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

Diff of /Sprout/Sprout.pm

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

revision 1.121, Wed Oct 15 11:46:22 2008 UTC revision 1.123, Fri Jan 23 13:44:51 2009 UTC
# Line 4  Line 4 
4      use strict;      use strict;
5      use DBKernel;      use DBKernel;
6      use XML::Simple;      use XML::Simple;
7      use DBQuery;      use ERDBQuery;
8      use ERDBObject;      use ERDBObject;
9      use Tracer;      use Tracer;
10      use FIGRules;      use FIGRules;
# Line 14  Line 14 
14      use BasicLocation;      use BasicLocation;
15      use CustomAttributes;      use CustomAttributes;
16      use RemoteCustomAttributes;      use RemoteCustomAttributes;
17      use CGI;      use CGI qw(-nosticky);
18      use WikiTools;      use WikiTools;
19      use BioWords;      use BioWords;
20      use base qw(ERDB);      use base qw(ERDB);
# Line 41  Line 41 
41    
42  =cut  =cut
43    
 #: Constructor SFXlate->new_sprout_only();  
   
44  =head2 Public Methods  =head2 Public Methods
45    
46  =head3 new  =head3 new
# Line 91  Line 89 
89    
90      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });
91    
92    In order to work properly with [[ERDBGeneratorPl]], the constructor has an alternate
93    form.
94    
95        my $sprout = Sprout->new(dbd => $filename);
96    
97    Where I<$fileName> is the name of the DBD file. This enables us to specify an alternate
98    DBD for the loader, which is important when the database format changes.
99    
100  =cut  =cut
101    
102  sub new {  sub new {
103      # Get the parameters.      # Get the parameters.
104      my ($class, $dbName, $options) = @_;      my ($class, $dbName, $options) = @_;
105      # Default the database name if it is missing.      # Check for the alternate signature, and default the database name if it is missing.
106      if (! defined $dbName) {      if ($dbName eq 'dbd') {
107            $dbName = $FIG_Config::sproutDB;
108            $options = { xmlFileName => $options };
109        } elsif (! defined $dbName) {
110          $dbName = $FIG_Config::sproutDB;          $dbName = $FIG_Config::sproutDB;
111      } elsif (ref $dbName eq 'HASH') {      } elsif (ref $dbName eq 'HASH') {
112          $options = $dbName;          $options = $dbName;
# Line 124  Line 133 
133                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
134                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
135                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
136                           demandDriven => 0,               # 1 for forward-only queries
137                        }, $options);                        }, $options);
138      # Get the data directory.      # Get the data directory.
139      my $dataDir = $optionTable->{dataDir};      my $dataDir = $optionTable->{dataDir};
# Line 139  Line 149 
149      }      }
150      # Create the ERDB object.      # Create the ERDB object.
151      my $xmlFileName = "$optionTable->{xmlFileName}";      my $xmlFileName = "$optionTable->{xmlFileName}";
152      my $retVal = ERDB::new($class, $dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName, %$optionTable);
153      # Add the option table and XML file name.      # Add the option table and XML file name.
154      $retVal->{_options} = $optionTable;      $retVal->{_options} = $optionTable;
155      $retVal->{_xmlName} = $xmlFileName;      $retVal->{_xmlName} = $xmlFileName;
156      # Set up space for the group file data.      # Set up space for the group file data.
157      $retVal->{groupHash} = undef;      $retVal->{groupHash} = undef;
158      # Set up space for the genome hash. We use this to identify NMPDR genomes.      # Set up space for the genome hash. We use this to identify NMPDR genomes
159      $retVal->{genomeHash} = undef;      # and remember genome data.
160        $retVal->{genomeHash} = {};
161        $retVal->{genomeHashFilled} = 0;
162      # Remember the data directory name.      # Remember the data directory name.
163      $retVal->{dataDir} = $dataDir;      $retVal->{dataDir} = $dataDir;
164      # Return it.      # Return it.
# Line 342  Line 354 
354  The files are loaded based on the presumption that each line of the file is a record in the  The files are loaded based on the presumption that each line of the file is a record in the
355  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside
356  fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must  fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must
