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

Diff of /Sprout/Sprout.pm

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

revision 1.33, Wed Sep 14 13:26:27 2005 UTC revision 1.108, Thu Feb 14 19:13:33 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 base qw(ERDB);
18    
19  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
20    
# Line 25  Line 27 
27  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>
28  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>.
29    
30  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' });
31    
32  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
33  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
34  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
35  L</dna_seq> returns the DNA sequence for a specified genome location.  L</DNASeq> returns the DNA sequence for a specified genome location.
36    
37    The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.
38    
39  =cut  =cut
40    
# Line 40  Line 44 
44    
45  =head3 new  =head3 new
46    
47  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
48    
49  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
50  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 66 
66    
67  * 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>)
68    
69  * 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)
70    
71  * B<port> connection port (default C<0>)  * B<port> connection port (default C<0>)
72    
73    * B<sock> connection socket (default same as SEED)
74    
75  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)
76    
77  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
78    
79  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
80    
81    * B<host> name of the database host
82    
83  =back  =back
84    
85  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
86  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
87  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
88    
89  C<< my $sprout = Sprout->new('Sprout', { userData =>; 'fig/admin', dataDir => '/usr/fig/SproutData' }); >>      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });
90    
91  =cut  =cut
92    
93  sub new {  sub new {
94      # Get the parameters.      # Get the parameters.
95      my ($class, $dbName, $options) = @_;      my ($class, $dbName, $options) = @_;
96        # Compute the DBD directory.
97        my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
98                                                      $FIG_Config::fig );
99      # 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
100      # the incoming data.      # the incoming data.
101      my $optionTable = Tracer::GetOptions({      my $optionTable = Tracer::GetOptions({
# Line 92  Line 103 
103                                                          # database type                                                          # database type
104                         dataDir      => $FIG_Config::sproutData,                         dataDir      => $FIG_Config::sproutData,
105                                                          # data file directory                                                          # data file directory
106                         xmlFileName  => "$FIG_Config::sproutData/SproutDBD.xml",                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
107                                                          # database definition file name                                                          # database definition file name
108                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
109                                                          # user name and password                                                          # user name and password
110                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::dbport,
111                                                          # database connection port                                                          # database connection port
112                           sock         => $FIG_Config::dbsock,
113                           host         => $FIG_Config::sprout_host,
114                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
115                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
116                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
# Line 110  Line 123 
123      # Connect to the database.      # Connect to the database.
124      my $dbh;      my $dbh;
125      if (! $optionTable->{noDBOpen}) {      if (! $optionTable->{noDBOpen}) {
126            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
127          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
128                                  $password, $optionTable->{port});                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
129      }      }
130      # Create the ERDB object.      # Create the ERDB object.
131      my $xmlFileName = "$optionTable->{xmlFileName}";      my $xmlFileName = "$optionTable->{xmlFileName}";
132      my $erdb = ERDB->new($dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName);
133      # Create this object.      # Add the option table and XML file name.
134      my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName };      $retVal->{_options} = $optionTable;
135      # Bless and return it.      $retVal->{_xmlName} = $xmlFileName;
136      bless $self;      # Set up space for the group file data.
137      return $self;      $retVal->{groupHash} = undef;
138  }      # Set up space for the genome hash. We use this to identify NMPDR genomes.
139        $retVal->{genomeHash} = undef;
140  =head3 MaxSegment      # Connect to the attributes.
141        if ($FIG_Config::attrURL) {
142  C<< my $length = $sprout->MaxSegment(); >>          Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
143            $retVal->{_ca} = RemoteCustomAttributes->new($FIG_Config::attrURL);
144  This method returns the maximum permissible length of a feature segment. The length is important      } elsif ($FIG_Config::attrDbName) {
145  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);
146  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()));
147  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};  
148  }  }
149        # Return it.
150  =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};  
151  }  }
152    
153  =head3 Get  =head3 CoreGenomes
   
 C<< my $query = $sprout->Get(\@objectNames, $filterClause, \@parameterList); >>  
   
 This method allows a general query against the Sprout data using a specified filter clause.  
   
 The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each  
 field name represented in the form B<I<objectName>(I<fieldName>)>. For example, the  
 following call requests all B<Genome> objects for the genus specified in the variable  
 $genus.  
   
 C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>  
   
 The WHERE clause contains a single question mark, so there is a single additional  
 parameter representing the parameter value. It would also be possible to code  
   
 C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  
   
 however, this version of the call would generate a syntax error if there were any quote  
 characters inside the variable C<$genus>.  
   
 The use of the strange parenthesized notation for field names enables us to distinguish  
 hyphens contained within field names from minus signs that participate in the computation  
 of the WHERE clause. All of the methods that manipulate fields will use this same notation.  
   
 It is possible to specify multiple entity and relationship names in order to retrieve more than  
 one object's data at the same time, which allows highly complex joined queries. For example,  
   
 C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>  
   
 This query returns all the genomes for a particular genus and allows access to the  
 sources from which they came. The join clauses to go from Genome to Source are generated  
 automatically.  
   
 Finally, the filter clause can contain sort information. To do this, simply put an C<ORDER BY>  
 clause at the end of the filter. Field references in the ORDER BY section follow the same rules  
 as they do in the filter itself; in other words, each one must be of the form B<I<objectName>(I<fieldName>)>.  
 For example, the following filter string gets all genomes for a particular genus and sorts  
 them by species name.  
   
 C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ? ORDER BY Genome(species)", [$genus]); >>  
   
 It is also permissible to specify I<only> an ORDER BY clause. For example, the following invocation gets  
 all genomes ordered by genus and species.  
154    
155  C<< $query = $sprout->Get(['Genome'], "ORDER BY Genome(genus), Genome(species)"); >>      my @genomes = $sprout->CoreGenomes($scope);
156    
157  Odd things may happen if one of the ORDER BY fields is in a secondary relation. So, for example, an  Return the IDs of NMPDR genomes in the specified scope.
 attempt to order B<Feature>s by alias may (depending on the underlying database engine used) cause  
 a single feature to appear more than once.  
   
 If multiple names are specified, then the query processor will automatically determine a  
 join path between the entities and relationships. The algorithm used is very simplistic.  
 In particular, you can't specify any entity or relationship more than once, and if a  
 relationship is recursive, the path is determined by the order in which the entity  
 and the relationship appear. For example, consider a recursive relationship B<IsParentOf>  
 which relates B<People> objects to other B<People> objects. If the join path is  
 coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,  
 the join path is C<['IsParentOf', 'People']>, then the people returned will be children.  
158    
159  =over 4  =over 4
160    
161  =item objectNames  =item scope
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
162    
163  =item parameterList  Scope of the desired genomes. C<core> covers the original core genomes,
164    C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
165  List of the parameters to be substituted in for the parameters marks in the filter clause.  genomes in the system.
166    
167  =item RETURN  =item RETURN
168    
169  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.
170    
171  =back  =back
172    
173  =cut  =cut
174    
175  sub Get {  sub CoreGenomes {
176      # Get the parameters.      # Get the parameters.
177      my ($self, $objectNames, $filterClause, $parameterList) = @_;      my ($self, $scope) = @_;
178      # We differ from the ERDB Get method in that the parameter list is passed in as a list reference      # Declare the return variable.
179      # rather than a list of parameters. The next step is to convert the parameters from a reference      my @retVal = ();
180      # to a real list. We can only do this if the parameters have been specified.      # If we want all genomes, then this is easy.
181      my @parameters;      if ($scope eq 'all') {
182      if ($parameterList) { @parameters = @{$parameterList}; }          @retVal = $self->Genomes();
183      return $self->{_erdb}->Get($objectNames, $filterClause, @parameters);      } else {
184            # Here we're dealing with groups. Get the hash of all the
185            # genome groups.
186            my %groups = $self->GetGroups();
187            # Loop through the groups, keeping the ones that we want.
188            for my $group (keys %groups) {
189                # Decide if we want to keep this group.
190                my $keepGroup = 0;
191                if ($scope eq 'nmpdr') {
192                    # NMPDR mode: keep all groups.
193                    $keepGroup = 1;
194                } elsif ($scope eq 'core') {
195                    # CORE mode. Only keep real core groups.
196                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
197                        $keepGroup = 1;
198                    }
199                }
200                # Add this group if we're keeping it.
201                if ($keepGroup) {
202                    push @retVal, @{$groups{$group}};
203                }
204            }
205        }
206        # Return the result.
207        return @retVal;
208  }  }
209    
210  =head3 GetEntity  =head3 SuperGroup
211    
212  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>      my $superGroup = $sprout->SuperGroup($groupName);
213    
214  Return an object describing the entity instance with a specified ID.  Return the name of the super-group containing the specified NMPDR genome
215    group. If no appropriate super-group can be found, an error will be
216    thrown.
217    
218  =over 4  =over 4
219    
220  =item entityType  =item groupName
   
 Entity type name.  
221    
222  =item ID  Name of the group whose super-group is desired.
   
