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

Diff of /Sprout/Sprout.pm

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

revision 1.32, Wed Sep 14 13:24:14 2005 UTC revision 1.79, Mon Jul 31 20:07:06 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>)
# Line 85  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({
# Line 92  Line 102 
102                                                          # database type                                                          # database type
103                         dataDir      => $FIG_Config::sproutData,                         dataDir      => $FIG_Config::sproutData,
104                                                          # data file directory                                                          # data file directory
105                         xmlFileName  => "$FIG_Config::sproutData/SproutDBD.xml",                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
106                                                          # database definition file name                                                          # database definition file name
107                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
108                                                          # user name and password                                                          # user name and password
109                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::dbport,
110                                                          # database connection port                                                          # database connection port
111                           sock         => $FIG_Config::dbsock,
112                           host         => $FIG_Config::dbhost,
113                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
114                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
115                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
# Line 111  Line 123 
123      my $dbh;      my $dbh;
124      if (! $optionTable->{noDBOpen}) {      if (! $optionTable->{noDBOpen}) {
125          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
126                                  $password, $optionTable->{port});                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
127      }      }
128      # Create the ERDB object.      # Create the ERDB object.
129      my $xmlFileName = "$optionTable->{xmlFileName}";      my $xmlFileName = "$optionTable->{xmlFileName}";
130      my $erdb = ERDB->new($dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName);
131      # Create this object.      # Add the option table and XML file name.
132      my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName };      $retVal->{_options} = $optionTable;
133      # Bless and return it.      $retVal->{_xmlName} = $xmlFileName;
134      bless $self;      # Return it.
135      return $self;      return $retVal;
136  }  }
137    
138  =head3 MaxSegment  =head3 MaxSegment
# Line 155  Line 167 
167      return $self->{_options}->{maxSequenceLength};      return $self->{_options}->{maxSequenceLength};
168  }  }
169    
 =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);  
 }  
   
