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

Diff of /Sprout/Sprout.pm

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

revision 1.13, Thu May 5 03:14:03 2005 UTC revision 1.78, Wed Jul 26 14:47:03 2006 UTC
# Line 1  Line 1 
1  package Sprout;  package Sprout;
2    
3        require Exporter;
4        use ERDB;
5        @ISA = qw(Exporter ERDB);
6          use Data::Dumper;          use Data::Dumper;
7          use strict;          use strict;
8          use Carp;          use Carp;
# Line 7  Line 10 
10          use XML::Simple;          use XML::Simple;
11          use DBQuery;          use DBQuery;
12          use DBObject;          use DBObject;
         use ERDB;  
13          use Tracer;          use Tracer;
14          use FIGRules;          use FIGRules;
15        use FidCheck;
16          use Stats;          use Stats;
17      use POSIX qw(strftime);      use POSIX qw(strftime);
18        use BasicLocation;
19    
20  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
21    
# Line 32  Line 35 
35  query tasks. For example, L</genomes> lists the IDs of all the genomes in the database and  query tasks. For example, L</genomes> lists the IDs of all the genomes in the database and
36  L</dna_seq> returns the DNA sequence for a specified genome location.  L</dna_seq> returns the DNA sequence for a specified genome location.
37    
38    The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.
39    
40  =cut  =cut
41    
42  #: Constructor SFXlate->new_sprout_only();  #: Constructor SFXlate->new_sprout_only();
# Line 62  Line 67 
67    
68  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)
69    
70  * B<userData> user name and password, delimited by a slash (default C<root/>)  * B<userData> user name and password, delimited by a slash (default same as SEED)
71    
72  * B<port> connection port (default C<0>)  * B<port> connection port (default C<0>)
73    
74    * B<sock> connection socket (default same as SEED)
75    
76  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)
77    
78  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
79    
80    * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
81    
82  =back  =back
83    
84  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
# Line 83  Line 92 
92  sub new {  sub new {
93          # Get the parameters.          # Get the parameters.
94          my ($class, $dbName, $options) = @_;          my ($class, $dbName, $options) = @_;
95        # Compute the DBD directory.
96        my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
97                                                      $FIG_Config::fig );
98          # 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
99          # the incoming data.          # the incoming data.
100          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
101                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
102                                             dataDir              => 'Data',                      # data file directory                                                          # database type
103                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
104                                             userData             => 'root/',                     # user name and password                                                          # data file directory
105                                             port                 => 0,                           # database connection port                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
106                                                            # database definition file name
107                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
108                                                            # user name and password
109                           port         => $FIG_Config::dbport,
110                                                            # database connection port
111                           sock         => $FIG_Config::dbsock,
112                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
113                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
114                           noDBOpen     => 0,               # 1 to suppress the database open
115                                            }, $options);                                            }, $options);
116          # Get the data directory.          # Get the data directory.
117          my $dataDir = $optionTable->{dataDir};          my $dataDir = $optionTable->{dataDir};
# Line 100  Line 119 
119          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
120          my ($userName, $password) = ($1, $2);          my ($userName, $password) = ($1, $2);
121          # Connect to the database.          # Connect to the database.
122          my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
123        if (! $optionTable->{noDBOpen}) {
124            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
125                                    $password, $optionTable->{port}, undef, $optionTable->{sock});
126        }
127          # Create the ERDB object.          # Create the ERDB object.
128          my $xmlFileName = "$optionTable->{xmlFileName}";          my $xmlFileName = "$optionTable->{xmlFileName}";
129          my $erdb = ERDB->new($dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName);
130          # Create this object.      # Add the option table and XML file name.
131          my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName };      $retVal->{_options} = $optionTable;
132          # Bless and return it.      $retVal->{_xmlName} = $xmlFileName;
133          bless $self;      # Return it.
134          return $self;      return $retVal;
135  }  }
136    
137  =head3 MaxSegment  =head3 MaxSegment
# Line 143  Line 166 
166          return $self->{_options}->{maxSequenceLength};          return $self->{_options}->{maxSequenceLength};
167  }  }
168    
 =head3 Get  
   
 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.  
   
 C<< $query = $sprout->Get(['Genome'], "ORDER BY Genome(genus), Genome(species)"); >>  
   
 Odd things may happen if one of the ORDER BY fields is in a secondary relation. So, for example, an  
 attempt to order B<Feature>s by alias may (depending on the underlying database engine used) cause  
 a single feature to appear more than once.  
   
 If multiple names are specified, then the query processor will automatically determine a  
 join path between the entities and relationships. The algorithm used is very simplistic.  
 In particular, you can't specify any entity or relationship more than once, and if a  
 relationship is recursive, the path is determined by the order in which the entity  
 and the relationship appear. For example, consider a recursive relationship B<IsParentOf>  
 which relates B<People> objects to other B<People> objects. If the join path is  
 coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,  
 the join path is C<['IsParentOf', 'People']>, then the people returned will be children.  
   
 =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 RETURN  
   
 Returns a B<DBQuery> that can be used to iterate through all of the results.  
   
 =back  
   
 =cut  
   
 sub Get {  
         # Get the parameters.  
         my ($self, $objectNames, $filterClause, $parameterList) = @_;  
         # We differ from the ERDB Get method in that the parameter list is passed in as a list reference  
         # rather than a list of parameters. The next step is to convert the parameters from a reference  
         # to a real list. We can only do this if the parameters have been specified.  
         my @parameters;  
         if ($parameterList) { @parameters = @{$parameterList}; }  
         return $self->{_erdb}->Get($objectNames, $filterClause, @parameters);  
 }  
   
 =head3 GetEntity  
   
 C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>  
   
 Return an object describing the entity instance with a specified ID.  
   
 =over 4  
   
 =item entityType  
   
 Entity type name.  
   
 =item ID  
   
 ID of the desired entity.  
   
 =item RETURN  
   
 Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  
 instance is found with the specified key.  
   
 =back  
   
 =cut  
   
 sub GetEntity {  
         # Get the parameters.  
         my ($self, $entityType, $ID) = @_;  
         # Call the ERDB method.  
         return $self->{_erdb}->GetEntity($entityType, $ID);  
 }  
   
 =head3 GetEntityValues  
   
 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  
   
 Returns a flattened list of the values of the specified fields for the specified entity.  
   
 =back  
   
 =cut  
 #: Return Type @;  
 sub GetEntityValues {  
         # Get the parameters.  
         my ($self, $entityType, $ID, $fields) = @_;  
         # Call the ERDB method.  
         return $self->{_erdb}->GetEntityValues($entityType, $ID, $fields);  
 }  
   
 =head3 ShowMetaData  
   
 C<< $sprout->ShowMetaData($fileName); >>  
   
 This method outputs a description of the database to an HTML file in the data directory.  
   
 =over 4  
   
 =item fileName  
   
 Fully-qualified name to give to the output file.  
   
