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

Diff of /Sprout/Sprout.pm

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

revision 1.10, Fri Feb 25 18:41:45 2005 UTC revision 1.109, Sun Mar 23 16:32:05 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
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({
103                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
104                                             dataDir              => 'Data',                      # data file directory                                                          # database type
105                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
106                                             userData             => 'root/',                     # user name and password                                                          # data file directory
107                                             port                 => 0,                           # database connection port                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
108                                                            # database definition file name
109                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
110                                                            # user name and password
111                           port         => $FIG_Config::dbport,
112                                                            # 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
118                                            }, $options);                                            }, $options);
119          # Get the data directory.          # Get the data directory.
120          my $dataDir = $optionTable->{dataDir};          my $dataDir = $optionTable->{dataDir};
# Line 100  Line 122 
122          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
123          my ($userName, $password) = ($1, $2);          my ($userName, $password) = ($1, $2);
124          # Connect to the database.          # Connect to the database.
125          my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
126        if (! $optionTable->{noDBOpen}) {
127            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
128            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
129                                    $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.  
155    
156  C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ? ORDER BY Genome(species)", [$genus]); >>      my @genomes = $sprout->CoreGenomes($scope);
157    
158  It is also permissible to specify I<only> an ORDER BY clause. For example, the following invocation gets  Return the IDs of NMPDR genomes in the specified scope.
 all genomes ordered by genus and species.  
   
 C<< $query = $sprout->Get(['Genome'], "ORDER BY Genome(genus), Genome(species)"); >>  
   