170  =head3 Load  =head3 Load
171    
172  C<< $sprout->Load($rebuild); >>;  C<< $sprout->Load($rebuild); >>;
# Line 379  Line 201 
201  sub Load {  sub Load {
202      # Get the parameters.      # Get the parameters.
203      my ($self, $rebuild) = @_;      my ($self, $rebuild) = @_;
     # Get the database object.  
     my $erdb = $self->{_erdb};  
204      # Load the tables from the data directory.      # Load the tables from the data directory.
205      my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild);      my $retVal = $self->LoadTables($self->{_options}->{dataDir}, $rebuild);
206      # Return the statistics.      # Return the statistics.
207      return $retVal;      return $retVal;
208  }  }
209    
210  =head3 LoadUpdate  =head3 LoadUpdate
211    
212  C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>  C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>
213    
214  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
215  or two tables without reloading the whole database. For each table, there must be a corresponding  or two tables without reloading the whole database. For each table, there must be a corresponding
# Line 422  Line 242 
242  sub LoadUpdate {  sub LoadUpdate {
243      # Get the parameters.      # Get the parameters.
244      my ($self, $truncateFlag, $tableList) = @_;      my ($self, $truncateFlag, $tableList) = @_;
     # Get the database object.  
     my $erdb = $self->{_erdb};  
245      # Declare the return value.      # Declare the return value.
246      my $retVal = Stats->new();      my $retVal = Stats->new();
247      # Get the data directory.      # Get the data directory.
# Line 437  Line 255 
255              Trace("No load file found for $tableName in $dataDir.") if T(0);              Trace("No load file found for $tableName in $dataDir.") if T(0);
256          } else {          } else {
257              # Attempt to load this table.              # Attempt to load this table.
258              my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, $truncateFlag);
259              # Accumulate the resulting statistics.              # Accumulate the resulting statistics.
260              $retVal->Accumulate($result);              $retVal->Accumulate($result);
261          }          }
# Line 446  Line 264 
264      return $retVal;      return $retVal;
265  }  }
266    
267    =head3 GenomeCounts
268    
269    C<< my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete); >>
270    
271    Count the number of genomes in each domain. If I<$complete> is TRUE, only complete
272    genomes will be included in the counts.
273    
274    =over 4
275    
276    =item complete
277    
278    TRUE if only complete genomes are to be counted, FALSE if all genomes are to be
279    counted
280    
281    =item RETURN
282    
283    A six-element list containing the number of genomes in each of six categories--
284    Archaea, Bacteria, Eukaryota, Viral, Environmental, and Unknown, respectively.
285    
286    =back
287    
288    =cut
289    
290    sub GenomeCounts {
291        # Get the parameters.
292        my ($self, $complete) = @_;
293        # Set the filter based on the completeness flag.
294        my $filter = ($complete ? "Genome(complete) = 1" : "");
295        # Get all the genomes and the related taxonomy information.
296        my @genomes = $self->GetAll(['Genome'], $filter, [], ['Genome(id)', 'Genome(taxonomy)']);
297        # Clear the counters.
298        my ($arch, $bact, $euk, $vir, $env, $unk) = (0, 0, 0, 0, 0, 0);
299        # Loop through, counting the domains.
300        for my $genome (@genomes) {
301            if    ($genome->[1] =~ /^archaea/i)  { ++$arch }
302            elsif ($genome->[1] =~ /^bacter/i)   { ++$bact }
303            elsif ($genome->[1] =~ /^eukar/i)    { ++$euk }
304            elsif ($genome->[1] =~ /^vir/i)      { ++$vir }
305            elsif ($genome->[1] =~ /^env/i)      { ++$env }
306            else  { ++$unk }
307        }
308        # Return the counts.
309        return ($arch, $bact, $euk, $vir, $env, $unk);
310    }
311    
312    =head3 ContigCount
313    
314    C<< my $count = $sprout->ContigCount($genomeID); >>
315    
316    Return the number of contigs for the specified genome ID.
317    
318    =over 4
319    
320    =item genomeID
321    
322    ID of the genome whose contig count is desired.
323    
324    =item RETURN
325    
326    Returns the number of contigs for the specified genome.
327    
328    =back
329    
330    =cut
331    
332    sub ContigCount {
333        # Get the parameters.
334        my ($self, $genomeID) = @_;
335        # Get the contig count.
336        my $retVal = $self->GetCount(['Contig', 'HasContig'], "HasContig(from-link) = ?", [$genomeID]);
337        # Return the result.
338        return $retVal;
339    }
340    
341    =head3 GeneMenu
342    
343    C<< my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params); >>
344    
345    Return an HTML select menu of genomes. Each genome will be an option in the menu,
346    and will be displayed by name with the ID and a contig count attached. The selection
347    value will be the genome ID. The genomes will be sorted by genus/species name.
348    
349    =over 4
350    
351    =item attributes
352    
353    Reference to a hash mapping attributes to values for the SELECT tag generated.
354    
355    =item filterString
356    
357    A filter string for use in selecting the genomes. The filter string must conform
358    to the rules for the C<< ERDB->Get >> method.
359    
360    =item params
361    
362    Reference to a list of values to be substituted in for the parameter marks in
363    the filter string.
364    
365    =item RETURN
366    
367    Returns an HTML select menu with the specified genomes as selectable options.
368    
369    =back
370    
371    =cut
372    
373    sub GeneMenu {
374        # Get the parameters.
375        my ($self, $attributes, $filterString, $params) = @_;
376        # Start the menu.
377        my $retVal = "<select " .
378            join(" ", map { "$_=\"$attributes->{$_}\"" } keys %{$attributes}) .
379            ">\n";
380        # Get the genomes.
381        my @genomes = $self->GetAll(['Genome'], $filterString, $params, ['Genome(id)',
382                                                                         'Genome(genus)',
383                                                                         'Genome(species)',
384                                                                         'Genome(unique-characterization)']);
385        # Sort them by name.
386        my @sorted = sort { lc("$a->[1] $a->[2]") cmp lc("$b->[1] $b->[2]") } @genomes;
387        # Loop through the genomes, creating the option tags.
388        for my $genomeData (@sorted) {
389            # Get the data for this genome.
390            my ($genomeID, $genus, $species, $strain) = @{$genomeData};
391            # Get the contig count.
392            my $count = $self->ContigCount($genomeID);
393            my $counting = ($count == 1 ? "contig" : "contigs");
394            # Build the option tag.
395            $retVal .= "<option value=\"$genomeID\">$genus $species $strain ($genomeID) [$count $counting]</option>\n";
396            Trace("Option tag built for $genomeID: $genus $species $strain.") if T(3);
397        }
398        # Close the SELECT tag.
399        $retVal .= "</select>\n";
400        # Return the result.
401        return $retVal;
402    }
403  =head3 Build  =head3 Build
404    
405  C<< $sprout->Build(); >>  C<< $sprout->Build(); >>
# Line 460  Line 414 
414      # Get the parameters.      # Get the parameters.
415      my ($self) = @_;      my ($self) = @_;
416      # Create the tables.      # Create the tables.
417      $self->{_erdb}->CreateTables;      $self->CreateTables();
418  }  }
419    
420  =head3 Genomes  =head3 Genomes
# Line 610  Line 564 
564          if ($prevContig eq $contigID && $dir eq $prevDir) {          if ($prevContig eq $contigID && $dir eq $prevDir) {