357  be presented in the order given in the relation tables produced by the L</ShowMetaData> method.  be presented in the order given in the relation tables produced by the database documentation.
358    
359  =over 4  =over 4
360    
# Line 531  Line 543 
543  =item filter  =item filter
544    
545  If specified, a filter for the list of genomes to display. The filter should be in the form of a  If specified, a filter for the list of genomes to display. The filter should be in the form of a
546  list reference. The first element of the list should be the filter string, and the remaining elements  list reference, a string, or a hash reference. If it is a list reference, the first element
547  the filter parameters.  of the list should be the filter string, and the remaining elements the filter parameters. If it is a
548    string, it will be split into a list at each included tab. If it is a hash reference, it should be
549    a hash that maps genomes which should be included to a TRUE value.
550    
551  =item multiSelect  =item multiSelect
552    
# Line 571  Line 585 
585      my $divID = "${menuID}_status";      my $divID = "${menuID}_status";
586      my $urlID = "${menuID}_url";      my $urlID = "${menuID}_url";
587      # Compute the code to show selected genomes in the status area.      # Compute the code to show selected genomes in the status area.
588      my $showSelect = "showSelected('$menuID', '$divID', '$urlID', 1000)";      my $showSelect = "showSelected('$menuID', '$divID', '$urlID', $FIG_Config::genome_control_cap)";
589      # Check for single-select or multi-select.      # Check for single-select or multi-select.
590      my $multiSelect = $options{multiSelect} || 0;      my $multiSelect = $options{multiSelect} || 0;
591      # Get the style data.      # Get the style data.
# Line 583  Line 597 
597      }      }
598      my %selected = map { $_ => 1 } @{$selections};      my %selected = map { $_ => 1 } @{$selections};
599      # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited      # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
600      # string or a list reference.      # string, a hash reference, or a list reference.
601        my ($filterHash, $filterString);
602      my $filterParms = $options{filter} || "";      my $filterParms = $options{filter} || "";
603        if (ref $filterParms eq 'HASH') {
604            $filterHash = $filterParms;
605            $filterParms = [];
606            $filterString = "";
607        } else {
608      if (! ref $filterParms) {      if (! ref $filterParms) {
609          $filterParms = [split /\t|\\t/, $filterParms];          $filterParms = [split /\t|\\t/, $filterParms];
610      }      }
611      my $filterString = shift @{$filterParms};          $filterString = shift @{$filterParms};
612        }
613        # Check for possible subsystem filtering. If there is one, we will tack the
614        # relationship onto the object name list.
615        my @objectNames = qw(Genome);
616        if ($filterString =~ /ParticipatesIn\(/) {
617            push @objectNames, 'ParticipatesIn';
618        }
619      # Get a list of all the genomes in group order. In fact, we only need them ordered      # Get a list of all the genomes in group order. In fact, we only need them ordered
620      # by name (genus,species,strain), but putting primary-group in front enables us to      # by name (genus,species,strain), but putting primary-group in front enables us to
621      # take advantage of an existing index.      # take advantage of an existing index.
622      my @genomeList = $self->GetAll(['Genome'], "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",      my @genomeList = $self->GetAll(\@objectNames, "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
623                                     $filterParms,                                     $filterParms,
624                                     [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);                                     [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
625        # Apply the hash filter (if any).
626        if (defined $filterHash) {
627            @genomeList = grep { $filterHash->{$_->[1]} } @genomeList;
628        }
629      # Create a hash to organize the genomes by group. Each group will contain a list of      # Create a hash to organize the genomes by group. Each group will contain a list of
630      # 2-tuples, the first element being the genome ID and the second being the genome      # 2-tuples, the first element being the genome ID and the second being the genome