 Odd things may happen if one of the ORDER BY fields is in a secondary relation. So, for example, an  
 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.  
163    
164  =item filterClause  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  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  genomes in the system.
 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.  
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          # Create a query.      # Declare the return variable.
237          my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);      my $retVal;
238          # Get the first (and only) object.      # Get the group hash.
239          my $retVal = $query->Fetch();      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.          # Return the result.
263          return $retVal;          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};
         # Get the specified entity.  
         my $entity = $self->GetEntity($entityType, $ID);  
         # Declare the return list.  
         my @retVal = ();  
         # If we found the entity, push the values into the return list.  
         if ($entity) {  
                 push @retVal, $entity->Values($fields);  
         }  
         # Return the result.  
         return @retVal;  
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 432  Line 378 
378          # Loop through the incoming table names.          # Loop through the incoming table names.
379          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
380                  # Find the table's file.                  # Find the table's file.
381                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
382                  if (! -e $fileName) {          if (! $fileName) {
383                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
384                  }          } 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          }          }
390        }
391          # Return the statistics.          # Return the statistics.
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 inTable
523    
524    If TRUE, then backslashes will be included at the end of each line in the resulting HTML. This enables the control
525    to be used in TWiki tables.
526    
527    =back
528    
529    =cut
530    
531    sub GenomeMenu {
532        # Get the parameters.
533        my ($self, %options) = @_;
534        # Get the control's name and ID.
535        my $menuName = $options{name} || 'myGenomeControl';
536        my $menuID = $options{id} || $menuName;
537        # Compute the IDs for the status display.
538        my $divID = "${menuID}_status";
539        my $urlID = "${menuID}_url";
540        # Compute the code to show selected genomes in the status area.
541        my $showSelect = "showSelected('$menuID', '$divID', '$urlID', 1000)";
542        # Check for single-select or multi-select.
543        my $multiSelect = $options{multiSelect} || 0;
544        # Get the list of pre-selected items.
545        my $selections = $options{selected} || [];
546        if (ref $selections ne 'ARRAY') {
547            $selections = [ split /\s*,\s*/, $selections ];
548        }
549        my %selected = map { $_ => } @{$selections};
550        # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
551        # string or a list reference.
552        my $filterParms = $options{filter} || "";
553        if (! ref $filterParms) {
554            $filterParms = [split /\t|\\t/, $filterParms];
555        }
556        my $filterString = shift @{$filterParms};
557        # Get a list of all the genomes in group order. In fact, we only need them ordered
558        # by name (genus,species,strain), but putting primary-group in front enables us to
559        # take advantage of an existing index.
560        my @genomeList = $self->GetAll(['Genome'], "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
561                                       $filterParms,
562                                       [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
563        # Create a hash to organize the genomes by group. Each group will contain a list of
564        # 2-tuples, the first element being the genome ID and the second being the genome
565        # name.
566        my %gHash = ();
567        for my $genome (@genomeList) {
568            # Get the genome data.
569            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
570            # Compute its name. This is the genus, species, strain (if any), and the contig count.
571            my $name = "$genus $species ";
572            $name .= "$strain " if $strain;
573            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
574            # Now we get the domain. The domain tells us the display style of the organism.
575            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
576            # Now compute the display group. This is normally the primary group, but if the
577            # organism is supporting, we blank it out.
578            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
579            # Push the genome into the group's list. Note that we use the real group
580            # name for the hash key here, not the display group name.
581            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
582        }
583        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
584        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
585        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
586        # that aren't "other". At some point, we will want to make this less complicated.
587        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
588                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
589        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
590        # Remember the number of NMPDR groups.
591        my $nmpdrGroupCount = scalar @groups;
592        # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
593        # of the domains found.
594        my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
595        my @domains = ();
596        for my $genomeData (@otherGenomes) {
597            my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
598            if (exists $gHash{$domain}) {
599                push @{$gHash{$domain}}, $genomeData;
600            } else {
601                $gHash{$domain} = [$genomeData];
602                push @domains, $domain;
603            }
604        }
605        # Add the domain groups at the end of the main group list. The main group list will now
606        # contain all the categories we need to display the genomes.
607        push @groups, sort @domains;
608        # Delete the supporting group.
609        delete $gHash{$FIG_Config::otherGroup};
610        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
611        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
612        # and use that to make the selections.
613        my $nmpdrCount = 0;
614        # Create the type counters.
615        my $groupCount = 1;
616        # Get the number of rows to display.
617        my $rows = $options{size} || 10;
618        # If we're multi-row, create an onChange event.
619        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
620        # Set up the multiple-select flag.
621        my $multipleTag = ($multiSelect ? " multiple" : "" );
622        # Create the SELECT tag and stuff it into the output array.
623        my @lines = ("<SELECT name=\"$menuID\" id=\"$menuID\" $onChangeTag$multipleTag size=\"$rows\" style=\"width: 100%\">");
624        # Loop through the groups.
625        for my $group (@groups) {
626            # Get the genomes in the group.
627            for my $genome (@{$gHash{$group}}) {
628                # If this is an NMPDR organism, we add an extra style and count it.
629                my $nmpdrStyle = "";
630                if ($nmpdrGroupCount > 0) {
631                    $nmpdrCount++;
632                    $nmpdrStyle = " Core";
633                }
634                # Get the organism ID, name, contig count, and domain.
635                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
636                # See if we're pre-selected.
637                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
638                # Compute the display name.
639                my $nameString = "$name ($genomeID$contigCount)";
640                # Generate the option tag.
641                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
642                push @lines, "    $optionTag";
643            }
644            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
645            # groups.
646            $nmpdrGroupCount--;
647        }
648        # Close the SELECT tag.
649        push @lines, "</SELECT>";
650        if ($rows > 1) {
651            # We're in a non-compact mode, so we need to add some selection helpers. First is
652            # the search box. This allows the user to type text and change which genomes are
653            # displayed. For multiple-select mode, we include a button that selects the displayed
654            # genes. For single-select mode, we use a plain label instead.
655            my $searchThingName = "${menuID}_SearchThing";
656            my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"
657                                                 : "Show genomes containing");
658            push @lines, "<br />$searchThingLabel&nbsp;" .
659                         "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />";
660            # For multi-select mode, we also have buttons to set and clear selections.
661            if ($multiSelect) {
662                push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll('$menuID'); $showSelect\" />";
663                push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll('$menuID'); $showSelect\" />";
664                push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome('$menuID', $nmpdrCount, true); $showSelect;\" />";
665            }
666            # Add a hidden field we can use to generate organism page hyperlinks.
667            push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/seedviewer.cgi?page=Organism;organism=\" />";
668            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
669            push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";
670        }
671        # Assemble all the lines into a string. This is where we do the "inTable" thing to insure we don't mess up TWiki tables.
672        my $delim = ($options{inTable} ? "\\" : "" ) . "\n";
673        my $retVal = join($delim, @lines, "");
674        # Return the result.
675        return $retVal;
676    }
677    
678    
679  =head3 Build  =head3 Build
680    
681  C<< $sprout->Build(); >>      $sprout->Build();
682    
683  Build the database. The database will be cleared and the tables re-created from the metadata.  Build the database. The database will be cleared and the tables re-created from the metadata.
684  This method is useful when a database is brand new or when the database definition has  This method is useful when a database is brand new or when the database definition has
# Line 459  Line 690 
690          # Get the parameters.          # Get the parameters.
691          my ($self) = @_;          my ($self) = @_;
692          # Create the tables.          # Create the tables.
693          $self->{_erdb}->CreateTables;      $self->CreateTables();
694  }  }
695    
696  =head3 Genomes  =head3 Genomes
697    
698  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
699    
700  Return a list of all the genome IDs.  Return a list of all the genome IDs.
701    
# Line 481  Line 712 
712    
713  =head3 GenusSpecies  =head3 GenusSpecies
714    
715  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
716    
717  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
718    
# Line 513  Line 744 
744    
745  =head3 FeaturesOf  =head3 FeaturesOf
746    
747  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
748    
749  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
750    
# Line 558  Line 789 
789    
790  =head3 FeatureLocation  =head3 FeatureLocation
791    
792  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
793    
794  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
795  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 582  Line 813 
813  =item RETURN  =item RETURN
814    
815  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
816  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
817    
818  =back  =back
819    
820  =cut  =cut
821  #: Return Type @;  
 #: Return Type $;  
822  sub FeatureLocation {  sub FeatureLocation {
823          # Get the parameters.          # Get the parameters.
824          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
825          # Create a query for the feature locations.      # Get the feature record.
826          my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",      my $object = $self->GetEntity('Feature', $featureID);
827                                                     [$featureID]);      Confess("Feature $featureID not found.") if ! defined($object);
828        # Get the location string.
829        my $locString = $object->PrimaryValue('Feature(location-string)');
830          # Create the return list.          # Create the return list.
831          my @retVal = ();      my @retVal = split /\s*,\s*/, $locString;
         # Set up the variables used to determine if we have adjacent segments. This initial setup will  
         # not match anything.  
         my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);  
         # Loop through the query results, creating location specifiers.  
         while (my $location = $query->Fetch()) {  
                 # Get the location parameters.  
                 my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',  
                         'IsLocatedIn(beg)', 'IsLocatedIn(dir)', 'IsLocatedIn(len)']);  
                 # Check to see if we are adjacent to the previous segment.  
                 if ($prevContig eq $contigID && $dir eq $prevDir) {  
                         # Here the new segment is in the same direction on the same contig. Insure the  
                         # new segment's beginning is next to the old segment's end.  
                         if (($dir eq "-" && $beg == $prevBeg - $prevLen) ||  
                                 ($dir eq "+" && $beg == $prevBeg + $prevLen)) {  
                                 # Here we need to merge two segments. Adjust the beginning and length values  
                                 # to include both segments.  
                                 $beg = $prevBeg;  
                                 $len += $prevLen;  
                                 # Pop the old segment off. The new one will replace it later.  
                                 pop @retVal;  
                         }  
                 }  
                 # Remember this specifier for the adjacent-segment test the next time through.  
                 ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);  
                 # Add the specifier to the list.  
                 push @retVal, "${contigID}_$beg$dir$len";  
         }  
832          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
833          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
834  }  }
835    
836  =head3 ParseLocation  =head3 ParseLocation
837    
838  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
839    
840  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
841  length.  length.
# Line 649  Line 854 
854  =back  =back
855    
856  =cut  =cut
857  #: Return Type @;  
858  sub ParseLocation {  sub ParseLocation {
859          # 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
860      # the first parameter.      # the first parameter.
861      shift if UNIVERSAL::isa($_[0],__PACKAGE__);      shift if UNIVERSAL::isa($_[0],__PACKAGE__);
862          my ($location) = @_;          my ($location) = @_;
863          # Parse it into segments.          # Parse it into segments.
864          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
865          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
866          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
867          if ($dir eq "_") {          if ($dir eq "_") {
# Line 672  Line 877 
877          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
878  }  }
879    
880    
881    
882  =head3 PointLocation  =head3 PointLocation
883    
884  C<< my $found = Sprout::PointLocation($location, $point); >>      my $found = Sprout::PointLocation($location, $point);
885    
886  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
887  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 703  Line 910 
910  =back  =back
911    
912  =cut  =cut
913  #: Return Type $;  
914  sub PointLocation {  sub PointLocation {
915          # 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
916      # the first parameter.      # the first parameter.
# Line 726  Line 933 
933    
934  =head3 DNASeq  =head3 DNASeq
935    
936  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
937    
938  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
939  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,
940  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>.
941    
942    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
943    between positions 1401 and 1532, inclusive.
944    
945        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
946    
947  =over 4  =over 4
948    
949  =item locationList  =item locationList
950    
951  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
952  L</FeatureLocation> for more about this format).  I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
953    
954  =item RETURN  =item RETURN
955    
# Line 764  Line 976 
976                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
977                  # before putting it in the return value.                  # before putting it in the return value.
978                  my ($start, $stop);                  my ($start, $stop);
979            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
980                  if ($dir eq "+") {                  if ($dir eq "+") {
981                          $start = $beg;                          $start = $beg;
982                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
983                  } else {                  } else {
984                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
985                          $stop = $beg;                          $stop = $beg;
986                  }                  }
987            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
988                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
989                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