 ID of the desired entity.  
223    
224  =item RETURN  =item RETURN
225    
226  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.  
227    
228  =back  =back
229    
230  =cut  =cut
231    
232  sub GetEntity {  sub SuperGroup {
233      # Get the parameters.      # Get the parameters.
234      my ($self, $entityType, $ID) = @_;      my ($self, $groupName) = @_;
235      # Call the ERDB method.      # Declare the return variable.
236      return $self->{_erdb}->GetEntity($entityType, $ID);      my $retVal;
237        # Get the group hash.
238        my %groupHash = $self->CheckGroupFile();
239        # Find the super-group genus.
240        $groupName =~ /([A-Z]\w+)/;
241        my $nameThing = $1;
242        # See if it's directly in the group hash.
243        if (exists $groupHash{$nameThing}) {
244            # Yes, then it's our result.
245            $retVal = $nameThing;
246        } else {
247            # No, so we have to search.
248            for my $superGroup (keys %groupHash) {
249                # Get this super-group's item list.
250                my $list = $groupHash{$superGroup}->{contents};
251                # Search it.
252                if (grep { $_->[0] eq $nameThing } @{$list}) {
253                    $retVal = $superGroup;
254                }
255            }
256            # Make sure we found something.
257            if (! $retVal) {
258                Confess("No super-group found for \"$groupName\".");
259            }
260        }
261        # Return the result.
262        return $retVal;
263  }  }
264    
265  =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  
266    
267  Returns a flattened list of the values of the specified fields for the specified entity.      my $length = $sprout->MaxSegment();
268    
269  =back  This method returns the maximum permissible length of a feature segment. The length is important
270    because it enables us to make reasonable guesses at how to find features inside a particular
271    contig region. For example, if the maximum length is 4000 and we're looking for a feature that
272    overlaps the region from 6000 to 7000 we know that the starting position must be between 2001
273    and 10999.
274    
275  =cut  =cut
276  #: Return Type @;  #: Return Type $;
277  sub GetEntityValues {  sub MaxSegment {
278      # Get the parameters.      my ($self) = @_;
279      my ($self, $entityType, $ID, $fields) = @_;      return $self->{_options}->{maxSegmentLength};
     # Call the ERDB method.  
     return $self->{_erdb}->GetEntityValues($entityType, $ID, $fields);  
280  }  }
281    
282  =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  
283    
284  Fully-qualified name to give to the output file.      my $length = $sprout->MaxSequence();
285    
286  =back  This method returns the maximum permissible length of a contig sequence. A contig is broken
287    into sequences in order to save memory resources. In particular, when manipulating features,
288    we generally only need a few sequences in memory rather than the entire contig.
289    
290  =cut  =cut
291    #: Return Type $;
292  sub ShowMetaData {  sub MaxSequence {
293      # Get the parameters.      my ($self) = @_;
294      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);  
295  }  }
296    
297  =head3 Load  =head3 Load
298    
299  C<< $sprout->Load($rebuild); >>;      $sprout->Load($rebuild);;
300    
301  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.
302    
# Line 379  Line 328 
328  sub Load {  sub Load {
329      # Get the parameters.      # Get the parameters.
330      my ($self, $rebuild) = @_;      my ($self, $rebuild) = @_;
     # Get the database object.  
     my $erdb = $self->{_erdb};  
331      # Load the tables from the data directory.      # Load the tables from the data directory.
332      my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild);      my $retVal = $self->LoadTables($self->{_options}->{dataDir}, $rebuild);
333      # Return the statistics.      # Return the statistics.
334      return $retVal;      return $retVal;
335  }  }
336    
337  =head3 LoadUpdate  =head3 LoadUpdate
338    
339  C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
340    
341  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
342  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 369 
369  sub LoadUpdate {  sub LoadUpdate {
370      # Get the parameters.      # Get the parameters.
371      my ($self, $truncateFlag, $tableList) = @_;      my ($self, $truncateFlag, $tableList) = @_;
     # Get the database object.  
     my $erdb = $self->{_erdb};  
372      # Declare the return value.      # Declare the return value.
373      my $retVal = Stats->new();      my $retVal = Stats->new();
374      # Get the data directory.      # Get the data directory.
# Line 437  Line 382 
382              Trace("No load file found for $tableName in $dataDir.") if T(0);              Trace("No load file found for $tableName in $dataDir.") if T(0);
383          } else {          } else {
384              # Attempt to load this table.              # Attempt to load this table.
385              my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
386              # Accumulate the resulting statistics.              # Accumulate the resulting statistics.
387              $retVal->Accumulate($result);              $retVal->Accumulate($result);
388          }          }
# Line 446  Line 391 
391      return $retVal;      return $retVal;
392  }  }
393    
394    =head3 GenomeCounts
395    
396        my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
397    
398    Count the number of genomes in each domain. If I<$complete> is TRUE, only complete
399    genomes will be included in the counts.
400    
401    =over 4
402    
403    =item complete
404    
405    TRUE if only complete genomes are to be counted, FALSE if all genomes are to be
406    counted
407    
408    =item RETURN
409    
410    A six-element list containing the number of genomes in each of six categories--
411    Archaea, Bacteria, Eukaryota, Viral, Environmental, and Unknown, respectively.
412    
413    =back
414    
415    =cut
416    
417    sub GenomeCounts {
418        # Get the parameters.
419        my ($self, $complete) = @_;
420        # Set the filter based on the completeness flag.
421        my $filter = ($complete ? "Genome(complete) = 1" : "");
422        # Get all the genomes and the related taxonomy information.
423        my @genomes = $self->GetAll(['Genome'], $filter, [], ['Genome(id)', 'Genome(taxonomy)']);
424        # Clear the counters.
425        my ($arch, $bact, $euk, $vir, $env, $unk) = (0, 0, 0, 0, 0, 0);
426        # Loop through, counting the domains.
427        for my $genome (@genomes) {
428            if    ($genome->[1] =~ /^archaea/i)  { ++$arch }
429            elsif ($genome->[1] =~ /^bacter/i)   { ++$bact }
430            elsif ($genome->[1] =~ /^eukar/i)    { ++$euk }
431            elsif ($genome->[1] =~ /^vir/i)      { ++$vir }
432            elsif ($genome->[1] =~ /^env/i)      { ++$env }
433            else  { ++$unk }
434        }
435        # Return the counts.
436        return ($arch, $bact, $euk, $vir, $env, $unk);
437    }
438    
439    =head3 ContigCount
440    
441        my $count = $sprout->ContigCount($genomeID);
442    
443    Return the number of contigs for the specified genome ID.
444    
445    =over 4
446    
447    =item genomeID
448    
449    ID of the genome whose contig count is desired.
450    
451    =item RETURN
452    
453    Returns the number of contigs for the specified genome.
454    
455    =back
456    
457    =cut
458    
459    sub ContigCount {
460        # Get the parameters.
461        my ($self, $genomeID) = @_;
462        # Get the contig count.
463        my $retVal = $self->GetCount(['Contig', 'HasContig'], "HasContig(from-link) = ?", [$genomeID]);
464        # Return the result.
465        return $retVal;
466    }
467    
468    =head3 GeneMenu
469    
470        my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params, $selected);
471    
472    Return an HTML select menu of genomes. Each genome will be an option in the menu,
473    and will be displayed by name with the ID and a contig count attached. The selection
474    value will be the genome ID. The genomes will be sorted by genus/species name.
475    
476    =over 4
477    
478    =item attributes
479    
480    Reference to a hash mapping attributes to values for the SELECT tag generated.
481    
482    =item filterString
483    
484    A filter string for use in selecting the genomes. The filter string must conform
485    to the rules for the C<< ERDB->Get >> method.
486    
487    =item params
488    
489    Reference to a list of values to be substituted in for the parameter marks in
490    the filter string.
491    
492    =item selected (optional)
493    
494    ID of the genome to be initially selected.
495    
496    =item fast (optional)
497    
498    If specified and TRUE, the contig counts will be omitted to improve performance.
499    
500    =item RETURN
501    
502    Returns an HTML select menu with the specified genomes as selectable options.
503    
504    =back
505    
506    =cut
507    
508    sub GeneMenu {
509        # Get the parameters.
510        my ($self, $attributes, $filterString, $params, $selected, $fast) = @_;
511        my $slowMode = ! $fast;
512        # Default to nothing selected. This prevents an execution warning if "$selected"
513        # is undefined.
514        $selected = "" unless defined $selected;
515        Trace("Gene Menu called with slow mode \"$slowMode\" and selection \"$selected\".") if T(3);
516        # Start the menu.
517        my $retVal = "<select " .
518            join(" ", map { "$_=\"$attributes->{$_}\"" } keys %{$attributes}) .
519            ">\n";
520        # Get the genomes.
521        my @genomes = $self->GetAll(['Genome'], $filterString, $params, ['Genome(id)',
522                                                                         'Genome(genus)',
523                                                                         'Genome(species)',
524                                                                         'Genome(unique-characterization)']);
525        # Sort them by name.
526        my @sorted = sort { lc("$a->[1] $a->[2]") cmp lc("$b->[1] $b->[2]") } @genomes;
527        # Loop through the genomes, creating the option tags.
528        for my $genomeData (@sorted) {
529            # Get the data for this genome.
530            my ($genomeID, $genus, $species, $strain) = @{$genomeData};
531            # Get the contig count.
532            my $contigInfo = "";
533            if ($slowMode) {
534                my $count = $self->ContigCount($genomeID);
535                my $counting = ($count == 1 ? "contig" : "contigs");
536                $contigInfo = "[$count $counting]";
537            }
538            # Find out if we're selected.
539            my $selectOption = ($selected eq $genomeID ? " selected" : "");
540            # Build the option tag.
541            $retVal .= "<option value=\"$genomeID\"$selectOption>$genus $species $strain ($genomeID)$contigInfo</option>\n";
542        }
543        # Close the SELECT tag.
544        $retVal .= "</select>\n";
545        # Return the result.
546        return $retVal;
547    }
548    
549  =head3 Build  =head3 Build
550    
551  C<< $sprout->Build(); >>      $sprout->Build();
552    
553  Build the database. The database will be cleared and the tables re-created from the metadata.  Build the database. The database will be cleared and the tables re-created from the metadata.
554  This method is useful when a database is brand new or when the database definition has  This method is useful when a database is brand new or when the database definition has
# Line 460  Line 560 
560      # Get the parameters.      # Get the parameters.
561      my ($self) = @_;      my ($self) = @_;
562      # Create the tables.      # Create the tables.
563      $self->{_erdb}->CreateTables;      $self->CreateTables();
564  }  }
565    
566  =head3 Genomes  =head3 Genomes
567    
568  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
569    
570  Return a list of all the genome IDs.  Return a list of all the genome IDs.
571    
# Line 482  Line 582 
582    
583  =head3 GenusSpecies  =head3 GenusSpecies
584    
585  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
586    
587  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
588    
# Line 514  Line 614 
614    
615  =head3 FeaturesOf  =head3 FeaturesOf
616    
617  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
618    
619  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
620    
# Line 559  Line 659 
659    
660  =head3 FeatureLocation  =head3 FeatureLocation
661    
662  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
663    
664  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
665  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 588  Line 688 
688  =back  =back
689    
690  =cut  =cut
691  #: Return Type @;  
 #: Return Type $;  
692  sub FeatureLocation {  sub FeatureLocation {
693      # Get the parameters.      # Get the parameters.
694      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
695      # Create a query for the feature locations.      # Get the feature record.
696      my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",      my $object = $self->GetEntity('Feature', $featureID);
697                             [$featureID]);      Confess("Feature $featureID not found.") if ! defined($object);
698        # Get the location string.
699        my $locString = $object->PrimaryValue('Feature(location-string)');
700      # Create the return list.      # Create the return list.
701      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);  
         # Compute the initial base pair.  
         my $start = ($dir eq "+" ? $beg : $beg + $len - 1);  
         # Add the specifier to the list.  
         push @retVal, "${contigID}_$start$dir$len";  
     }  
702      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
703      return (wantarray ? @retVal : join(',', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
704  }  }
705    
706  =head3 ParseLocation  =head3 ParseLocation
707    
708  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
709    
710  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
711  length.  length.
# Line 652  Line 724 
724  =back  =back
725    
726  =cut  =cut
727  #: Return Type @;  
728  sub ParseLocation {  sub ParseLocation {
729      # 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
730      # the first parameter.      # the first parameter.
731      shift if UNIVERSAL::isa($_[0],__PACKAGE__);      shift if UNIVERSAL::isa($_[0],__PACKAGE__);
732      my ($location) = @_;      my ($location) = @_;
733      # Parse it into segments.      # Parse it into segments.
734      $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
735      my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);      my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
736      # If the direction is an underscore, convert it to a + or -.      # If the direction is an underscore, convert it to a + or -.
737      if ($dir eq "_") {      if ($dir eq "_") {
# Line 675  Line 747 
747      return ($contigID, $start, $dir, $len);      return ($contigID, $start, $dir, $len);
748  }  }
749    
750    
751    
752  =head3 PointLocation  =head3 PointLocation
753    
754  C<< my $found = Sprout::PointLocation($location, $point); >>      my $found = Sprout::PointLocation($location, $point);
755    
756  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
757  the specified point is before the location, a negative value will be returned. If it is  the specified point is before the location, a negative value will be returned. If it is
# Line 706  Line 780 
780  =back  =back
781    
782  =cut  =cut
783  #: Return Type $;  
784  sub PointLocation {  sub PointLocation {
785      # 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
786      # the first parameter.      # the first parameter.
# Line 729  Line 803 
803    
804  =head3 DNASeq  =head3 DNASeq
805    
806  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
807    
808  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
809  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,
810  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>.
811    
812    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
813    between positions 1401 and 1532, inclusive.
814    
815        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
816    
817  =over 4  =over 4
818    
819  =item locationList  =item locationList
820    
821  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
822  L</FeatureLocation> for more about this format).  I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
823    
824  =item RETURN  =item RETURN
825    
# Line 767  Line 846 
846          # the start point is the ending. Note that in the latter case we must reverse the DNA string          # the start point is the ending. Note that in the latter case we must reverse the DNA string
847          # before putting it in the return value.          # before putting it in the return value.
848          my ($start, $stop);          my ($start, $stop);
849          Trace("Parsed location is $beg$dir$len.") if T(SDNA => 4);          Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
850          if ($dir eq "+") {          if ($dir eq "+") {
851              $start = $beg;              $start = $beg;
852              $stop = $beg + $len - 1;              $stop = $beg + $len - 1;
# Line 790  Line 869 
869              Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);              Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
870              # Figure out the start point and length of the relevant section.              # Figure out the start point and length of the relevant section.
871              my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);              my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
872              my $len1 = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
873              Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);              Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
874              # Add the relevant data to the location data.              # Add the relevant data to the location data.
875              $locationDNA .= substr($sequenceData, $pos1, $len1);              $locationDNA .= substr($sequenceData, $pos1, $len1);
# Line 808  Line 887 
887    
888  =head3 AllContigs  =head3 AllContigs
889    
890  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
891    
892  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
893    
# Line 836  Line 915 
915      return @retVal;      return @retVal;
916  }  }
917    
918  =head3 ContigLength  =head3 GenomeLength
919    
920  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->GenomeLength($genomeID);
921    
922  Compute the length of a contig.  Return the length of the specified genome in base pairs.
923    
924  =over 4  =over 4
925    
926  =item contigID  =item genomeID
927    
928  ID of the contig whose length is desired.  ID of the genome whose base pair count is desired.
929    
930  =item RETURN  =item RETURN
931    
932  Returns the number of positions in the contig.  Returns the number of base pairs in all the contigs of the specified
933    genome.
934    
935  =back  =back
936    
937  =cut  =cut
938  #: Return Type $;  
939  sub ContigLength {  sub GenomeLength {
940      # Get the parameters.      # Get the parameters.
941      my ($self, $contigID) = @_;      my ($self, $genomeID) = @_;
942      # 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.  
943      my $retVal = 0;      my $retVal = 0;
944      # Set it from the sequence data, if any.      # Get the genome's contig sequence lengths.
945      if ($sequence) {      my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',
946          my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                         [$genomeID], 'IsMadeUpOf(len)');
947          $retVal = $start + $len;      # Sum the lengths.
948      }      map { $retVal += $_ } @lens;
949      # Return the result.      # Return the result.
950      return $retVal;      return $retVal;
951  }  }
952    
953  =head3 GenesInRegion  =head3 FeatureCount
954    
955  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my $count = $sprout->FeatureCount($genomeID, $type);
956    
957  List the features which overlap a specified region in a contig.  Return the number of features of the specified type in the specified genome.
958    
959  =over 4  =over 4
960    
961  =item contigID  =item genomeID
962    
963  ID of the contig containing the region of interest.  ID of the genome whose feature count is desired.
964    
965  =item start  =item type
966    
967  Offset of the first residue in the region of interest.  Type of feature to count (eg. C<peg>, C<rna>, etc.).
968    
969  =item stop  =item RETURN
970    
971  Offset of the last residue in the region of interest.  Returns the number of features of the specified type for the specified genome.
972    
973    =back
974    
975    =cut
976    
977    sub FeatureCount {
978        # Get the parameters.
979        my ($self, $genomeID, $type) = @_;
980        # Compute the count.
981        my $retVal = $self->GetCount(['HasFeature', 'Feature'],
982                                    "HasFeature(from-link) = ? AND Feature(feature-type) = ?",
983                                    [$genomeID, $type]);
984        # Return the result.
985        return $retVal;
986    }
987    
988    =head3 GenomeAssignments
989    
990        my $fidHash = $sprout->GenomeAssignments($genomeID);
991    
992    Return a list of a genome's assigned features. The return hash will contain each
993    assigned feature of the genome mapped to the text of its most recent functional
994    assignment.
995    
996    =over 4
997    
998    =item genomeID
999    
1000    ID of the genome whose functional assignments are desired.
1001    
1002  =item RETURN  =item RETURN
1003    
1004  Returns a three-element list. The first element is a list of feature IDs for the features that  Returns a reference to a hash which maps each feature to its most recent
1005  overlap the region of interest. The second and third elements are the minimum and maximum  functional assignment.
 locations of the features provided on the specified contig. These may extend outside  
 the start and stop values. The first element (that is, the list of features) is sorted  
 roughly by location.  
1006    
1007  =back  =back
1008    
1009  =cut  =cut
1010  #: Return Type @@;  
1011  sub GenesInRegion {  sub GenomeAssignments {
1012      # Get the parameters.      # Get the parameters.
1013      my ($self, $contigID, $start, $stop) = @_;      my ($self, $genomeID) = @_;
1014        # Declare the return variable.
1015        my $retVal = {};
1016        # Query the genome's features.
1017        my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?",
1018                               [$genomeID]);
1019        # Loop through the features.
1020        while (my $data = $query->Fetch) {
1021            # Get the feature ID and assignment.
1022            my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
1023            if ($assignment) {
1024                $retVal->{$fid} = $assignment;
1025            }
1026        }
1027        # Return the result.
1028        return $retVal;
1029    }
1030    
1031    =head3 ContigLength
1032    
1033        my $length = $sprout->ContigLength($contigID);
1034    
1035    Compute the length of a contig.
1036    
1037    =over 4
1038    
1039    =item contigID
1040    
1041    ID of the contig whose length is desired.
1042    
1043    =item RETURN
1044    
1045    Returns the number of positions in the contig.
1046    
1047    =back
1048    
1049    =cut
1050    #: Return Type $;
1051    sub ContigLength {
1052        # Get the parameters.
1053        my ($self, $contigID) = @_;
1054        # Get the contig's last sequence.
1055        my $query = $self->Get(['IsMadeUpOf'],
1056            "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
1057            [$contigID]);
1058        my $sequence = $query->Fetch();
1059        # Declare the return value.
1060        my $retVal = 0;
1061        # Set it from the sequence data, if any.
1062        if ($sequence) {
1063            my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
1064            $retVal = $start + $len - 1;
1065        }
1066        # Return the result.
1067        return $retVal;
1068    }
1069    
1070    =head3 ClusterPEGs
1071    
1072        my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1073    
1074    Cluster the PEGs in a list according to the cluster coding scheme of the specified
1075    subsystem. In order for this to work properly, the subsystem object must have
1076    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> or
1077    B<get_row> methods. This causes the cluster numbers to be pulled into the
1078    subsystem's color hash. If a PEG is not found in the color hash, it will not
1079    appear in the output sequence.
1080    
1081    =over 4
1082    
1083    =item sub
1084    
1085    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
1086    method.
1087    
1088    =item pegs
1089    
1090    Reference to the list of PEGs to be clustered.
1091    
