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

Diff of /Sprout/SproutLoad.pm

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

revision 1.47, Fri Jun 30 18:31:34 2006 UTC revision 1.68, Sun Sep 24 17:14:16 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 136  Line 136 
136      # We only need it if load-only is NOT specified.      # We only need it if load-only is NOT specified.
137      if (! $options->{loadOnly}) {      if (! $options->{loadOnly}) {
138          if (! defined $subsysFile || $subsysFile eq '') {          if (! defined $subsysFile || $subsysFile eq '') {
139              # Here we want all the NMPDR subsystems. First we get the whole list.              # Here we want all the usable subsystems. First we get the whole list.
140              my @subs = $fig->all_subsystems();              my @subs = $fig->all_subsystems();
141              # Loop through, checking for the NMPDR file.              # Loop through, checking for usability.
142              for my $sub (@subs) {              for my $sub (@subs) {
143                  if (-e "$FIG_Config::data/Subsystems/$sub/NMPDR") {                  if ($fig->usable_subsystem($sub)) {
144                      $subsystems{$sub} = 1;                      $subsystems{$sub} = 1;
145                  }                  }
146              }              }
# Line 266  Line 266 
266              my $extra = join " ", @extraData;              my $extra = join " ", @extraData;
267              # Get the full taxonomy.              # Get the full taxonomy.
268              my $taxonomy = $fig->taxonomy_of($genomeID);              my $taxonomy = $fig->taxonomy_of($genomeID);
269                # Open the NMPDR group file for this genome.
270                my $group;
271                if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&
272                    defined($group = <TMP>)) {
273                    # Clean the line ending.
274                    chomp $group;
275                } else {
276                    # No group, so use the default.
277                    $group = $FIG_Config::otherGroup;
278                }
279                close TMP;
280              # Output the genome record.              # Output the genome record.
281              $loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus,              $loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus,
282                               $species, $extra, $taxonomy);                               $group, $species, $extra, $taxonomy);
283              # Now we loop through each of the genome's contigs.              # Now we loop through each of the genome's contigs.
284              my @contigs = $fig->all_contigs($genomeID);              my @contigs = $fig->all_contigs($genomeID);
285              for my $contigID (@contigs) {              for my $contigID (@contigs) {
# Line 340  Line 351 
351      my $fig = $self->{fig};      my $fig = $self->{fig};
352      # Get the genome hash.      # Get the genome hash.
353      my $genomeFilter = $self->{genomes};      my $genomeFilter = $self->{genomes};
354      my $genomeCount = (keys %{$genomeFilter});      # Set up an ID counter for the PCHs.
355      my $featureCount = $genomeCount * 4000;      my $pchID = 0;
356      # Start the loads.      # Start the loads.
357      my $loadCoupling = $self->_TableLoader('Coupling');      my $loadCoupling = $self->_TableLoader('Coupling');
358      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);
# Line 411  Line 422 
422                              }                              }
423                          }                          }
424                          for my $evidenceID (keys %evidenceMap) {                          for my $evidenceID (keys %evidenceMap) {
425                                # Get the ID for this evidence.
426                                $pchID++;
427                              # Create the evidence record.                              # Create the evidence record.
428                              my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};                              my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};
429                              $loadPCH->Put($evidenceID, $usage);                              $loadPCH->Put($pchID, $usage);
430                              # Connect it to the coupling.                              # Connect it to the coupling.
431                              $loadIsEvidencedBy->Put($coupleID, $evidenceID);                              $loadIsEvidencedBy->Put($coupleID, $pchID);
432                              # Connect it to the features.                              # Connect it to the features.
433                              $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);                              $loadUsesAsEvidence->Put($pchID, $peg3, 1);
434                              $loadUsesAsEvidence->Put($evidenceID, $peg4, 2);                              $loadUsesAsEvidence->Put($pchID, $peg4, 2);
435                          }                          }
436                      }                      }
437                  }                  }
# Line 486  Line 499 
499              $loadFeature->Add("genomeIn");              $loadFeature->Add("genomeIn");
500              # Get the feature list for this genome.              # Get the feature list for this genome.
501              my $features = $fig->all_features_detailed($genomeID);              my $features = $fig->all_features_detailed($genomeID);
502                # Sort and count the list.
503                my @featureTuples = sort { $a->[0] cmp $b->[0] } @{$features};
504                my $count = scalar @featureTuples;
505                Trace("$count features found for genome $genomeID.") if T(3);
506                # Set up for our duplicate-feature check.