990                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 782  Line 996 
996                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
997                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
998                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
999                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
1000                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
1001                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
1002                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
1003                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
1004                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
1005                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
1006                  }                  }
1007                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
1008                  if ($dir eq '+') {                  if ($dir eq '+') {
1009                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
1010                  } else {                  } else {
1011                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
1012                  }                  }
1013          }          }
1014          # Return the result.          # Return the result.
# Line 802  Line 1017 
1017    
1018  =head3 AllContigs  =head3 AllContigs
1019    
1020  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1021    
1022  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1023    
# Line 830  Line 1045 
1045          return @retVal;          return @retVal;
1046  }  }
1047    
1048  =head3 ContigLength  =head3 GenomeLength
1049    
1050  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->GenomeLength($genomeID);
1051    
1052  Compute the length of a contig.  Return the length of the specified genome in base pairs.
1053    
1054  =over 4  =over 4
1055    
1056  =item contigID  =item genomeID
1057    
1058  ID of the contig whose length is desired.  ID of the genome whose base pair count is desired.
1059    
1060  =item RETURN  =item RETURN
1061    
1062  Returns the number of positions in the contig.  Returns the number of base pairs in all the contigs of the specified
1063    genome.
1064    
1065  =back  =back
1066    
1067  =cut  =cut
1068  #: Return Type $;  
1069  sub ContigLength {  sub GenomeLength {
1070          # Get the parameters.          # Get the parameters.
1071          my ($self, $contigID) = @_;      my ($self, $genomeID) = @_;
1072          # 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.  
1073          my $retVal = 0;          my $retVal = 0;
1074          # Set it from the sequence data, if any.      # Get the genome's contig sequence lengths.
1075          if ($sequence) {      my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',
1076                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                         [$genomeID], 'IsMadeUpOf(len)');
1077                  $retVal = $start + $len;      # Sum the lengths.
1078          }      map { $retVal += $_ } @lens;
1079          # Return the result.          # Return the result.
1080          return $retVal;          return $retVal;
1081  }  }
1082    
1083  =head3 GenesInRegion  =head3 FeatureCount
1084    
1085  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my $count = $sprout->FeatureCount($genomeID, $type);
1086    
1087  List the features which overlap a specified region in a contig.  Return the number of features of the specified type in the specified genome.
1088    
1089  =over 4  =over 4
1090    
1091  =item contigID  =item genomeID
1092    
1093  ID of the contig containing the region of interest.  ID of the genome whose feature count is desired.
1094    
1095  =item start  =item type
1096    
1097  Offset of the first residue in the region of interest.  Type of feature to count (eg. C<peg>, C<rna>, etc.).
1098    
1099  =item stop  =item RETURN
1100    
1101  Offset of the last residue in the region of interest.  Returns the number of features of the specified type for the specified genome.
1102    
1103    =back
1104    
1105    =cut
1106    
1107    sub FeatureCount {
1108        # Get the parameters.
1109        my ($self, $genomeID, $type) = @_;
1110        # Compute the count.
1111        my $retVal = $self->GetCount(['HasFeature', 'Feature'],
1112                                    "HasFeature(from-link) = ? AND Feature(feature-type) = ?",
1113                                    [$genomeID, $type]);
1114        # Return the result.
1115        return $retVal;
1116    }
1117    
1118    =head3 GenomeAssignments
1119    
1120        my $fidHash = $sprout->GenomeAssignments($genomeID);
1121    
1122    Return a list of a genome's assigned features. The return hash will contain each
1123    assigned feature of the genome mapped to the text of its most recent functional
1124    assignment.
1125    
1126    =over 4
1127    
1128    =item genomeID
1129    
1130    ID of the genome whose functional assignments are desired.
1131    
1132    =item RETURN
1133    
1134    Returns a reference to a hash which maps each feature to its most recent
1135    functional assignment.
1136    
1137    =back
1138    
1139    =cut
1140    
1141    sub GenomeAssignments {
1142        # Get the parameters.
1143        my ($self, $genomeID) = @_;
1144        # Declare the return variable.
1145        my $retVal = {};
1146        # Query the genome's features.
1147        my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?",
1148                               [$genomeID]);
1149        # Loop through the features.
1150        while (my $data = $query->Fetch) {
1151            # Get the feature ID and assignment.
1152            my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
1153            if ($assignment) {
1154                $retVal->{$fid} = $assignment;
1155            }
1156        }
1157        # Return the result.
1158        return $retVal;
1159    }
1160    
1161    =head3 ContigLength
1162    
1163        my $length = $sprout->ContigLength($contigID);
1164    
1165    Compute the length of a contig.
1166    
1167    =over 4
1168    
1169    =item contigID
1170    
1171    ID of the contig whose length is desired.
1172    
1173    =item RETURN
1174    
1175    Returns the number of positions in the contig.
1176    
1177    =back
1178    
1179    =cut
1180    #: Return Type $;
1181    sub ContigLength {
1182        # Get the parameters.
1183        my ($self, $contigID) = @_;
1184        # Get the contig's last sequence.
1185        my $query = $self->Get(['IsMadeUpOf'],
1186            "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
1187            [$contigID]);
1188        my $sequence = $query->Fetch();
1189        # Declare the return value.
1190        my $retVal = 0;
1191        # Set it from the sequence data, if any.
1192        if ($sequence) {
1193            my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
1194            $retVal = $start + $len - 1;
1195        }
1196        # Return the result.
1197        return $retVal;
1198    }
1199    
1200    =head3 ClusterPEGs
1201    
1202        my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1203    
1204    Cluster the PEGs in a list according to the cluster coding scheme of the specified
1205    subsystem. In order for this to work properly, the subsystem object must have
1206    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> or
1207    B<get_row> methods. This causes the cluster numbers to be pulled into the
1208    subsystem's color hash. If a PEG is not found in the color hash, it will not
1209    appear in the output sequence.
1210    
1211    =over 4
1212    
1213    =item sub
1214    
1215    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
1216    method.
1217    
1218    =item pegs
1219    
1220    Reference to the list of PEGs to be clustered.
1221    
1222    =item RETURN
1223    
1224    Returns a list of the PEGs, grouped into smaller lists by cluster number.
1225    
1226    =back
1227    
1228    =cut
1229    #: Return Type $@@;
1230    sub ClusterPEGs {
1231        # Get the parameters.
1232        my ($self, $sub, $pegs) = @_;
1233        # Declare the return variable.
1234        my $retVal = [];
1235        # Loop through the PEGs, creating arrays for each cluster.
1236        for my $pegID (@{$pegs}) {
1237            my $clusterNumber = $sub->get_cluster_number($pegID);
1238            # Only proceed if the PEG is in a cluster.
1239            if ($clusterNumber >= 0) {
1240                # Push this PEG onto the sub-list for the specified cluster number.
1241                push @{$retVal->[$clusterNumber]}, $pegID;
1242            }
1243        }
1244        # Return the result.
1245        return $retVal;
1246    }
1247    
1248    =head3 GenesInRegion
1249    
1250        my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1251    
1252    List the features which overlap a specified region in a contig.
1253    
1254    =over 4
1255    
1256    =item contigID
1257    
1258    ID of the contig containing the region of interest.
1259    
1260    =item start
1261    
1262    Offset of the first residue in the region of interest.
1263    
1264    =item stop
1265    
1266    Offset of the last residue in the region of interest.
1267    
1268  =item RETURN  =item RETURN
1269    
# Line 900  Line 1276 
1276  =back  =back
1277    
1278  =cut  =cut
1279  #: Return Type @@;  
1280  sub GenesInRegion {  sub GenesInRegion {
1281          # Get the parameters.          # Get the parameters.
1282          my ($self, $contigID, $start, $stop) = @_;          my ($self, $contigID, $start, $stop) = @_;
1283          # Get the maximum segment length.          # Get the maximum segment length.
1284          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
         # Create a hash to receive the feature list. We use a hash so that we can eliminate  
         # duplicates easily. The hash key will be the feature ID. The value will be a two-element  
         # containing the minimum and maximum offsets. We will use the offsets to sort the results  
         # when we're building the result set.  
         my %featuresFound = ();  
1285          # Prime the values we'll use for the returned beginning and end.          # Prime the values we'll use for the returned beginning and end.
1286          my @initialMinMax = ($self->ContigLength($contigID), 0);          my @initialMinMax = ($self->ContigLength($contigID), 0);
1287          my ($min, $max) = @initialMinMax;          my ($min, $max) = @initialMinMax;
1288          # Create a table of parameters for each query. Each query looks for features travelling in      # Get the overlapping features.
1289        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1290        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1291        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1292        # of the feature's locations.
1293        my %featureMap = ();
1294        # Loop through them to do the begin/end analysis.
1295        for my $featureObject (@featureObjects) {
1296            # Get the feature's location string. This may contain multiple actual locations.
1297            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1298            my @locationSegments = split /\s*,\s*/, $locations;
1299            # Loop through the locations.
1300            for my $locationSegment (@locationSegments) {
1301                # Construct an object for the location.
1302                my $locationObject = BasicLocation->new($locationSegment);
1303                # Merge the current segment's begin and end into the min and max.
1304                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1305                my ($beg, $end);
1306                if (exists $featureMap{$fid}) {
1307                    ($beg, $end) = @{$featureMap{$fid}};
1308                    $beg = $left if $left < $beg;
1309                    $end = $right if $right > $end;
1310                } else {
1311                    ($beg, $end) = ($left, $right);
1312                }
1313                $min = $beg if $beg < $min;
1314                $max = $end if $end > $max;
1315                # Store the feature's new extent back into the hash table.
1316                $featureMap{$fid} = [$beg, $end];
1317            }
1318        }
1319        # Now we must compute the list of the IDs for the features found. We start with a list
1320        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1321        # but the result of the sort will be the same.)
1322        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1323        # Now we sort by midpoint and yank out the feature IDs.
1324        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1325        # Return it along with the min and max.
1326        return (\@retVal, $min, $max);
1327    }
1328    
1329    =head3 GeneDataInRegion
1330    
1331        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1332    
1333    List the features which overlap a specified region in a contig.
1334    
1335    =over 4
1336    
1337    =item contigID
1338    
1339    ID of the contig containing the region of interest.
1340    
1341    =item start
1342    
1343    Offset of the first residue in the region of interest.
1344    
1345    =item stop
1346    
1347    Offset of the last residue in the region of interest.
1348    
1349    =item RETURN
1350    
1351    Returns a list of B<ERDBObjects> for the desired features. Each object will
1352    contain a B<Feature> record.
1353    
1354    =back
1355    
1356    =cut
1357    
1358    sub GeneDataInRegion {
1359        # Get the parameters.
1360        my ($self, $contigID, $start, $stop) = @_;
1361        # Get the maximum segment length.
1362        my $maximumSegmentLength = $self->MaxSegment;
1363        # Create a hash to receive the feature list. We use a hash so that we can eliminate
1364        # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1365        # ERDBObject from the query.
1366        my %featuresFound = ();
1367        # Create a table of parameters for the queries. Each query looks for features travelling in
1368          # 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,
1369          # 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
1370          # 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 923  Line 1373 
1373          # Loop through the query parameters.          # Loop through the query parameters.
1374          for my $parms (values %queryParms) {          for my $parms (values %queryParms) {
1375                  # Create the query.                  # Create the query.
1376                  my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1377                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1378                          $parms);                          $parms);
1379                  # Loop through the feature segments found.                  # Loop through the feature segments found.
1380                  while (my $segment = $query->Fetch) {                  while (my $segment = $query->Fetch) {
1381                          # Get the data about this segment.                          # Get the data about this segment.
1382                          my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1383                                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1384                          # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1385                          # this will be the case if the segment is the maximum length, so to fine-tune                          # this will be the case if the segment is the maximum length, so to fine-tune
1386                          # the results we insure that the inequality from the query holds using the actual                          # the results we insure that the inequality from the query holds using the actual
1387                          # length.                          # length.
1388                          my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1389                          if ($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.  
                                         $found = 1;  
                                 }  
                         }  
1390                          if ($found) {                          if ($found) {
1391                                  # Here we need to record the feature and update the minima and maxima. First,                  # Save this feature in the result list.
1392                                  # 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 < $min;  
1393                                  }                                  }
                                 if ($end > $loc2) {  
                                         $loc2 = $end;  
                                         $max = $end if $end > $max;  
                                 }  
                                 # Store the entry back into the hash table.  
                                 $featuresFound{$featureID} = [$loc1, $loc2];  
1394                          }                          }
1395                  }                  }
1396          }      # Return the ERDB objects for the features found.
1397          # Now we must compute the list of the IDs for the features found. We start with a list      return values %featuresFound;
         # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,  
         # but the result of the sort will be the same.)  
         my @list = map { [$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);  
1398  }  }
1399    
1400  =head3 FType  =head3 FType
1401    
1402  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1403    
1404  Return the type of a feature.  Return the type of a feature.
1405    
# Line 1013  Line 1429 
1429    
1430  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1431    
1432  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1433    
1434  Return the annotations of a feature.  Return the annotations of a feature.
1435    
# Line 1023  Line 1439 
1439    
1440  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1441    
1442    =item rawFlag
1443    
1444    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1445    will be returned in human-readable form.
1446    
1447  =item RETURN  =item RETURN
1448    
1449  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1450    
1451  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1452    
1453  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1454    
1455  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1456    
# Line 1041  Line 1462 
1462  #: Return Type @%;  #: Return Type @%;
1463  sub FeatureAnnotations {  sub FeatureAnnotations {
1464          # Get the parameters.          # Get the parameters.
1465          my ($self, $featureID) = @_;      my ($self, $featureID, $rawFlag) = @_;
