[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 1.126, Thu Apr 2 01:47:00 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 287  Line 299 
299                  $retVal = $superGroup;                  $retVal = $superGroup;
300              }              }
301          }          }
         # Make sure we found something.  
         if (! $retVal) {  
             Confess("No super-group found for \"$groupName\".");  
         }  
302      }      }
303      # Return the result.      # Return the result.
304      return $retVal;      return $retVal;
# Line 342  Line 350 
350  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
351  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
352  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
353  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.
354    
355  =over 4  =over 4
356    
# Line 531  Line 539 
539  =item filter  =item filter
540    
541  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
542  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
543  the filter parameters.  of the list should be the filter string, and the remaining elements the filter parameters. If it is a
544    string, it will be split into a list at each included tab. If it is a hash reference, it should be
545    a hash that maps genomes which should be included to a TRUE value.
546    
547  =item multiSelect  =item multiSelect
548    
# Line 571  Line 581 
581      my $divID = "${menuID}_status";      my $divID = "${menuID}_status";
582      my $urlID = "${menuID}_url";      my $urlID = "${menuID}_url";
583      # Compute the code to show selected genomes in the status area.      # Compute the code to show selected genomes in the status area.
584      my $showSelect = "showSelected('$menuID', '$divID', '$urlID', 1000)";      my $showSelect = "showSelected('$menuID', '$divID', '$urlID', $FIG_Config::genome_control_cap)";
585      # Check for single-select or multi-select.      # Check for single-select or multi-select.
586      my $multiSelect = $options{multiSelect} || 0;      my $multiSelect = $options{multiSelect} || 0;
587      # Get the style data.      # Get the style data.
# Line 583  Line 593 
593      }      }
594      my %selected = map { $_ => 1 } @{$selections};      my %selected = map { $_ => 1 } @{$selections};
595      # 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
596      # string or a list reference.      # string, a hash reference, or a list reference.
597        my ($filterHash, $filterString);
598      my $filterParms = $options{filter} || "";      my $filterParms = $options{filter} || "";
599        if (ref $filterParms eq 'HASH') {
600            $filterHash = $filterParms;
601            $filterParms = [];
602            $filterString = "";
603        } else {
604      if (! ref $filterParms) {      if (! ref $filterParms) {
605          $filterParms = [split /\t|\\t/, $filterParms];          $filterParms = [split /\t|\\t/, $filterParms];
606      }      }
607      my $filterString = shift @{$filterParms};          $filterString = shift @{$filterParms};
608        }
609        # Check for possible subsystem filtering. If there is one, we will tack the
610        # relationship onto the object name list.
611        my @objectNames = qw(Genome);
612        if ($filterString =~ /ParticipatesIn\(/) {
613            push @objectNames, 'ParticipatesIn';
614        }
615      # 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
616      # 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
617      # take advantage of an existing index.      # take advantage of an existing index.
618      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)",
619                                     $filterParms,                                     $filterParms,
620                                     [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))]);
621        # Apply the hash filter (if any).
622        if (defined $filterHash) {
623            @genomeList = grep { $filterHash->{$_->[1]} } @genomeList;
624        }
625      # 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
626      # 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
627      # name.      # name.
# Line 624  Line 651 
651      my @groups = map { $sortGroups{$_} } sort keys %sortGroups;      my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
652      # Remember the number of NMPDR groups.      # Remember the number of NMPDR groups.
653      my $nmpdrGroupCount = scalar @groups;      my $nmpdrGroupCount = scalar @groups;
654        # Are there any supporting genomes?
655        if (exists $gHash{$FIG_Config::otherGroup}) {
656      # 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
657      # of the domains found.      # of the domains found.
658      my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};      my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
# Line 642  Line 671 
671      push @groups, sort @domains;      push @groups, sort @domains;
672      # Delete the supporting group.      # Delete the supporting group.
673      delete $gHash{$FIG_Config::otherGroup};      delete $gHash{$FIG_Config::otherGroup};
674        }
675      # 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
676      # 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
677      # and use that to make the selections.      # and use that to make the selections.
# Line 655  Line 685 
685      # Set up the multiple-select flag.      # Set up the multiple-select flag.
686      my $multipleTag = ($multiSelect ? " multiple" : "" );      my $multipleTag = ($multiSelect ? " multiple" : "" );
687      # Set up the style class.      # Set up the style class.
