                 # Store the entry back into the hash table.  
                 $featuresFound{$featureID} = [$loc1, $loc2];  
1401              }              }
1402          }          }
1403      }      # Return the ERDB objects for the features found.
1404      # Now we must compute the list of the IDs for the features found. We start with a list      return values %featuresFound;
     # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,  
     # but the result of the sort will be the same.)  
     my @list = map { [$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);  
1405  }  }
1406    
1407  =head3 FType  =head3 FType
1408    
1409  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1410    
1411  Return the type of a feature.  Return the type of a feature.
1412    
# Line 1019  Line 1436 
1436    
1437  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1438    
1439  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1440    
1441  Return the annotations of a feature.  Return the annotations of a feature.
1442    
# Line 1029  Line 1446 
1446    
1447  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1448    
1449    =item rawFlag
1450    
1451    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1452    will be returned in human-readable form.
1453    
1454  =item RETURN  =item RETURN
1455    
1456  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1457    
1458  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1459    
1460  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1461    
1462  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1463    
# Line 1047  Line 1469 
1469  #: Return Type @%;  #: Return Type @%;
1470  sub FeatureAnnotations {  sub FeatureAnnotations {
1471      # Get the parameters.      # Get the parameters.
1472      my ($self, $featureID) = @_;      my ($self, $featureID, $rawFlag) = @_;
1473      # 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.
1474      my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],      my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1475                             "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                             "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1060  Line 1482 
1482              $annotation->Values(['IsTargetOfAnnotation(from-link)',              $annotation->Values(['IsTargetOfAnnotation(from-link)',
1483                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1484                                   'Annotation(annotation)']);                                   'Annotation(annotation)']);
1485            # Convert the time, if necessary.
1486            if (! $rawFlag) {
1487                $timeStamp = FriendlyTimestamp($timeStamp);
1488            }
1489          # Assemble them into a hash.          # Assemble them into a hash.
1490          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1491                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1492                                 user => $user, text => $text };                                 user => $user, text => $text };
1493          # Add it to the return list.          # Add it to the return list.
1494          push @retVal, $annotationHash;          push @retVal, $annotationHash;
# Line 1073  Line 1499 
1499    
1500  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1501    
1502  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1503    
1504  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
1505  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 1091  Line 1517 
1517    
1518  =item RETURN  =item RETURN
1519    
1520  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1521    
1522  =back  =back
1523    
# Line 1101  Line 1527 
1527      # Get the parameters.      # Get the parameters.
1528      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1529      # Get all of the feature's annotations.      # Get all of the feature's annotations.
1530      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1531                              "IsTargetOfAnnotation(from-link) = ?",                              "IsTargetOfAnnotation(from-link) = ?",
1532                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1533                                               'MadeAnnotation(from-link)']);
1534      # Declare the return hash.      # Declare the return hash.
1535      my %retVal;      my %retVal;
     # Declare a hash for insuring we only make one assignment per user.  
     my %timeHash = ();  
1536      # Now we sort the assignments by timestamp in reverse.      # Now we sort the assignments by timestamp in reverse.
1537      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1538      # Loop until we run out of annotations.      # Loop until we run out of annotations.
1539      for my $annotation (@sortedQuery) {      for my $annotation (@sortedQuery) {
1540          # Get the annotation fields.          # Get the annotation fields.
1541          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text, $user) = @{$annotation};
1542          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
1543          my ($user, $function) = _ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1544          if ($user && ! exists $timeHash{$user}) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1545              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1546              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
1547              # return hash.              # return hash.
1548              $retVal{$function} = $user;              $retVal{$actualUser} = $function;
             # Insure we don't assign to this user again.  
             $timeHash{$user} = 1;  
1549          }          }
1550      }      }
1551      # Return the hash of assignments found.      # Return the hash of assignments found.
# Line 1131  Line 1554 
1554    
1555  =head3 FunctionOf  =head3 FunctionOf
1556    
1557  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1558    
1559  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1560    
1561  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
1562  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
1563  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.  
1564    
1565  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
1566  recent one by at least one of the trusted users. If no trusted user list is available, then  recent one by at least one of the trusted users. If no trusted user list is available, then
# Line 1159  Line 1579 
1579    
1580  =item userID (optional)  =item userID (optional)
1581    
1582  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
1583  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1584    
1585  =item RETURN  =item RETURN
1586    
# Line 1177  Line 1597 
1597      my $retVal;      my $retVal;
1598      # Determine the ID type.      # Determine the ID type.
1599      if ($featureID =~ m/^fig\|/) {      if ($featureID =~ m/^fig\|/) {
1600          # Here we have a FIG feature ID. We must build the list of trusted          # Here we have a FIG feature ID.
1601          # users.          if (!$userID) {
1602                # Use the primary assignment.
1603                ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);
1604            } else {
1605                # We must build the list of trusted users.
1606          my %trusteeTable = ();          my %trusteeTable = ();
1607          # Check the user ID.          # Check the user ID.
1608          if (!$userID) {          if (!$userID) {
# Line 1200  Line 1624 
1624              }              }
1625          }          }
1626          # 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.
1627          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1628                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1629                                 [$featureID]);                                 [$featureID]);
1630          my $timeSelected = 0;          my $timeSelected = 0;
1631          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1632          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1633              # Get the annotation text.              # Get the annotation text.
1634              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);                  my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1635                                                             'Annotation(time)', 'MadeAnnotation(from-link)']);
1636              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1637              my ($user, $function) = _ParseAssignment($text);                  my ($actualUser, $function) = _ParseAssignment($user, $text);
1638              if ($user) {                  Trace("Assignment user is $actualUser, text is $function.") if T(4);
1639                    if ($actualUser) {
1640                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1641                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1642                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                      if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1643                      $retVal = $function;                      $retVal = $function;
1644                      $timeSelected = $time;                      $timeSelected = $time;
1645                  }                  }
1646              }              }
1647          }          }
1648            }
1649      } else {      } else {
1650          # Here we have a non-FIG feature ID. In this case the user ID does not          # Here we have a non-FIG feature ID. In this case the user ID does not
1651          # matter. We simply get the information from the External Alias Function          # matter. We simply get the information from the External Alias Function
# Line 1229  Line 1656 
1656      return $retVal;      return $retVal;
1657  }  }
1658    
1659    =head3 FunctionsOf
1660    
1661        my @functionList = $sprout->FunctionOf($featureID, $userID);
1662    
1663    Return the functional assignments of a particular feature.
1664    
1665    The functional assignment is handled differently depending on the type of feature. If
1666    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1667    assignment is a type of annotation. The format of an assignment is described in
1668    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1669    annotation itself because it's a text field; however, this is not a big problem because
1670    most features only have a small number of annotations.
1671    
1672    If the feature is B<not> identified by a FIG ID, then the functional assignment
1673    information is taken from the B<ExternalAliasFunc> table. If the table does
1674    not contain an entry for the feature, an empty list is returned.
1675    
1676    =over 4
1677    
1678    =item featureID
1679    
1680    ID of the feature whose functional assignments are desired.
1681    
1682    =item RETURN
1683    
1684    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1685    that user.
1686    
1687    =back
1688    
1689    =cut
1690    #: Return Type @@;
1691    sub FunctionsOf {
1692        # Get the parameters.
1693        my ($self, $featureID) = @_;
1694        # Declare the return value.
1695        my @retVal = ();
1696        # Determine the ID type.
1697        if ($featureID =~ m/^fig\|/) {
1698            # Here we have a FIG feature ID. We must build the list of trusted
1699            # users.
1700            my %trusteeTable = ();
1701            # Build a query for all of the feature's annotations, sorted by date.
1702            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1703                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1704                                   [$featureID]);
1705            my $timeSelected = 0;
1706            # Loop until we run out of annotations.
1707            while (my $annotation = $query->Fetch()) {
1708                # Get the annotation text.
1709                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1710                                                                'Annotation(time)',
1711                                                                'MadeAnnotation(user)']);
1712                # Check to see if this is a functional assignment for a trusted user.
1713                my ($actualUser, $function) = _ParseAssignment($user, $text);
1714                if ($actualUser) {
1715                    # Here it is a functional assignment.
1716                    push @retVal, [$actualUser, $function];
1717                }
1718            }
1719        } else {
1720            # Here we have a non-FIG feature ID. In this case the user ID does not
1721            # matter. We simply get the information from the External Alias Function
1722            # table.
1723            my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1724                                                     ['ExternalAliasFunc(func)']);
1725            push @retVal, map { ['master', $_] } @assignments;
1726        }
1727        # Return the assignments found.
1728        return @retVal;
1729    }
1730    
1731  =head3 BBHList  =head3 BBHList
1732    
1733  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1734    
1735  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
1736  on a specified target genome.  on a specified target genome.
# Line 1262  Line 1761 
1761      my %retVal = ();      my %retVal = ();
1762      # Loop through the incoming features.      # Loop through the incoming features.
1763      for my $featureID (@{$featureList}) {      for my $featureID (@{$featureList}) {
1764          # Create a query to get the feature's best hit.          # Ask the server for the feature's best hit.
1765          my $query = $self->Get(['IsBidirectionalBestHitOf'],          my @bbhData = FIGRules::BBHData($featureID);
1766                                 "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",          # Peel off the BBHs found.
1767                                 [$featureID, $genomeID]);          my @found = ();
1768          # Look for the best hit.          for my $bbh (@bbhData) {
1769          my $bbh = $query->Fetch;              my $fid = $bbh->[0];
1770          if ($bbh) {              my $bbGenome = $self->GenomeOf($fid);
1771              my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              if ($bbGenome eq $genomeID) {
1772              $retVal{$featureID} = $targetFeature;                  push @found, $fid;
1773                }
1774          }          }
1775            $retVal{$featureID} = \@found;
1776      }      }
1777      # Return the mapping.      # Return the mapping.
1778      return \%retVal;      return \%retVal;
# Line 1279  Line 1780 
1780    
1781  =head3 SimList  =head3 SimList
1782    
1783  C<< my %similarities = $sprout->SimList($featureID, $count); >>      my %similarities = $sprout->SimList($featureID, $count);
1784    
1785  Return a list of the similarities to the specified feature.  Return a list of the similarities to the specified feature.
1786    
1787  Sprout does not support real similarities, so this method just returns the bidirectional  This method just returns the bidirectional best hits for performance reasons.
 best hits.  
1788    
1789  =over 4  =over 4
1790    
# Line 1304  Line 1804 
1804      # Get the parameters.      # Get the parameters.
1805      my ($self, $featureID, $count) = @_;      my ($self, $featureID, $count) = @_;
1806      # Ask for the best hits.      # Ask for the best hits.
1807      my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],      my @lists = FIGRules::BBHData($featureID);
                               "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",  
                               [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],  
                               $count);  
1808      # Create the return value.      # Create the return value.
1809      my %retVal = ();      my %retVal = ();
1810      for my $tuple (@lists) {      for my $tuple (@lists) {
# Line 1317  Line 1814 
1814      return %retVal;      return %retVal;
1815  }  }
1816    
   