1466          # 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.
1467          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1468                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1054  Line 1475 
1475                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1476                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1477                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1478            # Convert the time, if necessary.
1479            if (! $rawFlag) {
1480                $timeStamp = FriendlyTimestamp($timeStamp);
1481            }
1482                  # Assemble them into a hash.                  # Assemble them into a hash.
1483          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1484                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1485                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1486                  # Add it to the return list.                  # Add it to the return list.
1487                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1067  Line 1492 
1492    
1493  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1494    
1495  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1496    
1497  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
1498  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,
1499  It has the format "XXXX\nset XXXX function to\nYYYYY". In this instance, XXXX is the user ID  Functional assignments are described in the L</ParseAssignment> function. Its worth noting that
1500  and YYYYY is the functional assignment text. Its worth noting that we cannot filter on the content  we cannot filter on the content of the annotation itself because it's a text field; however,
1501  of the annotation itself because it's a text field; however, this is not a big problem because most  this is not a big problem because most features only have a small number of annotations.
1502  features only have a small number of annotations. Finally, if a single user has multiple  Finally, if a single user has multiple functional assignments, we will only keep the most
1503  functional assignments, we will only keep the most recent one.  recent one.
1504    
1505  =over 4  =over 4
1506    
# Line 1085  Line 1510 
1510    
1511  =item RETURN  =item RETURN
1512    
1513  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1514    
1515  =back  =back
1516    
# Line 1095  Line 1520 
1520          # Get the parameters.          # Get the parameters.
1521          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1522          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1523      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1524                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1525                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1526                                               'MadeAnnotation(from-link)']);
1527          # Declare the return hash.          # Declare the return hash.
1528          my %retVal;          my %retVal;
     # Declare a hash for insuring we only make one assignment per user.  
     my %timeHash = ();  
1529      # Now we sort the assignments by timestamp in reverse.      # Now we sort the assignments by timestamp in reverse.
1530      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1531          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1532      for my $annotation (@sortedQuery) {      for my $annotation (@sortedQuery) {
1533          # Get the annotation fields.          # Get the annotation fields.
1534          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text, $user) = @{$annotation};
1535                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1536                  my ($user, $function) = ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1537          if ($user && ! exists $timeHash{$user}) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1538              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1539              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
1540              # return hash.              # return hash.
1541                          $retVal{$function} = $user;              $retVal{$actualUser} = $function;
             # Insure we don't assign to this user again.  
             $timeHash{$user} = 1;  
1542                  }                  }
1543          }          }
1544          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1125  Line 1547 
1547    
1548  =head3 FunctionOf  =head3 FunctionOf
1549    
1550  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1551    
1552  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1553    
1554  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
1555  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
1556  assignment is a type of annotation. It has the format "XXXX\nset XXXX function to\nYYYYY". In this  assignment is taken from the B<Feature> or C<Annotation> table, depending.
 instance, XXXX is the user ID and YYYYY is the functional assignment text. Its worth noting that  
 we cannot filter on the content of the annotation itself because it's a text field; however, this  
 is not a big problem because most features only have a small number of annotations.  
1557    
1558  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
1559  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 1153  Line 1572 
1572    
1573  =item userID (optional)  =item userID (optional)
1574    
1575  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
1576  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1577    
1578  =item RETURN  =item RETURN
1579    
# Line 1171  Line 1590 
1590      my $retVal;      my $retVal;
1591      # Determine the ID type.      # Determine the ID type.
1592      if ($featureID =~ m/^fig\|/) {      if ($featureID =~ m/^fig\|/) {
1593          # Here we have a FIG feature ID. We must build the list of trusted          # Here we have a FIG feature ID.
1594          # users.          if (!$userID) {
1595                # Use the primary assignment.
1596                ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);
1597            } else {
1598                # We must build the list of trusted users.
1599          my %trusteeTable = ();          my %trusteeTable = ();
1600          # Check the user ID.          # Check the user ID.
1601          if (!$userID) {          if (!$userID) {
# Line 1194  Line 1617 
1617              }              }
1618          }          }
1619          # 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.
1620          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1621                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1622                                 [$featureID]);                                 [$featureID]);
1623          my $timeSelected = 0;          my $timeSelected = 0;
1624          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1625          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1626              # Get the annotation text.              # Get the annotation text.
1627              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);                  my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1628                                                             'Annotation(time)', 'MadeAnnotation(from-link)']);
1629              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1630              my ($user, $type, $function) = split(/\n/, $text);                  my ($actualUser, $function) = _ParseAssignment($user, $text);
1631              if ($type =~ m/^set $user function to$/i) {                  Trace("Assignment user is $actualUser, text is $function.") if T(4);
1632                    if ($actualUser) {
1633                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1634                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1635                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                      if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1636                      $retVal = $function;                      $retVal = $function;
1637                      $timeSelected = $time;                      $timeSelected = $time;
1638                  }                  }
1639              }              }
1640          }          }
1641            }
1642      } else {      } else {
1643          # 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
1644          # matter. We simply get the information from the External Alias Function          # matter. We simply get the information from the External Alias Function
# Line 1223  Line 1649 
1649          return $retVal;          return $retVal;
1650  }  }
1651    
1652    =head3 FunctionsOf
1653    
1654        my @functionList = $sprout->FunctionOf($featureID, $userID);
1655    
1656    Return the functional assignments of a particular feature.
1657    
1658    The functional assignment is handled differently depending on the type of feature. If
1659    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1660    assignment is a type of annotation. The format of an assignment is described in
1661    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1662    annotation itself because it's a text field; however, this is not a big problem because
1663    most features only have a small number of annotations.
1664    
1665    If the feature is B<not> identified by a FIG ID, then the functional assignment
1666    information is taken from the B<ExternalAliasFunc> table. If the table does
1667    not contain an entry for the feature, an empty list is returned.
1668    
1669    =over 4
1670    
1671    =item featureID
1672    
1673    ID of the feature whose functional assignments are desired.
1674    
1675    =item RETURN
1676    
1677    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1678    that user.
1679    
1680    =back
1681    
1682    =cut
1683    #: Return Type @@;
1684    sub FunctionsOf {
1685        # Get the parameters.
1686        my ($self, $featureID) = @_;
1687        # Declare the return value.
1688        my @retVal = ();
1689        # Determine the ID type.
1690        if ($featureID =~ m/^fig\|/) {
1691            # Here we have a FIG feature ID. We must build the list of trusted
1692            # users.
1693            my %trusteeTable = ();
1694            # Build a query for all of the feature's annotations, sorted by date.
1695            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1696                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1697                                   [$featureID]);
1698            my $timeSelected = 0;
1699            # Loop until we run out of annotations.
1700            while (my $annotation = $query->Fetch()) {
1701                # Get the annotation text.
1702                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1703                                                                'Annotation(time)',
1704                                                                'MadeAnnotation(user)']);
1705                # Check to see if this is a functional assignment for a trusted user.
1706                my ($actualUser, $function) = _ParseAssignment($user, $text);
1707                if ($actualUser) {
1708                    # Here it is a functional assignment.
1709                    push @retVal, [$actualUser, $function];
1710                }
1711            }
1712        } else {
1713            # Here we have a non-FIG feature ID. In this case the user ID does not
1714            # matter. We simply get the information from the External Alias Function
1715            # table.
1716            my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1717                                                     ['ExternalAliasFunc(func)']);
1718            push @retVal, map { ['master', $_] } @assignments;
1719        }
1720        # Return the assignments found.
1721        return @retVal;
1722    }
1723    
1724  =head3 BBHList  =head3 BBHList
1725    
1726  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1727    
1728  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
1729  on a specified target genome.  on a specified target genome.
# Line 1242  Line 1740 
1740    
1741  =item RETURN  =item RETURN
1742    
1743  Returns a reference to a hash that maps the IDs of the incoming features to the IDs of  Returns a reference to a hash that maps the IDs of the incoming features to the best hits
1744  their best hits.  on the target genome.
1745    
1746  =back  =back
1747    
# Line 1256  Line 1754 
1754          my %retVal = ();          my %retVal = ();
1755          # Loop through the incoming features.          # Loop through the incoming features.
1756          for my $featureID (@{$featureList}) {          for my $featureID (@{$featureList}) {
1757                  # Create a query to get the feature's best hit.          # Ask the server for the feature's best hit.
1758                  my $query = $self->Get(['IsBidirectionalBestHitOf'],          my @bbhData = FIGRules::BBHData($featureID);
1759                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",          # Peel off the BBHs found.
1760                                                             [$featureID, $genomeID]);          my @found = ();
1761                  # Look for the best hit.          for my $bbh (@bbhData) {
1762                  my $bbh = $query->Fetch;              my $fid = $bbh->[0];
1763                  if ($bbh) {              my $bbGenome = $self->GenomeOf($fid);
1764                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              if ($bbGenome eq $genomeID) {
1765                          $retVal{$featureID} = $targetFeature;                  push @found, $fid;
1766                }
1767                  }                  }
1768            $retVal{$featureID} = \@found;
1769          }          }
1770          # Return the mapping.          # Return the mapping.
1771          return \%retVal;          return \%retVal;
1772  }  }
1773    
1774  =head3 FeatureAliases  =head3 SimList
1775    
1776  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my %similarities = $sprout->SimList($featureID, $count);
1777    
1778  Return a list of the aliases for a specified feature.  Return a list of the similarities to the specified feature.
1779    
1780    This method just returns the bidirectional best hits for performance reasons.
1781    
1782  =over 4  =over 4
1783    
1784  =item featureID  =item featureID
1785    
1786  ID of the feature whose aliases are desired.  ID of the feature whose similarities are desired.
1787    
1788  =item RETURN  =item count
1789    
1790  Returns a list of the feature's aliases. If the feature is not found or has no aliases, it will  Maximum number of similar features to be returned, or C<0> to return them all.
 return an empty list.  
1791    
1792  =back  =back
1793    
1794  =cut  =cut
1795  #: Return Type @;  #: Return Type %;
1796  sub FeatureAliases {  sub SimList {
1797          # Get the parameters.          # Get the parameters.
1798          my ($self, $featureID) = @_;      my ($self, $featureID, $count) = @_;
1799          # Get the desired feature's aliases      # Ask for the best hits.
1800          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      my @lists = FIGRules::BBHData($featureID);
1801        # Create the return value.
1802        my %retVal = ();
1803        for my $tuple (@lists) {
1804            $retVal{$tuple->[0]} = $tuple->[1];
1805        }
1806        # Return the result.
1807        return %retVal;
1808    }
1809    
1810    =head3 IsComplete
1811    
1812        my $flag = $sprout->IsComplete($genomeID);
1813    
1814    Return TRUE if the specified genome is complete, else FALSE.
1815    
1816    =over 4
1817    
1818    =item genomeID
1819    
1820    ID of the genome whose completeness status is desired.
1821    
1822    =item RETURN
1823    
1824    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1825    not found.
1826    
1827    =back
1828    
1829    =cut
1830    #: Return Type $;
1831    sub IsComplete {
1832        # Get the parameters.
1833        my ($self, $genomeID) = @_;
1834        # Declare the return variable.
1835        my $retVal;
1836        # Get the genome's data.
1837        my $genomeData = $self->GetEntity('Genome', $genomeID);
1838        if ($genomeData) {
1839            # The genome exists, so get the completeness flag.
1840            $retVal = $genomeData->PrimaryValue('Genome(complete)');
1841        }
1842        # Return the result.
1843        return $retVal;
1844    }
1845    
1846    =head3 FeatureAliases
1847    
1848        my @aliasList = $sprout->FeatureAliases($featureID);
1849    
1850    Return a list of the aliases for a specified feature.
1851    
1852    =over 4
1853    
1854    =item featureID
1855    
1856    ID of the feature whose aliases are desired.
1857    
1858    =item RETURN
1859    
1860    Returns a list of the feature's aliases. If the feature is not found or has no aliases, it will
1861    return an empty list.
1862    
1863    =back
1864    
1865    =cut
1866    #: Return Type @;
1867    sub FeatureAliases {
1868        # Get the parameters.
1869        my ($self, $featureID) = @_;
1870        # Get the desired feature's aliases
1871        my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
1872          # Return the result.          # Return the result.
1873          return @retVal;          return @retVal;
1874  }  }
1875    
1876  =head3 GenomeOf  =head3 GenomeOf
1877    
1878  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $genomeID = $sprout->GenomeOf($featureID);
1879    
1880  Return the genome that contains a specified feature.  Return the genome that contains a specified feature or contig.
1881    
1882  =over 4  =over 4
1883    
1884  =item featureID  =item featureID
1885    
1886  ID of the feature whose genome is desired.  ID of the feature or contig whose genome is desired.
1887    
1888  =item RETURN  =item RETURN
1889    
1890  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
1891  an undefined value.  found, returns an undefined value.
1892    
1893  =back  =back
1894    
# Line 1325  Line 1897 
1897  sub GenomeOf {  sub GenomeOf {
1898          # Get the parameters.          # Get the parameters.
1899          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]);  
1900          # Declare the return value.          # Declare the return value.
1901          my $retVal;          my $retVal;
1902          # Get the genome ID.      # Parse the genome ID from the feature ID.
1903          if (my $relationship = $query->Fetch()) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
1904                  ($retVal) = $relationship->Value('HasContig(from-link)');          $retVal = $1;
1905        } else {