688      my $classTag = ($class ? " class=\"$class\"" : "" );      my $classTag = ($class ? " $class" : "" );
689      # Create the SELECT tag and stuff it into the output array.      # Create the SELECT tag and stuff it into the output array.
690      my @lines = ("<SELECT name=\"$menuName\" id=\"$menuID\" $onChangeTag$multipleTag$classTag size=\"$rows\">");      my @lines = qq(<SELECT name="$menuName" id="$menuID" class="genomeSelect $class" $onChangeTag$multipleTag$classTag size="$rows">);
691      # Loop through the groups.      # Loop through the groups.
692      for my $group (@groups) {      for my $group (@groups) {
693          # Get the genomes in the group.          # Get the genomes in the group.
# Line 690  Line 720 
720          # displayed. For multiple-select mode, we include a button that selects the displayed          # displayed. For multiple-select mode, we include a button that selects the displayed
721          # genes. For single-select mode, we use a plain label instead.          # genes. For single-select mode, we use a plain label instead.
722          my $searchThingName = "${menuID}_SearchThing";          my $searchThingName = "${menuID}_SearchThing";
723          my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"          my $searchThingLabel = "Type to narrow selection";
724                                               : "Show genomes containing");          my $searchThingButton = "";
725            if ($multiSelect) {
726                $searchThingButton = qq(<INPUT type="button" name="MacroSearch" class="button" value="Go" onClick="selectShowing('$menuID', '$searchThingName'); $showSelect;" />);
727            }
728          push @lines, "<br />$searchThingLabel&nbsp;" .          push @lines, "<br />$searchThingLabel&nbsp;" .
729                       "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />" .                       qq(<INPUT type="text" id="$searchThingName" name="$searchThingName" class="genomeSearchThing" onKeyup="showTyped('$menuID', '$searchThingName');" />) .
730                       Hint("GenomeControl", "Type here to filter the genomes displayed.") . "<br />";                       $searchThingButton .
731                         Hint("GenomeControl", 28) . "<br />";
732          # For multi-select mode, we also have buttons to set and clear selections.          # For multi-select mode, we also have buttons to set and clear selections.
733          if ($multiSelect) {          if ($multiSelect) {
734              push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll(getElementById('$menuID')); $showSelect\" />";              push @lines, qq(<INPUT type="button" name="ClearAll" class="bigButton genomeButton" value="Clear All" onClick="clearAll(getElementById('$menuID')); $showSelect" />);
735              push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll(getElementById('$menuID')); $showSelect\" />";              push @lines, qq(<INPUT type="button" name="SelectAll" class="bigButton genomeButton" value="Select All" onClick="selectAll(getElementById('$menuID')); $showSelect" />);
736              push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome(getElementById('$menuID'), $nmpdrCount, true); $showSelect;\" />";              push @lines, qq(<INPUT type="button" name="NMPDROnly" class="bigButton genomeButton" value="Select NMPDR" onClick="selectSome(getElementById('$menuID'), $nmpdrCount, true); $showSelect;" />);
737          }          }
738          # Add a hidden field we can use to generate organism page hyperlinks.          # Add a hidden field we can use to generate organism page hyperlinks.
739          push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/wiki/rest.cgi/NmpdrPlugin/SeedViewer?page=Organism;organism=\" />";          push @lines, qq(<INPUT type="hidden" id="$urlID" value="$FIG_Config::cgi_url/wiki/rest.cgi/NmpdrPlugin/SeedViewer?page=Organism;organism=" />);
740          # Add the status display. This tells the user what's selected no matter where the list is scrolled.          # Add the status display. This tells the user what's selected no matter where the list is scrolled.
741          push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";          push @lines, qq(<DIV id="$divID" class="Panel"></DIV>);
742      }      }
743      # Assemble all the lines into a string.      # Assemble all the lines into a string.
744      my $retVal = join("\n", @lines, "");      my $retVal = join("\n", @lines, "");
# Line 712  Line 746 
746      return $retVal;      return $retVal;
747  }  }
748    
749    =head3 Cleanup
750    
751        $sprout->Cleanup();
752    
753    Release the internal cache structures to free up memory.
754    
755    =cut
756    
757    sub Cleanup {
758        # Get the parameters.
759        my ($self) = @_;
760        # Delete the stemmer.
761        delete $self->{stemmer};
762        # Delete the attribute database.
763        delete $self->{_ca};
764        # Delete the group hash.
765        delete $self->{groupHash};
766        # Is there a FIG object?