   
1817  =head3 IsComplete  =head3 IsComplete
1818    
1819  C<< my $flag = $sprout->IsComplete($genomeID); >>      my $flag = $sprout->IsComplete($genomeID);
1820    
1821  Return TRUE if the specified genome is complete, else FALSE.  Return TRUE if the specified genome is complete, else FALSE.
1822    
# Line 1349  Line 1844 
1844      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->GetEntity('Genome', $genomeID);
1845      if ($genomeData) {      if ($genomeData) {
1846          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1847          ($retVal) = $genomeData->Value('complete');          $retVal = $genomeData->PrimaryValue('Genome(complete)');
1848      }      }
1849      # Return the result.      # Return the result.
1850      return $retVal;      return $retVal;
# Line 1357  Line 1852 
1852    
1853  =head3 FeatureAliases  =head3 FeatureAliases
1854    
1855  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1856    
1857  Return a list of the aliases for a specified feature.  Return a list of the aliases for a specified feature.
1858    
# Line 1380  Line 1875 
1875      # Get the parameters.      # Get the parameters.
1876      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1877      # Get the desired feature's aliases      # Get the desired feature's aliases
1878      my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
1879      # Return the result.      # Return the result.
1880      return @retVal;      return @retVal;
1881  }  }
1882    
1883  =head3 GenomeOf  =head3 GenomeOf
1884    
1885  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $genomeID = $sprout->GenomeOf($featureID);
1886    
1887  Return the genome that contains a specified feature.  Return the genome that contains a specified feature or contig.
1888    
1889  =over 4  =over 4
1890    
1891  =item featureID  =item featureID
1892    
1893  ID of the feature whose genome is desired.  ID of the feature or contig whose genome is desired.
1894    
1895  =item RETURN  =item RETURN
1896    
1897  Returns the ID of the genome for the specified feature. If the feature is not found, returns  Returns the ID of the genome for the specified feature or contig. If the feature or contig is not
1898  an undefined value.  found, returns an undefined value.
1899    
1900  =back  =back
1901    
# Line 1409  Line 1904 
1904  sub GenomeOf {  sub GenomeOf {
1905      # Get the parameters.      # Get the parameters.
1906      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
     # Create a query to find the genome associated with the feature.  
     my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);  
1907      # Declare the return value.      # Declare the return value.
1908      my $retVal;      my $retVal;
1909      # Get the genome ID.      # Parse the genome ID from the feature ID.
1910      if (my $relationship = $query->Fetch()) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
1911          ($retVal) = $relationship->Value('HasContig(from-link)');          $retVal = $1;
1912        } else {
1913            Confess("Invalid feature ID $featureID.");
1914      }      }
1915      # Return the value found.      # Return the value found.
1916      return $retVal;      return $retVal;
# Line 1423  Line 1918 
1918    
1919  =head3 CoupledFeatures  =head3 CoupledFeatures
1920    
1921  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
1922    
1923  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
1924  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 1445  Line 1940 
1940  sub CoupledFeatures {  sub CoupledFeatures {
1941      # Get the parameters.      # Get the parameters.
1942      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1943      # Create a query to retrieve the functionally-coupled features.      # Ask the coupling server for the data.
1944      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
1945                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
1946      # This value will be set to TRUE if we find at least one coupled feature.      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
1947      my $found = 0;      # Form them into a hash.
     # Create the return hash.  
1948      my %retVal = ();      my %retVal = ();
1949      # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
1950      while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
1951          # Get the ID and score of the coupling.          my ($featureID2, $score) = @{$pair};
1952          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',          # Only proceed if the feature is in NMPDR.
1953                                                          'Coupling(score)']);          if ($self->_CheckFeature($featureID2)) {
1954          # The coupling ID contains the two feature IDs separated by a space. We use              $retVal{$featureID2} = $score;
1955          # this information to find the ID of the other feature.          }
         my ($fid1, $fid2) = split / /, $couplingID;  
         my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);  
         # Attach the other feature's score to its ID.  
         $retVal{$otherFeatureID} = $score;  
         $found = 1;  
1956      }      }
1957      # Functional coupling is reflexive. If we found at least one coupled feature, we must add      # Functional coupling is reflexive. If we found at least one coupled feature, we must add
1958      # the incoming feature as well.      # the incoming feature as well.
1959      if ($found) {      if (keys %retVal) {
1960          $retVal{$featureID} = 9999;          $retVal{$featureID} = 9999;
1961      }      }
1962      # Return the hash.      # Return the hash.
# Line 1476  Line 1965 
1965    
1966  =head3 CouplingEvidence  =head3 CouplingEvidence
1967    
1968  C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>      my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
1969    
1970  Return the evidence for a functional coupling.  Return the evidence for a functional coupling.
1971    
# Line 1524  Line 2013 
2013      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
2014      # Declare the return variable.      # Declare the return variable.
2015      my @retVal = ();      my @retVal = ();
2016      # Our first task is to find out the nature of the coupling: whether or not      # Get the coupling and evidence data.
2017      # it exists, its score, and whether the features are stored in the same      my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
2018      # order as the ones coming in.      # Loop through the raw data, saving the ones that are in NMPDR genomes.
2019      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);      for my $rawTuple (@rawData) {
2020      # Only proceed if a coupling exists.          if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
2021      if ($couplingID) {              push @retVal, $rawTuple;
2022          # Determine the ordering to place on the evidence items. If we're          }
         # inverted, we want to see feature 2 before feature 1 (descending); otherwise,  
         # we want feature 1 before feature 2 (normal).  
         Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);  
         my $ordering = ($inverted ? "DESC" : "");  
         # Get the coupling evidence.  
         my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],  
                                           "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",  
                                           [$couplingID],  
                                           ['PCH(used)', 'UsesAsEvidence(to-link)']);  
         # Loop through the evidence items. Each piece of evidence is represented by two  
         # positions in the evidence list, one for each feature on the other side of the  
         # evidence link. If at some point we want to generalize to couplings with  
         # more than two positions, this section of code will need to be re-done.  
         while (@evidenceList > 0) {  
             my $peg1Data = shift @evidenceList;  
             my $peg2Data = shift @evidenceList;  
             Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);  
             push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];  
         }  
         Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);  
2023      }      }
2024      # Return the result.      # Return the result.
2025      return @retVal;      return @retVal;
2026  }  }
2027    
2028  =head3 GetCoupling  =head3 GetSynonymGroup
   