507                my $oldFeatureID = "";
508              # Loop through the features.              # Loop through the features.
509              for my $featureData (@{$features}) {              for my $featureTuple (@featureTuples) {
                 $loadFeature->Add("featureIn");  
510                  # Split the tuple.                  # Split the tuple.
511                  my ($featureID, $locations, undef, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureTuple};
512                    # Check for duplicates.
513                    if ($featureID eq $oldFeatureID) {
514                        Trace("Duplicate feature $featureID found.") if T(1);
515                    } else {
516                        $oldFeatureID = $featureID;
517                        # Count this feature.
518                        $loadFeature->Add("featureIn");
519                        # Get the functional assignment.
520                        my $assignment = $fig->function_of($featureID);
521                  # Create the feature record.                  # Create the feature record.
522                  $loadFeature->Put($featureID, 1, $type);                      $loadFeature->Put($featureID, 1, $type, $assignment);
523                  # Link it to the parent genome.                  # Link it to the parent genome.
524                  $loadHasFeature->Put($genomeID, $featureID, $type);                  $loadHasFeature->Put($genomeID, $featureID, $type);
525                  # Create the aliases.                  # Create the aliases.
# Line 546  Line 573 
573              }              }
574          }          }
575      }      }
576        }
577      # Finish the loads.      # Finish the loads.
578      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
579      return $retVal;      return $retVal;
# Line 594  Line 622 
622              Trace("Processing features for genome $genomeID.") if T(3);              Trace("Processing features for genome $genomeID.") if T(3);
623              # Get the feature list for this genome.              # Get the feature list for this genome.
624              my $features = $fig->all_features_detailed($genomeID);              my $features = $fig->all_features_detailed($genomeID);
625                # Count the BBHs we find.
626                my $bbhCount = 0;
627              # Loop through the features.              # Loop through the features.
628              for my $featureData (@{$features}) {              for my $featureData (@{$features}) {
629                  # Split the tuple.                  # Split the tuple.
# Line 609  Line 639 
639                      if ($genomeHash->{$targetGenomeID}) {                      if ($genomeHash->{$targetGenomeID}) {
640                          $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,                          $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,
641                                                             $score);                                                             $score);
642                            $bbhCount++;
643                      }                      }
644                  }                  }
645              }              }
646                Trace("$bbhCount BBHs found for $genomeID.") if T(3);
647          }          }
648      }      }
649      # Finish the loads.      # Finish the loads.
# Line 723  Line 755 
755                  my $curator = $sub->get_curator();                  my $curator = $sub->get_curator();
756                  my $notes = $sub->get_notes();                  my $notes = $sub->get_notes();
757                  $loadSubsystem->Put($subsysID, $curator, $notes);                  $loadSubsystem->Put($subsysID, $curator, $notes);
758                  my $class = $fig->subsystem_classification($subsysID);                  my $classList = $fig->subsystem_classification($subsysID);
759                  if ($class) {                  my @classes = @$classList;
760                    if (@classes) {
761                        for my $class (@classes) {
762                      $loadSubsystemClass->Put($subsysID, $class);                      $loadSubsystemClass->Put($subsysID, $class);
763                  }                  }
764                    }
765                  # 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.
766                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
767                      # Connect to this role.                      # Connect to this role.
# Line 843  Line 878 
878                      }                      }
879                  }                  }
880              }              }
881            }
882              # Now we loop through the diagrams. We need to create the diagram records              # Now we loop through the diagrams. We need to create the diagram records
883              # and link each diagram to its roles. Note that only roles which occur              # and link each diagram to its roles. Note that only roles which occur
884              # in subsystems (and therefore appear in the %ecToRoles hash) are              # in subsystems (and therefore appear in the %ecToRoles hash) are
# Line 876  Line 912 
912                  }                  }
913              }              }
914          }          }
     }  
915      # Finish the load.      # Finish the load.
916      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
917      return $retVal;      return $retVal;
# Line 929  Line 964 
964          my %propertyKeys = ();          my %propertyKeys = ();
965          my $nextID = 1;          my $nextID = 1;
966          # Loop through the genomes.          # Loop through the genomes.