631      # name.      # name.
# Line 624  Line 655 
655      my @groups = map { $sortGroups{$_} } sort keys %sortGroups;      my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
656      # Remember the number of NMPDR groups.      # Remember the number of NMPDR groups.
657      my $nmpdrGroupCount = scalar @groups;      my $nmpdrGroupCount = scalar @groups;
658        # Are there any supporting genomes?
659        if (exists $gHash{$FIG_Config::otherGroup}) {
660      # Loop through the supporting genomes, classifying them by domain. We'll also keep a list      # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
661      # of the domains found.      # of the domains found.
662      my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};      my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
# Line 642  Line 675 
675      push @groups, sort @domains;      push @groups, sort @domains;
676      # Delete the supporting group.      # Delete the supporting group.
677      delete $gHash{$FIG_Config::otherGroup};      delete $gHash{$FIG_Config::otherGroup};
678        }
679      # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage      # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
680      # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes      # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
681      # and use that to make the selections.      # and use that to make the selections.
# Line 813  Line 847 
847  sub GenusSpecies {  sub GenusSpecies {
848      # Get the parameters.      # Get the parameters.
849      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
850      # Get the data for the specified genome.      # Declare the return value.
851      my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',      my $retVal;
852                                                                'Genome(unique-characterization)']);      # Get the genome data.
853      # Format the result and return it.      my $genomeData = $self->_GenomeData($genomeID);
854      my $retVal = join(' ', @values);      # Only proceed if we found the genome.
855        if (defined $genomeData) {
856            $retVal = $genomeData->PrimaryValue('Genome(scientific-name)');
857        }
858        # Return it.
859      return $retVal;      return $retVal;
860  }  }
861    
# Line 1155  Line 1193 
1193      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
1194      # Declare the return variable.      # Declare the return variable.
1195      my $retVal = 0;      my $retVal = 0;
1196      # Get the genome's contig sequence lengths.      # Get the genome data.
1197      my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',      my $genomeData = $self->_GenomeData($genomeID);
1198                         [$genomeID], 'IsMadeUpOf(len)');      # Only proceed if it exists.
1199      # Sum the lengths.      if (defined $genomeData) {
1200      map { $retVal += $_ } @lens;          $retVal = $genomeData->PrimaryValue('Genome(dna-size)');
1201        }
1202      # Return the result.      # Return the result.
1203      return $retVal;      return $retVal;
1204  }  }
# Line 1826  Line 1865 
1865      # Loop through the incoming features.      # Loop through the incoming features.
1866      for my $featureID (@{$featureList}) {      for my $featureID (@{$featureList}) {
1867          # Ask the server for the feature's best hit.          # Ask the server for the feature's best hit.
1868          my @bbhData = FIGRules::BBHData($featureID);          my $bbhData = FIGRules::BBHData($featureID);
1869          # Peel off the BBHs found.          # Peel off the BBHs found.
1870          my @found = ();          my @found = ();
1871          for my $bbh (@bbhData) {          for my $bbh (@$bbhData) {
1872              my $fid = $bbh->[0];              my $fid = $bbh->[0];
1873              my $bbGenome = $self->GenomeOf($fid);              my $bbGenome = $self->GenomeOf($fid);
1874              if ($bbGenome eq $genomeID) {              if ($bbGenome eq $genomeID) {
# Line 1868  Line 1907 
1907      # Get the parameters.      # Get the parameters.
1908      my ($self, $featureID, $count) = @_;      my ($self, $featureID, $count) = @_;
1909      # Ask for the best hits.      # Ask for the best hits.
1910      my @lists = FIGRules::BBHData($featureID);      my $lists = FIGRules::BBHData($featureID);
1911      # Create the return value.      # Create the return value.
1912      my %retVal = ();      my %retVal = ();
1913      for my $tuple (@lists) {      for my $tuple (@$lists) {