 C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>  
   
 Return the coupling (if any) for the specified pair of PEGs. If a coupling  
 exists, we return the coupling ID along with an indicator of whether the  
 coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.  
 In the second case, we say the coupling is I<inverted>. The importance of an  
 inverted coupling is that the PEGs in the evidence will appear in reverse order.  
2029    
2030  =over 4      my $id = $sprout->GetSynonymGroup($fid);
2031    
2032  =item peg1  Return the synonym group name for the specified feature.
2033    
2034  ID of the feature of interest.  =over 4
2035    
2036  =item peg2  =item fid
2037    
2038  ID of the potentially coupled feature.  ID of the feature whose synonym group is desired.
2039    
2040  =item RETURN  =item RETURN
2041    
2042  Returns a three-element list. The first element contains the database ID of  The name of the synonym group to which the feature belongs. If the feature does
2043  the coupling. The second element is FALSE if the coupling is stored in the  not belong to a synonym group, the feature ID itself is returned.
 database in the caller specified order and TRUE if it is stored in the  
 inverted order. The third element is the coupling's score. If the coupling  
 does not exist, all three list elements will be C<undef>.  
2044    
2045  =back  =back
2046    
2047  =cut  =cut
2048  #: Return Type $%@;  
2049  sub GetCoupling {  sub GetSynonymGroup {
2050      # Get the parameters.      # Get the parameters.
2051      my ($self, $peg1, $peg2) = @_;      my ($self, $fid) = @_;
2052      # Declare the return values. We'll start with the coupling ID and undefine the      # Declare the return variable.
2053      # flag and score until we have more information.      my $retVal;
2054      my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);      # Find the synonym group.
2055      # Find the coupling data.      my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?",
2056      my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],                                     [$fid], 'IsSynonymGroupFor(from-link)');
                                  "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",  
                                  [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);  
2057      # Check to see if we found anything.      # Check to see if we found anything.
2058      if (!@pegs) {      if (@groups) {
2059          Trace("No coupling found.") if T(Coupling => 4);          $retVal = $groups[0];
         # No coupling, so undefine the return value.  
         $retVal = undef;  
2060      } else {      } else {
2061          # We have a coupling! Get the score and check for inversion.          $retVal = $fid;
         $score = $pegs[0]->[1];  
         my $firstFound = $pegs[0]->[0];  
         $inverted = ($firstFound ne $peg1);  
         Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);  
2062      }      }
2063      # Return the result.      # Return the result.
2064      return ($retVal, $inverted, $score);      return $retVal;
2065  }  }
2066    
2067  =head3 CouplingID  =head3 GetBoundaries
2068    
2069  C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>      my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2070    
2071  Return the coupling ID for a pair of feature IDs.  Determine the begin and end boundaries for the locations in a list. All of the
2072    locations must belong to the same contig and have mostly the same direction in
2073  The coupling ID is currently computed by joining the feature IDs in  order for this method to produce a meaningful result. The resulting
2074  sorted order with a space. Client modules (that is, modules which  begin/end pair will contain all of the bases in any of the locations.
 use Sprout) should not, however, count on this always being the  
 case. This method provides a way for abstracting the concept of a  
 coupling ID. All that we know for sure about it is that it can be  
 generated easily from the feature IDs and the order of the IDs  
 in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>  
 will have the same value as C<CouplingID("b1", "a1")>.  
2075    
2076  =over 4  =over 4
2077    
2078  =item peg1  =item locList
   
 First feature of interest.  
   
 =item peg2  
2079    
2080  Second feature of interest.  List of locations to process.
2081    
2082  =item RETURN  =item RETURN
2083    
2084  Returns the ID that would be used to represent a functional coupling of  Returns a 3-tuple consisting of the contig ID, the beginning boundary,
2085  the two specified PEGs.  and the ending boundary. The beginning boundary will be left of the
2086    end for mostly-forward locations and right of the end for mostly-backward
2087    locations.
2088    
2089  =back  =back
2090    
2091  =cut  =cut
 #: Return Type $;  
 sub CouplingID {  
     return join " ", sort @_;  
 }  
   
 =head3 GetEntityTypes  
2092    
2093  C<< my @entityList = $sprout->GetEntityTypes(); >>  sub GetBoundaries {
   
 Return the list of supported entity types.  
   
 =cut  
 #: Return Type @;  
 sub GetEntityTypes {  
2094      # Get the parameters.      # Get the parameters.
2095      my ($self) = @_;      my ($self, @locList) = @_;
2096      # Get the underlying database object.      # Set up the counters used to determine the most popular direction.
2097      my $erdb = $self->{_erdb};      my %counts = ( '+' => 0, '-' => 0 );
2098      # Get its entity type list.      # Get the last location and parse it.
2099      my @retVal = $erdb->GetEntityTypes();      my $locObject = BasicLocation->new(pop @locList);
2100        # Prime the loop with its data.
2101        my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right);
2102        # Count its direction.
2103        $counts{$locObject->Dir}++;
2104        # Loop through the remaining locations. Note that in most situations, this loop
2105        # will not iterate at all, because most of the time we will be dealing with a
2106        # singleton list.
2107        for my $loc (@locList) {
2108            # Create a location object.
2109            my $locObject = BasicLocation->new($loc);
2110            # Count the direction.
2111            $counts{$locObject->Dir}++;
2112            # Get the left end and the right end.
2113            my $left = $locObject->Left;
2114            my $right = $locObject->Right;
2115            # Merge them into the return variables.
2116            if ($left < $beg) {
2117                $beg = $left;
2118            }
2119            if ($right > $end) {
2120                $end = $right;
2121            }
2122        }
2123        # If the most common direction is reverse, flip the begin and end markers.
2124        if ($counts{'-'} > $counts{'+'}) {
2125            ($beg, $end) = ($end, $beg);
2126        }
2127        # Return the result.
2128        return ($contig, $beg, $end);
2129  }  }
2130    
2131  =head3 ReadFasta  =head3 ReadFasta
2132    
2133  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2134    
2135  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
2136  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 1737  Line 2196 
2196    
2197  =head3 FormatLocations  =head3 FormatLocations
2198    
2199  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2200    
2201  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
2202  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 1802  Line 2261 
2261    
2262  =head3 DumpData  =head3 DumpData
2263    
2264  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2265    
2266  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.
2267    
# Line 1814  Line 2273 
2273      # Get the data directory name.      # Get the data directory name.
2274      my $outputDirectory = $self->{_options}->{dataDir};      my $outputDirectory = $self->{_options}->{dataDir};
2275      # Dump the relations.      # Dump the relations.
2276      $self->{_erdb}->DumpRelations($outputDirectory);      $self->DumpRelations($outputDirectory);
2277  }  }
2278    
2279  =head3 XMLFileName  =head3 XMLFileName
2280    
2281  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2282    
2283  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2284    
# Line 1830  Line 2289 
2289      return $self->{_xmlName};      return $self->{_xmlName};
2290  }  }
2291    
2292    =head3 GetGenomeNameData
2293    
2294        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2295    
2296    Return the genus, species, and unique characterization for a genome. This
2297    is similar to L</GenusSpecies>, with the exception that it returns the
2298    values in three seperate fields.
2299    
2300    =over 4
2301    
2302    =item genomeID
2303    
2304    ID of the genome whose name data is desired.
2305    
2306    =item RETURN
2307    
2308    Returns a three-element list, consisting of the genus, species, and strain
2309    of the specified genome. If the genome is not found, an error occurs.
2310    
2311    =back
2312    
2313    =cut
2314    
2315    sub GetGenomeNameData {
2316        # Get the parameters.
2317        my ($self, $genomeID) = @_;
2318        # Get the desired values.
2319        my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>
2320                                                                [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);
2321        # Throw an error if they were not found.
2322        if (! defined $genus) {
2323            Confess("Genome $genomeID not found in database.");
2324        }
2325        # Return the results.
2326        return ($genus, $species, $strain);
2327    }
2328    
2329    =head3 GetGenomeByNameData
2330    
2331        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2332    
2333    Return a list of the IDs of the genomes with the specified genus,
2334    species, and strain. In almost every case, there will be either zero or
2335    one IDs returned; however, two or more IDs could be returned if there are
2336    multiple versions of the genome in the database.
2337    
2338    =over 4
2339    
2340    =item genus
2341    
2342    Genus of the desired genome.
2343    
2344    =item species
2345    
2346    Species of the desired genome.
2347    
2348    =item strain
2349    
2350    Strain (unique characterization) of the desired genome. This may be an empty
2351    string, in which case it is presumed that the desired genome has no strain
2352    specified.
2353    
2354    =item RETURN
2355    
2356    Returns a list of the IDs of the genomes having the specified genus, species, and
2357    strain.
2358    
2359    =back
2360    
2361    =cut
2362    
2363    sub GetGenomeByNameData {
2364        # Get the parameters.
2365        my ($self, $genus, $species, $strain) = @_;
2366        # Try to find the genomes.
2367        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2368                                    [$genus, $species, $strain], 'Genome(id)');
2369        # Return the result.
2370        return @retVal;
2371    }
2372    
2373  =head3 Insert  =head3 Insert
2374    
2375  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2376    
2377  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
2378  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 1841  Line 2381 
2381  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
2382  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>.
2383    
2384  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']});
2385    
2386  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
2387  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>.
2388    
2389  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>      $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2390    
2391  =over 4  =over 4
2392    
# Line 1866  Line 2406 
2406      # Get the parameters.      # Get the parameters.
2407      my ($self, $objectType, $fieldHash) = @_;      my ($self, $objectType, $fieldHash) = @_;
2408      # Call the underlying method.      # Call the underlying method.
2409      $self->{_erdb}->InsertObject($objectType, $fieldHash);      $self->InsertObject($objectType, $fieldHash);
2410  }  }
2411    
2412  =head3 Annotate  =head3 Annotate
2413    
2414  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2415    
2416  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
2417  specified feature and user.  specified feature and user.
# Line 1925  Line 2465 
2465    
2466  =head3 AssignFunction  =head3 AssignFunction
2467    
2468  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2469    
2470  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
2471  format is described in L</ParseAssignment>.  format is described in L</ParseAssignment>.
# Line 1985  Line 2525 
2525    
2526  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2527    
2528  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2529    
2530  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
2531  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 2019  Line 2559 
2559          push @retVal, $mappedAlias;          push @retVal, $mappedAlias;
2560      } else {      } else {
2561          # 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.
2562          @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2563      }      }
2564      # Return the result.      # Return the result.
2565      return @retVal;      return @retVal;
2566  }  }
2567    
 =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.  
     Trace("Checking existence of $entityName with ID=$entityID.") if T(4);  
     my $testInstance = $self->GetEntity($entityName, $entityID);  
     # Return an existence indicator.  
     my $retVal = ($testInstance ? 1 : 0);  
     return $retVal;  
 }  
   