1092    =item RETURN
1093    
1094    Returns a list of the PEGs, grouped into smaller lists by cluster number.
1095    
1096    =back
1097    
1098    =cut
1099    #: Return Type $@@;
1100    sub ClusterPEGs {
1101        # Get the parameters.
1102        my ($self, $sub, $pegs) = @_;
1103        # Declare the return variable.
1104        my $retVal = [];
1105        # Loop through the PEGs, creating arrays for each cluster.
1106        for my $pegID (@{$pegs}) {
1107            my $clusterNumber = $sub->get_cluster_number($pegID);
1108            # Only proceed if the PEG is in a cluster.
1109            if ($clusterNumber >= 0) {
1110                # Push this PEG onto the sub-list for the specified cluster number.
1111                push @{$retVal->[$clusterNumber]}, $pegID;
1112            }
1113        }
1114        # Return the result.
1115        return $retVal;
1116    }
1117    
1118    =head3 GenesInRegion
1119    
1120        my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1121    
1122    List the features which overlap a specified region in a contig.
1123    
1124    =over 4
1125    
1126    =item contigID
1127    
1128    ID of the contig containing the region of interest.
1129    
1130    =item start
1131    
1132    Offset of the first residue in the region of interest.
1133    
1134    =item stop
1135    
1136    Offset of the last residue in the region of interest.
1137    
1138    =item RETURN
1139    
1140    Returns a three-element list. The first element is a list of feature IDs for the features that
1141    overlap the region of interest. The second and third elements are the minimum and maximum
1142    locations of the features provided on the specified contig. These may extend outside
1143    the start and stop values. The first element (that is, the list of features) is sorted
1144    roughly by location.
1145    
1146    =back
1147    
1148    =cut
1149    
1150    sub GenesInRegion {
1151        # Get the parameters.
1152        my ($self, $contigID, $start, $stop) = @_;
1153      # Get the maximum segment length.      # Get the maximum segment length.
1154      my $maximumSegmentLength = $self->MaxSegment;      my $maximumSegmentLength = $self->MaxSegment;
     # Create a hash to receive the feature list. We use a hash so that we can eliminate  
     # duplicates easily. The hash key will be the feature ID. The value will be a two-element  
     # containing the minimum and maximum offsets. We will use the offsets to sort the results  
     # when we're building the result set.  
     my %featuresFound = ();  
1155      # Prime the values we'll use for the returned beginning and end.      # Prime the values we'll use for the returned beginning and end.
1156      my @initialMinMax = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
1157      my ($min, $max) = @initialMinMax;      my ($min, $max) = @initialMinMax;
1158      # Create a table of parameters for each query. Each query looks for features travelling in      # Get the overlapping features.
1159        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1160        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1161        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1162        # of the feature's locations.
1163        my %featureMap = ();
1164        # Loop through them to do the begin/end analysis.
1165        for my $featureObject (@featureObjects) {
1166            # Get the feature's location string. This may contain multiple actual locations.
1167            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1168            my @locationSegments = split /\s*,\s*/, $locations;
1169            # Loop through the locations.
1170            for my $locationSegment (@locationSegments) {
1171                # Construct an object for the location.
1172                my $locationObject = BasicLocation->new($locationSegment);
1173                # Merge the current segment's begin and end into the min and max.
1174                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1175                my ($beg, $end);
1176                if (exists $featureMap{$fid}) {
1177                    ($beg, $end) = @{$featureMap{$fid}};
1178                    $beg = $left if $left < $beg;
1179                    $end = $right if $right > $end;
1180                } else {
1181                    ($beg, $end) = ($left, $right);
1182                }
1183                $min = $beg if $beg < $min;
1184                $max = $end if $end > $max;
1185                # Store the feature's new extent back into the hash table.
1186                $featureMap{$fid} = [$beg, $end];
1187            }
1188        }
1189        # Now we must compute the list of the IDs for the features found. We start with a list
1190        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1191        # but the result of the sort will be the same.)
1192        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1193        # Now we sort by midpoint and yank out the feature IDs.
1194        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1195        # Return it along with the min and max.
1196        return (\@retVal, $min, $max);
1197    }
1198    
1199    =head3 GeneDataInRegion
1200    
1201        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1202    
1203    List the features which overlap a specified region in a contig.
1204    
1205    =over 4
1206    
1207    =item contigID
1208    
1209    ID of the contig containing the region of interest.
1210    
1211    =item start
1212    
1213    Offset of the first residue in the region of interest.
1214    
1215    =item stop
1216    
1217    Offset of the last residue in the region of interest.
1218    
1219    =item RETURN
1220    
1221    Returns a list of B<ERDBObjects> for the desired features. Each object will
1222    contain a B<Feature> record.
1223    
1224    =back
1225    
1226    =cut
1227    
1228    sub GeneDataInRegion {
1229        # Get the parameters.
1230        my ($self, $contigID, $start, $stop) = @_;
1231        # Get the maximum segment length.
1232        my $maximumSegmentLength = $self->MaxSegment;
1233        # Create a hash to receive the feature list. We use a hash so that we can eliminate
1234        # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1235        # ERDBObject from the query.
1236        my %featuresFound = ();
1237        # Create a table of parameters for the queries. Each query looks for features travelling in
1238      # 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,
1239      # 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
1240      # because each feature segment length must be no greater than the maximum segment length.      # because each feature segment length must be no greater than the maximum segment length.
# Line 929  Line 1243 
1243      # Loop through the query parameters.      # Loop through the query parameters.
1244      for my $parms (values %queryParms) {      for my $parms (values %queryParms) {
1245          # Create the query.          # Create the query.
1246          my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1247              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1248              $parms);              $parms);
1249          # Loop through the feature segments found.          # Loop through the feature segments found.
1250          while (my $segment = $query->Fetch) {          while (my $segment = $query->Fetch) {
1251              # Get the data about this segment.              # Get the data about this segment.
1252              my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1253                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1254              # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1255              # this will be the case if the segment is the maximum length, so to fine-tune              # this will be the case if the segment is the maximum length, so to fine-tune
1256              # the results we insure that the inequality from the query holds using the actual              # the results we insure that the inequality from the query holds using the actual
1257              # length.              # length.
1258              my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1259              if ($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.  
                     $found = 1;  
                 }  
             }  
1260              if ($found) {              if ($found) {
1261                  # Here we need to record the feature and update the minima and maxima. First,                  # Save this feature in the result list.
1262                  # 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 < $min;  
1263                  }                  }
                 if ($end > $loc2) {  
                     $loc2 = $end;  
                     $max = $end if $end > $max;  
                 }  
                 # Store the entry back into the hash table.  
                 $featuresFound{$featureID} = [$loc1, $loc2];  
1264              }              }
1265          }          }
1266      }      # Return the ERDB objects for the features found.
1267      # Now we must compute the list of the IDs for the features found. We start with a list      return values %featuresFound;
     # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,  
     # but the result of the sort will be the same.)  
     my @list = map { [$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);  
1268  }  }
1269    
1270  =head3 FType  =head3 FType
1271    
1272  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1273    
1274  Return the type of a feature.  Return the type of a feature.
1275    
# Line 1019  Line 1299 
1299    
1300  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1301    
1302  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1303    
1304  Return the annotations of a feature.  Return the annotations of a feature.
1305    
# Line 1029  Line 1309 
1309    
1310  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1311    
1312    =item rawFlag
1313    
1314    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1315    will be returned in human-readable form.
1316    
1317  =item RETURN  =item RETURN
1318    
1319  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1320    
1321  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1322    
1323  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1324    
1325  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1326    
# Line 1047  Line 1332 
1332  #: Return Type @%;  #: Return Type @%;
1333  sub FeatureAnnotations {  sub FeatureAnnotations {
1334      # Get the parameters.      # Get the parameters.
1335      my ($self, $featureID) = @_;      my ($self, $featureID, $rawFlag) = @_;
1336      # 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.
1337      my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],      my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1338                             "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                             "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1060  Line 1345 
1345              $annotation->Values(['IsTargetOfAnnotation(from-link)',              $annotation->Values(['IsTargetOfAnnotation(from-link)',
1346                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1347                                   'Annotation(annotation)']);                                   'Annotation(annotation)']);
1348            # Convert the time, if necessary.
1349            if (! $rawFlag) {
1350                $timeStamp = FriendlyTimestamp($timeStamp);
1351            }
1352          # Assemble them into a hash.          # Assemble them into a hash.
1353          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1354                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1355                                 user => $user, text => $text };                                 user => $user, text => $text };
1356          # Add it to the return list.          # Add it to the return list.
1357          push @retVal, $annotationHash;          push @retVal, $annotationHash;
# Line 1073  Line 1362 
1362    
1363  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1364    
1365  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1366    
1367  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
1368  hash of functional assignments to user IDs. A functional assignment is a type of annotation,  hash of functional assignments to user IDs. A functional assignment is a type of annotation,
# Line 1091  Line 1380 
1380    
1381  =item RETURN  =item RETURN
1382    
1383  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1384    
1385  =back  =back
1386    
# Line 1101  Line 1390 
1390      # Get the parameters.      # Get the parameters.
1391      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1392      # Get all of the feature's annotations.      # Get all of the feature's annotations.
1393      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1394                              "IsTargetOfAnnotation(from-link) = ?",                              "IsTargetOfAnnotation(from-link) = ?",
1395                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1396                                               'MadeAnnotation(from-link)']);
1397      # Declare the return hash.      # Declare the return hash.
1398      my %retVal;      my %retVal;
     # Declare a hash for insuring we only make one assignment per user.  
     my %timeHash = ();  
1399      # Now we sort the assignments by timestamp in reverse.      # Now we sort the assignments by timestamp in reverse.
1400      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1401      # Loop until we run out of annotations.      # Loop until we run out of annotations.
1402      for my $annotation (@sortedQuery) {      for my $annotation (@sortedQuery) {
1403          # Get the annotation fields.          # Get the annotation fields.
1404          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text, $user) = @{$annotation};
1405          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
1406          my ($user, $function) = _ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1407          if ($user && ! exists $timeHash{$user}) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1408              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1409              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
1410              # return hash.              # return hash.
1411              $retVal{$function} = $user;              $retVal{$actualUser} = $function;
             # Insure we don't assign to this user again.  
             $timeHash{$user} = 1;  
1412          }          }
1413      }      }
1414      # Return the hash of assignments found.      # Return the hash of assignments found.
# Line 1131  Line 1417 
1417    
1418  =head3 FunctionOf  =head3 FunctionOf
1419    
1420  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1421    
1422  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1423    
1424  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
1425  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
1426  assignment is a type of annotation. The format of an assignment is described in  assignment is taken from the B<Feature> or C<Annotation> table, depending.
 L</ParseLocation>. Its worth noting that we cannot filter on the content of the  
 annotation itself because it's a text field; however, this is not a big problem because  
 most features only have a small number of annotations.  
1427    
1428  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
1429  recent one by at least one of the trusted users. If no trusted user list is available, then  recent one by at least one of the trusted users. If no trusted user list is available, then
# Line 1159  Line 1442 
1442    
1443  =item userID (optional)  =item userID (optional)
1444    
1445  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
1446  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1447    
1448  =item RETURN  =item RETURN
1449    
# Line 1177  Line 1460 
1460      my $retVal;      my $retVal;
1461      # Determine the ID type.      # Determine the ID type.
1462      if ($featureID =~ m/^fig\|/) {      if ($featureID =~ m/^fig\|/) {
1463          # Here we have a FIG feature ID. We must build the list of trusted          # Here we have a FIG feature ID.
1464          # users.          if (!$userID) {
1465                # Use the primary assignment.
1466                ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);
1467            } else {
1468                # We must build the list of trusted users.
1469          my %trusteeTable = ();          my %trusteeTable = ();
1470          # Check the user ID.          # Check the user ID.
1471          if (!$userID) {          if (!$userID) {
# Line 1200  Line 1487 
1487              }              }
1488          }          }
1489          # 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.
1490          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1491                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1492                                 [$featureID]);                                 [$featureID]);
1493          my $timeSelected = 0;          my $timeSelected = 0;
1494          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1495          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1496              # Get the annotation text.              # Get the annotation text.
1497              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);                  my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1498                                                             'Annotation(time)', 'MadeAnnotation(from-link)']);
1499              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1500              my ($user, $function) = _ParseAssignment($text);                  my ($actualUser, $function) = _ParseAssignment($user, $text);
1501              if ($user) {                  Trace("Assignment user is $actualUser, text is $function.") if T(4);
1502                    if ($actualUser) {
1503                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1504                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1505                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                      if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1506                      $retVal = $function;                      $retVal = $function;
1507                      $timeSelected = $time;                      $timeSelected = $time;
1508                  }                  }
1509              }              }
1510          }          }
1511            }
1512      } else {      } else {
1513          # 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
1514          # matter. We simply get the information from the External Alias Function          # matter. We simply get the information from the External Alias Function
# Line 1229  Line 1519 
1519      return $retVal;      return $retVal;
1520  }  }
1521    
1522    =head3 FunctionsOf
1523    
1524        my @functionList = $sprout->FunctionOf($featureID, $userID);
1525    
1526    Return the functional assignments of a particular feature.
1527    
1528    The functional assignment is handled differently depending on the type of feature. If
1529    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1530    assignment is a type of annotation. The format of an assignment is described in
1531    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1532    annotation itself because it's a text field; however, this is not a big problem because
1533    most features only have a small number of annotations.
1534    
1535    If the feature is B<not> identified by a FIG ID, then the functional assignment
1536    information is taken from the B<ExternalAliasFunc> table. If the table does
1537    not contain an entry for the feature, an empty list is returned.
1538    
1539    =over 4
1540    
1541    =item featureID
1542    
1543    ID of the feature whose functional assignments are desired.
1544    
1545    =item RETURN
1546    
1547    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1548    that user.
1549    
1550    =back
1551    
1552    =cut
1553    #: Return Type @@;
1554    sub FunctionsOf {
1555        # Get the parameters.
1556        my ($self, $featureID) = @_;
1557        # Declare the return value.
1558        my @retVal = ();
1559        # Determine the ID type.
1560        if ($featureID =~ m/^fig\|/) {
1561            # Here we have a FIG feature ID. We must build the list of trusted
1562            # users.
1563            my %trusteeTable = ();
1564            # Build a query for all of the feature's annotations, sorted by date.
1565            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1566                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1567                                   [$featureID]);
1568            my $timeSelected = 0;
1569            # Loop until we run out of annotations.
1570            while (my $annotation = $query->Fetch()) {
1571                # Get the annotation text.
1572                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1573                                                                'Annotation(time)',
1574                                                                'MadeAnnotation(user)']);
1575                # Check to see if this is a functional assignment for a trusted user.
1576                my ($actualUser, $function) = _ParseAssignment($user, $text);
1577                if ($actualUser) {
1578                    # Here it is a functional assignment.
1579                    push @retVal, [$actualUser, $function];
1580                }
1581            }
1582        } else {
1583            # Here we have a non-FIG feature ID. In this case the user ID does not
1584            # matter. We simply get the information from the External Alias Function
1585            # table.
1586            my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1587                                                     ['ExternalAliasFunc(func)']);
1588            push @retVal, map { ['master', $_] } @assignments;
1589        }
1590        # Return the assignments found.
1591        return @retVal;
1592    }
1593    
1594  =head3 BBHList  =head3 BBHList
1595    
1596  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1597    
1598  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
1599  on a specified target genome.  on a specified target genome.
# Line 1262  Line 1624 
1624      my %retVal = ();      my %retVal = ();
1625      # Loop through the incoming features.      # Loop through the incoming features.
1626      for my $featureID (@{$featureList}) {      for my $featureID (@{$featureList}) {
1627          # Create a query to get the feature's best hit.          # Ask the server for the feature's best hit.
1628          my $query = $self->Get(['IsBidirectionalBestHitOf'],          my @bbhData = FIGRules::BBHData($featureID);
1629                                 "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",          # Peel off the BBHs found.
1630                                 [$featureID, $genomeID]);          my @found = ();
1631          # Look for the best hit.          for my $bbh (@bbhData) {
1632          my $bbh = $query->Fetch;              my $fid = $bbh->[0];
1633          if ($bbh) {              my $bbGenome = $self->GenomeOf($fid);
1634              my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              if ($bbGenome eq $genomeID) {
1635              $retVal{$featureID} = $targetFeature;                  push @found, $fid;
1636                }
1637          }          }
1638            $retVal{$featureID} = \@found;
1639      }      }
1640      # Return the mapping.      # Return the mapping.
1641      return \%retVal;      return \%retVal;
# Line 1279  Line 1643 
1643    
1644  =head3 SimList  =head3 SimList
1645    
1646  C<< my %similarities = $sprout->SimList($featureID, $count); >>      my %similarities = $sprout->SimList($featureID, $count);
1647    
1648  Return a list of the similarities to the specified feature.  Return a list of the similarities to the specified feature.
1649    
1650  Sprout does not support real similarities, so this method just returns the bidirectional  This method just returns the bidirectional best hits for performance reasons.
 best hits.  
1651    
1652  =over 4  =over 4
1653    
# Line 1304  Line 1667 
1667      # Get the parameters.      # Get the parameters.
1668      my ($self, $featureID, $count) = @_;      my ($self, $featureID, $count) = @_;
1669      # Ask for the best hits.      # Ask for the best hits.
1670      my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],      my @lists = FIGRules::BBHData($featureID);
                               "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",  
                               [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],  
                               $count);  
1671      # Create the return value.      # Create the return value.
1672      my %retVal = ();      my %retVal = ();
1673      for my $tuple (@lists) {      for my $tuple (@lists) {
# Line 1317  Line 1677 
1677      return %retVal;      return %retVal;
1678  }  }
1679    
   