1906            Confess("Invalid feature ID $featureID.");
1907          }          }
1908          # Return the value found.          # Return the value found.
1909          return $retVal;          return $retVal;
# Line 1339  Line 1911 
1911    
1912  =head3 CoupledFeatures  =head3 CoupledFeatures
1913    
1914  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
1915    
1916  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
1917  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 1361  Line 1933 
1933  sub CoupledFeatures {  sub CoupledFeatures {
1934          # Get the parameters.          # Get the parameters.
1935          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1936          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      # Ask the coupling server for the data.
1937          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
1938          # (B,A) will also be found.      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
1939          my $query = $self->Get(['IsClusteredOnChromosomeWith'],      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
1940                                                     "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);      # Form them into a hash.
         # This value will be set to TRUE if we find at least one coupled feature.  
         my $found = 0;  
         # Create the return hash.  
1941          my %retVal = ();          my %retVal = ();
1942          # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
1943          while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
1944                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          my ($featureID2, $score) = @{$pair};
1945                                                                      'IsClusteredOnChromosomeWith(score)']);          # Only proceed if the feature is in NMPDR.
1946                  $retVal{$otherFeatureID} = $score;          if ($self->_CheckFeature($featureID2)) {
1947                  $found = 1;              $retVal{$featureID2} = $score;
1948            }
1949          }          }
1950          # Functional coupling is reflexive. If we found at least one coupled feature, we must add          # Functional coupling is reflexive. If we found at least one coupled feature, we must add
1951          # the incoming feature as well.          # the incoming feature as well.
1952          if ($found) {      if (keys %retVal) {
1953                  $retVal{$featureID} = 9999;                  $retVal{$featureID} = 9999;
1954      }      }
1955          # Return the hash.          # Return the hash.
1956          return %retVal;          return %retVal;
1957  }  }
1958    
1959  =head3 GetEntityTypes  =head3 CouplingEvidence
1960    
1961        my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
1962    
1963    Return the evidence for a functional coupling.
1964    
1965    A pair of features is considered evidence of a coupling between two other
1966    features if they occur close together on a contig and both are similar to
1967    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1968    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1969    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1970    similar to B<A2>.
1971    
1972    The score of a coupling is determined by the number of pieces of evidence
1973    that are considered I<representative>. If several evidence items belong to
1974    a group of genomes that are close to each other, only one of those items
1975    is considered representative. The other evidence items are presumed to be
1976    there because of the relationship between the genomes rather than because
1977    the two proteins generated by the features have a related functionality.
1978    
1979    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1980    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1981    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1982    and FALSE otherwise.
1983    
1984    =over 4
1985    
1986    =item peg1
1987    
1988    ID of the feature of interest.
1989    
1990    =item peg2
1991    
1992    ID of a feature functionally coupled to the feature of interest.
1993    
1994    =item RETURN
1995    
1996    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1997    of interest, a feature similar to the functionally coupled feature, and a flag
1998    that is TRUE for a representative piece of evidence and FALSE otherwise.
1999    
2000    =back
2001    
2002    =cut
2003    #: Return Type @@;
2004    sub CouplingEvidence {
2005        # Get the parameters.
2006        my ($self, $peg1, $peg2) = @_;
2007        # Declare the return variable.
2008        my @retVal = ();
2009        # Get the coupling and evidence data.
2010        my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
2011        # Loop through the raw data, saving the ones that are in NMPDR genomes.
2012        for my $rawTuple (@rawData) {
2013            if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
2014                push @retVal, $rawTuple;
2015            }
2016        }
2017        # Return the result.
2018        return @retVal;
2019    }
2020    
2021    =head3 GetSynonymGroup
2022    
2023        my $id = $sprout->GetSynonymGroup($fid);
2024    
2025    Return the synonym group name for the specified feature.
2026    
2027    =over 4
2028    
2029    =item fid
2030    
2031    ID of the feature whose synonym group is desired.
2032    
2033    =item RETURN
2034    
2035  C<< my @entityList = $sprout->GetEntityTypes(); >>  The name of the synonym group to which the feature belongs. If the feature does
2036    not belong to a synonym group, the feature ID itself is returned.
2037    
2038  Return the list of supported entity types.  =back
2039    
2040  =cut  =cut
2041  #: Return Type @;  
2042  sub GetEntityTypes {  sub GetSynonymGroup {
2043          # Get the parameters.          # Get the parameters.
2044          my ($self) = @_;      my ($self, $fid) = @_;
2045          # Get the underlying database object.      # Declare the return variable.
2046          my $erdb = $self->{_erdb};      my $retVal;
2047          # Get its entity type list.      # Find the synonym group.
2048          my @retVal = $erdb->GetEntityTypes();      my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?",
2049                                       [$fid], 'IsSynonymGroupFor(from-link)');
2050        # Check to see if we found anything.
2051        if (@groups) {
2052            $retVal = $groups[0];
2053        } else {
2054            $retVal = $fid;
2055        }
2056        # Return the result.
2057        return $retVal;
2058    }
2059    
2060    =head3 GetBoundaries
2061    
2062        my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2063    
2064    Determine the begin and end boundaries for the locations in a list. All of the
2065    locations must belong to the same contig and have mostly the same direction in
2066    order for this method to produce a meaningful result. The resulting
2067    begin/end pair will contain all of the bases in any of the locations.
2068    
2069    =over 4
2070    
2071    =item locList
2072    
2073    List of locations to process.
2074    
2075    =item RETURN
2076    
2077    Returns a 3-tuple consisting of the contig ID, the beginning boundary,
2078    and the ending boundary. The beginning boundary will be left of the
2079    end for mostly-forward locations and right of the end for mostly-backward
2080    locations.
2081    
2082    =back
2083    
2084    =cut
2085    
2086    sub GetBoundaries {
2087        # Get the parameters.
2088        my ($self, @locList) = @_;
2089        # Set up the counters used to determine the most popular direction.
2090        my %counts = ( '+' => 0, '-' => 0 );
2091        # Get the last location and parse it.
2092        my $locObject = BasicLocation->new(pop @locList);
2093        # Prime the loop with its data.
2094        my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right);
2095        # Count its direction.
2096        $counts{$locObject->Dir}++;
2097        # Loop through the remaining locations. Note that in most situations, this loop
2098        # will not iterate at all, because most of the time we will be dealing with a
2099        # singleton list.
2100        for my $loc (@locList) {
2101            # Create a location object.
2102            my $locObject = BasicLocation->new($loc);
2103            # Count the direction.
2104            $counts{$locObject->Dir}++;
2105            # Get the left end and the right end.
2106            my $left = $locObject->Left;
2107            my $right = $locObject->Right;
2108            # Merge them into the return variables.
2109            if ($left < $beg) {
2110                $beg = $left;
2111            }
2112            if ($right > $end) {
2113                $end = $right;
2114            }
2115        }
2116        # If the most common direction is reverse, flip the begin and end markers.
2117        if ($counts{'-'} > $counts{'+'}) {
2118            ($beg, $end) = ($end, $beg);
2119        }
2120        # Return the result.
2121        return ($contig, $beg, $end);
2122  }  }
2123    
2124  =head3 ReadFasta  =head3 ReadFasta
2125    
2126  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2127    
2128  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
2129  one or more lines of data. The first line begins with a > character and contains an ID.  one or more lines of data. The first line begins with a > character and contains an ID.
# Line 1447  Line 2165 
2165                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
2166                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
2167                          if ($id) {                          if ($id) {
2168                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
2169                          }                          }
2170                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
2171                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
2172                  } else {                  } else {
2173                          # Here we have a data line, so we add it to the sequence accumulator.                          # Here we have a data line, so we add it to the sequence accumulator.
2174                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
2175                # case.
2176                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
2177                          $sequence .= $1;                          $sequence .= $1;
2178                  }                  }
2179          }          }
2180          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
2181          if ($sequence) {          if ($sequence) {
2182                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
2183          }          }
2184        # Close the file.
2185        close FASTAFILE;
2186          # Return the hash constructed from the file.          # Return the hash constructed from the file.
2187          return %retVal;          return %retVal;
2188  }  }
2189    
2190  =head3 FormatLocations  =head3 FormatLocations
2191    
2192  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2193    
2194  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
2195  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 1533  Line 2254 
2254    
2255  =head3 DumpData  =head3 DumpData
2256    
2257  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2258    
2259  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.
2260    
# Line 1545  Line 2266 
2266          # Get the data directory name.          # Get the data directory name.
2267          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
2268          # Dump the relations.          # Dump the relations.
2269          $self->{_erdb}->DumpRelations($outputDirectory);      $self->DumpRelations($outputDirectory);
2270  }  }
2271    
2272  =head3 XMLFileName  =head3 XMLFileName
2273    
2274  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2275    
2276  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2277    
# Line 1561  Line 2282 
2282          return $self->{_xmlName};          return $self->{_xmlName};
2283  }  }
2284    
2285    =head3 GetGenomeNameData
2286    
2287        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2288    
2289    Return the genus, species, and unique characterization for a genome. This
2290    is similar to L</GenusSpecies>, with the exception that it returns the
2291    values in three seperate fields.
2292    
2293    =over 4
2294    
2295    =item genomeID
2296    
2297    ID of the genome whose name data is desired.
2298    
2299    =item RETURN
2300    
2301    Returns a three-element list, consisting of the genus, species, and strain
2302    of the specified genome. If the genome is not found, an error occurs.
2303    
2304    =back
2305    
2306    =cut
2307    
2308    sub GetGenomeNameData {
2309        # Get the parameters.
2310        my ($self, $genomeID) = @_;
2311        # Get the desired values.
2312        my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>
2313                                                                [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);
2314        # Throw an error if they were not found.
2315        if (! defined $genus) {
2316            Confess("Genome $genomeID not found in database.");
2317        }
2318        # Return the results.
2319        return ($genus, $species, $strain);
2320    }
2321    
2322    =head3 GetGenomeByNameData
2323    
2324        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2325    
2326    Return a list of the IDs of the genomes with the specified genus,
2327    species, and strain. In almost every case, there will be either zero or
2328    one IDs returned; however, two or more IDs could be returned if there are
2329    multiple versions of the genome in the database.
2330    
2331    =over 4
2332    
2333    =item genus
2334    
2335    Genus of the desired genome.
2336    
2337    =item species
2338    
2339    Species of the desired genome.
2340    
2341    =item strain
2342    
2343    Strain (unique characterization) of the desired genome. This may be an empty
2344    string, in which case it is presumed that the desired genome has no strain
2345    specified.
2346    
2347    =item RETURN
2348    
2349    Returns a list of the IDs of the genomes having the specified genus, species, and
2350    strain.
2351    
2352    =back
2353    
2354    =cut
2355    
2356    sub GetGenomeByNameData {
2357        # Get the parameters.
2358        my ($self, $genus, $species, $strain) = @_;
2359        # Try to find the genomes.
2360        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2361                                    [$genus, $species, $strain], 'Genome(id)');
2362        # Return the result.
2363        return @retVal;
2364    }
2365    
2366  =head3 Insert  =head3 Insert
2367    
2368  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2369    
2370  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
2371  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 1572  Line 2374 
2374  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
2375  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>.
2376    
2377  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']});
2378    
2379  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
2380  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>.
2381    
2382  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>      $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2383    
2384  =over 4  =over 4
2385    
# Line 1597  Line 2399 
2399          # Get the parameters.          # Get the parameters.
2400          my ($self, $objectType, $fieldHash) = @_;          my ($self, $objectType, $fieldHash) = @_;
2401          # Call the underlying method.          # Call the underlying method.
2402          $self->{_erdb}->InsertObject($objectType, $fieldHash);      $self->InsertObject($objectType, $fieldHash);
2403  }  }
2404    
2405  =head3 Annotate  =head3 Annotate
2406    
2407  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2408    
2409  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
2410  specified feature and user.  specified feature and user.
# Line 1656  Line 2458 
2458    
2459  =head3 AssignFunction  =head3 AssignFunction
2460    
2461  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2462    
2463  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
2464  format is "XXXX\nset XXXX function to\nYYYYY" where XXXX is the feature type and YYYY is the functional  format is described in L</ParseAssignment>.
 assignment text.  
2465    
2466  =over 4  =over 4
2467    
# Line 1670  Line 2471 
2471    
2472  =item user  =item user
2473    
2474  Name of the user making the assignment. This is frequently a group name, like C<kegg> or C<fig>.  Name of the user group making the assignment, such as C<kegg> or C<fig>.
2475    
2476  =item function  =item function
2477    
2478  Text of the function being assigned.  Text of the function being assigned.
2479    
2480    =item assigningUser (optional)
2481    
2482    Name of the individual user making the assignment. If omitted, defaults to the user group.
2483    
2484  =item RETURN  =item RETURN
2485    
2486  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1686  Line 2491 
2491  #: Return Type $;  #: Return Type $;
2492  sub AssignFunction {  sub AssignFunction {
2493          # Get the parameters.          # Get the parameters.
2494          my ($self, $featureID, $user, $function) = @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
2495        # Default the assigning user.
2496        if (! $assigningUser) {
2497            $assigningUser = $user;
2498        }
2499          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
2500          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
2501          # Get the current time.          # Get the current time.
2502          my $now = time;          my $now = time;
2503          # Declare the return variable.          # Declare the return variable.
# Line 1709  Line 2518 
2518    
2519  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2520    
2521  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2522    
2523  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
2524  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 1743  Line 2552 
2552                  push @retVal, $mappedAlias;                  push @retVal, $mappedAlias;
2553          } else {          } else {
2554                  # 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.
2555                  @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2556          }          }
2557          # Return the result.          # Return the result.
2558          return @retVal;          return @retVal;
2559  }  }
2560    
 =head3 Exists  
   