767        if (defined $self->{fig}) {
768            # Yes, clear its subsystem cache.
769            $self->{fig}->clear_subsystem_cache();
770        }
771    }
772    
773    
774  =head3 Stem  =head3 Stem
775    
# Line 813  Line 871 
871  sub GenusSpecies {  sub GenusSpecies {
872      # Get the parameters.      # Get the parameters.
873      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
874      # Get the data for the specified genome.      # Declare the return value.
875      my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',      my $retVal;
876                                                                'Genome(unique-characterization)']);      # Get the genome data.
877      # Format the result and return it.      my $genomeData = $self->_GenomeData($genomeID);
878      my $retVal = join(' ', @values);      # Only proceed if we found the genome.
879        if (defined $genomeData) {
880            $retVal = $genomeData->PrimaryValue('Genome(scientific-name)');
881        }
882        # Return it.
883      return $retVal;      return $retVal;
884  }  }
885    
# Line 962  Line 1024 
1024  }  }
1025    
1026    
   
1027  =head3 PointLocation  =head3 PointLocation
1028    
1029      my $found = Sprout::PointLocation($location, $point);      my $found = Sprout::PointLocation($location, $point);
# Line 1155  Line 1216 
1216      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
1217      # Declare the return variable.      # Declare the return variable.
1218      my $retVal = 0;      my $retVal = 0;
1219      # Get the genome's contig sequence lengths.      # Get the genome data.
1220      my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',      my $genomeData = $self->_GenomeData($genomeID);
1221                         [$genomeID], 'IsMadeUpOf(len)');      # Only proceed if it exists.
1222      # Sum the lengths.      if (defined $genomeData) {
1223      map { $retVal += $_ } @lens;          $retVal = $genomeData->PrimaryValue('Genome(dna-size)');
1224        }
1225      # Return the result.      # Return the result.
1226      return $retVal;      return $retVal;
1227  }  }
# Line 1826  Line 1888 
1888      # Loop through the incoming features.      # Loop through the incoming features.
1889      for my $featureID (@{$featureList}) {      for my $featureID (@{$featureList}) {
1890          # Ask the server for the feature's best hit.          # Ask the server for the feature's best hit.
1891          my @bbhData = FIGRules::BBHData($featureID);          my $bbhData = FIGRules::BBHData($featureID);
1892          # Peel off the BBHs found.          # Peel off the BBHs found.
1893          my @found = ();          my @found = ();
1894          for my $bbh (@bbhData) {          for my $bbh (@$bbhData) {
1895              my $fid = $bbh->[0];              my $fid = $bbh->[0];
1896              my $bbGenome = $self->GenomeOf($fid);              my $bbGenome = $self->GenomeOf($fid);
1897              if ($bbGenome eq $genomeID) {              if ($bbGenome eq $genomeID) {
# Line 1868  Line 1930 
1930      # Get the parameters.      # Get the parameters.
1931      my ($self, $featureID, $count) = @_;      my ($self, $featureID, $count) = @_;
1932      # Ask for the best hits.      # Ask for the best hits.
1933      my @lists = FIGRules::BBHData($featureID);      my $lists = FIGRules::BBHData($featureID);
1934      # Create the return value.      # Create the return value.
1935      my %retVal = ();      my %retVal = ();
1936      for my $tuple (@lists) {      for my $tuple (@$lists) {
1937          $retVal{$tuple->[0]} = $tuple->[1];          $retVal{$tuple->[0]} = $tuple->[1];
1938      }      }
1939      # Return the result.      # Return the result.
# Line 1905  Line 1967 
1967      # Declare the return variable.      # Declare the return variable.
1968      my $retVal;      my $retVal;
1969      # Get the genome's data.      # Get the genome's data.
1970      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->_GenomeData($genomeID);
1971      if ($genomeData) {      # Only proceed if it exists.
1972        if (defined $genomeData) {
1973          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1974          $retVal = $genomeData->PrimaryValue('Genome(complete)');          $retVal = $genomeData->PrimaryValue('Genome(complete)');
1975      }      }
# Line 2022  Line 2085 
2085              $retVal{$featureID2} = $score;              $retVal{$featureID2} = $score;
2086          }          }
2087      }      }
     # 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;  
     }  
2088      # Return the hash.      # Return the hash.
2089      return %retVal;      return %retVal;
2090  }  }
# Line 2383  Line 2441 
2441  sub GetGenomeNameData {  sub GetGenomeNameData {
2442      # Get the parameters.      # Get the parameters.