 =back  
   
 =cut  
   
 sub ShowMetaData {  
         # Get the parameters.  
         my ($self, $fileName) = @_;  
         # Compute the file name.  
         my $options = $self->{_options};  
         # Call the show method on the underlying ERDB object.  
         $self->{_erdb}->ShowMetaData($fileName);  
 }  
   
169  =head3 Load  =head3 Load
170    
171  C<< $sprout->Load($rebuild); >>;  C<< $sprout->Load($rebuild); >>;
# Line 367  Line 200 
200  sub Load {  sub Load {
201          # Get the parameters.          # Get the parameters.
202          my ($self, $rebuild) = @_;          my ($self, $rebuild) = @_;
         # Get the database object.  
         my $erdb = $self->{_erdb};  
203          # Load the tables from the data directory.          # Load the tables from the data directory.
204          my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild);      my $retVal = $self->LoadTables($self->{_options}->{dataDir}, $rebuild);
205          # Return the statistics.          # Return the statistics.
206          return $retVal;          return $retVal;
207  }  }
208    
209  =head3 LoadUpdate  =head3 LoadUpdate
210    
211  C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>  C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>
212    
213  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
214  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 410  Line 241 
241  sub LoadUpdate {  sub LoadUpdate {
242          # Get the parameters.          # Get the parameters.
243          my ($self, $truncateFlag, $tableList) = @_;          my ($self, $truncateFlag, $tableList) = @_;
         # Get the database object.  
         my $erdb = $self->{_erdb};  
244          # Declare the return value.          # Declare the return value.
245          my $retVal = Stats->new();          my $retVal = Stats->new();
246          # Get the data directory.          # Get the data directory.
# Line 420  Line 249 
249          # Loop through the incoming table names.          # Loop through the incoming table names.
250          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
251                  # Find the table's file.                  # Find the table's file.
252                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
253                  if (! -e $fileName) {          if (! $fileName) {
254                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
255                  }          } else {
256                  # Attempt to load this table.                  # Attempt to load this table.
257                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, $truncateFlag);
258                  # Accumulate the resulting statistics.                  # Accumulate the resulting statistics.
259                  $retVal->Accumulate($result);                  $retVal->Accumulate($result);
260          }          }
261        }
262          # Return the statistics.          # Return the statistics.
263          return $retVal;          return $retVal;
264  }  }
265    
266    =head3 GenomeCounts
267    
268    C<< my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete); >>
269    
270    Count the number of genomes in each domain. If I<$complete> is TRUE, only complete
271    genomes will be included in the counts.
272    
273    =over 4
274    
275    =item complete
276    
277    TRUE if only complete genomes are to be counted, FALSE if all genomes are to be
278    counted
279    
280    =item RETURN
281    
282    A six-element list containing the number of genomes in each of six categories--
283    Archaea, Bacteria, Eukaryota, Viral, Environmental, and Unknown, respectively.
284    
285    =back
286    
287    =cut
288    
289    sub GenomeCounts {
290        # Get the parameters.
291        my ($self, $complete) = @_;
292        # Set the filter based on the completeness flag.
293        my $filter = ($complete ? "Genome(complete) = 1" : "");
294        # Get all the genomes and the related taxonomy information.
295        my @genomes = $self->GetAll(['Genome'], $filter, [], ['Genome(id)', 'Genome(taxonomy)']);
296        # Clear the counters.
297        my ($arch, $bact, $euk, $vir, $env, $unk) = (0, 0, 0, 0, 0, 0);
298        # Loop through, counting the domains.
299        for my $genome (@genomes) {
300            if    ($genome->[1] =~ /^archaea/i)  { ++$arch }
301            elsif ($genome->[1] =~ /^bacter/i)   { ++$bact }
302            elsif ($genome->[1] =~ /^eukar/i)    { ++$euk }
303            elsif ($genome->[1] =~ /^vir/i)      { ++$vir }
304            elsif ($genome->[1] =~ /^env/i)      { ++$env }
305            else  { ++$unk }
306        }
307        # Return the counts.
308        return ($arch, $bact, $euk, $vir, $env, $unk);
309    }
310    
311    =head3 ContigCount
312    
313    C<< my $count = $sprout->ContigCount($genomeID); >>
314    
315    Return the number of contigs for the specified genome ID.
316    
317    =over 4
318    
319    =item genomeID
320    
321    ID of the genome whose contig count is desired.
322    
323    =item RETURN
324    
325    Returns the number of contigs for the specified genome.
326    
327    =back
328    
329    =cut
330    
331    sub ContigCount {
332        # Get the parameters.
333        my ($self, $genomeID) = @_;
334        # Get the contig count.
335        my $retVal = $self->GetCount(['Contig', 'HasContig'], "HasContig(from-link) = ?", [$genomeID]);
336        # Return the result.
337        return $retVal;
338    }
339    
340    =head3 GeneMenu
341    
342    C<< my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params); >>
343    
344    Return an HTML select menu of genomes. Each genome will be an option in the menu,
345    and will be displayed by name with the ID and a contig count attached. The selection
346    value will be the genome ID. The genomes will be sorted by genus/species name.
347    
348    =over 4
349    
350    =item attributes
351    
352    Reference to a hash mapping attributes to values for the SELECT tag generated.
353    
354    =item filterString
355    
356    A filter string for use in selecting the genomes. The filter string must conform
357    to the rules for the C<< ERDB->Get >> method.
358    
359    =item params
360    
361    Reference to a list of values to be substituted in for the parameter marks in
362    the filter string.
363    
364    =item RETURN
365    
366    Returns an HTML select menu with the specified genomes as selectable options.
367    
368    =back
369    
370    =cut
371    
372    sub GeneMenu {
373        # Get the parameters.
374        my ($self, $attributes, $filterString, $params) = @_;
375        # Start the menu.
376        my $retVal = "<select " .
377            join(" ", map { "$_=\"$attributes->{$_}\"" } keys %{$attributes}) .
378            ">\n";
379        # Get the genomes.
380        my @genomes = $self->GetAll(['Genome'], $filterString, $params, ['Genome(id)',
381                                                                         'Genome(genus)',
382                                                                         'Genome(species)',
383                                                                         'Genome(unique-characterization)']);
384        # Sort them by name.
385        my @sorted = sort { lc("$a->[1] $a->[2]") cmp lc("$b->[1] $b->[2]") } @genomes;
386        # Loop through the genomes, creating the option tags.
387        for my $genomeData (@sorted) {
388            # Get the data for this genome.
389            my ($genomeID, $genus, $species, $strain) = @{$genomeData};
390            # Get the contig count.
391            my $count = $self->ContigCount($genomeID);
392            my $counting = ($count == 1 ? "contig" : "contigs");
393            # Build the option tag.
394            $retVal .= "<option value=\"$genomeID\">$genus $species $strain ($genomeID) [$count $counting]</option>\n";
395            Trace("Option tag built for $genomeID: $genus $species $strain.") if T(3);
396        }
397        # Close the SELECT tag.
398        $retVal .= "</select>\n";
399        # Return the result.
400        return $retVal;
401    }
402  =head3 Build  =head3 Build
403    
404  C<< $sprout->Build(); >>  C<< $sprout->Build(); >>
# Line 447  Line 413 
413          # Get the parameters.          # Get the parameters.
414          my ($self) = @_;          my ($self) = @_;
415          # Create the tables.          # Create the tables.
416          $self->{_erdb}->CreateTables;      $self->CreateTables();
417  }  }
418    
419  =head3 Genomes  =head3 Genomes
# Line 570  Line 536 
536  =item RETURN  =item RETURN
537    
538  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
539  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
540    
541  =back  =back
542    
# Line 597  Line 563 
563                  if ($prevContig eq $contigID && $dir eq $prevDir) {                  if ($prevContig eq $contigID && $dir eq $prevDir) {
564                          # Here the new segment is in the same direction on the same contig. Insure the                          # Here the new segment is in the same direction on the same contig. Insure the
565                          # new segment's beginning is next to the old segment's end.                          # new segment's beginning is next to the old segment's end.
566                          if (($dir eq "-" && $beg == $prevBeg - $prevLen) ||              if ($dir eq "-" && $beg + $len == $prevBeg) {
567                                  ($dir eq "+" && $beg == $prevBeg + $prevLen)) {                  # Here we're merging two backward blocks, so we keep the new begin point
568                                  # Here we need to merge two segments. Adjust the beginning and length values                  # and adjust the length.
569                                  # to include both segments.                  $len += $prevLen;
570                    # Pop the old segment off. The new one will replace it later.
571                    pop @retVal;
572                } elsif ($dir eq "+" && $beg == $prevBeg + $prevLen) {
573                    # Here we need to merge two forward blocks. Adjust the beginning and
574                    # length values to include both segments.
575                                  $beg = $prevBeg;                                  $beg = $prevBeg;
576                                  $len += $prevLen;                                  $len += $prevLen;
577                                  # Pop the old segment off. The new one will replace it later.                                  # Pop the old segment off. The new one will replace it later.
# Line 609  Line 580 
580                  }                  }