 C<< my $found = $sprout->Exists($entityName, $entityID); >>  
   
 Return TRUE if an entity exists, else FALSE.  
   
 =over 4  
   
 =item entityName  
   
 Name of the entity type (e.g. C<Feature>) relevant to the existence check.  
   
 =item entityID  
   
 ID of the entity instance whose existence is to be checked.  
   
 =item RETURN  
   
 Returns TRUE if the entity instance exists, else FALSE.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub Exists {  
         # Get the parameters.  
         my ($self, $entityName, $entityID) = @_;  
         # Check for the entity instance.  
         my $testInstance = $self->GetEntity($entityName, $entityID);  
         # Return an existence indicator.  
         my $retVal = ($testInstance ? 1 : 0);  
         return $retVal;  
 }  
   
2561  =head3 FeatureTranslation  =head3 FeatureTranslation
2562    
2563  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2564    
2565  Return the translation of a feature.  Return the translation of a feature.
2566    
# Line 1813  Line 2588 
2588    
2589  =head3 Taxonomy  =head3 Taxonomy
2590    
2591  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2592    
2593  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
2594  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>,
2595  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2596    
2597  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2598    
2599  =over 4  =over 4
2600    
# Line 1854  Line 2629 
2629    
2630  =head3 CrudeDistance  =head3 CrudeDistance
2631    
2632  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2633    
2634  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
2635  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 1906  Line 2681 
2681    
2682  =head3 RoleName  =head3 RoleName
2683    
2684  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2685    
2686  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
2687  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 1940  Line 2715 
2715    
2716  =head3 RoleDiagrams  =head3 RoleDiagrams
2717    
2718  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2719    
2720  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2721    
# Line 1968  Line 2743 
2743          return @retVal;          return @retVal;
2744  }  }
2745    
2746    =head3 GetProperties
2747    
2748        my @list = $sprout->GetProperties($fid, $key, $value, $url);
2749    
2750    Return a list of the properties with the specified characteristics.
2751    
2752    Properties are the Sprout analog of the FIG attributes. The call is
2753    passed directly to the CustomAttributes or RemoteCustomAttributes object
2754    contained in this object.
2755    
2756    This method returns a series of tuples that match the specified criteria. Each tuple
2757    will contain an object ID, a key, and one or more values. The parameters to this
2758    method therefore correspond structurally to the values expected in each tuple. In
2759    addition, you can ask for a generic search by suffixing a percent sign (C<%>) to any
2760    of the parameters. So, for example,
2761    
2762        my @attributeList = $sprout->GetProperties('fig|100226.1.peg.1004', 'structure%', 1, 2);
2763    
2764    would return something like
2765    
2766        ['fig}100226.1.peg.1004', 'structure', 1, 2]
2767        ['fig}100226.1.peg.1004', 'structure1', 1, 2]
2768        ['fig}100226.1.peg.1004', 'structure2', 1, 2]
2769        ['fig}100226.1.peg.1004', 'structureA', 1, 2]
2770    
2771    Use of C<undef> in any position acts as a wild card (all values). You can also specify
2772    a list reference in the ID column. Thus,
2773    
2774        my @attributeList = $sprout->GetProperties(['100226.1', 'fig|100226.1.%'], 'PUBMED');
2775    
2776    would get the PUBMED attribute data for Streptomyces coelicolor A3(2) and all its
2777    features.
2778    
2779    In addition to values in multiple sections, a single attribute key can have multiple
2780    values, so even
2781    
2782        my @attributeList = $sprout->GetProperties($peg, 'virulent');
2783    
2784    which has no wildcard in the key or the object ID, may return multiple tuples.
2785    
2786    =over 4
2787    
2788    =item objectID
2789    
2790    ID of object whose attributes are desired. If the attributes are desired for multiple
2791    objects, this parameter can be specified as a list reference. If the attributes are
2792    desired for all objects, specify C<undef> or an empty string. Finally, you can specify
2793    attributes for a range of object IDs by putting a percent sign (C<%>) at the end.
2794    
2795    =item key
2796    
2797    Attribute key name. A value of C<undef> or an empty string will match all
2798    attribute keys. If the values are desired for multiple keys, this parameter can be
2799    specified as a list reference. Finally, you can specify attributes for a range of
2800    keys by putting a percent sign (C<%>) at the end.
2801    
2802    =item values
2803    
2804    List of the desired attribute values, section by section. If C<undef>
2805    or an empty string is specified, all values in that section will match. A
2806    generic match can be requested by placing a percent sign (C<%>) at the end.
2807    In that case, all values that match up to and not including the percent sign
2808    will match. You may also specify a regular expression enclosed
2809    in slashes. All values that match the regular expression will be returned. For
2810    performance reasons, only values have this extra capability.
2811    
2812    =item RETURN
2813    
2814    Returns a list of tuples. The first element in the tuple is an object ID, the
2815    second is an attribute key, and the remaining elements are the sections of
2816    the attribute value. All of the tuples will match the criteria set forth in
2817    the parameter list.
2818    
2819    =back
2820    
2821    =cut
2822    
2823    sub GetProperties {
2824        # Get the parameters.
2825        my ($self, @parms) = @_;
2826        # Declare the return variable.
2827        my @retVal = $self->{_ca}->GetAttributes(@parms);
2828        # Return the result.
2829        return @retVal;
2830    }
2831    
2832  =head3 FeatureProperties  =head3 FeatureProperties
2833    
2834  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2835    
2836  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
2837  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
2838  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
2839  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
2840  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.  
2841    
2842  =over 4  =over 4
2843    
# Line 1988  Line 2847 
2847    
2848  =item RETURN  =item RETURN
2849    
2850  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.  
2851    
2852  =back  =back
2853    
# Line 1999  Line 2857 
2857          # Get the parameters.          # Get the parameters.
2858          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2859          # Get the properties.          # Get the properties.
2860          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->{_ca}->GetAttributes($featureID);
2861                                                          ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2862                                                           'HasProperty(evidence)']);      my @retVal = ();
2863        for my $attributeRow (@attributes) {
2864            shift @{$attributeRow};
2865            push @retVal, $attributeRow;
2866        }
2867          # Return the resulting list.          # Return the resulting list.
2868          return @retVal;          return @retVal;
2869  }  }
2870    
2871  =head3 DiagramName  =head3 DiagramName
2872    
2873  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2874    
2875  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2876    
# Line 2034  Line 2896 
2896          return $retVal;          return $retVal;
2897  }  }
2898    
2899    =head3 PropertyID
2900    
2901        my $id = $sprout->PropertyID($propName, $propValue);
2902    
2903    Return the ID of the specified property name and value pair, if the
2904    pair exists. Only a small subset of the FIG attributes are stored as
2905    Sprout properties, mostly for use in search optimization.
2906    
2907    =over 4
2908    
2909    =item propName
2910    
2911    Name of the desired property.
2912    
2913    =item propValue
2914    
2915    Value expected for the desired property.
2916    
2917    =item RETURN
2918    
2919    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2920    
2921    =back
2922    
2923    =cut
2924    
2925    sub PropertyID {
2926        # Get the parameters.
2927        my ($self, $propName, $propValue) = @_;
2928        # Try to find the ID.
2929        my ($retVal) = $self->GetFlat(['Property'],
2930                                      "Property(property-name) = ? AND Property(property-value) = ?",
2931                                      [$propName, $propValue], 'Property(id)');
2932        # Return the result.
2933        return $retVal;
2934    }
2935    
2936  =head3 MergedAnnotations  =head3 MergedAnnotations
2937    
2938  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2939    
2940  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2941  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2085  Line 2984 
2984    
2985  =head3 RoleNeighbors  =head3 RoleNeighbors
2986    
2987  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
2988    
2989  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
2990  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 2128  Line 3027 
3027    
3028  =head3 FeatureLinks  =head3 FeatureLinks
3029    
3030  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
3031    
3032  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
3033  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 2159  Line 3058 
3058    
3059  =head3 SubsystemsOf  =head3 SubsystemsOf
3060    
3061  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3062    
3063  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
3064  to the role the feature performs.  to the roles the feature performs.
3065    
3066  =over 4  =over 4
3067    
# Line 2172  Line 3071 
3071    
3072  =item RETURN  =item RETURN
3073    
3074  Returns a hash mapping all the feature's subsystems to the feature's role.  Returns a hash mapping all the feature's subsystems to a list of the feature's roles.
3075    
3076  =back  =back
3077    
3078  =cut  =cut
3079  #: Return Type %;  #: Return Type %@;
3080  sub SubsystemsOf {  sub SubsystemsOf {
3081          # Get the parameters.          # Get the parameters.
3082          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
3083          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
3084          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
3085                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
3086                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
3087          # Create the return value.          # Create the return value.
3088          my %retVal = ();          my %retVal = ();
3089        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
3090        # in two spreadsheet cells.
3091        my %dupHash = ();
3092          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
3093          for my $record (@subsystems) {          for my $record (@subsystems) {
3094                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
3095            my ($subsys, $role) = @{$record};
3096            # Insure it's the first time for both.
3097            my $dupKey = "$subsys\n$role";
3098            if (! exists $dupHash{"$subsys\n$role"}) {
3099                $dupHash{$dupKey} = 1;
3100                push @{$retVal{$subsys}}, $role;
3101            }
3102          }          }
3103          # Return the hash.          # Return the hash.
3104          return %retVal;          return %retVal;
3105  }  }
3106    
3107  =head3 RelatedFeatures  =head3 SubsystemList
3108    
3109  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @subsystems = $sprout->SubsystemList($featureID);
3110    
3111  Return a list of the features which are bi-directional best hits of the specified feature and  Return a list containing the names of the subsystems in which the specified
3112  have been assigned the specified function by the specified user. If no such features exists,  feature participates. Unlike L</SubsystemsOf>, this method only returns the
3113  an empty list will be returned.  subsystem names, not the roles.
3114    
3115    =over 4
3116    
3117    =item featureID
3118    
3119    ID of the feature whose subsystem names are desired.
3120    
3121    =item RETURN
3122    
3123    Returns a list of the names of the subsystems in which the feature participates.
3124    
3125    =back
3126    
3127    =cut
3128    #: Return Type @;
3129    sub SubsystemList {
3130        # Get the parameters.
3131        my ($self, $featureID) = @_;
3132        # Get the list of names.
3133        my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?",
3134                                    [$featureID], 'HasRoleInSubsystem(to-link)');
3135        # Return the result, sorted.
3136        return sort @retVal;
3137    }
3138    
3139    =head3 GenomeSubsystemData
3140    
3141        my %featureData = $sprout->GenomeSubsystemData($genomeID);
3142    
3143    Return a hash mapping genome features to their subsystem roles.
3144    
3145    =over 4
3146    
3147    =item genomeID
3148    
3149    ID of the genome whose subsystem feature map is desired.
3150    
3151    =item RETURN
3152    
3153    Returns a hash mapping each feature of the genome to a list of 2-tuples. Eacb
3154    2-tuple contains a subsystem name followed by a role ID.
3155    
3156    =back
3157    
3158    =cut
3159    
3160    sub GenomeSubsystemData {
3161        # Get the parameters.
3162        my ($self, $genomeID) = @_;
3163        # Declare the return variable.
3164        my %retVal = ();
3165        # Get a list of the genome features that participate in subsystems. For each
3166        # feature we get its spreadsheet cells and the corresponding roles.
3167        my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'],
3168                                 "HasFeature(from-link) = ?", [$genomeID],
3169                                 ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']);
3170        # Now we get a list of the spreadsheet cells and their associated subsystems. Subsystems
3171        # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the
3172        # list. We use it at the beginning to get all the spreadsheet cells for the genome and
3173        # again at the end to filter out participation in subsystems with a negative variant code.
3174        my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'],
3175                                     "IsGenomeOf(from-link) = ? AND ParticipatesIn(variant-code) >= 0 AND ParticipatesIn(from-link) = ?",
3176                                     [$genomeID, $genomeID], ['HasSSCell(to-link)', 'HasSSCell(from-link)']);
3177        # Now "@roleData" lists the spreadsheet cell and role for each of the genome's features.
3178        # "@cellData" lists the subsystem name for each of the genome's spreadsheet cells. We
3179        # link these two lists together to create the result. First, we want a hash mapping
3180        # spreadsheet cells to subsystem names.
3181        my %subHash = map { $_->[0] => $_->[1] } @cellData;
3182        # We loop through @cellData to build the hash.
3183        for my $roleEntry (@roleData) {
3184            # Get the data for this feature and cell.
3185            my ($fid, $cellID, $role) = @{$roleEntry};
3186            # Check for a subsystem name.
3187            my $subsys = $subHash{$cellID};
3188            if ($subsys) {
3189                # Insure this feature has an entry in the return hash.
3190                if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3191                # Merge in this new data.
3192                push @{$retVal{$fid}}, [$subsys, $role];
3193            }
3194        }
3195        # Return the result.
3196        return %retVal;
3197    }
3198    
3199    =head3 RelatedFeatures
3200    
3201        my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
3202    
3203    Return a list of the features which are bi-directional best hits of the specified feature and
3204    have been assigned the specified function by the specified user. If no such features exists,
3205    an empty list will be returned.
3206    
3207  =over 4  =over 4
3208    
# Line 2230  Line 3231 
3231          # Get the parameters.          # Get the parameters.
3232          my ($self, $featureID, $function, $userID) = @_;          my ($self, $featureID, $function, $userID) = @_;
3233          # 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.
3234          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);
                                                                          "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],  
                                                                          'IsBidirectionalBestHitOf(to-link)');  
3235          # 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
3236          # functional assignment.          # functional assignment.
3237          my @retVal = ();          my @retVal = ();
# Line 2250  Line 3249 
3249    
3250  =head3 TaxonomySort  =head3 TaxonomySort
3251    
3252  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3253    
3254  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a list formed by sorting the specified features by the taxonomy of the containing
3255  genome. This will cause genomes from similar organisms to float close to each other.  genome. This will cause genomes from similar organisms to float close to each other.
# Line 2285  Line 3284 
3284                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3285                                                                                  [$fid], 'Genome(taxonomy)');                                                                                  [$fid], 'Genome(taxonomy)');
3286                  # Add this feature to the hash buffer.                  # Add this feature to the hash buffer.
3287          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);          push @{$hashBuffer{$taxonomy}}, $fid;
3288          }          }
3289          # Sort the keys and get the elements.          # Sort the keys and get the elements.
3290          my @retVal = ();          my @retVal = ();
# Line 2296  Line 3295 
3295          return @retVal;          return @retVal;
3296  }  }
3297    
 =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) = @_;  
         # Create the query.  
         my $query = $self->Get($objectNames, $filterClause, $parameterList);  
         # Set up a counter of the number of records read.  
         my $fetched = 0;  
         # Insure the counter has a value.  
         if (!defined $count) {  
                 $count = 0;  
         }  
         # Loop through the records returned, extracting the fields. Note that if the  
         # counter is non-zero, we stop when the number of records read hits the count.  
         my @retVal = ();  
         while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {  
                 my @rowData = $row->Values($fields);  
                 push @retVal, \@rowData;  
                 $fetched++;  
         }  
         # Return the resulting list.  
         return @retVal;  
 }  
   
 =head3 GetFlat  
   
 C<< my @list = $sprout->GetFlat(\@objectNames, $filterClause, $parameterList, $field); >>  
   
 This is a variation of L</GetAll> that asks for only a single field per record and  
 returns a single flattened list.  
   
 =over 4  
   
 =item objectNames  
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
   
 =item field  
   
 Name of the field to be used to get the elements of the list returned.  
   