2443      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
2444        # Declare the return variables.
2445        my ($genus, $species, $strain);
2446        # Get the genome's data.
2447        my $genomeData = $self->_GenomeData($genomeID);
2448        # Only proceed if the genome exists.
2449        if (defined $genomeData) {
2450      # Get the desired values.      # Get the desired values.
2451      my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>          ($genus, $species, $strain) = $genomeData->Values(['Genome(genus)',
2452                                                              [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);                                                             'Genome(species)',
2453      # Throw an error if they were not found.                                                             'Genome(unique-characterization)']);
2454      if (! defined $genus) {      } else {
2455            # Throw an error because they were not found.
2456          Confess("Genome $genomeID not found in database.");          Confess("Genome $genomeID not found in database.");
2457      }      }
2458      # Return the results.      # Return the results.
# Line 2688  Line 2753 
2753  sub Taxonomy {  sub Taxonomy {
2754      # Get the parameters.      # Get the parameters.
2755      my ($self, $genome) = @_;      my ($self, $genome) = @_;
     # Find the specified genome's taxonomy string.  
     my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);  
2756      # Declare the return variable.      # Declare the return variable.
2757      my @retVal = ();      my @retVal = ();
2758      # If we found the genome, return its taxonomy string.      # Get the genome data.
2759      if ($list) {      my $genomeData = $self->_GenomeData($genome);
2760          @retVal = split /\s*;\s*/, $list;      # Only proceed if it exists.
2761        if (defined $genomeData) {
2762            # Create the taxonomy from the taxonomy string.
2763            @retVal = split /\s*;\s*/, $genomeData->PrimaryValue('Genome(taxonomy)');
2764      } else {      } else {
2765            # Genome doesn't exist, so emit a warning.
2766          Trace("Genome \"$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);
2767      }      }
2768      # Return the value found.      # Return the value found.
# Line 2740  Line 2807 
2807      }      }
2808      my @taxA = $self->Taxonomy($genomeA);      my @taxA = $self->Taxonomy($genomeA);
2809      my @taxB = $self->Taxonomy($genomeB);      my @taxB = $self->Taxonomy($genomeB);
2810      # Initialize the distance to 1. We'll reduce it each time we find a match between the      # Compute the distance.
2811      # 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;  
     }  
2812      return $retVal;      return $retVal;
2813  }  }
2814    
# Line 3215  Line 3273 
3273      # Get the parameters.      # Get the parameters.
3274      my ($self, $featureID, $function, $userID) = @_;      my ($self, $featureID, $function, $userID) = @_;
3275      # 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.
3276      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);      my $bbhData = FIGRules::BBHData($featureID);
3277        my @bbhFeatures = map { $_->[0] } @$bbhData;
3278      # 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
3279      # functional assignment.      # functional assignment.
3280      my @retVal = ();      my @retVal = ();
# Line 3388  Line 3447 
3447    
3448  =head3 BBHMatrix  =head3 BBHMatrix
3449    
3450      my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);      my $bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3451    
3452  Find all the bidirectional best hits for the features of a genome in a  Find all the bidirectional best hits for the features of a genome in a
3453  specified list of target genomes. The return value will be a hash mapping  specified list of target genomes. The return value will be a hash mapping
# Line 3412  Line 3471 
3471    
3472  =item RETURN  =item RETURN
3473    
3474  Returns a hash mapping each feature in the original genome to a hash mapping its  Returns a reference to a hash mapping each feature in the original genome
3475  BBH pegs in the target genomes to their scores.  to a sub-hash mapping its BBH pegs in the target genomes to their scores.
3476    
3477  =back  =back
3478    
# Line 3426  Line 3485 
3485      my %retVal = ();      my %retVal = ();
3486      # Ask for the BBHs.      # Ask for the BBHs.
3487      my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);      my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3488        Trace("Retrieved " . scalar(@bbhList) . " BBH results.") if T(3);
3489      # 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.
3490      for my $bbhData (@bbhList) {      for my $bbhData (@bbhList) {
3491          my ($peg1, $peg2, $score) = @{$bbhData};          my ($peg1, $peg2, $score) = @{$bbhData};
# Line 3436  Line 3496 
3496          }          }
3497      }      }
3498      # Return the result.      # Return the result.