   
1680  =head3 IsComplete  =head3 IsComplete
1681    
1682  C<< my $flag = $sprout->IsComplete($genomeID); >>      my $flag = $sprout->IsComplete($genomeID);
1683    
1684  Return TRUE if the specified genome is complete, else FALSE.  Return TRUE if the specified genome is complete, else FALSE.
1685    
# Line 1349  Line 1707 
1707      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->GetEntity('Genome', $genomeID);
1708      if ($genomeData) {      if ($genomeData) {
1709          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1710          ($retVal) = $genomeData->Value('complete');          $retVal = $genomeData->PrimaryValue('Genome(complete)');
1711      }      }
1712      # Return the result.      # Return the result.
1713      return $retVal;      return $retVal;
# Line 1357  Line 1715 
1715    
1716  =head3 FeatureAliases  =head3 FeatureAliases
1717    
1718  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1719    
1720  Return a list of the aliases for a specified feature.  Return a list of the aliases for a specified feature.
1721    
# Line 1380  Line 1738 
1738      # Get the parameters.      # Get the parameters.
1739      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1740      # Get the desired feature's aliases      # Get the desired feature's aliases
1741      my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
1742      # Return the result.      # Return the result.
1743      return @retVal;      return @retVal;
1744  }  }
1745    
1746  =head3 GenomeOf  =head3 GenomeOf
1747    
1748  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $genomeID = $sprout->GenomeOf($featureID);
1749    
1750  Return the genome that contains a specified feature.  Return the genome that contains a specified feature or contig.
1751    
1752  =over 4  =over 4
1753    
1754  =item featureID  =item featureID
1755    
1756  ID of the feature whose genome is desired.  ID of the feature or contig whose genome is desired.
1757    
1758  =item RETURN  =item RETURN
1759    
1760  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
1761  an undefined value.  found, returns an undefined value.
1762    
1763  =back  =back
1764    
# Line 1409  Line 1767 
1767  sub GenomeOf {  sub GenomeOf {
1768      # Get the parameters.      # Get the parameters.
1769      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]);  
1770      # Declare the return value.      # Declare the return value.
1771      my $retVal;      my $retVal;
1772      # Get the genome ID.      # Parse the genome ID from the feature ID.
1773      if (my $relationship = $query->Fetch()) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
1774          ($retVal) = $relationship->Value('HasContig(from-link)');          $retVal = $1;
1775        } else {
1776            Confess("Invalid feature ID $featureID.");
1777      }      }
1778      # Return the value found.      # Return the value found.
1779      return $retVal;      return $retVal;
# Line 1423  Line 1781 
1781    
1782  =head3 CoupledFeatures  =head3 CoupledFeatures
1783    
1784  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
1785    
1786  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
1787  functionally coupled if they tend to be clustered on the same chromosome.  functionally coupled if they tend to be clustered on the same chromosome.
# Line 1445  Line 1803 
1803  sub CoupledFeatures {  sub CoupledFeatures {
1804      # Get the parameters.      # Get the parameters.
1805      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1806      # Create a query to retrieve the functionally-coupled features.      # Ask the coupling server for the data.
1807      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
1808                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
1809      # This value will be set to TRUE if we find at least one coupled feature.      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
1810      my $found = 0;      # Form them into a hash.
     # Create the return hash.  
1811      my %retVal = ();      my %retVal = ();
1812      # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
1813      while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
1814          # Get the ID and score of the coupling.          my ($featureID2, $score) = @{$pair};
1815          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',          # Only proceed if the feature is in NMPDR.
1816                                                          'Coupling(score)']);          if ($self->_CheckFeature($featureID2)) {
1817          # The coupling ID contains the two feature IDs separated by a space. We use              $retVal{$featureID2} = $score;
1818          # this information to find the ID of the other feature.          }
         my ($fid1, $fid2) = split / /, $couplingID;  
         my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);  
         # Attach the other feature's score to its ID.  
         $retVal{$otherFeatureID} = $score;  
         $found = 1;  
1819      }      }
1820      # Functional coupling is reflexive. If we found at least one coupled feature, we must add      # Functional coupling is reflexive. If we found at least one coupled feature, we must add
1821      # the incoming feature as well.      # the incoming feature as well.
1822      if ($found) {      if (keys %retVal) {
1823          $retVal{$featureID} = 9999;          $retVal{$featureID} = 9999;
1824      }      }
1825      # Return the hash.      # Return the hash.
# Line 1476  Line 1828 
1828    
1829  =head3 CouplingEvidence  =head3 CouplingEvidence
1830    
1831  C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>      my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
1832    
1833  Return the evidence for a functional coupling.  Return the evidence for a functional coupling.
1834    
# Line 1524  Line 1876 
1876      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
1877      # Declare the return variable.      # Declare the return variable.
1878      my @retVal = ();      my @retVal = ();
1879      # Our first task is to find out the nature of the coupling: whether or not      # Get the coupling and evidence data.
1880      # it exists, its score, and whether the features are stored in the same      my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
1881      # order as the ones coming in.      # Loop through the raw data, saving the ones that are in NMPDR genomes.
1882      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);      for my $rawTuple (@rawData) {
1883      # Only proceed if a coupling exists.          if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
1884      if ($couplingID) {              push @retVal, $rawTuple;
1885          # Determine the ordering to place on the evidence items. If we're          }
         # inverted, we want to see feature 2 before feature 1 (descending); otherwise,  
         # we want feature 1 before feature 2 (normal).  
         Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);  
         my $ordering = ($inverted ? "DESC" : "");  
         # Get the coupling evidence.  
         my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],  
                                           "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",  
                                           [$couplingID],  
                                           ['PCH(used)', 'UsesAsEvidence(to-link)']);  
         # Loop through the evidence items. Each piece of evidence is represented by two  
         # positions in the evidence list, one for each feature on the other side of the  
         # evidence link. If at some point we want to generalize to couplings with  
         # more than two positions, this section of code will need to be re-done.  
         while (@evidenceList > 0) {  
             my $peg1Data = shift @evidenceList;  
             my $peg2Data = shift @evidenceList;  
             Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);  
             push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];  
         }  
         Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);  
1886      }      }
1887      # Return the result.      # Return the result.
1888      return @retVal;      return @retVal;
1889  }  }
1890    
1891  =head3 GetCoupling  =head3 GetSynonymGroup
   
