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

Diff of /Sprout/SproutLoad.pm

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

revision 1.57, Sat Jul 15 08:09:13 2006 UTC revision 1.74, Sat Oct 21 06:44:17 2006 UTC
# Line 120  Line 120 
120                      # an omitted access code can be defaulted to 1.                      # an omitted access code can be defaulted to 1.
121                      for my $genomeLine (@genomeList) {                      for my $genomeLine (@genomeList) {
122                          my ($genomeID, $accessCode) = split("\t", $genomeLine);                          my ($genomeID, $accessCode) = split("\t", $genomeLine);
123                          if (undef $accessCode) {                          if (! defined($accessCode)) {
124                              $accessCode = 1;                              $accessCode = 1;
125                          }                          }
126                          $genomes{$genomeID} = $accessCode;                          $genomes{$genomeID} = $accessCode;
# Line 163  Line 163 
163                  Confess("Invalid subsystem parameter in SproutLoad constructor.");                  Confess("Invalid subsystem parameter in SproutLoad constructor.");
164              }              }
165          }          }
166            # Go through the subsys hash again, creating the keyword list for each subsystem.
167            for my $subsystem (keys %subsystems) {
168                my $name = $subsystem;
169                $name =~ s/_/ /g;
170                my $classes = $fig->subsystem_classification($subsystem);
171                my @classList = map { " $_" } @{$classes};
172                $name .= join("", @classList);
173                $subsystems{$subsystem} = $name;
174            }
175      }      }
176      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
177      my ($directory) = $sprout->LoadInfo();      my ($directory) = $sprout->LoadInfo();
# Line 266  Line 275 
275              my $extra = join " ", @extraData;              my $extra = join " ", @extraData;
276              # Get the full taxonomy.              # Get the full taxonomy.
277              my $taxonomy = $fig->taxonomy_of($genomeID);              my $taxonomy = $fig->taxonomy_of($genomeID);
278                # Open the NMPDR group file for this genome.
279                my $group;
280                if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&
281                    defined($group = <TMP>)) {
282                    # Clean the line ending.
283                    chomp $group;
284                } else {
285                    # No group, so use the default.
286                    $group = $FIG_Config::otherGroup;
287                }
288                close TMP;
289              # Output the genome record.              # Output the genome record.
290              $loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus,              $loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus,
291                               $species, $extra, $taxonomy);                               $group, $species, $extra, $taxonomy);
292              # Now we loop through each of the genome's contigs.              # Now we loop through each of the genome's contigs.
293              my @contigs = $fig->all_contigs($genomeID);              my @contigs = $fig->all_contigs($genomeID);
294              for my $contigID (@contigs) {              for my $contigID (@contigs) {
# Line 449  Line 469 
469      FeatureUpstream      FeatureUpstream
470      IsLocatedIn      IsLocatedIn
471      HasFeature      HasFeature
472        HasRoleInSubsystem
473    
474  =over 4  =over 4
475    
# Line 463  Line 484 
484  sub LoadFeatureData {  sub LoadFeatureData {
485      # Get this object instance.      # Get this object instance.
486      my ($self) = @_;      my ($self) = @_;
487      # Get the FIG object.      # Get the FIG and Sprout objects.
488      my $fig = $self->{fig};      my $fig = $self->{fig};
489        my $sprout = $self->{sprout};
490      # Get the table of genome IDs.      # Get the table of genome IDs.
491      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
492      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
# Line 474  Line 496 
496      my $loadFeatureLink = $self->_TableLoader('FeatureLink');      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
497      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
498      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
499      my $loadHasFeature = $self->_TableLoader('HasFeature');      my $loadHasFeature = $self->_TableLoader('HasFeature', $self->PrimaryOnly);
500        my $loadHasRoleInSubsystem = $self->_TableLoader('HasRoleInSubsystem', $self->PrimaryOnly);
501        # Get the subsystem hash.
502        my $subHash = $self->{subsystems};
503      # Get the maximum sequence size. We need this later for splitting up the      # Get the maximum sequence size. We need this later for splitting up the
504      # locations.      # locations.
505      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
# Line 505  Line 530 
530                      $oldFeatureID = $featureID;                      $oldFeatureID = $featureID;
531                      # Count this feature.                      # Count this feature.
532                      $loadFeature->Add("featureIn");                      $loadFeature->Add("featureIn");
533                      # Create the feature record.                      # Get the functional assignment.
534                      $loadFeature->Put($featureID, 1, $type);                      my $assignment = $fig->function_of($featureID);
535                      # Link it to the parent genome.                      # Begin building the keywords.
536                        my $keywords = "$assignment $genomeID";
537                        # Link this feature to the parent genome.
538                      $loadHasFeature->Put($genomeID, $featureID, $type);                      $loadHasFeature->Put($genomeID, $featureID, $type);
539                      # Create the aliases.                      # Create the aliases.
540                      for my $alias ($fig->feature_aliases($featureID)) {                      for my $alias ($fig->feature_aliases($featureID)) {
541                          $loadFeatureAlias->Put($featureID, $alias);                          $loadFeatureAlias->Put($featureID, $alias);
542                            $keywords .= " $alias";
543                      }                      }
544                      # Get the links.                      # Get the links.
545                      my @links = $fig->fid_links($featureID);                      my @links = $fig->fid_links($featureID);
# Line 531  Line 559 
559                              $loadFeatureUpstream->Put($featureID, $upstream);                              $loadFeatureUpstream->Put($featureID, $upstream);
560                          }                          }
561                      }                      }
562                        # Now we need to find the subsystems this feature participates in.
563                        # We also add the subsystems to the keyword list. Before we do that,
564                        # we must convert underscores to spaces and tack on the classifications.
565                        my @subsystems = $fig->peg_to_subsystems($featureID);
566                        for my $subsystem (@subsystems) {
567                            # Only proceed if we like this subsystem.
568                            if (exists $subHash->{$subsystem}) {
569                                # Store the has-role link.
570                                $loadHasRoleInSubsystem->Put($featureID, $subsystem, $genomeID, $type);
571                                # Save the subsystem's keyword data.
572                                my $subKeywords = $subHash->{$subsystem};
573                                $keywords .= " $subKeywords";
574                            }
575                        }
576                        # The final task is to add virulence and essentiality attributes.
577                        if ($fig->virulent($featureID)) {
578                            $keywords .= " virulent";
579                        }
580                        if ($fig->essential($featureID)) {
581                            $keywords .= " essential";
582                        }
583                        # Clean the keyword list.
584                        my $cleanWords = $sprout->CleanKeywords($keywords);
585                        # Create the feature record.
586                        $loadFeature->Put($featureID, 1, $type, $assignment, $cleanWords);
587                      # This part is the roughest. We need to relate the features to contig                      # This part is the roughest. We need to relate the features to contig
588                      # locations, and the locations must be split so that none of them exceed                      # locations, and the locations must be split so that none of them exceed
589                      # the maximum segment size. This simplifies the genes_in_region processing                      # the maximum segment size. This simplifies the genes_in_region processing
# Line 566  Line 619 
619      return $retVal;      return $retVal;
620  }  }
621    
 =head3 LoadBBHData  
   