967          for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
968              $loadProperty->Add("genomeIn");              $loadProperty->Add("genomeIn");
969              Trace("Generating properties for $genomeID.") if T(3);              Trace("Generating properties for $genomeID.") if T(3);
970              # Get the genome's features. The feature ID is the first field in the              # Get the genome's features. The feature ID is the first field in the
# Line 1211  Line 1246 
1246      } else {      } else {
1247          Trace("Generating external data.") if T(2);          Trace("Generating external data.") if T(2);
1248          # We loop through the files one at a time. First, the organism file.          # We loop through the files one at a time. First, the organism file.
1249          Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1250          my $orgLine;          my $orgLine;
1251          while (defined($orgLine = <ORGS>)) {          while (defined($orgLine = <ORGS>)) {
1252              # Clean the input line.              # Clean the input line.
# Line 1223  Line 1258 
1258          close ORGS;          close ORGS;
1259          # Now the function file.          # Now the function file.
1260          my $funcLine;          my $funcLine;
1261          Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1262          while (defined($funcLine = <FUNCS>)) {          while (defined($funcLine = <FUNCS>)) {
1263              # Clean the line ending.              # Clean the line ending.
1264              chomp $funcLine;              chomp $funcLine;
# Line 1355  Line 1390 
1390    
1391      GenomeGroups      GenomeGroups
1392    
1393  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,
1394    butThere is no direct support for genome groups in FIG, so we access the SEED
1395  files directly.  files directly.
1396    
1397  =over 4  =over 4
# Line 1381  Line 1417 
1417          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1418      } else {      } else {
1419          Trace("Generating group data.") if T(2);          Trace("Generating group data.") if T(2);
1420          # 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;  
         }  
1421      }      }
1422      # Finish the load.      # Finish the load.
1423      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 1414  Line 1436 
1436      IsSynonymGroupFor      IsSynonymGroupFor
1437    
1438  The source information for these relations is taken from the C<maps_to_id> method  The source information for these relations is taken from the C<maps_to_id> method
1439  of the B<FIG> object. The process starts from the features, so it is possible  of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1440  that there will be duplicates in the SynonymGroup load file, since the relationship  SQL against the FIG database.
 is one-to-many toward the features. The automatic sort on primary entity relations  
 will fix this for us.  
1441    
1442  =over 4  =over 4
1443    
# Line 1443  Line 1463 
1463          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1464      } else {      } else {
1465          Trace("Generating synonym group data.") if T(2);          Trace("Generating synonym group data.") if T(2);
1466            # Get the database handle.
1467            my $dbh = $fig->db_handle();
1468            # Ask for the synonyms.
1469            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1470            my $result = $sth->execute();
1471            if (! defined($result)) {
1472                Confess("Database error in Synonym load: " . $sth->errstr());
1473            } else {
1474                # Remember the current synonym.
1475                my $current_syn = "";
1476                # Count the features.
1477                my $featureCount = 0;
1478                # Loop through the synonym/peg pairs.
1479                while (my @row = $sth->fetchrow()) {
1480                    # Get the synonym ID and feature ID.
1481                    my ($syn_id, $peg) = @row;
1482                    # Insure it's for one of our genomes.
1483                    my $genomeID = FIG::genome_of($peg);
1484                    if (exists $genomeHash->{$genomeID}) {
1485                        # Verify the synonym.
1486                        if ($syn_id ne $current_syn) {
1487                            # It's new, so put it in the group table.
1488                            $loadSynonymGroup->Put($syn_id);
1489                            $current_syn = $syn_id;
1490                        }
1491                        # Connect the synonym to the peg.
1492                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1493                        # Count this feature.
1494                        $featureCount++;
1495                        if ($featureCount % 1000 == 0) {
1496                            Trace("$featureCount features processed.") if T(3);
1497                        }
1498                    }
1499                }
1500            }
1501        }
1502        # Finish the load.
1503        my $retVal = $self->_FinishAll();
1504        return $retVal;
1505    }
1506    
1507    =head3 LoadFamilyData
1508    
1509    C<< my $stats = $spl->LoadFamilyData(); >>
1510    
1511    Load the protein families into Sprout.
1512    
1513    The following relations are loaded by this method.
1514    
1515        Family
1516        IsFamilyForFeature
1517    
1518    The source information for these relations is taken from the C<families_for_protein>,
1519    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1520    
1521    =over 4
1522    
1523    =item RETURNS
1524    
1525    Returns a statistics object for the loads.
1526    
1527    =back
1528    
1529    =cut
1530    #: Return Type $%;
1531    sub LoadFamilyData {
1532        # Get this object instance.
1533        my ($self) = @_;
1534        # Get the FIG object.
1535        my $fig = $self->{fig};
1536        # Get the genome hash.