3499      return %retVal;      return \%retVal;
3500  }  }
3501    
3502    
# Line 3542  Line 3602 
3602      # Create the return hash.      # Create the return hash.
3603      my %retVal = ();      my %retVal = ();
3604      # Query for the desired BBHs.      # Query for the desired BBHs.
3605      my @bbhList = FIGRules::BBHData($featureID, $cutoff);      my $bbhList = FIGRules::BBHData($featureID, $cutoff);
3606      # Form the results into the return hash.      # Form the results into the return hash.
3607      for my $pair (@bbhList) {      for my $pair (@$bbhList) {
3608          my $fid = $pair->[0];          my $fid = $pair->[0];
3609          if ($self->Exists('Feature', $fid)) {          if ($self->Exists('Feature', $fid)) {
3610              $retVal{$fid} = $pair->[1];              $retVal{$fid} = $pair->[1];
# Line 3942  Line 4002 
4002    
4003  =over 4  =over 4
4004    
4005  =item page  =item specials
4006    
4007  The super-group's web page in the NMPDR.  Reference to a hash whose keys are the names of special species.
4008    
4009  =item contents  =item contents
4010    
# Line 3967  Line 4027 
4027          my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");          my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
4028          # Loop through the list of sort-of groups.          # Loop through the list of sort-of groups.
4029          for my $groupLine (@groupLines) {          for my $groupLine (@groupLines) {
4030              my ($name, $page, @contents) = split /\t/, $groupLine;              my ($name, $specials, @contents) = split /\t/, $groupLine;
4031              $groupHash{$name} = { page => $page,              $groupHash{$name} = { specials => { map { $_ => 1 } split /\s*,\s*/, $specials },
4032                                    contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]                                    contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
4033                                  };                                  };
4034          }          }
# Line 4027  Line 4087 
4087  =cut  =cut
4088    
4089  sub GetSourceObject {  sub GetSourceObject {
4090      # Get access to the FIG code.      # Get the parameters.
4091        my ($self) = @_;
4092        # Do we already have one?
4093        my $retVal = $self->{fig};
4094        if (! defined $retVal) {
4095            # Create the object.
4096      require FIG;      require FIG;
4097      # Return a FIG object.          $retVal = FIG->new();
4098      return FIG->new();          Trace("FIG source object created for process $$.") if T(ERDBLoadGroup => 3);
4099            # Set up retries to prevent the lost-connection error when harvesting
4100            # the feature data.
4101            my $dbh = $retVal->db_handle();
4102            $dbh->set_retries(5);
4103            # Save it for other times.
4104            $self->{fig} = $retVal;
4105        }
4106        # Return the object.
4107        return $retVal;
4108  }  }
4109    
4110  =head3 SectionList  =head3 SectionList
4111    
4112      my @sections = $erdb->SectionList($source);      my @sections = $erdb->SectionList($fig);
4113    
4114  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.
4115  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
4116  entire database.  entire database.
4117    
 =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  
   
4118  =cut  =cut
4119    
4120  sub SectionList {  sub SectionList {
# Line 4070  Line 4129 
4129    
4130  =head3 Loader  =head3 Loader
4131    
4132      my $groupLoader = $erdb->Loader($groupName, $source, $options);      my $groupLoader = $erdb->Loader($groupName, $options);
4133    
4134  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
4135  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 4142 
4142  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
4143  guaranteed to be a single word with only the first letter capitalized.  guaranteed to be a single word with only the first letter capitalized.
4144    
 =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.  
   
4145  =item options  =item options
4146    
4147  Reference to a hash of command-line options.  Reference to a hash of command-line options.
# Line 4105  Line 4157 
4157    
4158  sub Loader {  sub Loader {
4159      # Get the parameters.      # Get the parameters.
4160      my ($self, $groupName, $source, $options) = @_;      my ($self, $groupName, $options) = @_;
4161      # Compute the loader name.      # Compute the loader name.
4162      my $loaderClass = "${groupName}SproutLoader";      my $loaderClass = "${groupName}SproutLoader";
4163      # Pull in its definition.      # Pull in its definition.
4164      require "$loaderClass.pm";      require "$loaderClass.pm";
4165      # Create an object for it.      # Create an object for it.
4166      my $retVal = eval("$loaderClass->new(\$self, \$source, \$options)");      my $retVal = eval("$loaderClass->new(\$self, \$options)");
4167      # Insure it worked.      # Insure it worked.