565              # Here the new segment is in the same direction on the same contig. Insure the              # Here the new segment is in the same direction on the same contig. Insure the
566              # new segment's beginning is next to the old segment's end.              # new segment's beginning is next to the old segment's end.
567              if (($dir eq "-" && $beg == $prevBeg - $prevLen) ||              if ($dir eq "-" && $beg + $len == $prevBeg) {
568                  ($dir eq "+" && $beg == $prevBeg + $prevLen)) {                  # Here we're merging two backward blocks, so we keep the new begin point
569                  # Here we need to merge two segments. Adjust the beginning and length values                  # and adjust the length.
570                  # to include both segments.                  $len += $prevLen;
571                    # Pop the old segment off. The new one will replace it later.
572                    pop @retVal;
573                } elsif ($dir eq "+" && $beg == $prevBeg + $prevLen) {
574                    # Here we need to merge two forward blocks. Adjust the beginning and
575                    # length values to include both segments.
576                  $beg = $prevBeg;                  $beg = $prevBeg;
577                  $len += $prevLen;                  $len += $prevLen;
578                  # 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 625  Line 584 
584          # Compute the initial base pair.          # Compute the initial base pair.
585          my $start = ($dir eq "+" ? $beg : $beg + $len - 1);          my $start = ($dir eq "+" ? $beg : $beg + $len - 1);
586          # Add the specifier to the list.          # Add the specifier to the list.
587          push @retVal, "${contigID}_$beg$dir$len";          push @retVal, "${contigID}_$start$dir$len";
588      }      }
589      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
590      return (wantarray ? @retVal : join(',', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
# Line 659  Line 618 
618      shift if UNIVERSAL::isa($_[0],__PACKAGE__);      shift if UNIVERSAL::isa($_[0],__PACKAGE__);
619      my ($location) = @_;      my ($location) = @_;
620      # Parse it into segments.      # Parse it into segments.
621      $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
622      my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);      my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
623      # If the direction is an underscore, convert it to a + or -.      # If the direction is an underscore, convert it to a + or -.
624      if ($dir eq "_") {      if ($dir eq "_") {
# Line 735  Line 694 
694  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,
695  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>.
696    
697    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
698    between positions 1401 and 1532, inclusive.
699    
700        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
701    
702  =over 4  =over 4
703    
704  =item locationList  =item locationList
705    
706  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
707  L</FeatureLocation> for more about this format).  I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
708    
709  =item RETURN  =item RETURN
710    
# Line 767  Line 731 
731          # the start point is the ending. Note that in the latter case we must reverse the DNA string          # the start point is the ending. Note that in the latter case we must reverse the DNA string
732          # before putting it in the return value.          # before putting it in the return value.
733          my ($start, $stop);          my ($start, $stop);
734          Trace("Parsed location is $beg$dir$len.") if T(SDNA => 4);          Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
735          if ($dir eq "+") {          if ($dir eq "+") {
736              $start = $beg;              $start = $beg;
737              $stop = $beg + $len - 1;              $stop = $beg + $len - 1;
# Line 790  Line 754 
754              Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);              Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
755              # Figure out the start point and length of the relevant section.              # Figure out the start point and length of the relevant section.
756              my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);              my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
757              my $len1 = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
758              Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);              Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
759              # Add the relevant data to the location data.              # Add the relevant data to the location data.
760              $locationDNA .= substr($sequenceData, $pos1, $len1);              $locationDNA .= substr($sequenceData, $pos1, $len1);
# Line 836  Line 800 
800      return @retVal;      return @retVal;
801  }  }
802    
803    =head3 GenomeLength
804    
805    C<< my $length = $sprout->GenomeLength($genomeID); >>
806    
807    Return the length of the specified genome in base pairs.
808    
809    =over 4
810    
811    =item genomeID
812    
813    ID of the genome whose base pair count is desired.
814    
815    =item RETURN
816    
817    Returns the number of base pairs in all the contigs of the specified
818    genome.
819    
820    =back
821    
822    =cut
823    
824    sub GenomeLength {
825        # Get the parameters.
826        my ($self, $genomeID) = @_;
827        # Declare the return variable.
828        my $retVal = 0;
829        # Get the genome's contig sequence lengths.
830        my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',
831                           [$genomeID], 'IsMadeUpOf(len)');
832        # Sum the lengths.
833        map { $retVal += $_ } @lens;
834        # Return the result.
835        return $retVal;
836    }
837    
838    =head3 FeatureCount
839    
840    C<< my $count = $sprout->FeatureCount($genomeID, $type); >>
841    
842    Return the number of features of the specified type in the specified genome.
843    
844    =over 4
845    
846    =item genomeID
847    
848    ID of the genome whose feature count is desired.
849    
850    =item type
851    
852    Type of feature to count (eg. C<peg>, C<rna>, etc.).
853    
854    =item RETURN
855    
856    Returns the number of features of the specified type for the specified genome.
857    
858    =back
859    
860    =cut
861    
862    sub FeatureCount {
863        # Get the parameters.
864        my ($self, $genomeID, $type) = @_;
865        # Compute the count.
866        my $retVal = $self->GetCount(['HasFeature', 'Feature'],
867                                    "HasFeature(from-link) = ? AND Feature(feature-type) = ?",
868                                    [$genomeID, $type]);
869        # Return the result.
870        return $retVal;
871    }
872    
873    =head3 GenomeAssignments
874    
875    C<< my $fidHash = $sprout->GenomeAssignments($genomeID); >>
876    
877    Return a list of a genome's assigned features. The return hash will contain each
878    assigned feature of the genome mapped to the text of its most recent functional
879    assignment.
880    
881    =over 4
882    
883    =item genomeID
884    
885    ID of the genome whose functional assignments are desired.
886    
887    =item RETURN
888    
889    Returns a reference to a hash which maps each feature to its most recent
890    functional assignment.
891    
892    =back
893    
894    =cut
895    
896    sub GenomeAssignments {
897        # Get the parameters.
898        my ($self, $genomeID) = @_;
899        # Declare the return variable.
900        my $retVal = {};
901        # Query the genome's features and annotations. We'll put the oldest annotations
902        # first so that the last assignment to go into the hash will be the correct one.