 C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>  
   
 Return the coupling (if any) for the specified pair of PEGs. If a coupling  
 exists, we return the coupling ID along with an indicator of whether the  
 coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.  
 In the second case, we say the coupling is I<inverted>. The importance of an  
 inverted coupling is that the PEGs in the evidence will appear in reverse order.  
1892    
1893  =over 4      my $id = $sprout->GetSynonymGroup($fid);
1894    
1895  =item peg1  Return the synonym group name for the specified feature.
1896    
1897  ID of the feature of interest.  =over 4
1898    
1899  =item peg2  =item fid
1900    
1901  ID of the potentially coupled feature.  ID of the feature whose synonym group is desired.
1902    
1903  =item RETURN  =item RETURN
1904    
1905  Returns a three-element list. The first element contains the database ID of  The name of the synonym group to which the feature belongs. If the feature does
1906  the coupling. The second element is FALSE if the coupling is stored in the  not belong to a synonym group, the feature ID itself is returned.
 database in the caller specified order and TRUE if it is stored in the  
 inverted order. The third element is the coupling's score. If the coupling  
 does not exist, all three list elements will be C<undef>.  
1907    
1908  =back  =back
1909    
1910  =cut  =cut
1911  #: Return Type $%@;  
1912  sub GetCoupling {  sub GetSynonymGroup {
1913      # Get the parameters.      # Get the parameters.
1914      my ($self, $peg1, $peg2) = @_;      my ($self, $fid) = @_;
1915      # Declare the return values. We'll start with the coupling ID and undefine the      # Declare the return variable.
1916      # flag and score until we have more information.      my $retVal;
1917      my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);      # Find the synonym group.
1918      # Find the coupling data.      my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?",
1919      my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],                                     [$fid], 'IsSynonymGroupFor(from-link)');
                                  "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",  
                                  [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);  
1920      # Check to see if we found anything.      # Check to see if we found anything.
1921      if (!@pegs) {      if (@groups) {
1922          Trace("No coupling found.") if T(Coupling => 4);          $retVal = $groups[0];
         # No coupling, so undefine the return value.  
         $retVal = undef;  
1923      } else {      } else {
1924          # We have a coupling! Get the score and check for inversion.          $retVal = $fid;
         $score = $pegs[0]->[1];  
         my $firstFound = $pegs[0]->[0];  
         $inverted = ($firstFound ne $peg1);  
         Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);  
1925      }      }
1926      # Return the result.      # Return the result.
1927      return ($retVal, $inverted, $score);      return $retVal;
1928  }  }
1929    
1930  =head3 CouplingID  =head3 GetBoundaries
1931    
1932  C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>      my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
1933    
1934  Return the coupling ID for a pair of feature IDs.  Determine the begin and end boundaries for the locations in a list. All of the
1935    locations must belong to the same contig and have mostly the same direction in
1936  The coupling ID is currently computed by joining the feature IDs in  order for this method to produce a meaningful result. The resulting
1937  sorted order with a space. Client modules (that is, modules which  begin/end pair will contain all of the bases in any of the locations.
 use Sprout) should not, however, count on this always being the  
 case. This method provides a way for abstracting the concept of a  
 coupling ID. All that we know for sure about it is that it can be  
 generated easily from the feature IDs and the order of the IDs  
 in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>  
 will have the same value as C<CouplingID("b1", "a1")>.  
1938    
1939  =over 4  =over 4
1940    
1941  =item peg1  =item locList
1942    
1943  First feature of interest.  List of locations to process.
1944    
1945  =item peg2  =item RETURN
1946    
1947  Second feature of interest.  Returns a 3-tuple consisting of the contig ID, the beginning boundary,
1948    and the ending boundary. The beginning boundary will be left of the
1949  =item RETURN  end for mostly-forward locations and right of the end for mostly-backward
1950    locations.
 Returns the ID that would be used to represent a functional coupling of  
 the two specified PEGs.  
1951    
1952  =back  =back
1953    
1954  =cut  =cut
 #: Return Type $;  
 sub CouplingID {  
     return join " ", sort @_;  
 }  
   
 =head3 GetEntityTypes  
   
 C<< my @entityList = $sprout->GetEntityTypes(); >>  
   
 Return the list of supported entity types.  
1955    
1956  =cut  sub GetBoundaries {
 #: Return Type @;  
 sub GetEntityTypes {  
1957      # Get the parameters.      # Get the parameters.
1958      my ($self) = @_;      my ($self, @locList) = @_;
1959      # Get the underlying database object.      # Set up the counters used to determine the most popular direction.
1960      my $erdb = $self->{_erdb};      my %counts = ( '+' => 0, '-' => 0 );
1961      # Get its entity type list.      # Get the last location and parse it.
1962      my @retVal = $erdb->GetEntityTypes();      my $locObject = BasicLocation->new(pop @locList);
1963        # Prime the loop with its data.
1964        my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right);
1965        # Count its direction.
1966        $counts{$locObject->Dir}++;
1967        # Loop through the remaining locations. Note that in most situations, this loop
1968        # will not iterate at all, because most of the time we will be dealing with a
1969        # singleton list.
1970        for my $loc (@locList) {
1971            # Create a location object.
1972            my $locObject = BasicLocation->new($loc);
1973            # Count the direction.
1974            $counts{$locObject->Dir}++;
1975            # Get the left end and the right end.
1976            my $left = $locObject->Left;
1977            my $right = $locObject->Right;
1978            # Merge them into the return variables.
1979            if ($left < $beg) {
1980                $beg = $left;
1981            }
1982            if ($right > $end) {
1983                $end = $right;
1984            }
1985        }
1986        # If the most common direction is reverse, flip the begin and end markers.
1987        if ($counts{'-'} > $counts{'+'}) {
1988            ($beg, $end) = ($end, $beg);
1989        }
1990        # Return the result.
1991        return ($contig, $beg, $end);
1992  }  }
1993    
1994  =head3 ReadFasta  =head3 ReadFasta
1995    
1996  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
1997    
1998  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
1999  one or more lines of data. The first line begins with a > character and contains an ID.  one or more lines of data. The first line begins with a > character and contains an ID.
# Line 1737  Line 2059 
2059    
2060  =head3 FormatLocations  =head3 FormatLocations
2061    
2062  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2063    
2064  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
2065  format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward  format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward
# Line 1802  Line 2124 
2124    
2125  =head3 DumpData  =head3 DumpData
2126    
2127  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2128    
2129  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.
2130    
# Line 1814  Line 2136 
2136      # Get the data directory name.      # Get the data directory name.
2137      my $outputDirectory = $self->{_options}->{dataDir};      my $outputDirectory = $self->{_options}->{dataDir};
2138      # Dump the relations.      # Dump the relations.
2139      $self->{_erdb}->DumpRelations($outputDirectory);      $self->DumpRelations($outputDirectory);
2140  }  }
2141    
2142  =head3 XMLFileName  =head3 XMLFileName
2143    
2144  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2145    
2146  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2147    
# Line 1830  Line 2152 
2152      return $self->{_xmlName};      return $self->{_xmlName};
2153  }  }
2154    
2155    =head3 GetGenomeNameData
2156    
2157        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2158    
2159    Return the genus, species, and unique characterization for a genome. This
2160    is similar to L</GenusSpecies>, with the exception that it returns the
2161    values in three seperate fields.
2162    
2163    =over 4
2164    
2165    =item genomeID
2166    
2167    ID of the genome whose name data is desired.
2168    
2169    =item RETURN
2170    
2171    Returns a three-element list, consisting of the genus, species, and strain
2172    of the specified genome. If the genome is not found, an error occurs.
2173    
2174    =back
2175    
2176    =cut
2177    
2178    sub GetGenomeNameData {
2179        # Get the parameters.
2180        my ($self, $genomeID) = @_;
2181        # Get the desired values.
2182        my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>
2183                                                                [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);
2184        # Throw an error if they were not found.
2185        if (! defined $genus) {
2186            Confess("Genome $genomeID not found in database.");
2187        }
2188        # Return the results.
2189        return ($genus, $species, $strain);
2190    }
2191    
2192    =head3 GetGenomeByNameData
2193    
2194        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2195    
2196    Return a list of the IDs of the genomes with the specified genus,
2197    species, and strain. In almost every case, there will be either zero or
2198    one IDs returned; however, two or more IDs could be returned if there are
2199    multiple versions of the genome in the database.
2200    
2201    =over 4
2202    
2203    =item genus
2204    
2205    Genus of the desired genome.
2206    
2207    =item species
2208    
2209    Species of the desired genome.
2210    
2211    =item strain
2212    
2213    Strain (unique characterization) of the desired genome. This may be an empty
2214    string, in which case it is presumed that the desired genome has no strain
2215    specified.
2216    
2217    =item RETURN
2218    
2219    Returns a list of the IDs of the genomes having the specified genus, species, and
2220    strain.
2221    
2222    =back
2223    
2224    =cut
2225    
2226    sub GetGenomeByNameData {
2227        # Get the parameters.
2228        my ($self, $genus, $species, $strain) = @_;
2229        # Try to find the genomes.
2230        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2231                                    [$genus, $species, $strain], 'Genome(id)');
2232        # Return the result.
2233        return @retVal;
2234    }
2235    
2236  =head3 Insert  =head3 Insert
2237    
2238  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2239    
2240  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
2241  is defined by a type name and then a hash of field names to values. Field values in the primary  is defined by a type name and then a hash of field names to values. Field values in the primary
# Line 1841  Line 2244 
2244  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
2245  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>.
2246    
2247  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']});
2248    
2249  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
2250  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>.
2251    
2252  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>      $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2253    
2254  =over 4  =over 4
2255    
# Line 1866  Line 2269 
2269      # Get the parameters.      # Get the parameters.
2270      my ($self, $objectType, $fieldHash) = @_;      my ($self, $objectType, $fieldHash) = @_;
2271      # Call the underlying method.      # Call the underlying method.
2272      $self->{_erdb}->InsertObject($objectType, $fieldHash);      $self->InsertObject($objectType, $fieldHash);
2273  }  }
2274    
2275  =head3 Annotate  =head3 Annotate
2276    
2277  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2278    
2279  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
2280  specified feature and user.  specified feature and user.
# Line 1925  Line 2328 
2328    
2329  =head3 AssignFunction  =head3 AssignFunction
2330    
2331  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2332    
2333  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
2334  format is described in L</ParseAssignment>.  format is described in L</ParseAssignment>.
# Line 1985  Line 2388 
2388    
2389  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2390    
2391  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2392    
2393  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
2394  the type of the alias. A string of digits is a GenBack ID and a string of exactly 6  the type of the alias. A string of digits is a GenBack ID and a string of exactly 6
# Line 2019  Line 2422 
2422          push @retVal, $mappedAlias;          push @retVal, $mappedAlias;
2423      } else {      } else {
2424          # 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.
2425          @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2426      }      }
2427      # Return the result.      # Return the result.
2428      return @retVal;      return @retVal;
2429  }  }
2430    
 =head3 Exists  
   
 C<< my $found = $sprout->Exists($entityName, $entityID); >>  
   
 Return TRUE if an entity exists, else FALSE.  
   
 =over 4  
   
 =item entityName  
   
 Name of the entity type (e.g. C<Feature>) relevant to the existence check.  
   
 =item entityID  
   
 ID of the entity instance whose existence is to be checked.  
   
 =item RETURN  
   
 Returns TRUE if the entity instance exists, else FALSE.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub Exists {  
     # Get the parameters.  
     my ($self, $entityName, $entityID) = @_;  
     # Check for the entity instance.  
     Trace("Checking existence of $entityName with ID=$entityID.") if T(4);  
     my $testInstance = $self->GetEntity($entityName, $entityID);  
     # Return an existence indicator.  
     my $retVal = ($testInstance ? 1 : 0);  
     return $retVal;  
 }  
   