4168      Confess("Could not create $loaderClass object: $@") if $@;      Confess("Could not create $loaderClass object: $@") if $@;
4169      # Return it to the caller.      # Return it to the caller.
4170      return $retVal;      return $retVal;
4171  }  }
4172    
4173    
4174  =head3 LoadGroupList  =head3 LoadGroupList
4175    
4176      my @groups = $erdb->LoadGroupList();      my @groups = $erdb->LoadGroupList();
# Line 4130  Line 4183 
4183    
4184  sub LoadGroupList {  sub LoadGroupList {
4185      # Return the list.      # Return the list.
4186      return qw(Genome Subsystem Annotation Property Source Reaction Synonym Drug Feature);      return qw(Feature Subsystem Genome Annotation Property Source Reaction Synonym Drug);
4187  }  }
4188    
4189  =head3 LoadDirectory  =head3 LoadDirectory
# Line 4168  Line 4221 
4221          # 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.
4222          $retVal = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",          $retVal = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
4223                                   stops => "$FIG_Config::sproutData/StopWords.txt",                                   stops => "$FIG_Config::sproutData/StopWords.txt",
4224                                   cache => 1);                                   cache => 0);
4225          $self->{stemmer} = $retVal;          $self->{stemmer} = $retVal;
4226      }      }
4227      # Return the result.      # Return the result.
# Line 4261  Line 4314 
4314      # Get the parameters.      # Get the parameters.
4315      my ($self, $fid) = @_;      my ($self, $fid) = @_;
4316      # Insure we have a genome hash.      # Insure we have a genome hash.
4317      if (! defined $self->{genomeHash}) {      my $genomes = $self->_GenomeHash();
         my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');  
         $self->{genomeHash} = \%genomeHash;  
     }  
4318      # Get the feature's genome ID.      # Get the feature's genome ID.
4319      my ($genomeID) = FIGRules::ParseFeatureID($fid);      my ($genomeID) = FIGRules::ParseFeatureID($fid);
4320      # 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 4300  Line 4350 
4350    
4351  =head3 Hint  =head3 Hint
4352    
4353      my $htmlText = SearchHelper::Hint($wikiPage, $hintText);      my $htmlText = Sprout::Hint($wikiPage, $hintID);
4354    
4355  Return the HTML for a small question mark that displays the specified hint text when it is clicked.  Return the HTML for a help link that displays the specified hint text when it is clicked.
4356  This HTML can be put in forms to provide a useful hinting mechanism.  This HTML can be put in forms to provide a useful hinting mechanism.
4357    
4358  =over 4  =over 4
# Line 4311  Line 4361 
4361    
4362  Name of the wiki page to be popped up when the hint mark is clicked.  Name of the wiki page to be popped up when the hint mark is clicked.
4363    
4364  =item hintText  =item hintID
4365    
4366  Text to display for the hint. It is raw html, but may not contain any double quotes.  ID of the text to display for the hint. This should correspond to a tip number
4367    in the Wiki.
4368    
4369  =item RETURN  =item RETURN
4370    
4371  Returns the html for the hint facility. The resulting html shows a small button-like thing that  Returns the html for the hint facility. The resulting html shows the word "help" and
4372  uses the standard FIG popup technology.  uses the standard FIG popup technology.
4373    
4374  =back  =back
# Line 4326  Line 4377 
4377    
4378  sub Hint {  sub Hint {
4379      # Get the parameters.      # Get the parameters.
4380      my ($wikiPage, $hintText) = @_;      my ($wikiPage, $hintID) = @_;
4381      # Escape the single quotes in the hint text.      # Declare the return variable.
4382      my $quotedText = $hintText;      my $retVal;
     $quotedText =~ s/'/\\'/g;  
4383      # Convert the wiki page name to a URL.      # Convert the wiki page name to a URL.
4384      my $wikiURL = join("", map { ucfirst $_ } split /\s+/, $wikiPage);      my $wikiURL;
4385      $wikiURL = "$FIG_Config::cgi_url/wiki/view.cgi/FIG/$wikiURL";      if ($wikiPage =~ m#/#) {
4386      # Compute the mouseover script.          # Here it's a URL of some sort.
4387      my $mouseOver = "doTooltip(this, '$quotedText')";          $wikiURL = $wikiPage;
4388      # Create the html.      } else {
4389      my $retVal = "&nbsp;<a href=\"$wikiURL\"><img src=\"$FIG_Config::cgi_url/Html/button-h.png\" class=\"helpicon\" onmouseover=\"$mouseOver\"/></a>";          # Here it's a wiki page.