903        my $query = $self->Get(['HasFeature', 'IsTargetOfAnnotation', 'Annotation'],
904                               "HasFeature(from-link) = ? ORDER BY Annotation(time)",
905                               [$genomeID]);
906        # Loop through the annotations.
907        while (my $data = $query->Fetch) {
908            # Get the feature ID and annotation text.
909            my ($fid, $annotation) = $data->Values(['HasFeature(to-link)',
910                                                    'Annotation(annotation)']);
911            # Check to see if this is an assignment. Note that the user really
912            # doesn't matter to us, other than we use it to determine whether or
913            # not this is an assignment.
914            my ($user, $assignment) = _ParseAssignment('fig', $annotation);
915            if ($user) {
916                # Here it's an assignment. We put it in the return hash, overwriting
917                # any older assignment that might be present.
918                $retVal->{$fid} = $assignment;
919            }
920        }
921        # Return the result.
922        return $retVal;
923    }
924    
925  =head3 ContigLength  =head3 ContigLength
926    
927  C<< my $length = $sprout->ContigLength($contigID); >>  C<< my $length = $sprout->ContigLength($contigID); >>
# Line 869  Line 955 
955      # Set it from the sequence data, if any.      # Set it from the sequence data, if any.
956      if ($sequence) {      if ($sequence) {
957          my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);          my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
958          $retVal = $start + $len;          $retVal = $start + $len - 1;
959        }
960        # Return the result.
961        return $retVal;
962    }
963    
964    =head3 ClusterPEGs
965    
966    C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>
967    
968    Cluster the PEGs in a list according to the cluster coding scheme of the specified
969    subsystem. In order for this to work properly, the subsystem object must have
970    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.
971    This causes the cluster numbers to be pulled into the subsystem's color hash.
972    If a PEG is not found in the color hash, it will not appear in the output
973    sequence.
974    
975    =over 4
976    
977    =item sub
978    
979    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
980    method.
981    
982    =item pegs
983    
984    Reference to the list of PEGs to be clustered.
985    
986    =item RETURN
987    
988    Returns a list of the PEGs, grouped into smaller lists by cluster number.
989    
990    =back
991    
992    =cut
993    #: Return Type $@@;
994    sub ClusterPEGs {
995        # Get the parameters.
996        my ($self, $sub, $pegs) = @_;
997        # Declare the return variable.
998        my $retVal = [];
999        # Loop through the PEGs, creating arrays for each cluster.
1000        for my $pegID (@{$pegs}) {
1001            my $clusterNumber = $sub->get_cluster_number($pegID);
1002            # Only proceed if the PEG is in a cluster.
1003            if ($clusterNumber >= 0) {
1004                # Push this PEG onto the sub-list for the specified cluster number.
1005                push @{$retVal->[$clusterNumber]}, $pegID;
1006            }
1007      }      }
1008      # Return the result.      # Return the result.
1009      return $retVal;      return $retVal;
# Line 1019  Line 1153 
1153    
1154  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1155    
1156  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>
1157    
1158  Return the annotations of a feature.  Return the annotations of a feature.
1159    
# Line 1029  Line 1163 
1163    
1164  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1165    
1166    =item rawFlag
1167    
1168    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1169    will be returned in human-readable form.
1170    
1171  =item RETURN  =item RETURN
1172    
1173  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1174    
1175  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1176    
1177  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1178    
1179  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1180    
# Line 1047  Line 1186 
1186  #: Return Type @%;  #: Return Type @%;
1187  sub FeatureAnnotations {  sub FeatureAnnotations {
1188      # Get the parameters.      # Get the parameters.
1189      my ($self, $featureID) = @_;      my ($self, $featureID, $rawFlag) = @_;
1190      # 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.
1191      my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],      my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1192                             "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                             "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1060  Line 1199 
1199              $annotation->Values(['IsTargetOfAnnotation(from-link)',              $annotation->Values(['IsTargetOfAnnotation(from-link)',
1200                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1201                                   'Annotation(annotation)']);                                   'Annotation(annotation)']);
1202            # Convert the time, if necessary.
1203            if (! $rawFlag) {
1204                $timeStamp = FriendlyTimestamp($timeStamp);
1205            }
1206          # Assemble them into a hash.          # Assemble them into a hash.
1207          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1208                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1209                                 user => $user, text => $text };                                 user => $user, text => $text };
1210          # Add it to the return list.          # Add it to the return list.
1211          push @retVal, $annotationHash;          push @retVal, $annotationHash;
# Line 1091  Line 1234 
1234    
1235  =item RETURN  =item RETURN
1236    
1237  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1238    
1239  =back  =back
1240    
# Line 1101  Line 1244 
1244      # Get the parameters.      # Get the parameters.
1245      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1246      # Get all of the feature's annotations.      # Get all of the feature's annotations.
1247      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1248                              "IsTargetOfAnnotation(from-link) = ?",                              "IsTargetOfAnnotation(from-link) = ?",
1249                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1250                                               'MadeAnnotation(from-link)']);
1251      # Declare the return hash.      # Declare the return hash.
1252      my %retVal;      my %retVal;
     # Declare a hash for insuring we only make one assignment per user.  
     my %timeHash = ();  
1253      # Now we sort the assignments by timestamp in reverse.      # Now we sort the assignments by timestamp in reverse.
1254      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1255      # Loop until we run out of annotations.      # Loop until we run out of annotations.
1256      for my $annotation (@sortedQuery) {      for my $annotation (@sortedQuery) {
1257          # Get the annotation fields.          # Get the annotation fields.
1258          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text, $user) = @{$annotation};
1259          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
1260          my ($user, $function) = _ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1261          if ($user && ! exists $timeHash{$user}) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1262              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1263              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
1264              # return hash.              # return hash.
1265              $retVal{$function} = $user;              $retVal{$actualUser} = $function;