2568  =head3 FeatureTranslation  =head3 FeatureTranslation
2569    
2570  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2571    
2572  Return the translation of a feature.  Return the translation of a feature.
2573    
# Line 2090  Line 2595 
2595    
2596  =head3 Taxonomy  =head3 Taxonomy
2597    
2598  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2599    
2600  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
2601  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>,
2602  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2603    
2604  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2605    
2606  =over 4  =over 4
2607    
# Line 2131  Line 2636 
2636    
2637  =head3 CrudeDistance  =head3 CrudeDistance
2638    
2639  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2640    
2641  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
2642  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 2183  Line 2688 
2688    
2689  =head3 RoleName  =head3 RoleName
2690    
2691  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2692    
2693  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
2694  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 2217  Line 2722 
2722    
2723  =head3 RoleDiagrams  =head3 RoleDiagrams
2724    
2725  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2726    
2727  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2728    
# Line 2247  Line 2752 
2752    
2753  =head3 GetProperties  =head3 GetProperties
2754    
2755  C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>      my @list = $sprout->GetProperties($fid, $key, $value, $url);
2756    
2757  Return a list of the properties with the specified characteristics.  Return a list of the properties with the specified characteristics.
2758    
2759  Properties are arbitrary key-value pairs associated with a feature. (At some point they  Properties are the Sprout analog of the FIG attributes. The call is
2760  will also be associated with genomes.) A property value is represented by a 4-tuple of  passed directly to the CustomAttributes or RemoteCustomAttributes object
2761  the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter  contained in this object.
2762    
2763  =over 4  This method returns a series of tuples that match the specified criteria. Each tuple
2764    will contain an object ID, a key, and one or more values. The parameters to this
2765    method therefore correspond structurally to the values expected in each tuple. In
2766    addition, you can ask for a generic search by suffixing a percent sign (C<%>) to any
2767    of the parameters. So, for example,
2768    
2769  =item fid      my @attributeList = $sprout->GetProperties('fig|100226.1.peg.1004', 'structure%', 1, 2);
2770    
2771  ID of the feature possessing the property.  would return something like
2772    
2773  =item key      ['fig}100226.1.peg.1004', 'structure', 1, 2]
2774        ['fig}100226.1.peg.1004', 'structure1', 1, 2]
2775        ['fig}100226.1.peg.1004', 'structure2', 1, 2]
2776        ['fig}100226.1.peg.1004', 'structureA', 1, 2]
2777    
2778  Name or key of the property.  Use of C<undef> in any position acts as a wild card (all values). You can also specify
2779    a list reference in the ID column. Thus,
2780    
2781  =item value      my @attributeList = $sprout->GetProperties(['100226.1', 'fig|100226.1.%'], 'PUBMED');
2782    
2783  Value of the property.  would get the PUBMED attribute data for Streptomyces coelicolor A3(2) and all its
2784    features.
2785    
2786  =item url  In addition to values in multiple sections, a single attribute key can have multiple
2787    values, so even
2788    
2789  URL of the document that indicated the property should have this particular value, or an      my @attributeList = $sprout->GetProperties($peg, 'virulent');
 empty string if no such document exists.  
2790    
2791  =back  which has no wildcard in the key or the object ID, may return multiple tuples.
2792    
2793    =over 4
2794    
2795    =item objectID
2796    
2797  The parameters act as a filter for the desired data. Any non-null parameter will  ID of object whose attributes are desired. If the attributes are desired for multiple
2798  automatically match all the tuples returned. So, specifying just the I<$fid> will  objects, this parameter can be specified as a list reference. If the attributes are
2799  return all the properties of the specified feature; similarly, specifying the I<$key>  desired for all objects, specify C<undef> or an empty string. Finally, you can specify
2800  and I<$value> parameters will return all the features having the specified property  attributes for a range of object IDs by putting a percent sign (C<%>) at the end.
 value.  
2801    
2802  A single property key can have many values, representing different ideas about the  =item key
2803  feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is  
2804  virulent, and another may declare that it is not virulent. A query about the virulence of  Attribute key name. A value of C<undef> or an empty string will match all
2805  C<fig|83333.1.peg.10> would be coded as  attribute keys. If the values are desired for multiple keys, this parameter can be
2806    specified as a list reference. Finally, you can specify attributes for a range of
2807    keys by putting a percent sign (C<%>) at the end.
2808    
2809    =item values
2810    
2811    List of the desired attribute values, section by section. If C<undef>
2812    or an empty string is specified, all values in that section will match. A
2813    generic match can be requested by placing a percent sign (C<%>) at the end.
2814    In that case, all values that match up to and not including the percent sign
2815    will match. You may also specify a regular expression enclosed
2816    in slashes. All values that match the regular expression will be returned. For
2817    performance reasons, only values have this extra capability.
2818    
2819      my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');  =item RETURN
2820    
2821  Here the I<$value> and I<$url> fields are left blank, indicating that those fields are  Returns a list of tuples. The first element in the tuple is an object ID, the
2822  not to be filtered. The tuples returned would be  second is an attribute key, and the remaining elements are the sections of
2823    the attribute value. All of the tuples will match the criteria set forth in
2824    the parameter list.
2825    
2826      ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')  =back
     ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')  
2827    
2828  =cut  =cut
2829  #: Return Type @@;  
2830  sub GetProperties {  sub GetProperties {
2831      # Get the parameters.      # Get the parameters.
2832      my ($self, @parms) = @_;      my ($self, @parms) = @_;
2833      # Declare the return variable.      # Declare the return variable.
2834      my @retVal = ();      my @retVal = $self->{_ca}->GetAttributes(@parms);
     # Now we need to create a WHERE clause that will get us the data we want. First,  
     # we create a list of the columns containing the data for each parameter.  
     my @colNames = ('HasProperty(from-link)', 'Property(property-name)',  
                     'Property(property-value)', 'HasProperty(evidence)');  
     # Now we build the WHERE clause and the list of parameter values.  
     my @where = ();  
     my @values = ();  
     for (my $i = 0; $i <= $#colNames; $i++) {  
         my $parm = $parms[$i];  
         if (defined $parm && ($parm ne '')) {  
             push @where, "$colNames[$i] = ?";  
             push @values, $parm;  
         }  
     }  
     # Format the WHERE clause.  
     my $filter = (@values > 0 ? (join " AND ", @where) : undef);  
     # Ask for all the propertie values with the desired characteristics.  
     my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);  
     while (my $valueObject = $query->Fetch()) {  
         my @tuple = $valueObject->Values(\@colNames);  
         push @retVal, \@tuple;  
     }  
2835      # Return the result.      # Return the result.
2836      return @retVal;      return @retVal;
2837  }  }
2838    
2839  =head3 FeatureProperties  =head3 FeatureProperties
2840    
2841  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2842    
2843  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
2844  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
2845  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
2846  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
2847  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.  
2848    
2849  =over 4  =over 4
2850    
# Line 2348  Line 2854 
2854    
2855  =item RETURN  =item RETURN
2856    
2857  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.  
2858    
2859  =back  =back
2860    
# Line 2359  Line 2864 
2864      # Get the parameters.      # Get the parameters.
2865      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2866      # Get the properties.      # Get the properties.
2867      my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->{_ca}->GetAttributes($featureID);
2868                              ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2869                               'HasProperty(evidence)']);      my @retVal = ();
2870        for my $attributeRow (@attributes) {
2871            shift @{$attributeRow};
2872            push @retVal, $attributeRow;
2873        }
2874      # Return the resulting list.      # Return the resulting list.
2875      return @retVal;      return @retVal;
2876  }  }
2877    
2878  =head3 DiagramName  =head3 DiagramName
2879    
2880  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2881    
2882  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2883    
# Line 2394  Line 2903 
2903      return $retVal;      return $retVal;
2904  }  }
2905    
2906    =head3 PropertyID
2907    
2908        my $id = $sprout->PropertyID($propName, $propValue);
2909    
2910    Return the ID of the specified property name and value pair, if the
2911    pair exists. Only a small subset of the FIG attributes are stored as
2912    Sprout properties, mostly for use in search optimization.
2913    
2914    =over 4
2915    
2916    =item propName
2917    
2918    Name of the desired property.
2919    
2920    =item propValue
2921    
2922    Value expected for the desired property.
2923    
2924    =item RETURN
2925    
2926    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2927    
2928    =back
2929    
2930    =cut
2931    
2932    sub PropertyID {
2933        # Get the parameters.
2934        my ($self, $propName, $propValue) = @_;
2935        # Try to find the ID.
2936        my ($retVal) = $self->GetFlat(['Property'],
2937                                      "Property(property-name) = ? AND Property(property-value) = ?",
2938                                      [$propName, $propValue], 'Property(id)');
2939        # Return the result.
2940        return $retVal;
2941    }
2942    
2943  =head3 MergedAnnotations  =head3 MergedAnnotations
2944    
2945  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2946    
2947  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2948  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2445  Line 2991 
2991    
2992  =head3 RoleNeighbors  =head3 RoleNeighbors
2993    
2994  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
2995    
2996  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
2997  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 2488  Line 3034 
3034    
3035  =head3 FeatureLinks  =head3 FeatureLinks
3036    
3037  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
3038    
3039  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
3040  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 2519  Line 3065 
3065    
3066  =head3 SubsystemsOf  =head3 SubsystemsOf
3067    
3068  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3069    
3070  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
3071  to the roles the feature performs.  to the roles the feature performs.
# Line 2547  Line 3093 
3093                                      ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                      ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
3094      # Create the return value.      # Create the return value.
3095      my %retVal = ();      my %retVal = ();
3096        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
3097        # in two spreadsheet cells.
3098        my %dupHash = ();
3099      # Loop through the results, adding them to the hash.      # Loop through the results, adding them to the hash.
3100      for my $record (@subsystems) {      for my $record (@subsystems) {
3101            # Get this subsystem and role.
3102          my ($subsys, $role) = @{$record};          my ($subsys, $role) = @{$record};
3103          if (exists $retVal{$subsys}) {          # Insure it's the first time for both.
3104            my $dupKey = "$subsys\n$role";
3105            if (! exists $dupHash{"$subsys\n$role"}) {
3106                $dupHash{$dupKey} = 1;
3107              push @{$retVal{$subsys}}, $role;              push @{$retVal{$subsys}}, $role;
         } else {  
             $retVal{$subsys} = [$role];  
3108          }          }
3109      }      }
3110      # Return the hash.      # Return the hash.
# Line 2562  Line 3113 
3113    
3114  =head3 SubsystemList  =head3 SubsystemList
3115    
3116  C<< my @subsystems = $sprout->SubsystemList($featureID); >>      my @subsystems = $sprout->SubsystemList($featureID);
3117    
3118  Return a list containing the names of the subsystems in which the specified  Return a list containing the names of the subsystems in which the specified
3119  feature participates. Unlike L</SubsystemsOf>, this method only returns the  feature participates. Unlike L</SubsystemsOf>, this method only returns the
# Line 2586  Line 3137 
3137      # Get the parameters.      # Get the parameters.
3138      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
3139      # Get the list of names.      # Get the list of names.
3140      my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",      my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?",
3141                                  [$featureID], 'HasSSCell(from-link)');                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3142        # Return the result, sorted.
3143        return sort @retVal;
3144    }
3145    
3146    =head3 GenomeSubsystemData
3147    
3148        my %featureData = $sprout->GenomeSubsystemData($genomeID);
3149    
3150    Return a hash mapping genome features to their subsystem roles.
3151    
3152    =over 4
3153    
3154    =item genomeID
3155    
3156    ID of the genome whose subsystem feature map is desired.
3157    
3158    =item RETURN
3159    
3160    Returns a hash mapping each feature of the genome to a list of 2-tuples. Eacb
3161    2-tuple contains a subsystem name followed by a role ID.
3162    
3163    =back
3164    
3165    =cut
3166    
3167    sub GenomeSubsystemData {
3168        # Get the parameters.
3169        my ($self, $genomeID) = @_;
3170        # Declare the return variable.
3171        my %retVal = ();
3172        # Get a list of the genome features that participate in subsystems. For each
3173        # feature we get its spreadsheet cells and the corresponding roles.
3174        my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'],
3175                                 "HasFeature(from-link) = ?", [$genomeID],
3176                                 ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']);
3177        # Now we get a list of the spreadsheet cells and their associated subsystems. Subsystems
3178        # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the
3179        # list. We use it at the beginning to get all the spreadsheet cells for the genome and
3180        # again at the end to filter out participation in subsystems with a negative variant code.
3181        my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'],
3182                                     "IsGenomeOf(from-link) = ? AND ParticipatesIn(variant-code) >= 0 AND ParticipatesIn(from-link) = ?",
3183                                     [$genomeID, $genomeID], ['HasSSCell(to-link)', 'HasSSCell(from-link)']);
3184        # Now "@roleData" lists the spreadsheet cell and role for each of the genome's features.
3185        # "@cellData" lists the subsystem name for each of the genome's spreadsheet cells. We
3186        # link these two lists together to create the result. First, we want a hash mapping
3187        # spreadsheet cells to subsystem names.
3188        my %subHash = map { $_->[0] => $_->[1] } @cellData;
3189        # We loop through @cellData to build the hash.
3190        for my $roleEntry (@roleData) {
3191            # Get the data for this feature and cell.
3192            my ($fid, $cellID, $role) = @{$roleEntry};
3193            # Check for a subsystem name.
3194            my $subsys = $subHash{$cellID};
3195            if ($subsys) {
3196                # Insure this feature has an entry in the return hash.
3197                if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3198                # Merge in this new data.
3199                push @{$retVal{$fid}}, [$subsys, $role];
3200            }
3201        }
3202      # Return the result.      # Return the result.
3203      return @retVal;      return %retVal;
3204  }  }
3205    
3206  =head3 RelatedFeatures  =head3 RelatedFeatures
3207    
3208  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
3209    
3210  Return a list of the features which are bi-directional best hits of the specified feature and  Return a list of the features which are bi-directional best hits of the specified feature and
3211  have been assigned the specified function by the specified user. If no such features exists,  have been assigned the specified function by the specified user. If no such features exists,
# Line 2627  Line 3238 
3238      # Get the parameters.      # Get the parameters.
3239      my ($self, $featureID, $function, $userID) = @_;      my ($self, $featureID, $function, $userID) = @_;
3240      # Get a list of the features that are BBHs of the incoming feature.      # Get a list of the features that are BBHs of the incoming feature.
3241      my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);
                                      "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],  
                                      'IsBidirectionalBestHitOf(to-link)');  
3242      # Now we loop through the features, pulling out the ones that have the correct      # Now we loop through the features, pulling out the ones that have the correct
3243      # functional assignment.      # functional assignment.
3244      my @retVal = ();      my @retVal = ();
# Line 2647  Line 3256 
3256    
3257  =head3 TaxonomySort  =head3 TaxonomySort
3258    
3259  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3260    
3261  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a list formed by sorting the specified features by the taxonomy of the containing
3262  genome. This will cause genomes from similar organisms to float close to each other.  genome. This will cause genomes from similar organisms to float close to each other.
# Line 2682  Line 3291 
3291          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3292                                          [$fid], 'Genome(taxonomy)');                                          [$fid], 'Genome(taxonomy)');
3293          # Add this feature to the hash buffer.          # Add this feature to the hash buffer.
3294          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);          push @{$hashBuffer{$taxonomy}}, $fid;
3295      }      }
3296      # Sort the keys and get the elements.      # Sort the keys and get the elements.
3297      my @retVal = ();      my @retVal = ();
# Line 2693  Line 3302 
3302      return @retVal;      return @retVal;
3303  }  }
3304    
 =head3 GetAll  
   