1914          $retVal{$tuple->[0]} = $tuple->[1];          $retVal{$tuple->[0]} = $tuple->[1];
1915      }      }
1916      # Return the result.      # Return the result.
# Line 1905  Line 1944 
1944      # Declare the return variable.      # Declare the return variable.
1945      my $retVal;      my $retVal;
1946      # Get the genome's data.      # Get the genome's data.
1947      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->_GenomeData($genomeID);
1948      if ($genomeData) {      # Only proceed if it exists.
1949        if (defined $genomeData) {
1950          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1951          $retVal = $genomeData->PrimaryValue('Genome(complete)');          $retVal = $genomeData->PrimaryValue('Genome(complete)');
1952      }      }
# Line 2022  Line 2062 
2062              $retVal{$featureID2} = $score;              $retVal{$featureID2} = $score;
2063          }          }
2064      }      }
     # Functional coupling is reflexive. If we found at least one coupled feature, we must add  
     # the incoming feature as well.  
     if (keys %retVal) {  
         $retVal{$featureID} = 9999;  
     }  
2065      # Return the hash.      # Return the hash.
2066      return %retVal;      return %retVal;
2067  }  }
# Line 2383  Line 2418 
2418  sub GetGenomeNameData {  sub GetGenomeNameData {
2419      # Get the parameters.      # Get the parameters.
2420      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
2421        # Declare the return variables.
2422        my ($genus, $species, $strain);
2423        # Get the genome's data.
2424        my $genomeData = $self->_GenomeData($genomeID);
2425        # Only proceed if the genome exists.
2426        if (defined $genomeData) {
2427      # Get the desired values.      # Get the desired values.
2428      my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>          ($genus, $species, $strain) = $genomeData->Values(['Genome(genus)',
2429                                                              [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);                                                             'Genome(species)',
2430      # Throw an error if they were not found.                                                             'Genome(unique-characterization)']);
2431      if (! defined $genus) {      } else {
2432            # Throw an error because they were not found.
2433          Confess("Genome $genomeID not found in database.");          Confess("Genome $genomeID not found in database.");
2434      }      }
2435      # Return the results.      # Return the results.
# Line 2688  Line 2730 
2730  sub Taxonomy {  sub Taxonomy {
2731      # Get the parameters.      # Get the parameters.
2732      my ($self, $genome) = @_;      my ($self, $genome) = @_;
     # Find the specified genome's taxonomy string.  
     my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);  
2733      # Declare the return variable.      # Declare the return variable.
2734      my @retVal = ();      my @retVal = ();
2735      # If we found the genome, return its taxonomy string.      # Get the genome data.
2736      if ($list) {      my $genomeData = $self->_GenomeData($genome);
2737          @retVal = split /\s*;\s*/, $list;      # Only proceed if it exists.
2738        if (defined $genomeData) {
2739            # Create the taxonomy from the taxonomy string.
2740            @retVal = split /\s*;\s*/, $genomeData->PrimaryValue('Genome(taxonomy)');
2741      } else {      } else {
2742            # Genome doesn't exist, so emit a warning.
2743          Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0);          Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0);
2744      }      }
2745      # Return the value found.      # Return the value found.
# Line 2740  Line 2784 
2784      }      }
2785      my @taxA = $self->Taxonomy($genomeA);      my @taxA = $self->Taxonomy($genomeA);
2786      my @taxB = $self->Taxonomy($genomeB);      my @taxB = $self->Taxonomy($genomeB);
2787      # Initialize the distance to 1. We'll reduce it each time we find a match between the      # Compute the distance.
2788      # taxonomies.      my $retVal = FIGRules::CrudeDistanceFormula(\@taxA, \@taxB);
     my $retVal = 1.0;  
     # Initialize the subtraction amount. This amount determines the distance reduction caused  
     # by a mismatch at the current level.  
     my $v = 0.5;  
     # Loop through the taxonomies.  
     for (my $i = 0; ($i < @taxA) && ($i < @taxB) && ($taxA[$i] eq $taxB[$i]); $i++) {  
         $retVal -= $v;  
         $v /= 2;  
     }  