             # Insure we don't assign to this user again.  
             $timeHash{$user} = 1;  
1266          }          }
1267      }      }
1268      # Return the hash of assignments found.      # Return the hash of assignments found.
# Line 1138  Line 1278 
1278  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
1279  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
1280  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
1281  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
1282  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
1283  most features only have a small number of annotations.  most features only have a small number of annotations.
1284    
# Line 1200  Line 1340 
1340              }              }
1341          }          }
1342          # 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.
1343          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1344                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1345                                 [$featureID]);                                 [$featureID]);
1346          my $timeSelected = 0;          my $timeSelected = 0;
1347          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1348          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1349              # Get the annotation text.              # Get the annotation text.
1350              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);              my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1351                                                         'Annotation(time)', 'MadeAnnotation(from-link)']);
1352              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1353              my ($user, $function) = _ParseAssignment($text);              my ($actualUser, $function) = _ParseAssignment($user, $text);
1354              if ($user) {              Trace("Assignment user is $actualUser, text is $function.") if T(4);
1355                if ($actualUser) {
1356                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1357                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1358                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1359                      $retVal = $function;                      $retVal = $function;
1360                      $timeSelected = $time;                      $timeSelected = $time;
1361                  }                  }
# Line 1229  Line 1371 
1371      return $retVal;      return $retVal;
1372  }  }
1373    
1374    =head3 FunctionsOf
1375    
1376    C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>
1377    
1378    Return the functional assignments of a particular feature.
1379    
1380    The functional assignment is handled differently depending on the type of feature. If
1381    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1382    assignment is a type of annotation. The format of an assignment is described in
1383    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1384    annotation itself because it's a text field; however, this is not a big problem because
1385    most features only have a small number of annotations.
1386    
1387    If the feature is B<not> identified by a FIG ID, then the functional assignment
1388    information is taken from the B<ExternalAliasFunc> table. If the table does
1389    not contain an entry for the feature, an empty list is returned.
1390    
1391    =over 4
1392    
1393    =item featureID
1394    
1395    ID of the feature whose functional assignments are desired.
1396    
1397    =item RETURN
1398    
1399    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1400    that user.
1401    
1402    =back
1403    
1404    =cut
1405    #: Return Type @@;
1406    sub FunctionsOf {
1407        # Get the parameters.
1408        my ($self, $featureID) = @_;
1409        # Declare the return value.
1410        my @retVal = ();
1411        # Determine the ID type.
1412        if ($featureID =~ m/^fig\|/) {
1413            # Here we have a FIG feature ID. We must build the list of trusted
1414            # users.
1415            my %trusteeTable = ();
1416            # Build a query for all of the feature's annotations, sorted by date.
1417            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1418                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1419                                   [$featureID]);
1420            my $timeSelected = 0;
1421            # Loop until we run out of annotations.
1422            while (my $annotation = $query->Fetch()) {
1423                # Get the annotation text.
1424                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1425                                                                'Annotation(time)',
1426                                                                'MadeAnnotation(user)']);
1427                # Check to see if this is a functional assignment for a trusted user.
1428                my ($actualUser, $function) = _ParseAssignment($user, $text);
1429                if ($actualUser) {
1430                    # Here it is a functional assignment.
1431                    push @retVal, [$actualUser, $function];
1432                }
1433            }
1434        } else {
1435            # Here we have a non-FIG feature ID. In this case the user ID does not
1436            # matter. We simply get the information from the External Alias Function
1437            # table.
1438            my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1439                                                     ['ExternalAliasFunc(func)']);
1440            push @retVal, map { ['master', $_] } @assignments;
1441        }
1442        # Return the assignments found.
1443        return @retVal;
1444    }
1445    
1446  =head3 BBHList  =head3 BBHList
1447    
1448  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>
# Line 1266  Line 1480 
1480          my $query = $self->Get(['IsBidirectionalBestHitOf'],          my $query = $self->Get(['IsBidirectionalBestHitOf'],
1481                                 "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",                                 "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1482                                 [$featureID, $genomeID]);                                 [$featureID, $genomeID]);
1483          # Look for the best hit.          # Peel off the BBHs found.
1484          my $bbh = $query->Fetch;          my @found = ();
1485          if ($bbh) {          while (my $bbh = $query->Fetch) {
1486              my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
             $retVal{$featureID} = $targetFeature;  
1487          }          }
1488            $retVal{$featureID} = \@found;
1489      }      }
1490      # Return the mapping.      # Return the mapping.
1491      return \%retVal;      return \%retVal;
# Line 1349  Line 1563 
1563      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->GetEntity('Genome', $genomeID);
1564      if ($genomeData) {      if ($genomeData) {
1565          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1566          ($retVal) = $genomeData->Value('complete');          ($retVal) = $genomeData->Value('Genome(complete)');
1567      }      }
1568      # Return the result.      # Return the result.
1569      return $retVal;      return $retVal;
# Line 1389  Line 1603 
1603    
1604  C<< my $genomeID = $sprout->GenomeOf($featureID); >>  C<< my $genomeID = $sprout->GenomeOf($featureID); >>
1605    
1606  Return the genome that contains a specified feature.  Return the genome that contains a specified feature or contig.
1607    
1608  =over 4  =over 4
1609    
1610  =item featureID  =item featureID
1611    
1612  ID of the feature whose genome is desired.  ID of the feature or contig whose genome is desired.
1613    
1614  =item RETURN  =item RETURN
1615    
1616  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
1617  an undefined value.  found, returns an undefined value.
1618    
1619  =back  =back