581                  # Remember this specifier for the adjacent-segment test the next time through.                  # Remember this specifier for the adjacent-segment test the next time through.
582                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);
583            # Compute the initial base pair.
584            my $start = ($dir eq "+" ? $beg : $beg + $len - 1);
585                  # Add the specifier to the list.                  # Add the specifier to the list.
586                  push @retVal, "${contigID}_$beg$dir$len";          push @retVal, "${contigID}_$start$dir$len";
587          }          }
588          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
589          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
590  }  }
591    
592  =head3 ParseLocation  =head3 ParseLocation
# Line 644  Line 617 
617      shift if UNIVERSAL::isa($_[0],__PACKAGE__);      shift if UNIVERSAL::isa($_[0],__PACKAGE__);
618          my ($location) = @_;          my ($location) = @_;
619          # Parse it into segments.          # Parse it into segments.
620          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
621          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
622          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
623          if ($dir eq "_") {          if ($dir eq "_") {
# Line 720  Line 693 
693  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,
694  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>.
695    
696    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
697    between positions 1401 and 1532, inclusive.
698    
699        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
700    
701  =over 4  =over 4
702    
703  =item locationList  =item locationList
704    
705  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
706  L</FeatureLocation> for more about this format).  I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
707    
708  =item RETURN  =item RETURN
709    
# Line 752  Line 730 
730                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
731                  # before putting it in the return value.                  # before putting it in the return value.
732                  my ($start, $stop);                  my ($start, $stop);
733            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
734                  if ($dir eq "+") {                  if ($dir eq "+") {
735                          $start = $beg;                          $start = $beg;
736                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
737                  } else {                  } else {
738                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
739                          $stop = $beg;                          $stop = $beg;
740                  }                  }
741            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
742                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
743                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
744                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 770  Line 750 
750                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
751                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
752                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
753                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
754                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
755                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
756                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
757                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
758                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
759                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
760                  }                  }
761                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
762                  if ($dir eq '+') {                  if ($dir eq '+') {
763                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
764                  } else {                  } else {
765                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
766                  }                  }
767          }          }
768          # Return the result.          # Return the result.
# Line 818  Line 799 
799          return @retVal;          return @retVal;
800  }  }
801    
802    =head3 GenomeLength
803    
804    C<< my $length = $sprout->GenomeLength($genomeID); >>
805    
806    Return the length of the specified genome in base pairs.
807    
808    =over 4
809    
810    =item genomeID
811    
812    ID of the genome whose base pair count is desired.
813    
814    =item RETURN
815    
816    Returns the number of base pairs in all the contigs of the specified
817    genome.
818    
819    =back
820    
821    =cut
822    
823    sub GenomeLength {
824        # Get the parameters.
825        my ($self, $genomeID) = @_;
826        # Declare the return variable.
827        my $retVal = 0;
828        # Get the genome's contig sequence lengths.
829        my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',
830                           [$genomeID], 'IsMadeUpOf(len)');
831        # Sum the lengths.
832        map { $retVal += $_ } @lens;
833        # Return the result.
834        return $retVal;
835    }
836    
837    =head3 FeatureCount
838    
839    C<< my $count = $sprout->FeatureCount($genomeID, $type); >>
840    
841    Return the number of features of the specified type in the specified genome.
842    
843    =over 4
844    
845    =item genomeID
846    
847    ID of the genome whose feature count is desired.
848    
849    =item type
850    
851    Type of feature to count (eg. C<peg>, C<rna>, etc.).
852    
853    =item RETURN
854    
855    Returns the number of features of the specified type for the specified genome.
856    
857    =back
858    
859    =cut
860    
861    sub FeatureCount {
862        # Get the parameters.
863        my ($self, $genomeID, $type) = @_;
864        # Compute the count.
865        my $retVal = $self->GetCount(['HasFeature', 'Feature'],
866                                    "HasFeature(from-link) = ? AND Feature(feature-type) = ?",
867                                    [$genomeID, $type]);
868        # Return the result.
869        return $retVal;
870    }
871    
872    =head3 GenomeAssignments
873    
874    C<< my $fidHash = $sprout->GenomeAssignments($genomeID); >>
875    
876    Return a list of a genome's assigned features. The return hash will contain each
877    assigned feature of the genome mapped to the text of its most recent functional
878    assignment.
879    
880    =over 4
881    
882    =item genomeID
883    
884    ID of the genome whose functional assignments are desired.
885    
886    =item RETURN
887    
888    Returns a reference to a hash which maps each feature to its most recent
889    functional assignment.
890    
891    =back
892    
893    =cut
894    
895    sub GenomeAssignments {
896        # Get the parameters.
897        my ($self, $genomeID) = @_;
898        # Declare the return variable.
899        my $retVal = {};
900        # Query the genome's features and annotations. We'll put the oldest annotations
901        # first so that the last assignment to go into the hash will be the correct one.
902        my $query = $self->Get(['HasFeature', 'IsTargetOfAnnotation', 'Annotation'],
903                               "HasFeature(from-link) = ? ORDER BY Annotation(time)",
904                               [$genomeID]);
905        # Loop through the annotations.
906        while (my $data = $query->Fetch) {
907            # Get the feature ID and annotation text.
908            my ($fid, $annotation) = $data->Values(['HasFeature(to-link)',
909                                                    'Annotation(annotation)']);
910            # Check to see if this is an assignment. Note that the user really
911            # doesn't matter to us, other than we use it to determine whether or
912            # not this is an assignment.
913            my ($user, $assignment) = _ParseAssignment('fig', $annotation);
914            if ($user) {
915                # Here it's an assignment. We put it in the return hash, overwriting
916                # any older assignment that might be present.
917                $retVal->{$fid} = $assignment;
918            }
919        }
920        # Return the result.
921        return $retVal;
922    }
923    
924  =head3 ContigLength  =head3 ContigLength
925    
926  C<< my $length = $sprout->ContigLength($contigID); >>  C<< my $length = $sprout->ContigLength($contigID); >>
# Line 851  Line 954 
954          # Set it from the sequence data, if any.          # Set it from the sequence data, if any.
955          if ($sequence) {          if ($sequence) {
956                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
957                  $retVal = $start + $len;          $retVal = $start + $len - 1;
958        }
959        # Return the result.
960        return $retVal;
961    }
962    
963    =head3 ClusterPEGs
964    
965    C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>
966    
967    Cluster the PEGs in a list according to the cluster coding scheme of the specified
968    subsystem. In order for this to work properly, the subsystem object must have
969    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.
970    This causes the cluster numbers to be pulled into the subsystem's color hash.
971    If a PEG is not found in the color hash, it will not appear in the output
972    sequence.
973    
974    =over 4
975    
976    =item sub
977    
978    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
979    method.
980    
981    =item pegs
982    
983    Reference to the list of PEGs to be clustered.
984    
985    =item RETURN
986    
987    Returns a list of the PEGs, grouped into smaller lists by cluster number.
988    
989    =back
990    
991    =cut
992    #: Return Type $@@;
993    sub ClusterPEGs {
994        # Get the parameters.
995        my ($self, $sub, $pegs) = @_;
996        # Declare the return variable.
997        my $retVal = [];
998        # Loop through the PEGs, creating arrays for each cluster.
999        for my $pegID (@{$pegs}) {
1000            my $clusterNumber = $sub->get_cluster_number($pegID);
1001            # Only proceed if the PEG is in a cluster.
1002            if ($clusterNumber >= 0) {
1003                # Push this PEG onto the sub-list for the specified cluster number.
1004                push @{$retVal->[$clusterNumber]}, $pegID;
1005            }
1006          }          }
1007          # Return the result.          # Return the result.
1008          return $retVal;          return $retVal;