2789      return $retVal;      return $retVal;
2790  }  }
2791    
# Line 3215  Line 3250 
3250      # Get the parameters.      # Get the parameters.
3251      my ($self, $featureID, $function, $userID) = @_;      my ($self, $featureID, $function, $userID) = @_;
3252      # Get a list of the features that are BBHs of the incoming feature.      # Get a list of the features that are BBHs of the incoming feature.
3253      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);      my $bbhData = FIGRules::BBHData($featureID);
3254        my @bbhFeatures = map { $_->[0] } @$bbhData;
3255      # Now we loop through the features, pulling out the ones that have the correct      # Now we loop through the features, pulling out the ones that have the correct
3256      # functional assignment.      # functional assignment.
3257      my @retVal = ();      my @retVal = ();
# Line 3388  Line 3424 
3424    
3425  =head3 BBHMatrix  =head3 BBHMatrix
3426    
3427      my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);      my $bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3428    
3429  Find all the bidirectional best hits for the features of a genome in a  Find all the bidirectional best hits for the features of a genome in a
3430  specified list of target genomes. The return value will be a hash mapping  specified list of target genomes. The return value will be a hash mapping
# Line 3412  Line 3448 
3448    
3449  =item RETURN  =item RETURN
3450    
3451  Returns a hash mapping each feature in the original genome to a hash mapping its  Returns a reference to a hash mapping each feature in the original genome
3452  BBH pegs in the target genomes to their scores.  to a sub-hash mapping its BBH pegs in the target genomes to their scores.
3453    
3454  =back  =back
3455    
# Line 3426  Line 3462 
3462      my %retVal = ();      my %retVal = ();
3463      # Ask for the BBHs.      # Ask for the BBHs.
3464      my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);      my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3465        Trace("Retrieved " . scalar(@bbhList) . " BBH results.") if T(3);
3466      # We now have a set of 4-tuples that we need to convert into a hash of hashes.      # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3467      for my $bbhData (@bbhList) {      for my $bbhData (@bbhList) {
3468          my ($peg1, $peg2, $score) = @{$bbhData};          my ($peg1, $peg2, $score) = @{$bbhData};
# Line 3436  Line 3473 
3473          }          }
3474      }      }
3475      # Return the result.      # Return the result.
3476      return %retVal;      return \%retVal;
3477  }  }
3478    
3479    
# Line 3542  Line 3579 
3579      # Create the return hash.      # Create the return hash.
3580      my %retVal = ();      my %retVal = ();
3581      # Query for the desired BBHs.      # Query for the desired BBHs.
3582      my @bbhList = FIGRules::BBHData($featureID, $cutoff);      my $bbhList = FIGRules::BBHData($featureID, $cutoff);
3583      # Form the results into the return hash.      # Form the results into the return hash.
3584      for my $pair (@bbhList) {      for my $pair (@$bbhList) {
3585          my $fid = $pair->[0];          my $fid = $pair->[0];
3586          if ($self->Exists('Feature', $fid)) {          if ($self->Exists('Feature', $fid)) {
3587              $retVal{$fid} = $pair->[1];              $retVal{$fid} = $pair->[1];
# Line 4027  Line 4064 
4064  =cut  =cut
4065    
4066  sub GetSourceObject {  sub GetSourceObject {
4067      # Get access to the FIG code.      # Get the parameters.
4068        my ($self) = @_;
4069        # Check to see if we already have a source object.
4070        my $retVal = $self->{_fig};
4071        if (! defined $retVal) {
4072            # No, so create one.
4073      require FIG;      require FIG;
4074      # Return a FIG object.          $retVal = FIG->new();
4075      return FIG->new();      }
4076        # Return the object.
4077        return $retVal;
4078  }  }
4079    
4080  =head3 SectionList  =head3 SectionList
4081    
4082      my @sections = $erdb->SectionList($source);      my @sections = $erdb->SectionList();
4083    
4084  Return a list of the names for the different data sections used when loading this database.  Return a list of the names for the different data sections used when loading this database.
4085  The default is an empty string, in which case there is only one section representing the  The default is a single string, in which case there is only one section representing the
4086  entire database.  entire database.
4087    
 =over 4  
   