1620    
# Line 1409  Line 1623 
1623  sub GenomeOf {  sub GenomeOf {
1624      # Get the parameters.      # Get the parameters.
1625      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1626      # Create a query to find the genome associated with the feature.      # Create a query to find the genome associated with the incoming ID.
1627      my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);      my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ? OR HasContig(to-link) = ?",
1628                               [$featureID, $featureID]);
1629      # Declare the return value.      # Declare the return value.
1630      my $retVal;      my $retVal;
1631      # Get the genome ID.      # Get the genome ID.
# Line 1445  Line 1660 
1660  sub CoupledFeatures {  sub CoupledFeatures {
1661      # Get the parameters.      # Get the parameters.
1662      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1663        Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
1664      # Create a query to retrieve the functionally-coupled features.      # Create a query to retrieve the functionally-coupled features.
1665      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1666                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
# Line 1457  Line 1673 
1673          # Get the ID and score of the coupling.          # Get the ID and score of the coupling.
1674          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1675                                                          'Coupling(score)']);                                                          'Coupling(score)']);
1676          # The coupling ID contains the two feature IDs separated by a space. We use          Trace("$featureID coupled with score $score to ID $couplingID.") if T(coupling => 4);
1677          # this information to find the ID of the other feature.          # Get the other feature that participates in the coupling.
1678          my ($fid1, $fid2) = split / /, $couplingID;          my ($otherFeatureID) = $self->GetFlat(['ParticipatesInCoupling'],
1679          my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);                                             "ParticipatesInCoupling(to-link) = ? AND ParticipatesInCoupling(from-link) <> ?",
1680                                               [$couplingID, $featureID], 'ParticipatesInCoupling(from-link)');
1681            Trace("$couplingID target feature is $otherFeatureID.") if T(coupling => 4);
1682          # Attach the other feature's score to its ID.          # Attach the other feature's score to its ID.
1683          $retVal{$otherFeatureID} = $score;          $retVal{$otherFeatureID} = $score;
1684          $found = 1;          $found = 1;
# Line 1593  Line 1811 
1811      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
1812      # Declare the return values. We'll start with the coupling ID and undefine the      # Declare the return values. We'll start with the coupling ID and undefine the
1813      # flag and score until we have more information.      # flag and score until we have more information.
1814      my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);      my ($retVal, $inverted, $score) = ($self->CouplingID($peg1, $peg2), undef, undef);
1815      # Find the coupling data.      # Find the coupling data.
1816      my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],      my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1817                                   "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",                                   "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
# Line 1614  Line 1832 
1832      return ($retVal, $inverted, $score);      return ($retVal, $inverted, $score);
1833  }  }
1834    
1835    =head3 GetSynonymGroup
1836    
1837    C<< my $id = $sprout->GetSynonymGroup($fid); >>
1838    
1839    Return the synonym group name for the specified feature.
1840    
1841    =over 4
1842    
1843    =item fid
1844    
1845    ID of the feature whose synonym group is desired.
1846    
1847    =item RETURN
1848    
1849    The name of the synonym group to which the feature belongs. If the feature does
1850    not belong to a synonym group, the feature ID itself is returned.
1851    
1852    =back
1853    
1854    =cut
1855    
1856    sub GetSynonymGroup {
1857        # Get the parameters.
1858        my ($self, $fid) = @_;
1859        # Declare the return variable.
1860        my $retVal;
1861        # Find the synonym group.
1862        my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?",
1863                                       [$fid], 'IsSynonymGroupFor(from-link)');
1864        # Check to see if we found anything.
1865        if (@groups) {
1866            $retVal = $groups[0];
1867        } else {
1868            $retVal = $fid;
1869        }
1870        # Return the result.
1871        return $retVal;
1872    }
1873    
1874    =head3 GetBoundaries
1875    
1876    C<< my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList); >>
1877    
1878    Determine the begin and end boundaries for the locations in a list. All of the
1879    locations must belong to the same contig and have mostly the same direction in
1880    order for this method to produce a meaningful result. The resulting
1881    begin/end pair will contain all of the bases in any of the locations.
1882    
1883    =over 4
1884    
1885    =item locList
1886    
1887    List of locations to process.
1888    
1889    =item RETURN
1890    
1891    Returns a 3-tuple consisting of the contig ID, the beginning boundary,
1892    and the ending boundary. The beginning boundary will be left of the
1893    end for mostly-forward locations and right of the end for mostly-backward
1894    locations.
1895    
1896    =back
1897    
1898    =cut
1899    
1900    sub GetBoundaries {
1901        # Get the parameters.
1902        my ($self, @locList) = @_;
1903        # Set up the counters used to determine the most popular direction.
1904        my %counts = ( '+' => 0, '-' => 0 );
1905        # Get the last location and parse it.
1906        my $locObject = BasicLocation->new(pop @locList);
1907        # Prime the loop with its data.
1908        my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right);
1909        # Count its direction.
1910        $counts{$locObject->Dir}++;
1911        # Loop through the remaining locations. Note that in most situations, this loop
1912        # will not iterate at all, because most of the time we will be dealing with a
1913        # singleton list.
1914        for my $loc (@locList) {
1915            # Create a location object.
1916            my $locObject = BasicLocation->new($loc);
1917            # Count the direction.
1918            $counts{$locObject->Dir}++;
1919            # Get the left end and the right end.
1920            my $left = $locObject->Left;
1921            my $right = $locObject->Right;
1922            # Merge them into the return variables.
1923            if ($left < $beg) {
1924                $beg = $left;
1925            }
1926            if ($right > $end) {
1927                $end = $right;
1928            }
1929        }
1930        # If the most common direction is reverse, flip the begin and end markers.
1931        if ($counts{'-'} > $counts{'+'}) {
1932            ($beg, $end) = ($end, $beg);
1933        }
1934        # Return the result.
1935        return ($contig, $beg, $end);
1936    }
1937    
1938  =head3 CouplingID  =head3 CouplingID
1939    
1940  C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>  C<< my $couplingID = $sprout->CouplingID($peg1, $peg2); >>
1941    
1942  Return the coupling ID for a pair of feature IDs.  Return the coupling ID for a pair of feature IDs.
1943    
# Line 1649  Line 1970 
1970  =cut  =cut
1971  #: Return Type $;  #: Return Type $;
1972  sub CouplingID {  sub CouplingID {
1973      return join " ", sort @_;      my ($self, @pegs) = @_;
1974  }      return $self->DigestKey(join " ", sort @pegs);
   