# Line 1001  Line 1152 
1152    
1153  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1154    
1155  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>
1156    
1157  Return the annotations of a feature.  Return the annotations of a feature.
1158    
# Line 1011  Line 1162 
1162    
1163  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1164    
1165    =item rawFlag
1166    
1167    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1168    will be returned in human-readable form.
1169    
1170  =item RETURN  =item RETURN
1171    
1172  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1173    
1174  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1175    
1176  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1177    
1178  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1179    
# Line 1029  Line 1185 
1185  #: Return Type @%;  #: Return Type @%;
1186  sub FeatureAnnotations {  sub FeatureAnnotations {
1187          # Get the parameters.          # Get the parameters.
1188          my ($self, $featureID) = @_;      my ($self, $featureID, $rawFlag) = @_;
1189          # 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.
1190          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1191                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1042  Line 1198 
1198                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1199                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1200                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1201            # Convert the time, if necessary.
1202            if (! $rawFlag) {
1203                $timeStamp = FriendlyTimestamp($timeStamp);
1204            }
1205                  # Assemble them into a hash.                  # Assemble them into a hash.
1206          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1207                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1208                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1209                  # Add it to the return list.                  # Add it to the return list.
1210                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1073  Line 1233 
1233    
1234  =item RETURN  =item RETURN
1235    
1236  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1237    
1238  =back  =back
1239    
# Line 1083  Line 1243 
1243          # Get the parameters.          # Get the parameters.
1244          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1245          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1246      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1247                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1248                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1249                                               'MadeAnnotation(from-link)']);
1250          # Declare the return hash.          # Declare the return hash.
1251          my %retVal;          my %retVal;
     # Declare a hash for insuring we only make one assignment per user.  
     my %timeHash = ();  
1252      # Now we sort the assignments by timestamp in reverse.      # Now we sort the assignments by timestamp in reverse.
1253      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1254          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1255      for my $annotation (@sortedQuery) {      for my $annotation (@sortedQuery) {
1256          # Get the annotation fields.          # Get the annotation fields.
1257          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text, $user) = @{$annotation};
1258                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1259                  my ($user, $function) = _ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1260          if ($user && ! exists $timeHash{$user}) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1261              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1262              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
1263              # return hash.              # return hash.
1264                          $retVal{$function} = $user;              $retVal{$actualUser} = $function;
             # Insure we don't assign to this user again.  
             $timeHash{$user} = 1;  
1265                  }                  }
1266          }          }
1267          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1120  Line 1277 
1277  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
1278  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 a functional
1279  assignment is a type of annotation. The format of an assignment is described in  assignment is a type of annotation. The format of an assignment is described in
1280  L</ParseLocation>. Its worth noting that we cannot filter on the content of the  L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1281  annotation itself because it's a text field; however, this is not a big problem because  annotation itself because it's a text field; however, this is not a big problem because
1282  most features only have a small number of annotations.  most features only have a small number of annotations.
1283    
# Line 1182  Line 1339 
1339              }              }
1340          }          }
1341          # 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.
1342          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1343                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1344                                 [$featureID]);                                 [$featureID]);
1345          my $timeSelected = 0;          my $timeSelected = 0;
1346          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1347          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1348              # Get the annotation text.              # Get the annotation text.
1349              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);              my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1350                                                         'Annotation(time)', 'MadeAnnotation(from-link)']);
1351              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1352              my ($user, $function) = _ParseAssignment($text);              my ($actualUser, $function) = _ParseAssignment($user, $text);
1353              if ($user) {              Trace("Assignment user is $actualUser, text is $function.") if T(4);
1354                if ($actualUser) {
1355                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1356                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1357                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1358                      $retVal = $function;                      $retVal = $function;
1359                      $timeSelected = $time;                      $timeSelected = $time;
1360                  }                  }
# Line 1211  Line 1370 
1370          return $retVal;          return $retVal;
1371  }  }
1372    
1373    =head3 FunctionsOf
1374    
1375    C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>
1376    
1377    Return the functional assignments of a particular feature.
1378    
1379    The functional assignment is handled differently depending on the type of feature. If
1380    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1381    assignment is a type of annotation. The format of an assignment is described in
1382    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1383    annotation itself because it's a text field; however, this is not a big problem because
1384    most features only have a small number of annotations.
1385    
1386    If the feature is B<not> identified by a FIG ID, then the functional assignment
1387    information is taken from the B<ExternalAliasFunc> table. If the table does
1388    not contain an entry for the feature, an empty list is returned.
1389    
1390    =over 4
1391    
1392    =item featureID
1393    
1394    ID of the feature whose functional assignments are desired.
1395    
1396    =item RETURN
1397    
1398    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1399    that user.
1400    
1401    =back
1402    
1403    =cut
1404    #: Return Type @@;
1405    sub FunctionsOf {
1406        # Get the parameters.
1407        my ($self, $featureID) = @_;
1408        # Declare the return value.
1409        my @retVal = ();
1410        # Determine the ID type.
1411        if ($featureID =~ m/^fig\|/) {
1412            # Here we have a FIG feature ID. We must build the list of trusted
1413            # users.
1414            my %trusteeTable = ();
1415            # Build a query for all of the feature's annotations, sorted by date.
1416            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1417                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1418                                   [$featureID]);
1419            my $timeSelected = 0;
1420            # Loop until we run out of annotations.
1421            while (my $annotation = $query->Fetch()) {
1422                # Get the annotation text.
1423                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1424                                                                'Annotation(time)',
1425                                                                'MadeAnnotation(user)']);
1426                # Check to see if this is a functional assignment for a trusted user.
1427                my ($actualUser, $function) = _ParseAssignment($user, $text);
1428                if ($actualUser) {
1429                    # Here it is a functional assignment.
1430                    push @retVal, [$actualUser, $function];
1431                }
1432            }
1433        } else {
1434            # Here we have a non-FIG feature ID. In this case the user ID does not
1435            # matter. We simply get the information from the External Alias Function
1436            # table.
1437            my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1438                                                     ['ExternalAliasFunc(func)']);
1439            push @retVal, map { ['master', $_] } @assignments;
1440        }
1441        # Return the assignments found.
1442        return @retVal;
1443    }
1444    
1445  =head3 BBHList  =head3 BBHList
1446    
1447  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>
# Line 1230  Line 1461 
1461    
1462  =item RETURN  =item RETURN
1463    
1464  Returns a reference to a hash that maps the IDs of the incoming features to the IDs of  Returns a reference to a hash that maps the IDs of the incoming features to the best hits
1465  their best hits.  on the target genome.
1466    
1467  =back  =back
1468    