 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.  
   
 The list returned will be a list of lists. Each element of the list will contain  
 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.  
   
 C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  
   
 =over 4  
   
 =item objectNames  
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
   
 =item fields  
   
 List of the fields to be returned in each element of the list returned.  
   
 =item count  
   
 Maximum number of records to return. If omitted or 0, all available records will be returned.  
   
 =item RETURN  
   
 Returns a list of list references. Each element of the return list contains the values for the  
 fields specified in the B<fields> parameter.  
   
 =back  
   
 =cut  
 #: Return Type @@;  
 sub GetAll {  
     # Get the parameters.  
     my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;  
     # Call the ERDB method.  
     my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,  
                                         $fields, $count);  
     # Return the resulting list.  
     return @retVal;  
 }  
   
 =head3 GetFlat  
   
 C<< my @list = $sprout->GetFlat(\@objectNames, $filterClause, $parameterList, $field); >>  
   
 This is a variation of L</GetAll> that asks for only a single field per record and  
 returns a single flattened list.  
   
 =over 4  
   
 =item objectNames  
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
   
 =item field  
   
 Name of the field to be used to get the elements of the list returned.  
   
 =item RETURN  
   
 Returns a list of values.  
   
 =back  
   
 =cut  
 #: Return Type @;  
 sub GetFlat {  
     # Get the parameters.  
     my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;  
     # Construct the query.  
     my $query = $self->Get($objectNames, $filterClause, $parameterList);  
     # Create the result list.  
     my @retVal = ();  
     # Loop through the records, adding the field values found to the result list.  
     while (my $row = $query->Fetch()) {  
         push @retVal, $row->Value($field);  
     }  
     # Return the list created.  
     return @retVal;  
 }  
   