1537        my $genomeHash = $self->{genomes};
1538        # Create load objects for the tables we're loading.
1539        my $loadFamily = $self->_TableLoader('Family');
1540        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1541        if ($self->{options}->{loadOnly}) {
1542            Trace("Loading from existing files.") if T(2);
1543        } else {
1544            Trace("Generating family data.") if T(2);
1545            # Create a hash for the family IDs.
1546            my %familyHash = ();
1547          # Loop through the genomes.          # Loop through the genomes.
1548          for my $genomeID (sort keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1549              Trace("Processing $genomeID.") if T(3);              Trace("Processing features for $genomeID.") if T(2);
1550              # Get all of the features for this genome. The only method that does this is              # Loop through this genome's PEGs.
1551              # all_features_detailed, which returns extra baggage that we discard.              for my $fid ($fig->all_features($genomeID, "peg")) {
1552              my $featureData = $fig->all_features_detailed($genomeID);                  $loadIsFamilyForFeature->Add("features", 1);
1553              my @fids = map { $_->[0] } @{$featureData};                  # Get this feature's families.
1554              Trace(scalar(@fids) . " features found for genome $genomeID.") if T(3);                  my @families = $fig->families_for_protein($fid);
1555              # Loop through the feature IDs.                  # Loop through the families, connecting them to the feature.
1556              for my $fid (@fids) {                  for my $family (@families) {
1557                  # Get the group for this feature.                      $loadIsFamilyForFeature->Put($family, $fid);
1558                  my $synonym = $fig->maps_to_id($fid);                      # If this is a new family, create a record for it.
1559                  # Only proceed if the synonym is a real group.                      if (! exists $familyHash{$family}) {
1560                  if ($synonym ne $fid) {                          $familyHash{$family} = 1;
1561                      $loadSynonymGroup->Put($synonym);                          $loadFamily->Add("families", 1);
1562                      $loadIsSynonymGroupFor->Put($synonym, $fid);                          my $size = $fig->sz_family($family);
1563                            my $func = $fig->family_function($family);
1564                            $loadFamily->Put($family, $size, $func);
1565                        }
1566                  }                  }
1567              }              }
1568          }          }
# Line 1468  Line 1572 
1572      return $retVal;      return $retVal;
1573  }  }
1574    
   
1575  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1576    
1577  =head3 TableLoader  =head3 TableLoader
# Line 1536  Line 1639 
1639      my $retVal = Stats->new();      my $retVal = Stats->new();
1640      # Get the loader list.      # Get the loader list.
1641      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1642        # Create a hash to hold the statistics objects, keyed on relation name.
1643        my %loaderHash = ();
1644      # Loop through the list, finishing the loads. Note that if the finish fails, we die      # Loop through the list, finishing the loads. Note that if the finish fails, we die
1645      # ignominiously. At some future point, we want to make the loads restartable.      # ignominiously. At some future point, we want to make the loads more restartable.
1646      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1647          # Get the relation name.          # Get the relation name.
1648          my $relName = $loader->RelName;          my $relName = $loader->RelName;
# Line 1548  Line 1653 
1653              # Here we really need to finish.              # Here we really need to finish.
1654              Trace("Finishing $relName.") if T(2);              Trace("Finishing $relName.") if T(2);
1655              my $stats = $loader->Finish();              my $stats = $loader->Finish();
1656                $loaderHash{$relName} = $stats;
1657            }
1658        }
1659        # Now we loop through again, actually loading the tables. We want to finish before
1660        # loading so that if something goes wrong at this point, all the load files are usable
1661        # and we don't have to redo all that work.
1662        for my $relName (sort keys %loaderHash) {
1663            # Get the statistics for this relation.
1664            my $stats = $loaderHash{$relName};
1665            # Check for a database load.
1666              if ($self->{options}->{dbLoad}) {              if ($self->{options}->{dbLoad}) {
1667                  # Here we want to use the load file just created to load the database.                  # Here we want to use the load file just created to load the database.
1668                  Trace("Loading relation $relName.") if T(2);                  Trace("Loading relation $relName.") if T(2);
# Line 1558  Line 1673 
1673              $retVal->Accumulate($stats);              $retVal->Accumulate($stats);
1674              Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);              Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1675          }          }
     }  
1676      # Return the load statistics.      # Return the load statistics.
1677      return $retVal;      return $retVal;
1678  }  }

Legend:
Removed from v.1.47  
changed lines
  Added in v.1.68

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3