 =item RETURN  
   
 Returns a list of values.  
   
 =back  
   
 =cut  
 #: Return Type @;  
 sub GetFlat {  
         # Get the parameters.  
         my ($self, $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;  
 }  
   
3298  =head3 Protein  =head3 Protein
3299    
3300  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3301    
3302  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3303    
# Line 2500  Line 3367 
3367          # Loop through the input triples.          # Loop through the input triples.
3368          my $n = length $sequence;          my $n = length $sequence;
3369          for (my $i = 0; $i < $n; $i += 3) {          for (my $i = 0; $i < $n; $i += 3) {
3370                  # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3371                  my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3372            my $triple = uc substr($sequence, $i, 3);
3373                  # Translate it using the table.                  # Translate it using the table.
3374                  my $protein = "X";                  my $protein = "X";
3375                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 2515  Line 3383 
3383    
3384  =head3 LoadInfo  =head3 LoadInfo
3385    
3386  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3387    
3388  Return the name of the directory from which data is to be loaded and a list of the relation  Return the name of the directory from which data is to be loaded and a list of the relation
3389  names. This information is useful when trying to analyze what needs to be put where in order  names. This information is useful when trying to analyze what needs to be put where in order
# Line 2529  Line 3397 
3397          # Create the return list, priming it with the name of the data directory.          # Create the return list, priming it with the name of the data directory.
3398          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
3399          # Concatenate the table names.          # Concatenate the table names.
3400          push @retVal, $self->{_erdb}->GetTableNames();      push @retVal, $self->GetTableNames();
3401          # Return the result.          # Return the result.
3402          return @retVal;          return @retVal;
3403  }  }
3404    
3405    =head3 BBHMatrix
3406    
3407        my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3408    
3409    Find all the bidirectional best hits for the features of a genome in a
3410    specified list of target genomes. The return value will be a hash mapping
3411    features in the original genome to their bidirectional best hits in the
3412    target genomes.
3413    
3414    =over 4
3415    
3416    =item genomeID
3417    
3418    ID of the genome whose features are to be examined for bidirectional best hits.
3419    
3420    =item cutoff
3421    
3422    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3423    
3424    =item targets
3425    
3426    List of target genomes. Only pairs originating in the original
3427    genome and landing in one of the target genomes will be returned.
3428    
3429    =item RETURN
3430    
3431    Returns a hash mapping each feature in the original genome to a hash mapping its
3432    BBH pegs in the target genomes to their scores.
3433    
3434    =back
3435    
3436    =cut
3437    
3438    sub BBHMatrix {
3439        # Get the parameters.
3440        my ($self, $genomeID, $cutoff, @targets) = @_;
3441        # Declare the return variable.
3442        my %retVal = ();
3443        # Ask for the BBHs.
3444        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3445        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3446        for my $bbhData (@bbhList) {
3447            my ($peg1, $peg2, $score) = @{$bbhData};
3448            if (! exists $retVal{$peg1}) {
3449                $retVal{$peg1} = { $peg2 => $score };
3450            } else {
3451                $retVal{$peg1}->{$peg2} = $score;
3452            }
3453        }
3454        # Return the result.
3455        return %retVal;
3456    }
3457    
3458    
3459    =head3 SimMatrix
3460    
3461        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3462    
3463    Find all the similarities for the features of a genome in a
3464    specified list of target genomes. The return value will be a hash mapping
3465    features in the original genome to their similarites in the
3466    target genomes.
3467    
3468    =over 4
3469    
3470    =item genomeID
3471    
3472    ID of the genome whose features are to be examined for similarities.
3473    
3474    =item cutoff
3475    
3476    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3477    
3478    =item targets
3479    
3480    List of target genomes. Only pairs originating in the original
3481    genome and landing in one of the target genomes will be returned.
3482    
3483    =item RETURN
3484    
3485    Returns a hash mapping each feature in the original genome to a hash mapping its
3486    similar pegs in the target genomes to their scores.
3487    
3488    =back
3489    
3490    =cut
3491    
3492    sub SimMatrix {
3493        # Get the parameters.
3494        my ($self, $genomeID, $cutoff, @targets) = @_;
3495        # Declare the return variable.
3496        my %retVal = ();
3497        # Get the list of features in the source organism.
3498        my @fids = $self->FeaturesOf($genomeID);
3499        # Ask for the sims. We only want similarities to fig features.
3500        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3501        if (! defined $simList) {
3502            Confess("Unable to retrieve similarities from server.");
3503        } else {
3504            Trace("Processing sims.") if T(3);
3505            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3506            # Create a hash for the target genomes.
3507            my %targetHash = map { $_ => 1 } @targets;
3508            for my $simData (@{$simList}) {
3509                # Get the PEGs and the score.
3510                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3511                # Insure the second ID is in the target list.
3512                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3513                if (exists $targetHash{$genome2}) {
3514                    # Here it is. Now we need to add it to the return hash. How we do that depends
3515                    # on whether or not $peg1 is new to us.
3516                    if (! exists $retVal{$peg1}) {
3517                        $retVal{$peg1} = { $peg2 => $score };
3518                    } else {
3519                        $retVal{$peg1}->{$peg2} = $score;
3520                    }
3521                }
3522            }
3523        }
3524        # Return the result.
3525        return %retVal;
3526    }
3527    
3528    
3529  =head3 LowBBHs  =head3 LowBBHs
3530    
3531  C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3532    
3533  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3534  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 2565  Line 3557 
3557          my ($self, $featureID, $cutoff) = @_;          my ($self, $featureID, $cutoff) = @_;
3558          # Create the return hash.          # Create the return hash.
3559          my %retVal = ();          my %retVal = ();
3560          # Create a query to get the desired BBHs.      # Query for the desired BBHs.
3561          my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],      my @bbhList = FIGRules::BBHData($featureID, $cutoff);
                                                                 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',  
                                                                 [$cutoff, $featureID],  
                                                                 ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);  
3562          # Form the results into the return hash.          # Form the results into the return hash.
3563          for my $pair (@bbhList) {          for my $pair (@bbhList) {
3564                  $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3565            if ($self->Exists('Feature', $fid)) {
3566                $retVal{$fid} = $pair->[1];
3567            }
3568          }          }
3569          # Return the result.          # Return the result.
3570          return %retVal;          return %retVal;
3571  }  }
3572    
3573    =head3 Sims
3574    
3575        my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3576    
3577    Get a list of similarities for a specified feature. Similarity information is not kept in the
3578    Sprout database; rather, they are retrieved from a network server. The similarities are
3579    returned as B<Sim> objects. A Sim object is actually a list reference that has been blessed
3580    so that its elements can be accessed by name.
3581    
3582    Similarities can be either raw or expanded. The raw similarities are basic
3583    hits between features with similar DNA. Expanding a raw similarity drags in any
3584    features considered substantially identical. So, for example, if features B<A1>,
3585    B<A2>, and B<A3> are all substantially identical to B<A>, then a raw similarity
3586    B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3587    
3588    =over 4
3589    
3590    =item fid
3591    
3592    ID of the feature whose similarities are desired, or reference to a list of IDs
3593    of features whose similarities are desired.
3594    
3595    =item maxN
3596    
3597    Maximum number of similarities to return.
3598    
3599    =item maxP
3600    
3601    Minumum allowable similarity score.
3602    
3603    =item select
3604    
3605    Selection criterion: C<raw> means only raw similarities are returned; C<fig>
3606    means only similarities to FIG features are returned; C<all> means all expanded
3607    similarities are returned; and C<figx> means similarities are expanded until the
3608    number of FIG features equals the maximum.
3609    
3610    =item max_expand
3611    
3612    The maximum number of features to expand.
3613    
3614    =item filters
3615    
3616    Reference to a hash containing filter information, or a subroutine that can be
3617    used to filter the sims.
3618    
3619    =item RETURN
3620    
3621    Returns a reference to a list of similarity objects, or C<undef> if an error
3622    occurred.
3623    
3624    =back
3625    
3626    =cut
3627    
3628    sub Sims {
3629        # Get the parameters.
3630        my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_;
3631        # Create the shim object to test for deleted FIDs.
3632        my $shim = FidCheck->new($self);
3633        # Ask the network for sims.
3634        my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters);
3635        # Return the result.
3636        return $retVal;
3637    }
3638    
3639    =head3 IsAllGenomes
3640    
3641        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3642    
3643    Return TRUE if all genomes in the second list are represented in the first list at
3644    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3645    compared to a list of all the genomes.
3646    
3647    =over 4
3648    
3649    =item list
3650    
3651    Reference to the list to be compared to the second list.
3652    
3653    =item checkList (optional)
3654    
3655    Reference to the comparison target list. Every genome ID in this list must occur at
3656    least once in the first list. If this parameter is omitted, a list of all the genomes
3657    is used.
3658    
3659    =item RETURN
3660    
3661    Returns TRUE if every item in the second list appears at least once in the
3662    first list, else FALSE.
3663    
3664    =back
3665    
3666    =cut
3667    
3668    sub IsAllGenomes {
3669        # Get the parameters.
3670        my ($self, $list, $checkList) = @_;
3671        # Supply the checklist if it was omitted.
3672        $checkList = [$self->Genomes()] if ! defined($checkList);
3673        # Create a hash of the original list.
3674        my %testList = map { $_ => 1 } @{$list};
3675        # Declare the return variable. We assume that the representation
3676        # is complete and stop at the first failure.
3677        my $retVal = 1;
3678        my $n = scalar @{$checkList};
3679        for (my $i = 0; $retVal && $i < $n; $i++) {
3680            if (! $testList{$checkList->[$i]}) {
3681                $retVal = 0;
3682            }
3683        }
3684        # Return the result.
3685        return $retVal;
3686    }
3687    
3688  =head3 GetGroups  =head3 GetGroups
3689    
3690  C<< my %groups = $sprout->GetGroups(\@groupList); >>      my %groups = $sprout->GetGroups(\@groupList);
3691    
3692  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.
3693  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 2599  Line 3706 
3706          # Here we have a group list. Loop through them individually,          # Here we have a group list. Loop through them individually,
3707          # getting a list of the relevant genomes.          # getting a list of the relevant genomes.
3708          for my $group (@{$groupList}) {          for my $group (@{$groupList}) {
3709              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3710                  [$group], "Genome(id)");                  [$group], "Genome(id)");
3711              $retVal{$group} = \@genomeIDs;              $retVal{$group} = \@genomeIDs;
3712          }          }
# Line 2607  Line 3714 
3714          # 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
3715          # of the genome records, putting each one found into the appropriate          # of the genome records, putting each one found into the appropriate
3716          # 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
3717          # in groups are included in the return set.          # in real NMPDR groups are included in the return set.
3718          my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],          my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3719                                      ['Genome(id)', 'Genome(group-name)']);                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3720          # Loop through the genomes found.          # Loop through the genomes found.
3721          for my $genome (@genomes) {          for my $genome (@genomes) {