2431  =head3 FeatureTranslation  =head3 FeatureTranslation
2432    
2433  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2434    
2435  Return the translation of a feature.  Return the translation of a feature.
2436    
# Line 2090  Line 2458 
2458    
2459  =head3 Taxonomy  =head3 Taxonomy
2460    
2461  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2462    
2463  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
2464  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>,
2465  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2466    
2467  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2468    
2469  =over 4  =over 4
2470    
# Line 2131  Line 2499 
2499    
2500  =head3 CrudeDistance  =head3 CrudeDistance
2501    
2502  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2503    
2504  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
2505  that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.  that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.
# Line 2183  Line 2551 
2551    
2552  =head3 RoleName  =head3 RoleName
2553    
2554  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2555    
2556  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
2557  will only have a descriptive name if it is coded as an EC number.  will only have a descriptive name if it is coded as an EC number.
# Line 2217  Line 2585 
2585    
2586  =head3 RoleDiagrams  =head3 RoleDiagrams
2587    
2588  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2589    
2590  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2591    
# Line 2247  Line 2615 
2615    
2616  =head3 GetProperties  =head3 GetProperties
2617    
2618  C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>      my @list = $sprout->GetProperties($fid, $key, $value, $url);
2619    
2620  Return a list of the properties with the specified characteristics.  Return a list of the properties with the specified characteristics.
2621    
2622  Properties are arbitrary key-value pairs associated with a feature. (At some point they  Properties are the Sprout analog of the FIG attributes. The call is
2623  will also be associated with genomes.) A property value is represented by a 4-tuple of  passed directly to the CustomAttributes or RemoteCustomAttributes object
2624  the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter  contained in this object.
2625    
2626  =over 4  This method returns a series of tuples that match the specified criteria. Each tuple
2627    will contain an object ID, a key, and one or more values. The parameters to this
2628    method therefore correspond structurally to the values expected in each tuple. In
2629    addition, you can ask for a generic search by suffixing a percent sign (C<%>) to any
2630    of the parameters. So, for example,
2631    
2632  =item fid      my @attributeList = $sprout->GetProperties('fig|100226.1.peg.1004', 'structure%', 1, 2);
2633    
2634  ID of the feature possessing the property.  would return something like
2635    
2636  =item key      ['fig}100226.1.peg.1004', 'structure', 1, 2]
2637        ['fig}100226.1.peg.1004', 'structure1', 1, 2]
2638        ['fig}100226.1.peg.1004', 'structure2', 1, 2]
2639        ['fig}100226.1.peg.1004', 'structureA', 1, 2]
2640    
2641  Name or key of the property.  Use of C<undef> in any position acts as a wild card (all values). You can also specify
2642    a list reference in the ID column. Thus,
2643    
2644  =item value      my @attributeList = $sprout->GetProperties(['100226.1', 'fig|100226.1.%'], 'PUBMED');
2645    
2646  Value of the property.  would get the PUBMED attribute data for Streptomyces coelicolor A3(2) and all its
2647    features.
2648    
2649  =item url  In addition to values in multiple sections, a single attribute key can have multiple
2650    values, so even
2651    
2652  URL of the document that indicated the property should have this particular value, or an      my @attributeList = $sprout->GetProperties($peg, 'virulent');
 empty string if no such document exists.  
2653    
2654  =back  which has no wildcard in the key or the object ID, may return multiple tuples.
2655    
2656  The parameters act as a filter for the desired data. Any non-null parameter will  =over 4
 automatically match all the tuples returned. So, specifying just the I<$fid> will  
 return all the properties of the specified feature; similarly, specifying the I<$key>  
 and I<$value> parameters will return all the features having the specified property  
 value.  
2657    
2658  A single property key can have many values, representing different ideas about the  =item objectID
 feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is  
 virulent, and another may declare that it is not virulent. A query about the virulence of  
 C<fig|83333.1.peg.10> would be coded as  
2659    
2660      my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');  ID of object whose attributes are desired. If the attributes are desired for multiple
2661    objects, this parameter can be specified as a list reference. If the attributes are
2662    desired for all objects, specify C<undef> or an empty string. Finally, you can specify
2663    attributes for a range of object IDs by putting a percent sign (C<%>) at the end.
2664    
2665  Here the I<$value> and I<$url> fields are left blank, indicating that those fields are  =item key
 not to be filtered. The tuples returned would be  
2666    
2667      ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')  Attribute key name. A value of C<undef> or an empty string will match all
2668      ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')  attribute keys. If the values are desired for multiple keys, this parameter can be
2669    specified as a list reference. Finally, you can specify attributes for a range of
2670    keys by putting a percent sign (C<%>) at the end.
2671    
2672    =item values
2673    
2674    List of the desired attribute values, section by section. If C<undef>
2675    or an empty string is specified, all values in that section will match. A
2676    generic match can be requested by placing a percent sign (C<%>) at the end.
2677    In that case, all values that match up to and not including the percent sign
2678    will match. You may also specify a regular expression enclosed
2679    in slashes. All values that match the regular expression will be returned. For
2680    performance reasons, only values have this extra capability.
2681    
2682    =item RETURN
2683    
2684    Returns a list of tuples. The first element in the tuple is an object ID, the
2685    second is an attribute key, and the remaining elements are the sections of
2686    the attribute value. All of the tuples will match the criteria set forth in
2687    the parameter list.
2688    
2689    =back
2690    
2691  =cut  =cut
2692  #: Return Type @@;  
2693  sub GetProperties {  sub GetProperties {
2694      # Get the parameters.      # Get the parameters.
2695      my ($self, @parms) = @_;      my ($self, @parms) = @_;
2696      # Declare the return variable.      # Declare the return variable.
2697      my @retVal = ();      my @retVal = $self->{_ca}->GetAttributes(@parms);
     # Now we need to create a WHERE clause that will get us the data we want. First,  
     # we create a list of the columns containing the data for each parameter.  
     my @colNames = ('HasProperty(from-link)', 'Property(property-name)',  
                     'Property(property-value)', 'HasProperty(evidence)');  
     # Now we build the WHERE clause and the list of parameter values.  
     my @where = ();  
     my @values = ();  
     for (my $i = 0; $i <= $#colNames; $i++) {  
         my $parm = $parms[$i];  
         if (defined $parm && ($parm ne '')) {  
             push @where, "$colNames[$i] = ?";  
             push @values, $parm;  
         }  
     }  
     # Format the WHERE clause.  
     my $filter = (@values > 0 ? (join " AND ", @where) : undef);  
     # Ask for all the propertie values with the desired characteristics.  
     my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);  
     while (my $valueObject = $query->Fetch()) {  
         my @tuple = $valueObject->Values(\@colNames);  
         push @retVal, \@tuple;  
     }  
2698      # Return the result.      # Return the result.
2699      return @retVal;      return @retVal;
2700  }  }
2701    
2702  =head3 FeatureProperties  =head3 FeatureProperties
2703    
2704  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2705    
2706  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
2707  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
2708  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
2709  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
2710  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.  
2711    
2712  =over 4  =over 4
2713    
# Line 2348  Line 2717 
2717    
2718  =item RETURN  =item RETURN
2719    
2720  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.  
2721    
2722  =back  =back
2723    
# Line 2359  Line 2727 
2727      # Get the parameters.      # Get the parameters.
2728      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2729      # Get the properties.      # Get the properties.
2730      my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->{_ca}->GetAttributes($featureID);
2731                              ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2732                               'HasProperty(evidence)']);      my @retVal = ();
2733        for my $attributeRow (@attributes) {
2734            shift @{$attributeRow};
2735            push @retVal, $attributeRow;
2736        }
2737      # Return the resulting list.      # Return the resulting list.
2738      return @retVal;      return @retVal;
2739  }  }
2740    
2741  =head3 DiagramName  =head3 DiagramName
2742    
2743  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2744    
2745  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2746    
# Line 2394  Line 2766 
2766      return $retVal;      return $retVal;
2767  }  }
2768    
2769    =head3 PropertyID
2770    
2771        my $id = $sprout->PropertyID($propName, $propValue);
2772    
2773    Return the ID of the specified property name and value pair, if the
2774    pair exists. Only a small subset of the FIG attributes are stored as
2775    Sprout properties, mostly for use in search optimization.
2776    
2777    =over 4
2778    
2779    =item propName
2780    
2781    Name of the desired property.
2782    
2783    =item propValue
2784    
2785    Value expected for the desired property.
2786    
2787    =item RETURN
2788    
2789    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2790    
2791    =back
2792    
2793    =cut
2794    
2795    sub PropertyID {
2796        # Get the parameters.
2797        my ($self, $propName, $propValue) = @_;
2798        # Try to find the ID.
2799        my ($retVal) = $self->GetFlat(['Property'],
2800                                      "Property(property-name) = ? AND Property(property-value) = ?",
2801                                      [$propName, $propValue], 'Property(id)');
2802        # Return the result.
2803        return $retVal;
2804    }
2805    
2806  =head3 MergedAnnotations  =head3 MergedAnnotations
2807    
2808  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2809    
2810  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2811  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2445  Line 2854 
2854    
2855  =head3 RoleNeighbors  =head3 RoleNeighbors
2856    
2857  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
2858    
2859  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
2860  diagrams and roles are in a many-to-many relationship with each other, the list is  diagrams and roles are in a many-to-many relationship with each other, the list is
# Line 2488  Line 2897 
2897    
2898  =head3 FeatureLinks  =head3 FeatureLinks
2899    
2900  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
2901    
2902  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
2903  to external websites describing either the feature itself or the organism containing it  to external websites describing either the feature itself or the organism containing it
# Line 2519  Line 2928 
2928    
2929  =head3 SubsystemsOf  =head3 SubsystemsOf
2930    
2931  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
2932    
2933  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
2934  to the roles the feature performs.  to the roles the feature performs.
# Line 2547  Line 2956 
2956                                      ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                      ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2957      # Create the return value.      # Create the return value.
2958      my %retVal = ();      my %retVal = ();
2959        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2960        # in two spreadsheet cells.
2961        my %dupHash = ();
2962      # Loop through the results, adding them to the hash.      # Loop through the results, adding them to the hash.
2963      for my $record (@subsystems) {      for my $record (@subsystems) {
2964            # Get this subsystem and role.
2965          my ($subsys, $role) = @{$record};          my ($subsys, $role) = @{$record};
2966          if (exists $retVal{$subsys}) {          # Insure it's the first time for both.
2967            my $dupKey = "$subsys\n$role";
2968            if (! exists $dupHash{"$subsys\n$role"}) {
2969                $dupHash{$dupKey} = 1;
2970              push @{$retVal{$subsys}}, $role;              push @{$retVal{$subsys}}, $role;
         } else {  
             $retVal{$subsys} = [$role];  
2971          }          }
2972      }      }
2973      # Return the hash.      # Return the hash.
# Line 2562  Line 2976 
2976    
2977  =head3 SubsystemList  =head3 SubsystemList
2978    
2979  C<< my @subsystems = $sprout->SubsystemList($featureID); >>      my @subsystems = $sprout->SubsystemList($featureID);
2980    
2981  Return a list containing the names of the subsystems in which the specified  Return a list containing the names of the subsystems in which the specified
2982  feature participates. Unlike L</SubsystemsOf>, this method only returns the  feature participates. Unlike L</SubsystemsOf>, this method only returns the
# Line 2586  Line 3000 
3000      # Get the parameters.      # Get the parameters.
3001      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
3002      # Get the list of names.      # Get the list of names.
3003      my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",      my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?",
3004                                  [$featureID], 'HasSSCell(from-link)');                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3005        # Return the result, sorted.
3006        return sort @retVal;
3007    }
3008    
3009    =head3 GenomeSubsystemData
3010    
3011        my %featureData = $sprout->GenomeSubsystemData($genomeID);
3012    
3013    Return a hash mapping genome features to their subsystem roles.
3014    
3015    =over 4
3016    
3017    =item genomeID
3018    
3019    ID of the genome whose subsystem feature map is desired.
3020    
3021    =item RETURN
3022    
3023    Returns a hash mapping each feature of the genome to a list of 2-tuples. Eacb
3024    2-tuple contains a subsystem name followed by a role ID.
3025    
3026    =back
3027    
3028    =cut
3029    
3030    sub GenomeSubsystemData {
3031        # Get the parameters.
3032        my ($self, $genomeID) = @_;
3033        # Declare the return variable.
3034        my %retVal = ();
3035        # Get a list of the genome features that participate in subsystems. For each
3036        # feature we get its spreadsheet cells and the corresponding roles.
3037        my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'],
3038                                 "HasFeature(from-link) = ?", [$genomeID],
3039                                 ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']);
3040        # Now we get a list of the spreadsheet cells and their associated subsystems. Subsystems
3041        # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the
3042        # list. We use it at the beginning to get all the spreadsheet cells for the genome and
3043        # again at the end to filter out participation in subsystems with a negative variant code.
3044        my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'],
3045                                     "IsGenomeOf(from-link) = ? AND ParticipatesIn(variant-code) >= 0 AND ParticipatesIn(from-link) = ?",
3046                                     [$genomeID, $genomeID], ['HasSSCell(to-link)', 'HasSSCell(from-link)']);
3047        # Now "@roleData" lists the spreadsheet cell and role for each of the genome's features.
3048        # "@cellData" lists the subsystem name for each of the genome's spreadsheet cells. We
3049        # link these two lists together to create the result. First, we want a hash mapping
3050        # spreadsheet cells to subsystem names.
3051        my %subHash = map { $_->[0] => $_->[1] } @cellData;
3052        # We loop through @cellData to build the hash.
3053        for my $roleEntry (@roleData) {
3054            # Get the data for this feature and cell.
3055            my ($fid, $cellID, $role) = @{$roleEntry};
3056            # Check for a subsystem name.
3057            my $subsys = $subHash{$cellID};
3058            if ($subsys) {
3059                # Insure this feature has an entry in the return hash.
3060                if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3061                # Merge in this new data.
3062                push @{$retVal{$fid}}, [$subsys, $role];
3063            }
3064        }
3065      # Return the result.      # Return the result.
3066      return @retVal;      return %retVal;
3067  }  }
3068    
3069  =head3 RelatedFeatures  =head3 RelatedFeatures
3070    
3071  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
3072    
3073  Return a list of the features which are bi-directional best hits of the specified feature and  Return a list of the features which are bi-directional best hits of the specified feature and
3074  have been assigned the specified function by the specified user. If no such features exists,  have been assigned the specified function by the specified user. If no such features exists,
# Line 2627  Line 3101 
3101      # Get the parameters.      # Get the parameters.
3102      my ($self, $featureID, $function, $userID) = @_;      my ($self, $featureID, $function, $userID) = @_;
3103      # 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.
3104      my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);
                                      "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],  
                                      'IsBidirectionalBestHitOf(to-link)');  
3105      # 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
3106      # functional assignment.      # functional assignment.
3107      my @retVal = ();      my @retVal = ();
# Line 2647  Line 3119 
3119    
3120  =head3 TaxonomySort  =head3 TaxonomySort
3121    
3122  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3123    
3124  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a list formed by sorting the specified features by the taxonomy of the containing
3125  genome. This will cause genomes from similar organisms to float close to each other.  genome. This will cause genomes from similar organisms to float close to each other.
# Line 2682  Line 3154 
3154          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3155                                          [$fid], 'Genome(taxonomy)');                                          [$fid], 'Genome(taxonomy)');
3156          # Add this feature to the hash buffer.          # Add this feature to the hash buffer.
3157          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);          push @{$hashBuffer{$taxonomy}}, $fid;
3158      }      }
3159      # Sort the keys and get the elements.      # Sort the keys and get the elements.
3160      my @retVal = ();      my @retVal = ();
# Line 2693  Line 3165 
3165      return @retVal;      return @retVal;
3166  }  }
3167    
 =head3 GetAll  
   
 C<< my @list = $sprout->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>  
   
 Return a list of values taken from the objects returned by a query. The first three  
 parameters correspond to the parameters of the L</Get> method. The final parameter is  
 a list of the fields desired from each record found by the query. The field name  
 syntax is the standard syntax used for fields in the B<ERDB> system--  
 B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity  
 or relationship and I<fieldName> is the name of the field.  
   