4390      # Return it.          my $page = join("", map { ucfirst $_ } split /\s+/, $wikiPage);
4391            if ($page =~ /^(.+?)\.(.+)$/) {
4392                $page = "$1/$2";
4393            } else {
4394                $page = "FIG/$page";
4395            }
4396            $wikiURL = "$FIG_Config::cgi_url/wiki/view.cgi/$page";
4397        }
4398        # Is there hint text?
4399        if (! $hintID) {
4400            # No. Create a new-page hint.
4401            $retVal = qq(&nbsp;<a class="hint" onclick="doPagePopup(this, '$wikiURL')">(help)</a>);
4402        } else {
4403            # With hint text, we create a popup window hint. We need to compute the hint URL.
4404            my $tipURL = "$FIG_Config::cgi_url/wiki/view.cgi/FIG/TWikiCustomTip" .
4405                Tracer::Pad($hintID, 3, 1, "0");
4406            # Create a hint pop-up link.
4407            $retVal = qq(&nbsp;<a class="hint" onclick="doHintPopup(this, '$wikiURL', '$tipURL')">(help)</a>);
4408        }
4409        # Return the HTML.
4410      return $retVal;      return $retVal;
4411  }  }
4412    
4413    =head3 _GenomeHash
4414    
4415        my $gHash = $sprout->_GenomeHash();
4416    
4417    Return a hash mapping all NMPDR genome IDs to [[ERDBObjectPm]] genome objects.
4418    
4419    =cut
4420    
4421    sub _GenomeHash {
4422        # Get the parameters.
4423        my ($self) = @_;
4424        # Do we already have a filled hash?
4425        if (! $self->{genomeHashFilled}) {
4426            # No, create it.
4427            my %gHash = map { $_->PrimaryValue('id') => $_ } $self->GetList("Genome", "", []);
4428            $self->{genomeHash} = \%gHash;
4429            # Denote we have it.
4430            $self->{genomeHashFilled} = 1;
4431        }
4432        # Return the hash.
4433        return $self->{genomeHash};
4434    }
4435    
4436    =head3 _GenomeData
4437    
4438        my $genomeData = $sprout->_GenomeData($genomeID);
4439    
4440    Return an [[ERDBObjectPm]] object for the specified genome, or an undefined
4441    value if the genome does not exist.
4442    
4443    =over 4
4444    
4445    =item genomeID
4446    
4447    ID of the desired genome.
4448    
4449    =item RETURN
4450    
4451    Returns either an [[ERDBObjectPm]] containing the genome, or an undefined value.
4452    If the genome exists, it will have been read into the genome cache.
4453    
4454    =back
4455    
4456    =cut
4457    
4458    sub _GenomeData {
4459        # Get the parameters.
4460        my ($self, $genomeID) = @_;
4461        # Are we in the genome hash?
4462        if (! exists $self->{genomeHash}->{$genomeID} && ! $self->{genomeHashFilled}) {
4463            # The genome isn't in the hash, and the hash is not complete, so we try to
4464            # read it.
4465            $self->{genomeHash}->{$genomeID} = $self->GetEntity(Genome => $genomeID);
4466        }
4467        # Return the result.
4468        return $self->{genomeHash}->{$genomeID};
4469    }
4470    
4471    =head3 _CacheGenome
4472    
4473        $sprout->_CacheGenome($genomeID, $genomeData);
4474    
4475    Store the specified genome object in the genome cache if it is already there.
4476    
4477    =over 4
4478    
4479    =item genomeID
4480    
4481    ID of the genome to store in the cache.
4482    
4483    =item genomeData
4484    
4485    An [[ERDBObjectPm]] containing at least the data for the specified genome.
4486    Note that the Genome may not be the primary object in it, so a fully-qualified
4487    field name has to be used to retrieve data from it.
4488    
4489    =back
4490    
4491    =cut
4492    
4493    sub _CacheGenome {
4494        # Get the parameters.
4495        my ($self, $genomeID, $genomeData) = @_;
4496        # Only proceed if we don't already have the genome.
4497        if (! exists $self->{genomeHash}->{$genomeID}) {
4498            $self->{genomeHash}->{$genomeID} = $genomeData;
4499        }
4500    }
4501    
4502  1;  1;

Legend:
Removed from v.1.121  
changed lines
  Added in v.1.126

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3