3722              # Pop this genome's ID off the current list.              # Get the genome ID and group, and add this genome to the group's list.
3723              my @groups = @{$genome};              my ($genomeID, $group) = @{$genome};
3724              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, $genomeID);  
             }  
3725          }          }
3726      }      }
3727      # Return the hash we just built.      # Return the hash we just built.
3728      return %retVal;      return %retVal;
3729  }  }
3730    
3731    =head3 MyGenomes
3732    
3733        my @genomes = Sprout::MyGenomes($dataDir);
3734    
3735    Return a list of the genomes to be included in the Sprout.
3736    
3737    This method is provided for use during the Sprout load. It presumes the Genome load file has
3738    already been created. (It will be in the Sprout data directory and called either C<Genome>
3739    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3740    IDs.
3741    
3742    =over 4
3743    
3744    =item dataDir
3745    
3746    Directory containing the Sprout load files.
3747    
3748    =back
3749    
3750    =cut
3751    #: Return Type @;
3752    sub MyGenomes {
3753        # Get the parameters.
3754        my ($dataDir) = @_;
3755        # Compute the genome file name.
3756        my $genomeFileName = LoadFileName($dataDir, "Genome");
3757        # Extract the genome IDs from the files.
3758        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3759        # Return the result.
3760        return @retVal;
3761    }
3762    
3763    =head3 LoadFileName
3764    
3765        my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3766    
3767    Return the name of the load file for the specified table in the specified data
3768    directory.
3769    
3770    =over 4
3771    
3772    =item dataDir
3773    
3774    Directory containing the Sprout load files.
3775    
3776    =item tableName
3777    
3778    Name of the table whose load file is desired.
3779    
3780    =item RETURN
3781    
3782    Returns the name of the file containing the load data for the specified table, or
3783    C<undef> if no load file is present.
3784    
3785    =back
3786    
3787    =cut
3788    #: Return Type $;
3789    sub LoadFileName {
3790        # Get the parameters.
3791        my ($dataDir, $tableName) = @_;
3792        # Declare the return variable.
3793        my $retVal;
3794        # Check for the various file names.
3795        if (-e "$dataDir/$tableName") {
3796            $retVal = "$dataDir/$tableName";
3797        } elsif (-e "$dataDir/$tableName.dtx") {
3798            $retVal = "$dataDir/$tableName.dtx";
3799        }
3800        # Return the result.
3801        return $retVal;
3802    }
3803    
3804    =head3 DeleteGenome
3805    
3806        my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3807    
3808    Delete a genome from the database.
3809    
3810    =over 4
3811    
3812    =item genomeID
3813    
3814    ID of the genome to delete
3815    
3816    =item testFlag
3817    
3818    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3819    
3820    =item RETURN
3821    
3822    Returns a statistics object describing the rows deleted.
3823    
3824    =back
3825    
3826    =cut
3827    #: Return Type $%;
3828    sub DeleteGenome {
3829        # Get the parameters.
3830        my ($self, $genomeID, $testFlag) = @_;
3831        # Perform the delete for the genome's features.
3832        my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3833        # Perform the delete for the primary genome data.
3834        my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3835        $retVal->Accumulate($stats);
3836        # Return the result.
3837        return $retVal;
3838    }
3839    
3840    =head3 Fix
3841    
3842        my %fixedHash = $sprout->Fix(%groupHash);
3843    
3844    Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3845    The groups will be combined into the appropriate super-groups.
3846    
3847    =over 4
3848    
3849    =item groupHash
3850    
3851    Hash to be fixed up.
3852    
3853    =item RETURN
3854    
3855    Returns a fixed-up version of the hash.
3856    
3857    =back
3858    
3859    =cut
3860    
3861    sub Fix {
3862        # Get the parameters.
3863        my ($self, %groupHash) = @_;
3864        # Create the result hash.
3865        my %retVal = ();
3866        # Copy over the genomes.
3867        for my $groupID (keys %groupHash) {
3868            # Get the super-group name.
3869            my $realGroupID = $self->SuperGroup($groupID);
3870            # Append this group's genomes into the result hash
3871            # using the super-group name.
3872            push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3873        }
3874        # Return the result hash.
3875        return %retVal;
3876    }
3877    
3878    =head3 GroupPageName
3879    
3880        my $name = $sprout->GroupPageName($group);
3881    
3882    Return the name of the page for the specified NMPDR group.
3883    
3884    =over 4
3885    
3886    =item group
3887    
3888    Name of the relevant group.
3889    
3890    =item RETURN
3891    
3892    Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3893    memory it will be read in.
3894    
3895    =back
3896    
3897    =cut
3898    
3899    sub GroupPageName {
3900        # Get the parameters.
3901        my ($self, $group) = @_;
3902        # Check for the group file data.
3903        my %superTable = $self->CheckGroupFile();
3904        # Compute the real group name.
3905        my $realGroup = $self->SuperGroup($group);
3906        # Get the associated page name.
3907        my $retVal = "../content/$superTable{$realGroup}->{page}";
3908        # Return the result.
3909        return $retVal;
3910    }
3911    
3912    
3913    =head3 AddProperty
3914    
3915        $sprout->AddProperty($featureID, $key, @values);
3916    
3917    Add a new attribute value (Property) to a feature.
3918    
3919    =over 4
3920    
3921    =item peg
3922    
3923    ID of the feature to which the attribute is to be added.
3924    
3925    =item key
3926    
3927    Name of the attribute (key).
3928    
3929    =item values
3930    
3931    Values of the attribute.
3932    
3933    =back
3934    
3935    =cut
3936    #: Return Type ;
3937    sub AddProperty {
3938        # Get the parameters.
3939        my ($self, $featureID, $key, @values) = @_;
3940        # Add the property using the attached attributes object.
3941        $self->{_ca}->AddAttribute($featureID, $key, @values);
3942    }
3943    
3944    =head3 CheckGroupFile
3945    
3946        my %groupData = $sprout->CheckGroupFile();
3947    
3948    Get the group file hash. The group file hash describes the relationship
3949    between a group and the super-group to which it belongs for purposes of
3950    display. The super-group name is computed from the first capitalized word
3951    in the actual group name. For each super-group, the group file contains
3952    the page name and a list of the species expected to be in the group.
3953    Each species is specified by a genus and a species name. A species name
3954    of C<0> implies an entire genus.
3955    
3956    This method returns a hash from super-group names to a hash reference. Each
3957    resulting hash reference contains the following fields.
3958    
3959    =over 4
3960    
3961    =item page
3962    
3963    The super-group's web page in the NMPDR.
3964    
3965    =item contents
3966    
3967    A list of 2-tuples, each containing a genus name followed by a species name
3968    (or 0, indicating all species). This list indicates which organisms belong
3969    in the super-group.
3970    
3971    =back
3972    
3973    =cut
3974    
3975    sub CheckGroupFile {
3976        # Get the parameters.
3977        my ($self) = @_;
3978        # Check to see if we already have this hash.
3979        if (! defined $self->{groupHash}) {
3980            # We don't, so we need to read it in.
3981            my %groupHash;
3982            # Read the group file.
3983            my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
3984            # Loop through the list of sort-of groups.
3985            for my $groupLine (@groupLines) {
3986                my ($name, $page, @contents) = split /\t/, $groupLine;
3987                $groupHash{$name} = { page => $page,
3988                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
3989                                    };
3990            }
3991            # Save the hash.
3992            $self->{groupHash} = \%groupHash;
3993        }
3994        # Return the result.
3995        return %{$self->{groupHash}};
3996    }
3997    
3998    =head2 Virtual Methods
3999    
4000    =head3 CleanKeywords
4001    
4002        my $cleanedString = $sprout->CleanKeywords($searchExpression);
4003    
4004    Clean up a search expression or keyword list. This involves converting the periods
4005    in EC numbers to underscores, converting non-leading minus signs to underscores,
4006    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
4007    characters. In addition, any extra spaces are removed.
4008    
4009    =over 4
4010    
4011    =item searchExpression
4012    
4013    Search expression or keyword list to clean. Note that a search expression may
4014    contain boolean operators which need to be preserved. This includes leading
4015    minus signs.
4016    
4017    =item RETURN
4018    
4019    Cleaned expression or keyword list.
4020    
4021    =back
4022    
4023    =cut
4024    
4025    sub CleanKeywords {
4026        # Get the parameters.
4027        my ($self, $searchExpression) = @_;
4028        # Perform the standard cleanup.
4029        my $retVal = $self->ERDB::CleanKeywords($searchExpression);
4030        # Fix the periods in EC and TC numbers.
4031        $retVal =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;
4032        # Fix non-trailing periods.
4033        $retVal =~ s/\.(\w)/_$1/g;
4034        # Fix non-leading minus signs.
4035        $retVal =~ s/(\w)[\-]/$1_/g;
4036        # Fix the vertical bars and colons
4037        $retVal =~ s/(\w)[|:](\w)/$1'$2/g;
4038        # Return the result.
4039        return $retVal;
4040    }
4041    
4042  =head2 Internal Utility Methods  =head2 Internal Utility Methods
4043    
4044  =head3 ParseAssignment  =head3 ParseAssignment
4045    
4046  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
4047  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
4048  will be returned.  isn't, an empty list will be returned.
4049    
4050    A functional assignment is always of the form
4051    
4052        set YYYY function to
4053        ZZZZ
4054    
4055    where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
4056    the user and the assigning user (from MadeAnnotation) will be the same, but that is
4057    not always the case.
4058    
4059    In addition, the functional role may contain extra data that is stripped, such as
4060    terminating spaces or a comment separated from the rest of the text by a tab.
4061    
4062  This is a static method.  This is a static method.
4063    
4064  =over 4  =over 4
4065    
4066    =item user
4067    
4068    Name of the assigning user.
4069    
4070  =item text  =item text
4071    
4072  Text of the annotation.  Text of the annotation.
# Line 2651  Line 4080 
4080    
4081  =cut  =cut
4082    
4083  sub ParseAssignment {  sub _ParseAssignment {
4084          # Get the parameters.          # Get the parameters.
4085          my ($text) = @_;      my ($user, $text) = @_;
4086          # Declare the return value.          # Declare the return value.
4087          my @retVal = ();          my @retVal = ();
4088          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
4089          my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
4090          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set function to$/i) {
4091                  # Here it is, so we return the user name and function text.          # Here we have an assignment without a user, so we use the incoming user ID.
4092                  @retVal = ($user, $function);                  @retVal = ($user, $function);
4093        } elsif ($type =~ m/^set (\S+) function to$/i) {
4094            # Here we have an assignment with a user that is passed back to the caller.
4095            @retVal = ($1, $function);
4096        }
4097        # If we have an assignment, we need to clean the function text. There may be
4098        # extra junk at the end added as a note from the user.
4099        if (defined( $retVal[1] )) {
4100            $retVal[1] =~ s/(\t\S)?\s*$//;
4101          }          }
4102          # Return the result list.          # Return the result list.
4103          return @retVal;          return @retVal;
4104  }  }
4105    
4106    =head3 _CheckFeature
4107    
4108        my $flag = $sprout->_CheckFeature($fid);
4109    
4110    Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
4111    
4112    =over 4
4113    
4114    =item fid
4115    
4116    Feature ID to check.
4117    
4118    =item RETURN
4119    
4120    Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE.
4121    
4122    =back
4123    
4124    =cut
4125    
4126    sub _CheckFeature {
4127        # Get the parameters.
4128        my ($self, $fid) = @_;
4129        # Insure we have a genome hash.
4130        if (! defined $self->{genomeHash}) {
4131            my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');
4132            $self->{genomeHash} = \%genomeHash;
4133        }
4134        # Get the feature's genome ID.
4135        my ($genomeID) = FIGRules::ParseFeatureID($fid);
4136        # Return an indicator of whether or not the genome ID is in the hash.
4137        return ($self->{genomeHash}->{$genomeID} ? 1 : 0);
4138    }
4139    
4140  =head3 FriendlyTimestamp  =head3 FriendlyTimestamp
4141    
4142  Convert a time number to a user-friendly time stamp for display.  Convert a time number to a user-friendly time stamp for display.
# Line 2688  Line 4159 
4159    
4160  sub FriendlyTimestamp {  sub FriendlyTimestamp {
4161      my ($timeValue) = @_;      my ($timeValue) = @_;
4162      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
4163      return $retVal;      return $retVal;
4164  }  }
4165    
4166    
4167  1;  1;

Legend:
Removed from v.1.10  
changed lines
  Added in v.1.109

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3