# Line 1248  Line 1479 
1479                  my $query = $self->Get(['IsBidirectionalBestHitOf'],                  my $query = $self->Get(['IsBidirectionalBestHitOf'],
1480                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1481                                                             [$featureID, $genomeID]);                                                             [$featureID, $genomeID]);
1482                  # Look for the best hit.          # Peel off the BBHs found.
1483                  my $bbh = $query->Fetch;          my @found = ();
1484                  if ($bbh) {          while (my $bbh = $query->Fetch) {
1485                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
                         $retVal{$featureID} = $targetFeature;  
1486                  }                  }
1487            $retVal{$featureID} = \@found;
1488          }          }
1489          # Return the mapping.          # Return the mapping.
1490          return \%retVal;          return \%retVal;
1491  }  }
1492    
1493    =head3 SimList
1494    
1495    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1496    
1497    Return a list of the similarities to the specified feature.
1498    
1499    Sprout does not support real similarities, so this method just returns the bidirectional
1500    best hits.
1501    
1502    =over 4
1503    
1504    =item featureID
1505    
1506    ID of the feature whose similarities are desired.
1507    
1508    =item count
1509    
1510    Maximum number of similar features to be returned, or C<0> to return them all.
1511    
1512    =back
1513    
1514    =cut
1515    #: Return Type %;
1516    sub SimList {
1517        # Get the parameters.
1518        my ($self, $featureID, $count) = @_;
1519        # Ask for the best hits.
1520        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1521                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1522                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1523                                  $count);
1524        # Create the return value.
1525        my %retVal = ();
1526        for my $tuple (@lists) {
1527            $retVal{$tuple->[0]} = $tuple->[1];
1528        }
1529        # Return the result.
1530        return %retVal;
1531    }
1532    
1533    
1534    
1535    =head3 IsComplete
1536    
1537    C<< my $flag = $sprout->IsComplete($genomeID); >>
1538    
1539    Return TRUE if the specified genome is complete, else FALSE.
1540    
1541    =over 4
1542    
1543    =item genomeID
1544    
1545    ID of the genome whose completeness status is desired.
1546    
1547    =item RETURN
1548    
1549    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1550    not found.
1551    
1552    =back
1553    
1554    =cut
1555    #: Return Type $;
1556    sub IsComplete {
1557        # Get the parameters.
1558        my ($self, $genomeID) = @_;
1559        # Declare the return variable.
1560        my $retVal;
1561        # Get the genome's data.
1562        my $genomeData = $self->GetEntity('Genome', $genomeID);
1563        if ($genomeData) {
1564            # The genome exists, so get the completeness flag.
1565            ($retVal) = $genomeData->Value('Genome(complete)');
1566        }
1567        # Return the result.
1568        return $retVal;
1569    }
1570    
1571  =head3 FeatureAliases  =head3 FeatureAliases
1572    
1573  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1293  Line 1602 
1602    
1603  C<< my $genomeID = $sprout->GenomeOf($featureID); >>  C<< my $genomeID = $sprout->GenomeOf($featureID); >>
1604    
1605  Return the genome that contains a specified feature.  Return the genome that contains a specified feature or contig.
1606    
1607  =over 4  =over 4
1608    
1609  =item featureID  =item featureID
1610    
1611  ID of the feature whose genome is desired.  ID of the feature or contig whose genome is desired.
1612    
1613  =item RETURN  =item RETURN
1614    
1615  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
1616  an undefined value.  found, returns an undefined value.
1617    
1618  =back  =back
1619    
# Line 1313  Line 1622 
1622  sub GenomeOf {  sub GenomeOf {
1623          # Get the parameters.          # Get the parameters.
1624          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1625          # Create a query to find the genome associated with the feature.      # Create a query to find the genome associated with the incoming ID.
1626          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);      my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ? OR HasContig(to-link) = ?",
1627                               [$featureID, $featureID]);
1628          # Declare the return value.          # Declare the return value.
1629          my $retVal;          my $retVal;
1630          # Get the genome ID.          # Get the genome ID.
# Line 1349  Line 1659 
1659  sub CoupledFeatures {  sub CoupledFeatures {
1660          # Get the parameters.          # Get the parameters.
1661          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1662          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
1663          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      # Create a query to retrieve the functionally-coupled features.
1664          # (B,A) will also be found.      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1665          my $query = $self->Get(['IsClusteredOnChromosomeWith'],                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1666          # This value will be set to TRUE if we find at least one coupled feature.          # This value will be set to TRUE if we find at least one coupled feature.
1667          my $found = 0;          my $found = 0;
1668          # Create the return hash.          # Create the return hash.
1669          my %retVal = ();          my %retVal = ();
1670          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1671          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1672                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1673                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1674                                                            'Coupling(score)']);
1675            Trace("$featureID coupled with score $score to ID $couplingID.") if T(coupling => 4);
1676            # Get the other feature that participates in the coupling.
1677            my ($otherFeatureID) = $self->GetFlat(['ParticipatesInCoupling'],
1678                                               "ParticipatesInCoupling(to-link) = ? AND ParticipatesInCoupling(from-link) <> ?",
1679                                               [$couplingID, $featureID], 'ParticipatesInCoupling(from-link)');
1680            Trace("$couplingID target feature is $otherFeatureID.") if T(coupling => 4);
1681            # Attach the other feature's score to its ID.
1682                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1683                  $found = 1;                  $found = 1;
1684          }          }
# Line 1374  Line 1691 
1691          return %retVal;          return %retVal;
1692  }  }
1693    
1694  =head3 GetEntityTypes  =head3 CouplingEvidence
1695    
1696    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1697    
1698    Return the evidence for a functional coupling.
1699    
1700    A pair of features is considered evidence of a coupling between two other
1701    features if they occur close together on a contig and both are similar to
1702    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1703    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1704    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1705    similar to B<A2>.
1706    
1707    The score of a coupling is determined by the number of pieces of evidence
1708    that are considered I<representative>. If several evidence items belong to
1709    a group of genomes that are close to each other, only one of those items
1710    is considered representative. The other evidence items are presumed to be
1711    there because of the relationship between the genomes rather than because
1712    the two proteins generated by the features have a related functionality.
1713    
1714    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1715    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1716    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1717    and FALSE otherwise.
1718    
1719    =over 4
1720    
1721    =item peg1
1722    
1723    ID of the feature of interest.
1724    
1725    =item peg2
1726    
1727    ID of a feature functionally coupled to the feature of interest.
1728    
1729    =item RETURN
1730    
1731    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1732    of interest, a feature similar to the functionally coupled feature, and a flag
1733    that is TRUE for a representative piece of evidence and FALSE otherwise.
1734    
1735    =back
1736    
1737    =cut
1738    #: Return Type @@;
1739    sub CouplingEvidence {
1740        # Get the parameters.
1741        my ($self, $peg1, $peg2) = @_;
1742        # Declare the return variable.
1743        my @retVal = ();
1744        # Our first task is to find out the nature of the coupling: whether or not
1745        # it exists, its score, and whether the features are stored in the same
1746        # order as the ones coming in.
1747        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1748        # Only proceed if a coupling exists.
1749        if ($couplingID) {
1750            # Determine the ordering to place on the evidence items. If we're
1751            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1752            # we want feature 1 before feature 2 (normal).
1753            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1754            my $ordering = ($inverted ? "DESC" : "");
1755            # Get the coupling evidence.
1756            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1757                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1758                                              [$couplingID],
1759                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1760            # Loop through the evidence items. Each piece of evidence is represented by two
1761            # positions in the evidence list, one for each feature on the other side of the
1762            # evidence link. If at some point we want to generalize to couplings with
1763            # more than two positions, this section of code will need to be re-done.
1764            while (@evidenceList > 0) {
1765                my $peg1Data = shift @evidenceList;
1766                my $peg2Data = shift @evidenceList;
1767                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1768                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1769            }