 C<< my $stats = $spl->LoadBBHData(); >>  
   
 Load the bidirectional best hit data from FIG into Sprout.  
   
 Sprout does not store information on similarities. Instead, it has only the  
 bi-directional best hits. Even so, the BBH table is one of the largest in  
 the database.  
   
 The following relations are loaded by this method.  
   
     IsBidirectionalBestHitOf  
   
 =over 4  
   
 =item RETURNS  
   
 Returns a statistics object for the loads.  
   
 =back  
   
 =cut  
 #: Return Type $%;  
 sub LoadBBHData {  
     # Get this object instance.  
     my ($self) = @_;  
     # Get the FIG object.  
     my $fig = $self->{fig};  
     # Get the table of genome IDs.  
     my $genomeHash = $self->{genomes};  
     # Create load objects for each of the tables we're loading.  
     my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');  
     if ($self->{options}->{loadOnly}) {  
         Trace("Loading from existing files.") if T(2);  
     } else {  
         Trace("Generating BBH data.") if T(2);  
         # Now we loop through the genomes, generating the data for each one.  
         for my $genomeID (sort keys %{$genomeHash}) {  
             $loadIsBidirectionalBestHitOf->Add("genomeIn");  
             Trace("Processing features for genome $genomeID.") if T(3);  
             # Get the feature list for this genome.  
             my $features = $fig->all_features_detailed($genomeID);  
             # Loop through the features.  
             for my $featureData (@{$features}) {  
                 # Split the tuple.  
                 my ($featureID, $locations, $aliases, $type) = @{$featureData};  
                 # Get the bi-directional best hits.  
                 my @bbhList = $fig->bbhs($featureID);  
                 for my $bbhEntry (@bbhList) {  
                     # Get the target feature ID and the score.  
                     my ($targetID, $score) = @{$bbhEntry};  
                     # Check the target feature's genome.  
                     my $targetGenomeID = $fig->genome_of($targetID);  
                     # Only proceed if it's one of our genomes.  
                     if ($genomeHash->{$targetGenomeID}) {  
                         $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,  
                                                            $score);  
                     }  
                 }  
             }  
         }  
     }  
     # Finish the loads.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
 }  
   