 =item source  
   
 Source object used to access the data from which the database is loaded. This is the  
 same object returned by L</GetSourceObject>; however, we ask the caller to pass it  
 in as a parameter so that we don't end up creating multiple copies of a potentially  
 expensive data structure.  
   
 =item RETURN  
   
 Returns a list of section names.  
   
 =back  
   
4088  =cut  =cut
4089    
4090  sub SectionList {  sub SectionList {
# Line 4063  Line 4092 
4092      my ($self, $source) = @_;      my ($self, $source) = @_;
4093      # Ask the BaseSproutLoader for a section list.      # Ask the BaseSproutLoader for a section list.
4094      require BaseSproutLoader;      require BaseSproutLoader;
4095      my @retVal = BaseSproutLoader::GetSectionList($self, $source);      my @retVal = BaseSproutLoader::GetSectionList($self);
4096      # Return the list.      # Return the list.
4097      return @retVal;      return @retVal;
4098  }  }
4099    
4100  =head3 Loader  =head3 Loader
4101    
4102      my $groupLoader = $erdb->Loader($groupName, $source, $options);      my $groupLoader = $erdb->Loader($groupName, $options);
4103    
4104  Return an [[ERDBLoadGroupPm]] object for the specified load group. This method is used  Return an [[ERDBLoadGroupPm]] object for the specified load group. This method is used
4105  by [[ERDBGeneratorPl]] to create the load group objects. If you are not using  by [[ERDBGeneratorPl]] to create the load group objects. If you are not using
# Line 4083  Line 4112 
4112  Name of the load group whose object is to be returned. The group name is  Name of the load group whose object is to be returned. The group name is
4113  guaranteed to be a single word with only the first letter capitalized.  guaranteed to be a single word with only the first letter capitalized.
4114    
 =item source  
   
 The source object used to access the data from which the load file is derived. This  
 is the same object returned by L</GetSourceObject>; however, we ask the caller to pass  
 it in as a parameter so that we don't end up creating multiple copies of a potentially  
 expensive data structure.  
   