1770            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1771        }
1772        # Return the result.
1773        return @retVal;
1774    }
1775    
1776    =head3 GetCoupling
1777    
1778    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1779    
1780    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1781    exists, we return the coupling ID along with an indicator of whether the
1782    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1783    In the second case, we say the coupling is I<inverted>. The importance of an
1784    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1785    
1786    =over 4
1787    
1788    =item peg1
1789    
1790    ID of the feature of interest.
1791    
1792    =item peg2
1793    
1794    ID of the potentially coupled feature.
1795    
1796    =item RETURN
1797    
1798    Returns a three-element list. The first element contains the database ID of
1799    the coupling. The second element is FALSE if the coupling is stored in the
1800    database in the caller specified order and TRUE if it is stored in the
1801    inverted order. The third element is the coupling's score. If the coupling
1802    does not exist, all three list elements will be C<undef>.
1803    
1804    =back
1805    
1806    =cut
1807    #: Return Type $%@;
1808    sub GetCoupling {
1809        # Get the parameters.
1810        my ($self, $peg1, $peg2) = @_;
1811        # Declare the return values. We'll start with the coupling ID and undefine the
1812        # flag and score until we have more information.
1813        my ($retVal, $inverted, $score) = ($self->CouplingID($peg1, $peg2), undef, undef);
1814        # Find the coupling data.
1815        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1816                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1817                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1818        # Check to see if we found anything.
1819        if (!@pegs) {
1820            Trace("No coupling found.") if T(Coupling => 4);
1821            # No coupling, so undefine the return value.
1822            $retVal = undef;
1823        } else {
1824            # We have a coupling! Get the score and check for inversion.
1825            $score = $pegs[0]->[1];
1826            my $firstFound = $pegs[0]->[0];
1827            $inverted = ($firstFound ne $peg1);
1828            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1829        }
1830        # Return the result.
1831        return ($retVal, $inverted, $score);
1832    }
1833    
1834    =head3 GetSynonymGroup
1835    
1836    C<< my $id = $sprout->GetSynonymGroup($fid); >>
1837    
1838    Return the synonym group name for the specified feature.
1839    
1840    =over 4
1841    
1842    =item fid
1843    
1844    ID of the feature whose synonym group is desired.
1845    
1846    =item RETURN
1847    
1848    The name of the synonym group to which the feature belongs. If the feature does
1849    not belong to a synonym group, the feature ID itself is returned.
1850    
1851    =back
1852    
1853    =cut
1854    
1855    sub GetSynonymGroup {
1856        # Get the parameters.
1857        my ($self, $fid) = @_;
1858        # Declare the return variable.
1859        my $retVal;
1860        # Find the synonym group.
1861        my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?",
1862                                       [$fid], 'IsSynonymGroupFor(from-link)');
1863        # Check to see if we found anything.
1864        if (@groups) {
1865            $retVal = $groups[0];
1866        } else {
1867            $retVal = $fid;
1868        }
1869        # Return the result.
1870        return $retVal;
1871    }
1872    
1873    =head3 GetBoundaries
1874    
1875    C<< my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList); >>
1876    
1877    Determine the begin and end boundaries for the locations in a list. All of the
1878    locations must belong to the same contig and have mostly the same direction in
1879    order for this method to produce a meaningful result. The resulting
1880    begin/end pair will contain all of the bases in any of the locations.
1881    
1882    =over 4
1883    
1884    =item locList
1885    
1886    List of locations to process.
1887    
1888    =item RETURN
1889    
1890    Returns a 3-tuple consisting of the contig ID, the beginning boundary,
1891    and the ending boundary. The beginning boundary will be left of the
1892    end for mostly-forward locations and right of the end for mostly-backward
1893    locations.
1894    
1895    =back
1896    
1897    =cut
1898    
1899    sub GetBoundaries {
1900        # Get the parameters.
1901        my ($self, @locList) = @_;
1902        # Set up the counters used to determine the most popular direction.
1903        my %counts = ( '+' => 0, '-' => 0 );
1904        # Get the last location and parse it.
1905        my $locObject = BasicLocation->new(pop @locList);
1906        # Prime the loop with its data.
1907        my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right);
1908        # Count its direction.
1909        $counts{$locObject->Dir}++;
1910        # Loop through the remaining locations. Note that in most situations, this loop
1911        # will not iterate at all, because most of the time we will be dealing with a
1912        # singleton list.
1913        for my $loc (@locList) {
1914            # Create a location object.
1915            my $locObject = BasicLocation->new($loc);
1916            # Count the direction.
1917            $counts{$locObject->Dir}++;
1918            # Get the left end and the right end.
1919            my $left = $locObject->Left;
1920            my $right = $locObject->Right;
1921            # Merge them into the return variables.
1922            if ($left < $beg) {
1923                $beg = $left;
1924            }
1925            if ($right > $end) {
1926                $end = $right;
1927            }
1928        }
1929        # If the most common direction is reverse, flip the begin and end markers.
1930        if ($counts{'-'} > $counts{'+'}) {
1931            ($beg, $end) = ($end, $beg);
1932        }
1933        # Return the result.
1934        return ($contig, $beg, $end);
1935    }
1936    
1937    =head3 CouplingID
1938    
1939    C<< my $couplingID = $sprout->CouplingID($peg1, $peg2); >>
1940    
1941    Return the coupling ID for a pair of feature IDs.
1942    
1943    The coupling ID is currently computed by joining the feature IDs in
1944    sorted order with a space. Client modules (that is, modules which
1945    use Sprout) should not, however, count on this always being the
1946    case. This method provides a way for abstracting the concept of a
1947    coupling ID. All that we know for sure about it is that it can be
1948    generated easily from the feature IDs and the order of the IDs
1949    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1950    will have the same value as C<CouplingID("b1", "a1")>.
1951    
1952    =over 4
1953    
1954    =item peg1
1955    
1956    First feature of interest.
1957    
1958    =item peg2
1959    
1960    Second feature of interest.
1961    
1962    =item RETURN
1963    
1964  C<< my @entityList = $sprout->GetEntityTypes(); >>  Returns the ID that would be used to represent a functional coupling of
1965    the two specified PEGs.
1966    
1967  Return the list of supported entity types.  =back
1968    
1969  =cut  =cut
1970  #: Return Type @;  #: Return Type $;
1971  sub GetEntityTypes {  sub CouplingID {
1972          # Get the parameters.      my ($self, @pegs) = @_;
1973          my ($self) = @_;      return $self->DigestKey(join " ", sort @pegs);
         # Get the underlying database object.  
         my $erdb = $self->{_erdb};  
         # Get its entity type list.  
         my @retVal = $erdb->GetEntityTypes();  
1974  }  }
1975    
1976  =head3 ReadFasta  =head3 ReadFasta
# Line 1435  Line 2017 
2017                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
2018                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
2019                          if ($id) {                          if ($id) {
2020                                  $retVal{$id} = uc $sequence;                  $retVal{$id} = lc $sequence;
2021                          }                          }
2022                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
2023                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
2024                  } else {                  } else {
2025                          # Here we have a data line, so we add it to the sequence accumulator.                          # Here we have a data line, so we add it to the sequence accumulator.
2026                          # First, we get the actual data out. Note that we normalize to upper              # First, we get the actual data out. Note that we normalize to lower
2027                          # case.                          # case.
2028                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
2029                          $sequence .= $1;                          $sequence .= $1;
# Line 1449  Line 2031 
2031          }          }
2032          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
2033          if ($sequence) {          if ($sequence) {
2034                  $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
2035          }          }
2036          # Close the file.          # Close the file.
2037          close FASTAFILE;          close FASTAFILE;
# Line 1536  Line 2118 
2118          # Get the data directory name.          # Get the data directory name.
2119          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
2120          # Dump the relations.          # Dump the relations.
2121          $self->{_erdb}->DumpRelations($outputDirectory);      $self->DumpRelations($outputDirectory);
2122  }  }
2123    
2124  =head3 XMLFileName  =head3 XMLFileName
# Line 1568  Line 2150 
2150  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
2151  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>.
2152    
2153  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
2154    
2155  =over 4  =over 4
2156    
# Line 1588  Line 2170 
2170          # Get the parameters.          # Get the parameters.
2171          my ($self, $objectType, $fieldHash) = @_;          my ($self, $objectType, $fieldHash) = @_;
2172          # Call the underlying method.          # Call the underlying method.
2173          $self->{_erdb}->InsertObject($objectType, $fieldHash);      $self->InsertObject($objectType, $fieldHash);
2174  }  }
2175    
2176  =head3 Annotate  =head3 Annotate
# Line 1747  Line 2329 
2329          return @retVal;          return @retVal;
2330  }  }
2331    
 =head3 Exists  
   