622  =head3 LoadSubsystemData  =head3 LoadSubsystemData
623    
624  C<< my $stats = $spl->LoadSubsystemData(); >>  C<< my $stats = $spl->LoadSubsystemData(); >>
# Line 738  Line 723 
723                  my $curator = $sub->get_curator();                  my $curator = $sub->get_curator();
724                  my $notes = $sub->get_notes();                  my $notes = $sub->get_notes();
725                  $loadSubsystem->Put($subsysID, $curator, $notes);                  $loadSubsystem->Put($subsysID, $curator, $notes);
726                  my $class = $fig->subsystem_classification($subsysID);                  # Now for the classification string. This comes back as a list
727                  if ($class) {                  # reference and we convert it to a space-delimited string.
728                      $loadSubsystemClass->Put($subsysID, $class);                  my $classList = $fig->subsystem_classification($subsysID);
729                  }                  my $classString = join(" : ", grep { $_ } @$classList);
730                    $loadSubsystemClass->Put($subsysID, $classString);
731                  # Connect it to its roles. Each role is a column in the subsystem spreadsheet.                  # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
732                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
733                      # Connect to this role.                      # Connect to this role.
# Line 944  Line 930 
930          my %propertyKeys = ();          my %propertyKeys = ();
931          my $nextID = 1;          my $nextID = 1;
932          # Loop through the genomes.          # Loop through the genomes.
933          for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
934              $loadProperty->Add("genomeIn");              $loadProperty->Add("genomeIn");
935              Trace("Generating properties for $genomeID.") if T(3);              Trace("Generating properties for $genomeID.") if T(3);
936              # Get the genome's features. The feature ID is the first field in the              # Get the genome's features. The feature ID is the first field in the
# Line 958  Line 944 
944                  # Get all attributes for this feature. We do this one feature at a time                  # Get all attributes for this feature. We do this one feature at a time
945                  # to insure we do not get any genome attributes.                  # to insure we do not get any genome attributes.
946                  my @attributeList = $fig->get_attributes($fid, '', '', '');                  my @attributeList = $fig->get_attributes($fid, '', '', '');
947                    # Add essentiality and virulence attributes.
948                    if ($fig->essential($fid)) {
949                        push @attributeList, [$fid, 'essential', 1, ''];
950                    }
951                    if ($fig->virulent($fid)) {
952                        push @attributeList, [$fid, 'virulent', 1, ''];
953                    }
954                  if (scalar @attributeList) {                  if (scalar @attributeList) {
955                      $featureCount++;                      $featureCount++;
956                  }                  }
# Line 1226  Line 1219 
1219      } else {      } else {
1220          Trace("Generating external data.") if T(2);          Trace("Generating external data.") if T(2);
1221          # We loop through the files one at a time. First, the organism file.          # We loop through the files one at a time. First, the organism file.
1222          Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1223          my $orgLine;          my $orgLine;
1224          while (defined($orgLine = <ORGS>)) {          while (defined($orgLine = <ORGS>)) {
1225              # Clean the input line.              # Clean the input line.
# Line 1238  Line 1231 
1231          close ORGS;          close ORGS;
1232          # Now the function file.          # Now the function file.
1233          my $funcLine;          my $funcLine;
1234          Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1235          while (defined($funcLine = <FUNCS>)) {          while (defined($funcLine = <FUNCS>)) {
1236              # Clean the line ending.              # Clean the line ending.
1237              chomp $funcLine;              chomp $funcLine;
# Line 1370  Line 1363 
1363    
1364      GenomeGroups      GenomeGroups
1365    
1366  There is no direct support for genome groups in FIG, so we access the SEED  Currently, we do not use groups. We used to use them for NMPDR groups,
1367    butThere is no direct support for genome groups in FIG, so we access the SEED
1368  files directly.  files directly.
1369    
1370  =over 4  =over 4