3305  =head3 Protein  =head3 Protein
3306    
3307  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3308    
3309  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3310    
# Line 2884  Line 3374 
3374      # Loop through the input triples.      # Loop through the input triples.
3375      my $n = length $sequence;      my $n = length $sequence;
3376      for (my $i = 0; $i < $n; $i += 3) {      for (my $i = 0; $i < $n; $i += 3) {
3377          # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3378          my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3379            my $triple = uc substr($sequence, $i, 3);
3380          # Translate it using the table.          # Translate it using the table.
3381          my $protein = "X";          my $protein = "X";
3382          if (exists $table->{$triple}) { $protein = $table->{$triple}; }          if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 2899  Line 3390 
3390    
3391  =head3 LoadInfo  =head3 LoadInfo
3392    
3393  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3394    
3395  Return the name of the directory from which data is to be loaded and a list of the relation  Return the name of the directory from which data is to be loaded and a list of the relation
3396  names. This information is useful when trying to analyze what needs to be put where in order  names. This information is useful when trying to analyze what needs to be put where in order
# Line 2913  Line 3404 
3404      # Create the return list, priming it with the name of the data directory.      # Create the return list, priming it with the name of the data directory.
3405      my @retVal = ($self->{_options}->{dataDir});      my @retVal = ($self->{_options}->{dataDir});
3406      # Concatenate the table names.      # Concatenate the table names.
3407      push @retVal, $self->{_erdb}->GetTableNames();      push @retVal, $self->GetTableNames();
3408      # Return the result.      # Return the result.
3409      return @retVal;      return @retVal;
3410  }  }
3411    
3412    =head3 BBHMatrix
3413    
3414        my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3415    
3416    Find all the bidirectional best hits for the features of a genome in a
3417    specified list of target genomes. The return value will be a hash mapping
3418    features in the original genome to their bidirectional best hits in the
3419    target genomes.
3420    
3421    =over 4
3422    
3423    =item genomeID
3424    
3425    ID of the genome whose features are to be examined for bidirectional best hits.
3426    
3427    =item cutoff
3428    
3429    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3430    
3431    =item targets
3432    
3433    List of target genomes. Only pairs originating in the original
3434    genome and landing in one of the target genomes will be returned.
3435    
3436    =item RETURN
3437    
3438    Returns a hash mapping each feature in the original genome to a hash mapping its
3439    BBH pegs in the target genomes to their scores.
3440    
3441    =back
3442    
3443    =cut
3444    
3445    sub BBHMatrix {
3446        # Get the parameters.
3447        my ($self, $genomeID, $cutoff, @targets) = @_;
3448        # Declare the return variable.
3449        my %retVal = ();
3450        # Ask for the BBHs.
3451        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3452        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3453        for my $bbhData (@bbhList) {
3454            my ($peg1, $peg2, $score) = @{$bbhData};
3455            if (! exists $retVal{$peg1}) {
3456                $retVal{$peg1} = { $peg2 => $score };
3457            } else {
3458                $retVal{$peg1}->{$peg2} = $score;
3459            }
3460        }
3461        # Return the result.
3462        return %retVal;
3463    }
3464    
3465    
3466    =head3 SimMatrix
3467    
3468        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3469    
3470    Find all the similarities for the features of a genome in a
3471    specified list of target genomes. The return value will be a hash mapping
3472    features in the original genome to their similarites in the
3473    target genomes.
3474    
3475    =over 4
3476    
3477    =item genomeID
3478    
3479    ID of the genome whose features are to be examined for similarities.
3480    
3481    =item cutoff
3482    
3483    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3484    
3485    =item targets
3486    
3487    List of target genomes. Only pairs originating in the original
3488    genome and landing in one of the target genomes will be returned.
3489    
3490    =item RETURN
3491    
3492    Returns a hash mapping each feature in the original genome to a hash mapping its
3493    similar pegs in the target genomes to their scores.
3494    
3495    =back
3496    
3497    =cut
3498    
3499    sub SimMatrix {
3500        # Get the parameters.
3501        my ($self, $genomeID, $cutoff, @targets) = @_;
3502        # Declare the return variable.
3503        my %retVal = ();
3504        # Get the list of features in the source organism.
3505        my @fids = $self->FeaturesOf($genomeID);
3506        # Ask for the sims. We only want similarities to fig features.
3507        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3508        if (! defined $simList) {
3509            Confess("Unable to retrieve similarities from server.");
3510        } else {
3511            Trace("Processing sims.") if T(3);
3512            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3513            # Create a hash for the target genomes.
3514            my %targetHash = map { $_ => 1 } @targets;
3515            for my $simData (@{$simList}) {
3516                # Get the PEGs and the score.
3517                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3518                # Insure the second ID is in the target list.
3519                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3520                if (exists $targetHash{$genome2}) {
3521                    # Here it is. Now we need to add it to the return hash. How we do that depends
3522                    # on whether or not $peg1 is new to us.
3523                    if (! exists $retVal{$peg1}) {
3524                        $retVal{$peg1} = { $peg2 => $score };
3525                    } else {
3526                        $retVal{$peg1}->{$peg2} = $score;
3527                    }
3528                }
3529            }
3530        }
3531        # Return the result.
3532        return %retVal;
3533    }
3534    
3535    
3536  =head3 LowBBHs  =head3 LowBBHs
3537    
3538  C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3539    
3540  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3541  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 2949  Line 3564 
3564      my ($self, $featureID, $cutoff) = @_;      my ($self, $featureID, $cutoff) = @_;
3565      # Create the return hash.      # Create the return hash.
3566      my %retVal = ();      my %retVal = ();
3567      # Create a query to get the desired BBHs.      # Query for the desired BBHs.
3568      my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],      my @bbhList = FIGRules::BBHData($featureID, $cutoff);
                                 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',  
                                 [$cutoff, $featureID],  
                                 ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);  
3569      # Form the results into the return hash.      # Form the results into the return hash.
3570      for my $pair (@bbhList) {      for my $pair (@bbhList) {
3571          $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3572            if ($self->Exists('Feature', $fid)) {
3573                $retVal{$fid} = $pair->[1];
3574            }
3575      }      }
3576      # Return the result.      # Return the result.
3577      return %retVal;      return %retVal;
3578  }  }
3579    
3580    =head3 Sims
3581    
3582        my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3583    
3584    Get a list of similarities for a specified feature. Similarity information is not kept in the
3585    Sprout database; rather, they are retrieved from a network server. The similarities are
3586    returned as B<Sim> objects. A Sim object is actually a list reference that has been blessed
3587    so that its elements can be accessed by name.
3588    
3589    Similarities can be either raw or expanded. The raw similarities are basic
3590    hits between features with similar DNA. Expanding a raw similarity drags in any
3591    features considered substantially identical. So, for example, if features B<A1>,
3592    B<A2>, and B<A3> are all substantially identical to B<A>, then a raw similarity
3593    B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3594    
3595    =over 4
3596    
3597    =item fid
3598    
3599    ID of the feature whose similarities are desired, or reference to a list of IDs
3600    of features whose similarities are desired.
3601    
3602    =item maxN
3603    
3604    Maximum number of similarities to return.
3605    
3606    =item maxP
3607    
3608    Minumum allowable similarity score.
3609    
3610    =item select
3611    
3612    Selection criterion: C<raw> means only raw similarities are returned; C<fig>
3613    means only similarities to FIG features are returned; C<all> means all expanded
3614    similarities are returned; and C<figx> means similarities are expanded until the
3615    number of FIG features equals the maximum.
3616    
3617    =item max_expand
3618    
3619    The maximum number of features to expand.
3620    
3621    =item filters
3622    
3623    Reference to a hash containing filter information, or a subroutine that can be
3624    used to filter the sims.
3625    
3626    =item RETURN
3627    
3628    Returns a reference to a list of similarity objects, or C<undef> if an error
3629    occurred.
3630    
3631    =back
3632    
3633    =cut
3634    
3635    sub Sims {
3636        # Get the parameters.
3637        my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_;
3638        # Create the shim object to test for deleted FIDs.
3639        my $shim = FidCheck->new($self);
3640        # Ask the network for sims.
3641        my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters);
3642        # Return the result.
3643        return $retVal;
3644    }
3645    
3646    =head3 IsAllGenomes
3647    
3648        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3649    
3650    Return TRUE if all genomes in the second list are represented in the first list at
3651    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3652    compared to a list of all the genomes.
3653    
3654    =over 4
3655    
3656    =item list
3657    
3658    Reference to the list to be compared to the second list.
3659    
3660    =item checkList (optional)
3661    
3662    Reference to the comparison target list. Every genome ID in this list must occur at
3663    least once in the first list. If this parameter is omitted, a list of all the genomes
3664    is used.
3665    
3666    =item RETURN
3667    
3668    Returns TRUE if every item in the second list appears at least once in the
3669    first list, else FALSE.
3670    
3671    =back
3672    
3673    =cut
3674    
3675    sub IsAllGenomes {
3676        # Get the parameters.
3677        my ($self, $list, $checkList) = @_;
3678        # Supply the checklist if it was omitted.
3679        $checkList = [$self->Genomes()] if ! defined($checkList);
3680        # Create a hash of the original list.
3681        my %testList = map { $_ => 1 } @{$list};
3682        # Declare the return variable. We assume that the representation
3683        # is complete and stop at the first failure.
3684        my $retVal = 1;
3685        my $n = scalar @{$checkList};
3686        for (my $i = 0; $retVal && $i < $n; $i++) {
3687            if (! $testList{$checkList->[$i]}) {
3688                $retVal = 0;
3689            }
3690        }
3691        # Return the result.
3692        return $retVal;
3693    }
3694    
3695  =head3 GetGroups  =head3 GetGroups
3696    
3697  C<< my %groups = $sprout->GetGroups(\@groupList); >>      my %groups = $sprout->GetGroups(\@groupList);
3698    
3699  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.
3700  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 2983  Line 3713 
3713          # Here we have a group list. Loop through them individually,          # Here we have a group list. Loop through them individually,
3714          # getting a list of the relevant genomes.          # getting a list of the relevant genomes.
3715          for my $group (@{$groupList}) {          for my $group (@{$groupList}) {
3716              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3717                  [$group], "Genome(id)");                  [$group], "Genome(id)");
3718              $retVal{$group} = \@genomeIDs;              $retVal{$group} = \@genomeIDs;
3719          }          }
# Line 2991  Line 3721 
3721          # 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
3722          # of the genome records, putting each one found into the appropriate          # of the genome records, putting each one found into the appropriate
3723          # 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
3724          # in groups are included in the return set.          # in real NMPDR groups are included in the return set.
3725          my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],          my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3726                                      ['Genome(id)', 'Genome(group-name)']);                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3727          # Loop through the genomes found.          # Loop through the genomes found.