 C<< my $found = $sprout->Exists($entityName, $entityID); >>  
   
 Return TRUE if an entity exists, else FALSE.  
   
 =over 4  
   
 =item entityName  
   
 Name of the entity type (e.g. C<Feature>) relevant to the existence check.  
   
 =item entityID  
   
 ID of the entity instance whose existence is to be checked.  
   
 =item RETURN  
   
 Returns TRUE if the entity instance exists, else FALSE.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub Exists {  
         # Get the parameters.  
         my ($self, $entityName, $entityID) = @_;  
         # Check for the entity instance.  
         my $testInstance = $self->GetEntity($entityName, $entityID);  
         # Return an existence indicator.  
         my $retVal = ($testInstance ? 1 : 0);  
         return $retVal;  
 }  
   
2332  =head3 FeatureTranslation  =head3 FeatureTranslation
2333    
2334  C<< my $translation = $sprout->FeatureTranslation($featureID); >>  C<< my $translation = $sprout->FeatureTranslation($featureID); >>
# Line 1966  Line 2514 
2514          return @retVal;          return @retVal;
2515  }  }
2516    
2517    =head3 GetProperties
2518    
2519    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2520    
2521    Return a list of the properties with the specified characteristics.
2522    
2523    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2524    will also be associated with genomes.) A property value is represented by a 4-tuple of
2525    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2526    
2527    =over 4
2528    
2529    =item fid
2530    
2531    ID of the feature possessing the property.
2532    
2533    =item key
2534    
2535    Name or key of the property.
2536    
2537    =item value
2538    
2539    Value of the property.
2540    
2541    =item url
2542    
2543    URL of the document that indicated the property should have this particular value, or an
2544    empty string if no such document exists.
2545    
2546    =back
2547    
2548    The parameters act as a filter for the desired data. Any non-null parameter will
2549    automatically match all the tuples returned. So, specifying just the I<$fid> will
2550    return all the properties of the specified feature; similarly, specifying the I<$key>
2551    and I<$value> parameters will return all the features having the specified property
2552    value.
2553    
2554    A single property key can have many values, representing different ideas about the
2555    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2556    virulent, and another may declare that it is not virulent. A query about the virulence of
2557    C<fig|83333.1.peg.10> would be coded as
2558    
2559        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2560    
2561    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2562    not to be filtered. The tuples returned would be
2563    
2564        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2565        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2566    
2567    =cut
2568    #: Return Type @@;
2569    sub GetProperties {
2570        # Get the parameters.
2571        my ($self, @parms) = @_;
2572        # Declare the return variable.
2573        my @retVal = ();
2574        # Now we need to create a WHERE clause that will get us the data we want. First,
2575        # we create a list of the columns containing the data for each parameter.
2576        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2577                        'Property(property-value)', 'HasProperty(evidence)');
2578        # Now we build the WHERE clause and the list of parameter values.
2579        my @where = ();
2580        my @values = ();
2581        for (my $i = 0; $i <= $#colNames; $i++) {
2582            my $parm = $parms[$i];
2583            if (defined $parm && ($parm ne '')) {
2584                push @where, "$colNames[$i] = ?";
2585                push @values, $parm;
2586            }
2587        }
2588        # Format the WHERE clause.
2589        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2590        # Ask for all the propertie values with the desired characteristics.
2591        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2592        while (my $valueObject = $query->Fetch()) {
2593            my @tuple = $valueObject->Values(\@colNames);
2594            push @retVal, \@tuple;
2595        }
2596        # Return the result.
2597        return @retVal;
2598    }
2599    
2600  =head3 FeatureProperties  =head3 FeatureProperties
2601    
2602  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2160  Line 2791 
2791  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2792    
2793  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
2794  to the role the feature performs.  to the roles the feature performs.
2795    
2796  =over 4  =over 4
2797    
# Line 2170  Line 2801 
2801    
2802  =item RETURN  =item RETURN
2803    
2804  Returns a hash mapping all the feature's subsystems to the feature's role.  Returns a hash mapping all the feature's subsystems to a list of the feature's roles.
2805    
2806  =back  =back
2807    
2808  =cut  =cut
2809  #: Return Type %;  #: Return Type %@;
2810  sub SubsystemsOf {  sub SubsystemsOf {
2811          # Get the parameters.          # Get the parameters.
2812          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2813          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
2814          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2815                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2816                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2817          # Create the return value.          # Create the return value.
2818          my %retVal = ();          my %retVal = ();
2819        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2820        # in two spreadsheet cells.
2821        my %dupHash = ();
2822          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2823          for my $record (@subsystems) {          for my $record (@subsystems) {
2824                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
2825            my ($subsys, $role) = @{$record};
2826            # Insure it's the first time for both.
2827            my $dupKey = "$subsys\n$role";
2828            if (! exists $dupHash{"$subsys\n$role"}) {
2829                $dupHash{$dupKey} = 1;
2830                push @{$retVal{$subsys}}, $role;
2831            }
2832          }          }
2833          # Return the hash.          # Return the hash.
2834          return %retVal;          return %retVal;
2835  }  }
2836    
2837    =head3 SubsystemList
2838    
2839    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2840    
2841    Return a list containing the names of the subsystems in which the specified
2842    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2843    subsystem names, not the roles.
2844    
2845    =over 4
2846    
2847    =item featureID
2848    
2849    ID of the feature whose subsystem names are desired.
2850    
2851    =item RETURN
2852    
2853    Returns a list of the names of the subsystems in which the feature participates.
2854    
2855    =back
2856    
2857    =cut
2858    #: Return Type @;
2859    sub SubsystemList {
2860        # Get the parameters.
2861        my ($self, $featureID) = @_;
2862        # Get the list of names.
2863        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2864                                    [$featureID], 'HasSSCell(from-link)');
2865        # Return the result.
2866        return @retVal;
2867    }
2868    
2869  =head3 RelatedFeatures  =head3 RelatedFeatures
2870    
2871  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2294  Line 2967 
2967          return @retVal;          return @retVal;
2968  }  }
2969    
 =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;  
 }  
   