 The list returned will be a list of lists. Each element of the list will contain  
 the values returned for the fields specified in the fourth parameter. If one of the  
 fields specified returns multiple values, they are flattened in with the rest. For  
 example, the following call will return a list of the features in a particular  
 spreadsheet cell, and each feature will be represented by a list containing the  
 feature ID followed by all of its aliases.  
   
 C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  
   
 =over 4  
   
 =item objectNames  
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
   
 =item fields  
   
 List of the fields to be returned in each element of the list returned.  
   
 =item count  
   
 Maximum number of records to return. If omitted or 0, all available records will be returned.  
   
 =item RETURN  
   
 Returns a list of list references. Each element of the return list contains the values for the  
 fields specified in the B<fields> parameter.  
   
 =back  
   
 =cut  
 #: Return Type @@;  
 sub GetAll {  
     # Get the parameters.  
     my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;  
     # Call the ERDB method.  
     my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,  
                                         $fields, $count);  
     # Return the resulting list.  
     return @retVal;  
 }  
   
 =head3 GetFlat  
   
 C<< my @list = $sprout->GetFlat(\@objectNames, $filterClause, $parameterList, $field); >>  
   
 This is a variation of L</GetAll> that asks for only a single field per record and  
 returns a single flattened list.  
   
 =over 4  
   
 =item objectNames  
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
   
 =item field  
   
 Name of the field to be used to get the elements of the list returned.  
   
 =item RETURN  
   
 Returns a list of values.  
   
 =back  
   
 =cut  
 #: Return Type @;  
 sub GetFlat {  
     # Get the parameters.  
     my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;  
     # Construct the query.  
     my $query = $self->Get($objectNames, $filterClause, $parameterList);  
     # Create the result list.  
     my @retVal = ();  
     # Loop through the records, adding the field values found to the result list.  
     while (my $row = $query->Fetch()) {  
         push @retVal, $row->Value($field);  
     }  
     # Return the list created.  
     return @retVal;  
 }  
   