4115  =item options  =item options
4116    
4117  Reference to a hash of command-line options.  Reference to a hash of command-line options.
# Line 4105  Line 4127 
4127    
4128  sub Loader {  sub Loader {
4129      # Get the parameters.      # Get the parameters.
4130      my ($self, $groupName, $source, $options) = @_;      my ($self, $groupName, $options) = @_;
4131      # Compute the loader name.      # Compute the loader name.
4132      my $loaderClass = "${groupName}SproutLoader";      my $loaderClass = "${groupName}SproutLoader";
4133      # Pull in its definition.      # Pull in its definition.
4134      require "$loaderClass.pm";      require "$loaderClass.pm";
4135      # Create an object for it.      # Create an object for it.
4136      my $retVal = eval("$loaderClass->new(\$self, \$source, \$options)");      my $retVal = eval("$loaderClass->new(\$self, \$options)");
4137      # Insure it worked.      # Insure it worked.
4138      Confess("Could not create $loaderClass object: $@") if $@;      Confess("Could not create $loaderClass object: $@") if $@;
4139      # Return it to the caller.      # Return it to the caller.
4140      return $retVal;      return $retVal;
4141  }  }
4142    
4143    
4144  =head3 LoadGroupList  =head3 LoadGroupList
4145    
4146      my @groups = $erdb->LoadGroupList();      my @groups = $erdb->LoadGroupList();
# Line 4130  Line 4153 
4153    
4154  sub LoadGroupList {  sub LoadGroupList {
4155      # Return the list.      # Return the list.
4156      return qw(Genome Subsystem Annotation Property Source Reaction Synonym Drug Feature);      return qw(Genome Subsystem Annotation Property Source Reaction Synonym Feature Drug);
4157  }  }
4158    
4159  =head3 LoadDirectory  =head3 LoadDirectory
# Line 4168  Line 4191 
4191          # We don't have one pre-built, so we build and save it now.          # We don't have one pre-built, so we build and save it now.
4192          $retVal = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",          $retVal = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
4193                                   stops => "$FIG_Config::sproutData/StopWords.txt",                                   stops => "$FIG_Config::sproutData/StopWords.txt",
4194                                   cache => 1);                                   cache => 0);
4195          $self->{stemmer} = $retVal;          $self->{stemmer} = $retVal;
4196      }      }
4197      # Return the result.      # Return the result.
# Line 4261  Line 4284 
4284      # Get the parameters.      # Get the parameters.
4285      my ($self, $fid) = @_;      my ($self, $fid) = @_;
4286      # Insure we have a genome hash.      # Insure we have a genome hash.
4287      if (! defined $self->{genomeHash}) {      my $genomes = $self->_GenomeHash();
         my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');  
         $self->{genomeHash} = \%genomeHash;  
     }  
4288      # Get the feature's genome ID.      # Get the feature's genome ID.
4289      my ($genomeID) = FIGRules::ParseFeatureID($fid);      my ($genomeID) = FIGRules::ParseFeatureID($fid);
4290      # Return an indicator of whether or not the genome ID is in the hash.      # Return an indicator of whether or not the genome ID is in the hash.
# Line 4341  Line 4361 
4361      return $retVal;      return $retVal;
4362  }  }
4363    
4364    =head3 _GenomeHash
4365    
4366        my $gHash = $sprout->_GenomeHash();
4367    
4368    Return a hash mapping all NMPDR genome IDs to [[ERDBObjectPm]] genome objects.
4369    
4370    =cut
4371    
4372    sub _GenomeHash {
4373        # Get the parameters.
4374        my ($self) = @_;
4375        # Do we already have a filled hash?
4376        if (! $self->{genomeHashFilled}) {
4377            # No, create it.
4378            my %gHash = map { $_->PrimaryValue('id') => $_ } $self->GetList("Genome", "", []);
4379            $self->{genomeHash} = \%gHash;
4380            # Denote we have it.
4381            $self->{genomeHashFilled} = 1;
4382        }
4383        # Return the hash.
4384        return $self->{genomeHash};
4385    }
4386    
4387    =head3 _GenomeData
4388    
4389        my $genomeData = $sprout->_GenomeData($genomeID);
4390    
4391    Return an [[ERDBObjectPm]] object for the specified genome, or an undefined
4392    value if the genome does not exist.
4393    
4394    =over 4
4395    
4396    =item genomeID
4397    
4398    ID of the desired genome.
4399    
4400    =item RETURN
4401    
4402    Returns either an [[ERDBObjectPm]] containing the genome, or an undefined value.
4403    If the genome exists, it will have been read into the genome cache.
4404    
4405    =back
4406    
4407    =cut
4408    
4409    sub _GenomeData {
4410        # Get the parameters.
4411        my ($self, $genomeID) = @_;
4412        # Are we in the genome hash?
4413        if (! exists $self->{genomeHash}->{$genomeID} && ! $self->{genomeHashFilled}) {
4414            # The genome isn't in the hash, and the hash is not complete, so we try to
4415            # read it.
4416            $self->{genomeHash}->{$genomeID} = $self->GetEntity(Genome => $genomeID);
4417        }
4418        # Return the result.
4419        return $self->{genomeHash}->{$genomeID};
4420    }
4421    
4422    =head3 _CacheGenome
4423    
4424        $sprout->_CacheGenome($genomeID, $genomeData);
4425    
4426    Store the specified genome object in the genome cache if it is already there.
4427    
4428    =over 4
4429    
4430    =item genomeID
4431    
4432    ID of the genome to store in the cache.
4433    
4434    =item genomeData
4435    
4436    An [[ERDBObjectPm]] containing at least the data for the specified genome.
4437    Note that the Genome may not be the primary object in it, so a fully-qualified
4438    field name has to be used to retrieve data from it.
4439    
4440    =back
4441    
4442    =cut
4443    
4444    sub _CacheGenome {
4445        # Get the parameters.
4446        my ($self, $genomeID, $genomeData) = @_;
4447        # Only proceed if we don't already have the genome.
4448        if (! exists $self->{genomeHash}->{$genomeID}) {
4449            $self->{genomeHash}->{$genomeID} = $genomeData;
4450        }
4451    }
4452    
4453  1;  1;

Legend:
Removed from v.1.121  
changed lines
  Added in v.1.123

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3