3728          for my $genome (@genomes) {          for my $genome (@genomes) {
3729              # Pop this genome's ID off the current list.              # Get the genome ID and group, and add this genome to the group's list.
3730              my @groups = @{$genome};              my ($genomeID, $group) = @{$genome};
3731              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, $genomeID);  
             }  
3732          }          }
3733      }      }
3734      # Return the hash we just built.      # Return the hash we just built.
# Line 3012  Line 3737 
3737    
3738  =head3 MyGenomes  =head3 MyGenomes
3739    
3740  C<< my @genomes = Sprout::MyGenomes($dataDir); >>      my @genomes = Sprout::MyGenomes($dataDir);
3741    
3742  Return a list of the genomes to be included in the Sprout.  Return a list of the genomes to be included in the Sprout.
3743    
# Line 3044  Line 3769 
3769    
3770  =head3 LoadFileName  =head3 LoadFileName
3771    
3772  C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>      my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3773    
3774  Return the name of the load file for the specified table in the specified data  Return the name of the load file for the specified table in the specified data
3775  directory.  directory.
# Line 3083  Line 3808 
3808      return $retVal;      return $retVal;
3809  }  }
3810    
3811    =head3 DeleteGenome
3812    
3813        my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3814    
3815    Delete a genome from the database.
3816    
3817    =over 4
3818    
3819    =item genomeID
3820    
3821    ID of the genome to delete
3822    
3823    =item testFlag
3824    
3825    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3826    
3827    =item RETURN
3828    
3829    Returns a statistics object describing the rows deleted.
3830    
3831    =back
3832    
3833    =cut
3834    #: Return Type $%;
3835    sub DeleteGenome {
3836        # Get the parameters.
3837        my ($self, $genomeID, $testFlag) = @_;
3838        # Perform the delete for the genome's features.
3839        my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3840        # Perform the delete for the primary genome data.
3841        my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3842        $retVal->Accumulate($stats);
3843        # Return the result.
3844        return $retVal;
3845    }
3846    
3847    =head3 Fix
3848    
3849        my %fixedHash = $sprout->Fix(%groupHash);
3850    
3851    Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3852    The groups will be combined into the appropriate super-groups.
3853    
3854    =over 4
3855    
3856    =item groupHash
3857    
3858    Hash to be fixed up.
3859    
3860    =item RETURN
3861    
3862    Returns a fixed-up version of the hash.
3863    
3864    =back
3865    
3866    =cut
3867    
3868    sub Fix {
3869        # Get the parameters.
3870        my ($self, %groupHash) = @_;
3871        # Create the result hash.
3872        my %retVal = ();
3873        # Copy over the genomes.
3874        for my $groupID (keys %groupHash) {
3875            # Get the super-group name.
3876            my $realGroupID = $self->SuperGroup($groupID);
3877            # Append this group's genomes into the result hash
3878            # using the super-group name.
3879            push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3880        }
3881        # Return the result hash.
3882        return %retVal;
3883    }
3884    
3885    =head3 GroupPageName
3886    
3887        my $name = $sprout->GroupPageName($group);
3888    
3889    Return the name of the page for the specified NMPDR group.
3890    
3891    =over 4
3892    
3893    =item group
3894    
3895    Name of the relevant group.
3896    
3897    =item RETURN
3898    
3899    Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3900    memory it will be read in.
3901    
3902    =back
3903    
3904    =cut
3905    
3906    sub GroupPageName {
3907        # Get the parameters.
3908        my ($self, $group) = @_;
3909        # Check for the group file data.
3910        my %superTable = $self->CheckGroupFile();
3911        # Compute the real group name.
3912        my $realGroup = $self->SuperGroup($group);
3913        # Get the associated page name.
3914        my $retVal = "../content/$superTable{$realGroup}->{page}";
3915        # Return the result.
3916        return $retVal;
3917    }
3918    
3919    
3920    =head3 AddProperty
3921    
3922        $sprout->AddProperty($featureID, $key, @values);
3923    
3924    Add a new attribute value (Property) to a feature.
3925    
3926    =over 4
3927    
3928    =item peg
3929    
3930    ID of the feature to which the attribute is to be added.
3931    
3932    =item key
3933    
3934    Name of the attribute (key).
3935    
3936    =item values
3937    
3938    Values of the attribute.
3939    
3940    =back
3941    
3942    =cut
3943    #: Return Type ;
3944    sub AddProperty {
3945        # Get the parameters.
3946        my ($self, $featureID, $key, @values) = @_;
3947        # Add the property using the attached attributes object.
3948        $self->{_ca}->AddAttribute($featureID, $key, @values);
3949    }
3950    
3951    =head3 CheckGroupFile
3952    
3953        my %groupData = $sprout->CheckGroupFile();
3954    
3955    Get the group file hash. The group file hash describes the relationship
3956    between a group and the super-group to which it belongs for purposes of
3957    display. The super-group name is computed from the first capitalized word
3958    in the actual group name. For each super-group, the group file contains
3959    the page name and a list of the species expected to be in the group.
3960    Each species is specified by a genus and a species name. A species name
3961    of C<0> implies an entire genus.
3962    
3963    This method returns a hash from super-group names to a hash reference. Each
3964    resulting hash reference contains the following fields.
3965    
3966    =over 4
3967    
3968    =item page
3969    
3970    The super-group's web page in the NMPDR.
3971    
3972    =item contents
3973    
3974    A list of 2-tuples, each containing a genus name followed by a species name
3975    (or 0, indicating all species). This list indicates which organisms belong
3976    in the super-group.
3977    
3978    =back
3979    
3980    =cut
3981    
3982    sub CheckGroupFile {
3983        # Get the parameters.
3984        my ($self) = @_;
3985        # Check to see if we already have this hash.
3986        if (! defined $self->{groupHash}) {
3987            # We don't, so we need to read it in.
3988            my %groupHash;
3989            # Read the group file.
3990            my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
3991            # Loop through the list of sort-of groups.
3992            for my $groupLine (@groupLines) {
3993                my ($name, $page, @contents) = split /\t/, $groupLine;
3994                $groupHash{$name} = { page => $page,
3995                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
3996                                    };
3997            }
3998            # Save the hash.
3999            $self->{groupHash} = \%groupHash;
4000        }
4001        # Return the result.
4002        return %{$self->{groupHash}};
4003    }
4004    
4005    =head2 Virtual Methods
4006    
4007    =head3 CleanKeywords
4008    
4009        my $cleanedString = $sprout->CleanKeywords($searchExpression);
4010    
4011    Clean up a search expression or keyword list. This involves converting the periods
4012    in EC numbers to underscores, converting non-leading minus signs to underscores,
4013    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
4014    characters. In addition, any extra spaces are removed.
4015    
4016    =over 4
4017    
4018    =item searchExpression
4019    
4020    Search expression or keyword list to clean. Note that a search expression may
4021    contain boolean operators which need to be preserved. This includes leading
4022    minus signs.
4023    
4024    =item RETURN
4025    
4026    Cleaned expression or keyword list.
4027    
4028    =back
4029    
4030    =cut
4031    
4032    sub CleanKeywords {
4033        # Get the parameters.
4034        my ($self, $searchExpression) = @_;
4035        # Perform the standard cleanup.
4036        my $retVal = $self->ERDB::CleanKeywords($searchExpression);
4037        # Fix the periods in EC and TC numbers.
4038        $retVal =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;
4039        # Fix non-trailing periods.
4040        $retVal =~ s/\.(\w)/_$1/g;
4041        # Fix non-leading minus signs.
4042        $retVal =~ s/(\w)[\-]/$1_/g;
4043        # Fix the vertical bars and colons
4044        $retVal =~ s/(\w)[|:](\w)/$1'$2/g;
4045        # Return the result.
4046        return $retVal;
4047    }
4048    
4049  =head2 Internal Utility Methods  =head2 Internal Utility Methods
4050    
4051  =head3 ParseAssignment  =head3 ParseAssignment
# Line 3093  Line 4056 
4056    
4057  A functional assignment is always of the form  A functional assignment is always of the form
4058    
4059      I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>      set YYYY function to
4060        ZZZZ
4061    
4062  where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the  where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
4063  actual functional role. In most cases, the user and the assigning user will be the  the user and the assigning user (from MadeAnnotation) will be the same, but that is
4064  same, but that is not always the case.  not always the case.
4065    
4066    In addition, the functional role may contain extra data that is stripped, such as
4067    terminating spaces or a comment separated from the rest of the text by a tab.
4068    
4069  This is a static method.  This is a static method.
4070    
4071  =over 4  =over 4
4072    
4073    =item user
4074    
4075    Name of the assigning user.
4076    
4077  =item text  =item text
4078    
4079  Text of the annotation.  Text of the annotation.
# Line 3118  Line 4089 
4089    
4090  sub _ParseAssignment {  sub _ParseAssignment {
4091      # Get the parameters.      # Get the parameters.
4092      my ($text) = @_;      my ($user, $text) = @_;
4093      # Declare the return value.      # Declare the return value.
4094      my @retVal = ();      my @retVal = ();
4095      # Check to see if this is a functional assignment.      # Check to see if this is a functional assignment.
4096      my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
4097      if ($type =~ m/^set ([^ ]+) function to$/i) {      if ($type =~ m/^set function to$/i) {
4098          # Here it is, so we return the user name (which is in $1), the functional role text,          # Here we have an assignment without a user, so we use the incoming user ID.
4099          # and the assigning user.          @retVal = ($user, $function);
4100          @retVal = ($1, $function, $user);      } elsif ($type =~ m/^set (\S+) function to$/i) {
4101            # Here we have an assignment with a user that is passed back to the caller.
4102            @retVal = ($1, $function);
4103        }
4104        # If we have an assignment, we need to clean the function text. There may be
4105        # extra junk at the end added as a note from the user.
4106        if (defined( $retVal[1] )) {
4107            $retVal[1] =~ s/(\t\S)?\s*$//;
4108      }      }
4109      # Return the result list.      # Return the result list.
4110      return @retVal;      return @retVal;
4111  }  }
4112    
4113  =head3 FriendlyTimestamp  =head3 _CheckFeature
4114    
4115  Convert a time number to a user-friendly time stamp for display.      my $flag = $sprout->_CheckFeature($fid);
4116    
4117  This is a static method.  Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
4118    
4119  =over 4  =over 4
4120    
4121  =item timeValue  =item fid
4122    
4123  Numeric time value.  Feature ID to check.
4124    
4125  =item RETURN  =item RETURN
4126    
4127  Returns a string containing the same time in user-readable format.  Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE.
4128    
4129  =back  =back
4130    
4131  =cut  =cut
4132    
4133  sub FriendlyTimestamp {  sub _CheckFeature {
4134      my ($timeValue) = @_;      # Get the parameters.
4135      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my ($self, $fid) = @_;
4136      return $retVal;      # Insure we have a genome hash.
4137        if (! defined $self->{genomeHash}) {
4138            my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');
4139            $self->{genomeHash} = \%genomeHash;
4140        }
4141        # Get the feature's genome ID.
4142        my ($genomeID) = FIGRules::ParseFeatureID($fid);
4143        # Return an indicator of whether or not the genome ID is in the hash.
4144        return ($self->{genomeHash}->{$genomeID} ? 1 : 0);
4145  }  }
4146    
4147  =head3 AddProperty  =head3 FriendlyTimestamp
4148    
4149  C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>  Convert a time number to a user-friendly time stamp for display.
4150    
4151  Add a new attribute value (Property) to a feature. In the SEED system, attributes can  This is a static method.
 be added to almost any object. In Sprout, they can only be added to features. In  
 Sprout, attributes are implemented using I<properties>. A property represents a key/value  
 pair. If the particular key/value pair coming in is not already in the database, a new  
 B<Property> record is created to hold it.  
4152    
4153  =over 4  =over 4
4154    
4155  =item peg  =item timeValue
   