2970  =head3 Protein  =head3 Protein
2971    
2972  C<< my $protein = Sprout::Protein($sequence, $table); >>  C<< my $protein = Sprout::Protein($sequence, $table); >>
# Line 2514  Line 3068 
3068          # Create the return list, priming it with the name of the data directory.          # Create the return list, priming it with the name of the data directory.
3069          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
3070          # Concatenate the table names.          # Concatenate the table names.
3071          push @retVal, $self->{_erdb}->GetTableNames();      push @retVal, $self->GetTableNames();
3072          # Return the result.          # Return the result.
3073          return @retVal;          return @retVal;
3074  }  }
3075    
3076  =head3 LowBBHs  =head3 LowBBHs
3077    
3078  C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>  C<< my %bbhMap = $sprout->LowBBHs($featureID, $cutoff); >>
3079    
3080  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
3081  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 2563  Line 3117 
3117          return %retVal;          return %retVal;
3118  }  }
3119    
3120    =head3 Sims
3121    
3122    C<< my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters); >>
3123    
3124    Get a list of similarities for a specified feature. Similarity information is not kept in the
3125    Sprout database; rather, they are retrieved from a network server. The similarities are
3126    returned as B<Sim> objects. A Sim object is actually a list reference that has been blessed
3127    so that its elements can be accessed by name.
3128    
3129    Similarities can be either raw or expanded. The raw similarities are basic
3130    hits between features with similar DNA. Expanding a raw similarity drags in any
3131    features considered substantially identical. So, for example, if features B<A1>,
3132    B<A2>, and B<A3> are all substatially identical to B<A>, then a raw similarity
3133    B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3134    
3135    =over 4
3136    
3137    =item fid
3138    
3139    ID of the feature whose similarities are desired.
3140    
3141    =item maxN
3142    
3143    Maximum number of similarities to return.
3144    
3145    =item maxP
3146    
3147    Minumum allowable similarity score.
3148    
3149    =item select
3150    
3151    Selection criterion: C<raw> means only raw similarities are returned; C<fig>
3152    means only similarities to FIG features are returned; C<all> means all expanded
3153    similarities are returned; and C<figx> means similarities are expanded until the
3154    number of FIG features equals the maximum.
3155    
3156    =item max_expand
3157    
3158    The maximum number of features to expand.
3159    
3160    =item filters
3161    
3162    Reference to a hash containing filter information, or a subroutine that can be
3163    used to filter the sims.
3164    
3165    =item RETURN
3166    
3167    Returns a reference to a list of similarity objects, or C<undef> if an error
3168    occurred.
3169    
3170    =back
3171    
3172    =cut
3173    
3174    sub Sims {
3175        # Get the parameters.
3176        my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_;
3177        # Create the shim object to test for deleted FIDs.
3178        my $shim = FidCheck->new($self);
3179        # Ask the network for sims.
3180        my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters);
3181        # Return the result.
3182        return $retVal;
3183    }
3184    
3185  =head3 GetGroups  =head3 GetGroups
3186    
3187  C<< my %groups = $sprout->GetGroups(\@groupList); >>  C<< my %groups = $sprout->GetGroups(\@groupList); >>
# Line 2611  Line 3230 
3230      return %retVal;      return %retVal;
3231  }  }
3232    
3233    =head3 MyGenomes
3234    
3235    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3236    
3237    Return a list of the genomes to be included in the Sprout.
3238    
3239    This method is provided for use during the Sprout load. It presumes the Genome load file has
3240    already been created. (It will be in the Sprout data directory and called either C<Genome>
3241    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3242    IDs.
3243    
3244    =over 4
3245    
3246    =item dataDir
3247    
3248    Directory containing the Sprout load files.
3249    
3250    =back
3251    
3252    =cut
3253    #: Return Type @;
3254    sub MyGenomes {
3255        # Get the parameters.
3256        my ($dataDir) = @_;
3257        # Compute the genome file name.
3258        my $genomeFileName = LoadFileName($dataDir, "Genome");
3259        # Extract the genome IDs from the files.
3260        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3261        # Return the result.
3262        return @retVal;
3263    }
3264    
3265    =head3 LoadFileName
3266    
3267    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3268    
3269    Return the name of the load file for the specified table in the specified data
3270    directory.
3271    
3272    =over 4
3273    
3274    =item dataDir
3275    
3276    Directory containing the Sprout load files.
3277    
3278    =item tableName
3279    
3280    Name of the table whose load file is desired.
3281    
3282    =item RETURN
3283    
3284    Returns the name of the file containing the load data for the specified table, or
3285    C<undef> if no load file is present.
3286    
3287    =back
3288    
3289    =cut
3290    #: Return Type $;
3291    sub LoadFileName {
3292        # Get the parameters.
3293        my ($dataDir, $tableName) = @_;
3294        # Declare the return variable.
3295        my $retVal;
3296        # Check for the various file names.
3297        if (-e "$dataDir/$tableName") {
3298            $retVal = "$dataDir/$tableName";
3299        } elsif (-e "$dataDir/$tableName.dtx") {
3300            $retVal = "$dataDir/$tableName.dtx";
3301        }
3302        # Return the result.
3303        return $retVal;
3304    }
3305    
3306    =head3 DeleteGenome
3307    
3308    C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>
3309    
3310    Delete a genome from the database.
3311    
3312    =over 4
3313    
3314    =item genomeID
3315    
3316    ID of the genome to delete
3317    
3318    =item testFlag
3319    
3320    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3321    
3322    =item RETURN
3323    
3324    Returns a statistics object describing the rows deleted.
3325    
3326    =back
3327    
3328    =cut
3329    #: Return Type $%;
3330    sub DeleteGenome {
3331        # Get the parameters.
3332        my ($self, $genomeID, $testFlag) = @_;
3333        # Perform the delete for the genome's features.
3334        my $retVal = $self->Delete('Feature', "fig|$genomeID.%", $testFlag);
3335        # Perform the delete for the primary genome data.
3336        my $stats = $self->Delete('Genome', $genomeID, $testFlag);
3337        $retVal->Accumulate($stats);
3338        # Return the result.
3339        return $retVal;
3340    }
3341    
3342  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3343    
3344  =head3 ParseAssignment  =head3 ParseAssignment
# Line 2621  Line 3349 
3349    
3350  A functional assignment is always of the form  A functional assignment is always of the form
3351    
3352      I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>      C<set >I<YYYY>C< function to\n>I<ZZZZZ>
3353    
3354  where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the  where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
3355  actual functional role. In most cases, the user and the assigning user will be the  the user and the assigning user (from MadeAnnotation) will be the same, but that is
3356  same, but that is not always the case.  not always the case.
3357    
3358    In addition, the functional role may contain extra data that is stripped, such as
3359    terminating spaces or a comment separated from the rest of the text by a tab.
3360    
3361  This is a static method.  This is a static method.
3362    
3363  =over 4  =over 4
3364    
3365    =item user
3366    
3367    Name of the assigning user.
3368    
3369  =item text  =item text
3370    
3371  Text of the annotation.  Text of the annotation.
# Line 2646  Line 3381 
3381    
3382  sub _ParseAssignment {  sub _ParseAssignment {
3383          # Get the parameters.          # Get the parameters.
3384          my ($text) = @_;      my ($user, $text) = @_;
3385          # Declare the return value.          # Declare the return value.
3386          my @retVal = ();          my @retVal = ();
3387          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3388          my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
3389          if ($type =~ m/^set ([^ ]+) function to$/i) {      if ($type =~ m/^set function to$/i) {
3390                  # Here it is, so we return the user name (which is in $1), the functional role text,          # Here we have an assignment without a user, so we use the incoming user ID.
3391          # and the assigning user.          @retVal = ($user, $function);
3392                  @retVal = ($1, $function, $user);      } elsif ($type =~ m/^set (\S+) function to$/i) {
3393            # Here we have an assignment with a user that is passed back to the caller.
3394            @retVal = ($1, $function);
3395        }
3396        # If we have an assignment, we need to clean the function text. There may be
3397        # extra junk at the end added as a note from the user.
3398        if (@retVal) {
3399            $retVal[1] =~ s/(\t\S)?\s*$//;
3400          }          }
3401          # Return the result list.          # Return the result list.
3402          return @retVal;          return @retVal;
# Line 2682  Line 3424 
3424    
3425  sub FriendlyTimestamp {  sub FriendlyTimestamp {
3426      my ($timeValue) = @_;      my ($timeValue) = @_;
3427      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
3428      return $retVal;      return $retVal;
3429  }  }
3430    
3431    =head3 AddProperty
3432    
3433    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3434    
3435    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3436    be added to almost any object. In Sprout, they can only be added to features. In
3437    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3438    pair. If the particular key/value pair coming in is not already in the database, a new
3439    B<Property> record is created to hold it.
3440    
3441    =over 4
3442    
3443    =item peg
3444    
3445    ID of the feature to which the attribute is to be replied.
3446    
3447    =item key
3448    
3449    Name of the attribute (key).
3450    
3451    =item value
3452    
3453    Value of the attribute.
3454    
3455    =item url
3456    
3457    URL or text citation from which the property was obtained.
3458    
3459    =back
3460    
3461    =cut
3462    #: Return Type ;
3463    sub AddProperty {
3464        # Get the parameters.
3465        my ($self, $featureID, $key, $value, $url) = @_;
3466        # Declare the variable to hold the desired property ID.
3467        my $propID;
3468        # Attempt to find a property record for this key/value pair.
3469        my @properties = $self->GetFlat(['Property'],
3470                                       "Property(property-name) = ? AND Property(property-value) = ?",
3471                                       [$key, $value], 'Property(id)');
3472        if (@properties) {
3473            # Here the property is already in the database. We save its ID.
3474            $propID = $properties[0];
3475            # Here the property value does not exist. We need to generate an ID. It will be set
3476            # to a number one greater than the maximum value in the database. This call to
3477            # GetAll will stop after one record.
3478            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3479                                            1);
3480            $propID = $maxProperty[0]->[0] + 1;
3481            # Insert the new property value.
3482            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3483        }
3484        # Now we connect the incoming feature to the property.
3485        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3486    }
3487    
3488    
3489  1;  1;

Legend:
Removed from v.1.13  
changed lines
  Added in v.1.78

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3