3168  =head3 Protein  =head3 Protein
3169    
3170  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3171    
3172  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3173    
# Line 2884  Line 3237 
3237      # Loop through the input triples.      # Loop through the input triples.
3238      my $n = length $sequence;      my $n = length $sequence;
3239      for (my $i = 0; $i < $n; $i += 3) {      for (my $i = 0; $i < $n; $i += 3) {
3240          # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3241          my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3242            my $triple = uc substr($sequence, $i, 3);
3243          # Translate it using the table.          # Translate it using the table.
3244          my $protein = "X";          my $protein = "X";
3245          if (exists $table->{$triple}) { $protein = $table->{$triple}; }          if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 2899  Line 3253 
3253    
3254  =head3 LoadInfo  =head3 LoadInfo
3255    
3256  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3257    
3258  Return the name of the directory from which data is to be loaded and a list of the relation  Return the name of the directory from which data is to be loaded and a list of the relation
3259  names. This information is useful when trying to analyze what needs to be put where in order  names. This information is useful when trying to analyze what needs to be put where in order
# Line 2913  Line 3267 
3267      # Create the return list, priming it with the name of the data directory.      # Create the return list, priming it with the name of the data directory.
3268      my @retVal = ($self->{_options}->{dataDir});      my @retVal = ($self->{_options}->{dataDir});
3269      # Concatenate the table names.      # Concatenate the table names.
3270      push @retVal, $self->{_erdb}->GetTableNames();      push @retVal, $self->GetTableNames();
3271      # Return the result.      # Return the result.
3272      return @retVal;      return @retVal;
3273  }  }
3274    
3275    =head3 BBHMatrix
3276    
3277        my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3278    
3279    Find all the bidirectional best hits for the features of a genome in a
3280    specified list of target genomes. The return value will be a hash mapping
3281    features in the original genome to their bidirectional best hits in the
3282    target genomes.
3283    
3284    =over 4
3285    
3286    =item genomeID
3287    
3288    ID of the genome whose features are to be examined for bidirectional best hits.
3289    
3290    =item cutoff
3291    
3292    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3293    
3294    =item targets
3295    
3296    List of target genomes. Only pairs originating in the original
3297    genome and landing in one of the target genomes will be returned.
3298    
3299    =item RETURN
3300    
3301    Returns a hash mapping each feature in the original genome to a hash mapping its
3302    BBH pegs in the target genomes to their scores.
3303    
3304    =back
3305    
3306    =cut
3307    
3308    sub BBHMatrix {
3309        # Get the parameters.
3310        my ($self, $genomeID, $cutoff, @targets) = @_;
3311        # Declare the return variable.
3312        my %retVal = ();
3313        # Ask for the BBHs.
3314        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3315        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3316        for my $bbhData (@bbhList) {
3317            my ($peg1, $peg2, $score) = @{$bbhData};
3318            if (! exists $retVal{$peg1}) {
3319                $retVal{$peg1} = { $peg2 => $score };
3320            } else {
3321                $retVal{$peg1}->{$peg2} = $score;
3322            }
3323        }
3324        # Return the result.
3325        return %retVal;
3326    }
3327    
3328    
3329    =head3 SimMatrix
3330    
3331        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3332    
3333    Find all the similarities for the features of a genome in a
3334    specified list of target genomes. The return value will be a hash mapping
3335    features in the original genome to their similarites in the
3336    target genomes.
3337    
3338    =over 4
3339    
3340    =item genomeID
3341    
3342    ID of the genome whose features are to be examined for similarities.
3343    
3344    =item cutoff
3345    
3346    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3347    
3348    =item targets
3349    
3350    List of target genomes. Only pairs originating in the original
3351    genome and landing in one of the target genomes will be returned.
3352    
3353    =item RETURN
3354    
3355    Returns a hash mapping each feature in the original genome to a hash mapping its
3356    similar pegs in the target genomes to their scores.
3357    
3358    =back
3359    
3360    =cut
3361    
3362    sub SimMatrix {
3363        # Get the parameters.
3364        my ($self, $genomeID, $cutoff, @targets) = @_;
3365        # Declare the return variable.
3366        my %retVal = ();
3367        # Get the list of features in the source organism.
3368        my @fids = $self->FeaturesOf($genomeID);
3369        # Ask for the sims. We only want similarities to fig features.
3370        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3371        if (! defined $simList) {
3372            Confess("Unable to retrieve similarities from server.");
3373        } else {
3374            Trace("Processing sims.") if T(3);
3375            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3376            # Create a hash for the target genomes.
3377            my %targetHash = map { $_ => 1 } @targets;
3378            for my $simData (@{$simList}) {
3379                # Get the PEGs and the score.
3380                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3381                # Insure the second ID is in the target list.
3382                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3383                if (exists $targetHash{$genome2}) {
3384                    # Here it is. Now we need to add it to the return hash. How we do that depends
3385                    # on whether or not $peg1 is new to us.
3386                    if (! exists $retVal{$peg1}) {
3387                        $retVal{$peg1} = { $peg2 => $score };
3388                    } else {
3389                        $retVal{$peg1}->{$peg2} = $score;
3390                    }
3391                }
3392            }
3393        }
3394        # Return the result.
3395        return %retVal;
3396    }
3397    
3398    
3399  =head3 LowBBHs  =head3 LowBBHs
3400    
3401  C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3402    
3403  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3404  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 2949  Line 3427 
3427      my ($self, $featureID, $cutoff) = @_;      my ($self, $featureID, $cutoff) = @_;
3428      # Create the return hash.      # Create the return hash.
3429      my %retVal = ();      my %retVal = ();
3430      # Create a query to get the desired BBHs.      # Query for the desired BBHs.
3431      my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],      my @bbhList = FIGRules::BBHData($featureID, $cutoff);
                                 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',  
                                 [$cutoff, $featureID],  
                                 ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);  
3432      # Form the results into the return hash.      # Form the results into the return hash.
3433      for my $pair (@bbhList) {      for my $pair (@bbhList) {
3434          $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3435            if ($self->Exists('Feature', $fid)) {
3436                $retVal{$fid} = $pair->[1];
3437            }
3438      }      }
3439      # Return the result.      # Return the result.
3440      return %retVal;      return %retVal;
3441  }  }
3442    
3443    =head3 Sims
3444    
3445        my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3446    
3447    Get a list of similarities for a specified feature. Similarity information is not kept in the
3448    Sprout database; rather, they are retrieved from a network server. The similarities are
3449    returned as B<Sim> objects. A Sim object is actually a list reference that has been blessed
3450    so that its elements can be accessed by name.
3451    
3452    Similarities can be either raw or expanded. The raw similarities are basic
3453    hits between features with similar DNA. Expanding a raw similarity drags in any
3454    features considered substantially identical. So, for example, if features B<A1>,
3455    B<A2>, and B<A3> are all substantially identical to B<A>, then a raw similarity
3456    B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3457    
3458    =over 4
3459    
3460    =item fid
3461    
3462    ID of the feature whose similarities are desired, or reference to a list of IDs
3463    of features whose similarities are desired.
3464    
3465    =item maxN
3466    
3467    Maximum number of similarities to return.
3468    
3469    =item maxP
3470    
3471    Minumum allowable similarity score.
3472    
3473    =item select
3474    
3475    Selection criterion: C<raw> means only raw similarities are returned; C<fig>
3476    means only similarities to FIG features are returned; C<all> means all expanded
3477    similarities are returned; and C<figx> means similarities are expanded until the
3478    number of FIG features equals the maximum.
3479    
3480    =item max_expand
3481    
3482    The maximum number of features to expand.
3483    
3484    =item filters
3485    
3486    Reference to a hash containing filter information, or a subroutine that can be
3487    used to filter the sims.
3488    
3489    =item RETURN
3490    
3491    Returns a reference to a list of similarity objects, or C<undef> if an error
3492    occurred.
3493    
3494    =back
3495    
3496    =cut
3497    
3498    sub Sims {
3499        # Get the parameters.
3500        my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_;
3501        # Create the shim object to test for deleted FIDs.
3502        my $shim = FidCheck->new($self);
3503        # Ask the network for sims.
3504        my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters);
3505        # Return the result.
3506        return $retVal;
3507    }
3508    
3509    =head3 IsAllGenomes
3510    
3511        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3512    
3513    Return TRUE if all genomes in the second list are represented in the first list at
3514    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3515    compared to a list of all the genomes.
3516    
3517    =over 4
3518    
3519    =item list
3520    
3521    Reference to the list to be compared to the second list.
3522    
3523    =item checkList (optional)
3524    
3525    Reference to the comparison target list. Every genome ID in this list must occur at
3526    least once in the first list. If this parameter is omitted, a list of all the genomes
3527    is used.
3528    
3529    =item RETURN
3530    
3531    Returns TRUE if every item in the second list appears at least once in the
3532    first list, else FALSE.
3533    
3534    =back
3535    
3536    =cut
3537    
3538    sub IsAllGenomes {
3539        # Get the parameters.
3540        my ($self, $list, $checkList) = @_;
3541        # Supply the checklist if it was omitted.
3542        $checkList = [$self->Genomes()] if ! defined($checkList);
3543        # Create a hash of the original list.
3544        my %testList = map { $_ => 1 } @{$list};
3545        # Declare the return variable. We assume that the representation
3546        # is complete and stop at the first failure.
3547        my $retVal = 1;
3548        my $n = scalar @{$checkList};
3549        for (my $i = 0; $retVal && $i < $n; $i++) {
3550            if (! $testList{$checkList->[$i]}) {
3551                $retVal = 0;
3552            }
3553        }
3554        # Return the result.
3555        return $retVal;
3556    }
3557    
3558  =head3 GetGroups  =head3 GetGroups
3559    
3560  C<< my %groups = $sprout->GetGroups(\@groupList); >>      my %groups = $sprout->GetGroups(\@groupList);
3561    
3562  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.
3563  A list of groups may be specified, in which case only those groups will be  A list of groups may be specified, in which case only those groups will be
# Line 2983  Line 3576 
3576          # Here we have a group list. Loop through them individually,          # Here we have a group list. Loop through them individually,
3577          # getting a list of the relevant genomes.          # getting a list of the relevant genomes.
3578          for my $group (@{$groupList}) {          for my $group (@{$groupList}) {
3579              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3580                  [$group], "Genome(id)");                  [$group], "Genome(id)");
3581              $retVal{$group} = \@genomeIDs;              $retVal{$group} = \@genomeIDs;
3582          }          }
# Line 2991  Line 3584 
3584          # 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
3585          # of the genome records, putting each one found into the appropriate          # of the genome records, putting each one found into the appropriate
3586          # 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
3587          # in groups are included in the return set.          # in real NMPDR groups are included in the return set.
3588          my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],          my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3589                                      ['Genome(id)', 'Genome(group-name)']);                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3590          # Loop through the genomes found.          # Loop through the genomes found.
3591          for my $genome (@genomes) {          for my $genome (@genomes) {
3592              # Pop this genome's ID off the current list.              # Get the genome ID and group, and add this genome to the group's list.
3593              my @groups = @{$genome};              my ($genomeID, $group) = @{$genome};
3594              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, $genomeID);  
             }  
3595          }          }
3596      }      }
3597      # Return the hash we just built.      # Return the hash we just built.
# Line 3012  Line 3600 
3600    
3601  =head3 MyGenomes  =head3 MyGenomes
3602    
3603  C<< my @genomes = Sprout::MyGenomes($dataDir); >>      my @genomes = Sprout::MyGenomes($dataDir);
3604    
3605  Return a list of the genomes to be included in the Sprout.  Return a list of the genomes to be included in the Sprout.
3606    
# Line 3044  Line 3632 
3632    
3633  =head3 LoadFileName  =head3 LoadFileName
3634    
3635  C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>      my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3636    
3637  Return the name of the load file for the specified table in the specified data  Return the name of the load file for the specified table in the specified data
3638  directory.  directory.
# Line 3083  Line 3671 
3671      return $retVal;      return $retVal;
3672  }  }
3673    
3674    =head3 DeleteGenome
3675    
3676        my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3677    
3678    Delete a genome from the database.
3679    
3680    =over 4
3681    
3682    =item genomeID
3683    
3684    ID of the genome to delete
3685    
3686    =item testFlag
3687    
3688    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3689    
3690    =item RETURN
3691    
3692    Returns a statistics object describing the rows deleted.
3693    
3694    =back
3695    
3696    =cut
3697    #: Return Type $%;
3698    sub DeleteGenome {
3699        # Get the parameters.
3700        my ($self, $genomeID, $testFlag) = @_;
3701        # Perform the delete for the genome's features.
3702        my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3703        # Perform the delete for the primary genome data.
3704        my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3705        $retVal->Accumulate($stats);
3706        # Return the result.
3707        return $retVal;
3708    }
3709    
3710    =head3 Fix
3711    
3712        my %fixedHash = $sprout->Fix(%groupHash);
3713    
3714    Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3715    The groups will be combined into the appropriate super-groups.
3716    
3717    =over 4
3718    
3719    =item groupHash
3720    
3721    Hash to be fixed up.
3722    
3723    =item RETURN
3724    
3725    Returns a fixed-up version of the hash.
3726    
3727    =back
3728    
3729    =cut
3730    
3731    sub Fix {
3732        # Get the parameters.
3733        my ($self, %groupHash) = @_;
3734        # Create the result hash.
3735        my %retVal = ();
3736        # Copy over the genomes.
3737        for my $groupID (keys %groupHash) {
3738            # Get the super-group name.
3739            my $realGroupID = $self->SuperGroup($groupID);
3740            # Append this group's genomes into the result hash
3741            # using the super-group name.
3742            push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3743        }
3744        # Return the result hash.
3745        return %retVal;
3746    }
3747    
3748    =head3 GroupPageName
3749    
3750        my $name = $sprout->GroupPageName($group);
3751    
3752    Return the name of the page for the specified NMPDR group.
3753    
3754    =over 4
3755    
3756    =item group
3757    
3758    Name of the relevant group.
3759    
3760    =item RETURN
3761    
3762    Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3763    memory it will be read in.
3764    
3765    =back
3766    
3767    =cut
3768    
3769    sub GroupPageName {
3770        # Get the parameters.
3771        my ($self, $group) = @_;
3772        # Check for the group file data.
3773        my %superTable = $self->CheckGroupFile();
3774        # Compute the real group name.
3775        my $realGroup = $self->SuperGroup($group);
3776        # Get the associated page name.
3777        my $retVal = "../content/$superTable{$realGroup}->{page}";
3778        # Return the result.
3779        return $retVal;
3780    }
3781    
3782    
3783    =head3 AddProperty
3784    
3785        $sprout->AddProperty($featureID, $key, @values);
3786    
3787    Add a new attribute value (Property) to a feature.
3788    
3789    =over 4
3790    
3791    =item peg
3792    
3793    ID of the feature to which the attribute is to be added.
3794    
3795    =item key
3796    
3797    Name of the attribute (key).
3798    
3799    =item values
3800    
3801    Values of the attribute.
3802    
3803    =back
3804    
3805    =cut
3806    #: Return Type ;
3807    sub AddProperty {
3808        # Get the parameters.
3809        my ($self, $featureID, $key, @values) = @_;
3810        # Add the property using the attached attributes object.
3811        $self->{_ca}->AddAttribute($featureID, $key, @values);
3812    }
3813    
3814    =head3 CheckGroupFile
3815    
3816        my %groupData = $sprout->CheckGroupFile();
3817    
3818    Get the group file hash. The group file hash describes the relationship
3819    between a group and the super-group to which it belongs for purposes of
3820    display. The super-group name is computed from the first capitalized word
3821    in the actual group name. For each super-group, the group file contains
3822    the page name and a list of the species expected to be in the group.
3823    Each species is specified by a genus and a species name. A species name
3824    of C<0> implies an entire genus.
3825    
3826    This method returns a hash from super-group names to a hash reference. Each
3827    resulting hash reference contains the following fields.
3828    
3829    =over 4
3830    
3831    =item page
3832    
3833    The super-group's web page in the NMPDR.
3834    
3835    =item contents
3836    
3837    A list of 2-tuples, each containing a genus name followed by a species name
3838    (or 0, indicating all species). This list indicates which organisms belong
3839    in the super-group.
3840    
3841    =back
3842    
3843    =cut
3844    
3845    sub CheckGroupFile{
3846        # Get the parameters.
3847        my ($self) = @_;
3848        # Check to see if we already have this hash.
3849        if (! defined $self->{groupHash}) {
3850            # We don't, so we need to read it in.
3851            my %groupHash;
3852            # Read the group file.
3853            my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
3854            # Loop through the list of sort-of groups.
3855            for my $groupLine (@groupLines) {
3856                my ($name, $page, @contents) = split /\t/, $groupLine;
3857                $groupHash{$name} = { page => $page,
3858                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
3859                                    };
3860            }
3861            # Save the hash.
3862            $self->{groupHash} = \%groupHash;
3863        }
3864        # Return the result.
3865        return %{$self->{groupHash}};
3866    }
3867    
3868    =head2 Virtual Methods
3869    
3870    =head3 CleanKeywords
3871    
3872        my $cleanedString = $sprout->CleanKeywords($searchExpression);
3873    
3874    Clean up a search expression or keyword list. This involves converting the periods
3875    in EC numbers to underscores, converting non-leading minus signs to underscores,
3876    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
3877    characters. In addition, any extra spaces are removed.
3878    
3879    =over 4
3880    
3881    =item searchExpression
3882    
3883    Search expression or keyword list to clean. Note that a search expression may
3884    contain boolean operators which need to be preserved. This includes leading
3885    minus signs.
3886    
3887    =item RETURN
3888    
3889    Cleaned expression or keyword list.
3890    
3891    =back
3892    
3893    =cut
3894    
3895    sub CleanKeywords {
3896        # Get the parameters.
3897        my ($self, $searchExpression) = @_;
3898        # Perform the standard cleanup.
3899        my $retVal = $self->ERDB::CleanKeywords($searchExpression);
3900        # Fix the periods in EC and TC numbers.
3901        $retVal =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;
3902        # Fix non-trailing periods.
3903        $retVal =~ s/\.(\w)/_$1/g;
3904        # Fix non-leading minus signs.
3905        $retVal =~ s/(\w)[\-]/$1_/g;
3906        # Fix the vertical bars and colons
3907        $retVal =~ s/(\w)[|:](\w)/$1'$2/g;
3908        # Return the result.
3909        return $retVal;
3910    }
3911    
3912  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3913    
3914  =head3 ParseAssignment  =head3 ParseAssignment
# Line 3093  Line 3919 
3919    
3920  A functional assignment is always of the form  A functional assignment is always of the form
3921    
3922      I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>      set YYYY function to
3923        ZZZZ
3924    
3925  where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the  where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
3926  actual functional role. In most cases, the user and the assigning user will be the  the user and the assigning user (from MadeAnnotation) will be the same, but that is
3927  same, but that is not always the case.  not always the case.
3928    
3929    In addition, the functional role may contain extra data that is stripped, such as
3930    terminating spaces or a comment separated from the rest of the text by a tab.
3931    
3932  This is a static method.  This is a static method.
3933    
3934  =over 4  =over 4
3935    
3936    =item user
3937    
3938    Name of the assigning user.
3939    
3940  =item text  =item text
3941    
3942  Text of the annotation.  Text of the annotation.
# Line 3118  Line 3952 
3952    
3953  sub _ParseAssignment {  sub _ParseAssignment {
3954      # Get the parameters.      # Get the parameters.
3955      my ($text) = @_;      my ($user, $text) = @_;
3956      # Declare the return value.      # Declare the return value.
3957      my @retVal = ();      my @retVal = ();
3958      # Check to see if this is a functional assignment.      # Check to see if this is a functional assignment.
3959      my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
3960      if ($type =~ m/^set ([^ ]+) function to$/i) {      if ($type =~ m/^set function to$/i) {
3961          # Here it is, so we return the user name (which is in $1), the functional role text,          # Here we have an assignment without a user, so we use the incoming user ID.
3962          # and the assigning user.          @retVal = ($user, $function);
3963          @retVal = ($1, $function, $user);      } elsif ($type =~ m/^set (\S+) function to$/i) {
3964            # Here we have an assignment with a user that is passed back to the caller.
3965            @retVal = ($1, $function);
3966        }
3967        # If we have an assignment, we need to clean the function text. There may be
3968        # extra junk at the end added as a note from the user.
3969        if (defined( $retVal[1] )) {
3970            $retVal[1] =~ s/(\t\S)?\s*$//;
3971      }      }
3972      # Return the result list.      # Return the result list.
3973      return @retVal;      return @retVal;
3974  }  }
3975    
3976  =head3 FriendlyTimestamp  =head3 _CheckFeature
3977    
3978  Convert a time number to a user-friendly time stamp for display.      my $flag = $sprout->_CheckFeature($fid);
3979    
3980  This is a static method.  Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
3981    
3982  =over 4  =over 4
3983    
3984  =item timeValue  =item fid
3985    
3986  Numeric time value.  Feature ID to check.
3987    
3988  =item RETURN  =item RETURN
3989    
3990  Returns a string containing the same time in user-readable format.  Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE.
3991    
3992  =back  =back
3993    
3994  =cut  =cut
3995    
3996  sub FriendlyTimestamp {  sub _CheckFeature {
3997      my ($timeValue) = @_;      # Get the parameters.
3998      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my ($self, $fid) = @_;
3999      return $retVal;      # Insure we have a genome hash.
4000        if (! defined $self->{genomeHash}) {
4001            my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');
4002            $self->{genomeHash} = \%genomeHash;
4003        }
4004        # Get the feature's genome ID.
4005        my ($genomeID) = FIGRules::ParseFeatureID($fid);
4006        # Return an indicator of whether or not the genome ID is in the hash.
4007        return ($self->{genomeHash}->{$genomeID} ? 1 : 0);
4008  }  }
4009    
4010  =head3 AddProperty  =head3 FriendlyTimestamp
4011    
4012  C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>  Convert a time number to a user-friendly time stamp for display.
4013    
4014  Add a new attribute value (Property) to a feature. In the SEED system, attributes can  This is a static method.
 be added to almost any object. In Sprout, they can only be added to features. In  
 Sprout, attributes are implemented using I<properties>. A property represents a key/value  
 pair. If the particular key/value pair coming in is not already in the database, a new  
 B<Property> record is created to hold it.  
4015    
4016  =over 4  =over 4
4017    
4018  =item peg  =item timeValue
   
 ID of the feature to which the attribute is to be replied.  
   
 =item key  
   
 Name of the attribute (key).  
   
 =item value  
4019    
4020  Value of the attribute.  Numeric time value.
4021    
4022  =item url  =item RETURN
4023    
4024  URL or text citation from which the property was obtained.  Returns a string containing the same time in user-readable format.
4025    
4026  =back  =back
4027    
4028  =cut  =cut
 #: Return Type ;  
 sub AddProperty {  
     # Get the parameters.  
     my ($self, $featureID, $key, $value, $url) = @_;  
     # Declare the variable to hold the desired property ID.  
     my $propID;  
     # Attempt to find a property record for this key/value pair.  
     my @properties = $self->GetFlat(['Property'],  
                                    "Property(property-name) = ? AND Property(property-value) = ?",  
                                    [$key, $value], 'Property(id)');  
     if (@properties) {  
         # Here the property is already in the database. We save its ID.  
         $propID = $properties[0];  
         # Here the property value does not exist. We need to generate an ID. It will be set  
         # to a number one greater than the maximum value in the database. This call to  
         # GetAll will stop after one record.  
         my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],  
                                         1);  
         $propID = $maxProperty[0]->[0] + 1;  
         # Insert the new property value.  
         $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });  
     }  
     # Now we connect the incoming feature to the property.  
     $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });  
 }  
4029    
4030    sub FriendlyTimestamp {
4031        my ($timeValue) = @_;
4032        my $retVal = localtime($timeValue);
4033        return $retVal;
4034    }
4035    
4036    
4037  1;  1;

Legend:
Removed from v.1.33  
changed lines
  Added in v.1.108

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3