# Line 1396  Line 1390 
1390          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1391      } else {      } else {
1392          Trace("Generating group data.") if T(2);          Trace("Generating group data.") if T(2);
1393          # Loop through the genomes.          # Currently there are no groups.
         my $line;  
         for my $genomeID (keys %{$genomeHash}) {  
             Trace("Processing $genomeID.") if T(3);  
             # Open the NMPDR group file for this genome.  
             if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&  
                 defined($line = <TMP>)) {  
                 # Clean the line ending.  
                 chomp $line;  
                 # Add the group to the table. Note that there can only be one group  
                 # per genome.  
                 $loadGenomeGroups->Put($genomeID, $line);  
             }  
             close TMP;  
         }  
1394      }      }
1395      # Finish the load.      # Finish the load.
1396      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 1459  Line 1439 
1439          # Get the database handle.          # Get the database handle.
1440          my $dbh = $fig->db_handle();          my $dbh = $fig->db_handle();
1441          # Ask for the synonyms.          # Ask for the synonyms.
1442          my $sth = $dbh->prepare_command("SELECT syn_id, maps_to FROM peg_synonyms ORDER BY syn_id");          my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1443          my $result = $sth->execute();          my $result = $sth->execute();
1444          if (! defined($result)) {          if (! defined($result)) {
1445              Confess("Database error in Synonym load: " . $sth->errstr());              Confess("Database error in Synonym load: " . $sth->errstr());
# Line 1497  Line 1477 
1477      return $retVal;      return $retVal;
1478  }  }
1479    
1480    =head3 LoadFamilyData
1481    
1482    C<< my $stats = $spl->LoadFamilyData(); >>
1483    
1484    Load the protein families into Sprout.
1485    
1486    The following relations are loaded by this method.
1487    
1488        Family
1489        IsFamilyForFeature
1490    
1491    The source information for these relations is taken from the C<families_for_protein>,
1492    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1493    
1494    =over 4
1495    
1496    =item RETURNS
1497    
1498    Returns a statistics object for the loads.
1499    
1500    =back
1501    
1502    =cut
1503    #: Return Type $%;
1504    sub LoadFamilyData {
1505        # Get this object instance.
1506        my ($self) = @_;
1507        # Get the FIG object.
1508        my $fig = $self->{fig};
1509        # Get the genome hash.
1510        my $genomeHash = $self->{genomes};
1511        # Create load objects for the tables we're loading.
1512        my $loadFamily = $self->_TableLoader('Family');
1513        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1514        if ($self->{options}->{loadOnly}) {
1515            Trace("Loading from existing files.") if T(2);
1516        } else {
1517            Trace("Generating family data.") if T(2);
1518            # Create a hash for the family IDs.
1519            my %familyHash = ();
1520            # Loop through the genomes.
1521            for my $genomeID (sort keys %{$genomeHash}) {
1522                Trace("Processing features for $genomeID.") if T(2);
1523                # Loop through this genome's PEGs.
1524                for my $fid ($fig->all_features($genomeID, "peg")) {
1525                    $loadIsFamilyForFeature->Add("features", 1);
1526                    # Get this feature's families.
1527                    my @families = $fig->families_for_protein($fid);
1528                    # Loop through the families, connecting them to the feature.
1529                    for my $family (@families) {
1530                        $loadIsFamilyForFeature->Put($family, $fid);
1531                        # If this is a new family, create a record for it.
1532                        if (! exists $familyHash{$family}) {
1533                            $familyHash{$family} = 1;
1534                            $loadFamily->Add("families", 1);
1535                            my $size = $fig->sz_family($family);
1536                            my $func = $fig->family_function($family);
1537                            $loadFamily->Put($family, $size, $func);
1538                        }
1539                    }
1540                }
1541            }
1542        }
1543        # Finish the load.
1544        my $retVal = $self->_FinishAll();
1545        return $retVal;
1546    }
1547    
1548    
1549    
1550  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1551    

Legend:
Removed from v.1.57  
changed lines
  Added in v.1.74

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3