 =head3 GetEntityTypes  
   
 C<< my @entityList = $sprout->GetEntityTypes(); >>  
   
 Return the list of supported entity types.  
   
 =cut  
 #: Return Type @;  
 sub GetEntityTypes {  
     # Get the parameters.  
     my ($self) = @_;  
     # Get the underlying database object.  
     my $erdb = $self->{_erdb};  
     # Get its entity type list.  
     my @retVal = $erdb->GetEntityTypes();  
1975  }  }
1976    
1977  =head3 ReadFasta  =head3 ReadFasta
# Line 1814  Line 2119 
2119      # Get the data directory name.      # Get the data directory name.
2120      my $outputDirectory = $self->{_options}->{dataDir};      my $outputDirectory = $self->{_options}->{dataDir};
2121      # Dump the relations.      # Dump the relations.
2122      $self->{_erdb}->DumpRelations($outputDirectory);      $self->DumpRelations($outputDirectory);
2123  }  }
2124    
2125  =head3 XMLFileName  =head3 XMLFileName
# Line 1866  Line 2171 
2171      # Get the parameters.      # Get the parameters.
2172      my ($self, $objectType, $fieldHash) = @_;      my ($self, $objectType, $fieldHash) = @_;
2173      # Call the underlying method.      # Call the underlying method.
2174      $self->{_erdb}->InsertObject($objectType, $fieldHash);      $self->InsertObject($objectType, $fieldHash);
2175  }  }
2176    
2177  =head3 Annotate  =head3 Annotate
# Line 2025  Line 2330 
2330      return @retVal;      return @retVal;
2331  }  }
2332    
 =head3 Exists  
   
 C<< my $found = $sprout->Exists($entityName, $entityID); >>  
   
 Return TRUE if an entity exists, else FALSE.  
   
 =over 4  
   
 =item entityName  
   
 Name of the entity type (e.g. C<Feature>) relevant to the existence check.  
   
 =item entityID  
   
 ID of the entity instance whose existence is to be checked.  
   
 =item RETURN  
   
 Returns TRUE if the entity instance exists, else FALSE.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub Exists {  
     # Get the parameters.  
     my ($self, $entityName, $entityID) = @_;  
     # Check for the entity instance.  
     Trace("Checking existence of $entityName with ID=$entityID.") if T(4);  
     my $testInstance = $self->GetEntity($entityName, $entityID);  
     # Return an existence indicator.  
     my $retVal = ($testInstance ? 1 : 0);  
     return $retVal;  
 }  
   
2333  =head3 FeatureTranslation  =head3 FeatureTranslation
2334    
2335  C<< my $translation = $sprout->FeatureTranslation($featureID); >>  C<< my $translation = $sprout->FeatureTranslation($featureID); >>
# Line 2547  Line 2817 
2817                                      ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                      ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2818      # Create the return value.      # Create the return value.
2819      my %retVal = ();      my %retVal = ();
2820        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2821        # in two spreadsheet cells.
2822        my %dupHash = ();
2823      # Loop through the results, adding them to the hash.      # Loop through the results, adding them to the hash.
2824      for my $record (@subsystems) {      for my $record (@subsystems) {
2825            # Get this subsystem and role.
2826          my ($subsys, $role) = @{$record};          my ($subsys, $role) = @{$record};
2827          if (exists $retVal{$subsys}) {          # Insure it's the first time for both.
2828            my $dupKey = "$subsys\n$role";
2829            if (! exists $dupHash{"$subsys\n$role"}) {
2830                $dupHash{$dupKey} = 1;
2831              push @{$retVal{$subsys}}, $role;              push @{$retVal{$subsys}}, $role;
         } else {  
             $retVal{$subsys} = [$role];  
2832          }          }
2833      }      }
2834      # Return the hash.      # Return the hash.
# Line 2693  Line 2968 
2968      return @retVal;      return @retVal;
2969  }  }
2970    
 =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;  
 }  
   