 ID of the feature to which the attribute is to be replied.  
   
 =item key  
   
 Name of the attribute (key).  
   
 =item value  
4156    
4157  Value of the attribute.  Numeric time value.
4158    
4159  =item url  =item RETURN
4160    
4161  URL or text citation from which the property was obtained.  Returns a string containing the same time in user-readable format.
4162    
4163  =back  =back
4164    
4165  =cut  =cut
 #: Return Type ;  
 sub AddProperty {  
     # Get the parameters.  
     my ($self, $featureID, $key, $value, $url) = @_;  
     # Declare the variable to hold the desired property ID.  
     my $propID;  
     # Attempt to find a property record for this key/value pair.  
     my @properties = $self->GetFlat(['Property'],  
                                    "Property(property-name) = ? AND Property(property-value) = ?",  
                                    [$key, $value], 'Property(id)');  
     if (@properties) {  
         # Here the property is already in the database. We save its ID.  
         $propID = $properties[0];  
         # Here the property value does not exist. We need to generate an ID. It will be set  
         # to a number one greater than the maximum value in the database. This call to  
         # GetAll will stop after one record.  
         my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],  
                                         1);  
         $propID = $maxProperty[0]->[0] + 1;  
         # Insert the new property value.  
         $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });  
     }  
     # Now we connect the incoming feature to the property.  
     $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });  
 }  
4166    
4167    sub FriendlyTimestamp {
4168        my ($timeValue) = @_;
4169        my $retVal = localtime($timeValue);
4170        return $retVal;
4171    }
4172    
4173    
4174  1;  1;

Legend:
Removed from v.1.33  
changed lines
  Added in v.1.110

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3