2971  =head3 Protein  =head3 Protein
2972    
2973  C<< my $protein = Sprout::Protein($sequence, $table); >>  C<< my $protein = Sprout::Protein($sequence, $table); >>
# Line 2913  Line 3069 
3069      # Create the return list, priming it with the name of the data directory.      # Create the return list, priming it with the name of the data directory.
3070      my @retVal = ($self->{_options}->{dataDir});      my @retVal = ($self->{_options}->{dataDir});
3071      # Concatenate the table names.      # Concatenate the table names.
3072      push @retVal, $self->{_erdb}->GetTableNames();      push @retVal, $self->GetTableNames();
3073      # Return the result.      # Return the result.
3074      return @retVal;      return @retVal;
3075  }  }
3076    
3077  =head3 LowBBHs  =head3 LowBBHs
3078    
3079  C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>  C<< my %bbhMap = $sprout->LowBBHs($featureID, $cutoff); >>
3080    
3081  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
3082  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 2962  Line 3118 
3118      return %retVal;      return %retVal;
3119  }  }
3120    
3121    =head3 Sims
3122    
3123    C<< my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters); >>
3124    
3125    Get a list of similarities for a specified feature. Similarity information is not kept in the
3126    Sprout database; rather, they are retrieved from a network server. The similarities are
3127    returned as B<Sim> objects. A Sim object is actually a list reference that has been blessed
3128    so that its elements can be accessed by name.
3129    
3130    Similarities can be either raw or expanded. The raw similarities are basic
3131    hits between features with similar DNA. Expanding a raw similarity drags in any
3132    features considered substantially identical. So, for example, if features B<A1>,
3133    B<A2>, and B<A3> are all substatially identical to B<A>, then a raw similarity
3134    B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3135    
3136    =over 4
3137    
3138    =item fid
3139    
3140    ID of the feature whose similarities are desired.
3141    
3142    =item maxN
3143    
3144    Maximum number of similarities to return.
3145    
3146    =item maxP
3147    
3148    Minumum allowable similarity score.
3149    
3150    =item select
3151    
3152    Selection criterion: C<raw> means only raw similarities are returned; C<fig>
3153    means only similarities to FIG features are returned; C<all> means all expanded
3154    similarities are returned; and C<figx> means similarities are expanded until the
3155    number of FIG features equals the maximum.
3156    
3157    =item max_expand
3158    
3159    The maximum number of features to expand.
3160    
3161    =item filters
3162    
3163    Reference to a hash containing filter information, or a subroutine that can be
3164    used to filter the sims.
3165    
3166    =item RETURN
3167    
3168    Returns a reference to a list of similarity objects, or C<undef> if an error
3169    occurred.
3170    
3171    =back
3172    
3173    =cut
3174    
3175    sub Sims {
3176        # Get the parameters.
3177        my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_;
3178        # Create the shim object to test for deleted FIDs.
3179        my $shim = FidCheck->new($self);
3180        # Ask the network for sims.
3181        my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters);
3182        # Return the result.
3183        return $retVal;
3184    }
3185    
3186  =head3 GetGroups  =head3 GetGroups
3187    
3188  C<< my %groups = $sprout->GetGroups(\@groupList); >>  C<< my %groups = $sprout->GetGroups(\@groupList); >>
# Line 3083  Line 3304 
3304      return $retVal;      return $retVal;
3305  }  }
3306    
3307    =head3 DeleteGenome
3308    
3309    C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>
3310    
3311    Delete a genome from the database.
3312    
3313    =over 4
3314    
3315    =item genomeID
3316    
3317    ID of the genome to delete
3318    
3319    =item testFlag
3320    
3321    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3322    
3323    =item RETURN
3324    
3325    Returns a statistics object describing the rows deleted.
3326    
3327    =back
3328    
3329    =cut
3330    #: Return Type $%;
3331    sub DeleteGenome {
3332        # Get the parameters.
3333        my ($self, $genomeID, $testFlag) = @_;
3334        # Perform the delete for the genome's features.
3335        my $retVal = $self->Delete('Feature', "fig|$genomeID.%", $testFlag);
3336        # Perform the delete for the primary genome data.
3337        my $stats = $self->Delete('Genome', $genomeID, $testFlag);
3338        $retVal->Accumulate($stats);
3339        # Return the result.
3340        return $retVal;
3341    }
3342    
3343  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3344    
3345  =head3 ParseAssignment  =head3 ParseAssignment
# Line 3093  Line 3350 
3350    
3351  A functional assignment is always of the form  A functional assignment is always of the form
3352    
3353      I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>      C<set >I<YYYY>C< function to\n>I<ZZZZZ>
3354    
3355  where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the  where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
3356  actual functional role. In most cases, the user and the assigning user will be the  the user and the assigning user (from MadeAnnotation) will be the same, but that is
3357  same, but that is not always the case.  not always the case.
3358    
3359    In addition, the functional role may contain extra data that is stripped, such as
3360    terminating spaces or a comment separated from the rest of the text by a tab.
3361    
3362  This is a static method.  This is a static method.
3363    
3364  =over 4  =over 4
3365    
3366    =item user
3367    
3368    Name of the assigning user.
3369    
3370  =item text  =item text
3371    
3372  Text of the annotation.  Text of the annotation.
# Line 3118  Line 3382 
3382    
3383  sub _ParseAssignment {  sub _ParseAssignment {
3384      # Get the parameters.      # Get the parameters.
3385      my ($text) = @_;      my ($user, $text) = @_;
3386      # Declare the return value.      # Declare the return value.
3387      my @retVal = ();      my @retVal = ();
3388      # Check to see if this is a functional assignment.      # Check to see if this is a functional assignment.
3389      my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
3390      if ($type =~ m/^set ([^ ]+) function to$/i) {      if ($type =~ m/^set function to$/i) {
3391          # Here it is, so we return the user name (which is in $1), the functional role text,          # Here we have an assignment without a user, so we use the incoming user ID.
3392          # and the assigning user.          @retVal = ($user, $function);
3393          @retVal = ($1, $function, $user);      } elsif ($type =~ m/^set (\S+) function to$/i) {
3394            # Here we have an assignment with a user that is passed back to the caller.
3395            @retVal = ($1, $function);
3396        }
3397        # If we have an assignment, we need to clean the function text. There may be
3398        # extra junk at the end added as a note from the user.
3399        if (@retVal) {
3400            $retVal[1] =~ s/(\t\S)?\s*$//;
3401      }      }
3402      # Return the result list.      # Return the result list.
3403      return @retVal;      return @retVal;
# Line 3154  Line 3425 
3425    
3426  sub FriendlyTimestamp {  sub FriendlyTimestamp {
3427      my ($timeValue) = @_;      my ($timeValue) = @_;
3428      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
3429      return $retVal;      return $retVal;
3430  }  }
3431    
# Line 3216  Line 3487 
3487  }  }
3488    
3489    
   
3490  1;  1;

Legend:
Removed from v.1.32  
changed lines
  Added in v.1.79

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3