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

Diff of /Sprout/SproutLoad.pm

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

revision 1.46, Mon Jun 26 19:13:16 2006 UTC revision 1.64, Sat Aug 12 08:43:37 2006 UTC
# 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 340  Line 340 
340      my $fig = $self->{fig};      my $fig = $self->{fig};
341      # Get the genome hash.      # Get the genome hash.
342      my $genomeFilter = $self->{genomes};      my $genomeFilter = $self->{genomes};
343      my $genomeCount = (keys %{$genomeFilter});      # Set up an ID counter for the PCHs.
344      my $featureCount = $genomeCount * 4000;      my $pchID = 0;
345      # Start the loads.      # Start the loads.
346      my $loadCoupling = $self->_TableLoader('Coupling');      my $loadCoupling = $self->_TableLoader('Coupling');
347      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);
# Line 375  Line 375 
375                  for my $coupleData (@couplings) {                  for my $coupleData (@couplings) {
376                      my ($peg2, $score) = @{$coupleData};                      my ($peg2, $score) = @{$coupleData};
377                      # Compute the coupling ID.                      # Compute the coupling ID.
378                      my $coupleID = Sprout::CouplingID($peg1, $peg2);                      my $coupleID = $self->{erdb}->CouplingID($peg1, $peg2);
379                      if (! exists $dupHash{$coupleID}) {                      if (! exists $dupHash{$coupleID}) {
380                          $loadCoupling->Add("couplingIn");                          $loadCoupling->Add("couplingIn");
381                          # Here we have a new coupling to store in the load files.                          # Here we have a new coupling to store in the load files.
# Line 411  Line 411 
411                              }                              }
412                          }                          }
413                          for my $evidenceID (keys %evidenceMap) {                          for my $evidenceID (keys %evidenceMap) {
414                                # Get the ID for this evidence.
415                                $pchID++;
416                              # Create the evidence record.                              # Create the evidence record.
417                              my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};                              my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};
418                              $loadPCH->Put($evidenceID, $usage);                              $loadPCH->Put($pchID, $usage);
419                              # Connect it to the coupling.                              # Connect it to the coupling.
420                              $loadIsEvidencedBy->Put($coupleID, $evidenceID);                              $loadIsEvidencedBy->Put($coupleID, $pchID);
421                              # Connect it to the features.                              # Connect it to the features.
422                              $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);                              $loadUsesAsEvidence->Put($pchID, $peg3, 1);
423                              $loadUsesAsEvidence->Put($evidenceID, $peg4, 2);                              $loadUsesAsEvidence->Put($pchID, $peg4, 2);
424                          }                          }
425                      }                      }
426                  }                  }
# Line 486  Line 488 
488              $loadFeature->Add("genomeIn");              $loadFeature->Add("genomeIn");
489              # Get the feature list for this genome.              # Get the feature list for this genome.
490              my $features = $fig->all_features_detailed($genomeID);              my $features = $fig->all_features_detailed($genomeID);
491                # Sort and count the list.
492                my @featureTuples = sort { $a->[0] cmp $b->[0] } @{$features};
493                my $count = scalar @featureTuples;
494                Trace("$count features found for genome $genomeID.") if T(3);
495                # Set up for our duplicate-feature check.
496                my $oldFeatureID = "";
497              # Loop through the features.              # Loop through the features.
498              for my $featureData (@{$features}) {              for my $featureTuple (@featureTuples) {
                 $loadFeature->Add("featureIn");  
499                  # Split the tuple.                  # Split the tuple.
500                  my ($featureID, $locations, undef, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureTuple};
501                    # Check for duplicates.
502                    if ($featureID eq $oldFeatureID) {
503                        Trace("Duplicate feature $featureID found.") if T(1);
504                    } else {
505                        $oldFeatureID = $featureID;
506                        # Count this feature.
507                        $loadFeature->Add("featureIn");
508                  # Create the feature record.                  # Create the feature record.
509                  $loadFeature->Put($featureID, 1, $type);                  $loadFeature->Put($featureID, 1, $type);
510                  # Link it to the parent genome.                  # Link it to the parent genome.
# Line 546  Line 560 
560              }              }
561          }          }
562      }      }
563        }
564      # Finish the loads.      # Finish the loads.
565      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
566      return $retVal;      return $retVal;
# Line 723  Line 738 
738                  my $curator = $sub->get_curator();                  my $curator = $sub->get_curator();
739                  my $notes = $sub->get_notes();                  my $notes = $sub->get_notes();
740                  $loadSubsystem->Put($subsysID, $curator, $notes);                  $loadSubsystem->Put($subsysID, $curator, $notes);
741                  my $class = $fig->subsystem_classification($subsysID);                  my $classList = $fig->subsystem_classification($subsysID);
742                  if ($class) {                  my @classes = @$classList;
743                    if (@classes) {
744                        for my $class (@classes) {
745                      $loadSubsystemClass->Put($subsysID, $class);                      $loadSubsystemClass->Put($subsysID, $class);
746                  }                  }
747                    }
748                  # 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.
749                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
750                      # Connect to this role.                      # Connect to this role.
# Line 843  Line 861 
861                      }                      }
862                  }                  }
863              }              }
864            }
865              # 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
866              # 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
867              # in subsystems (and therefore appear in the %ecToRoles hash) are              # in subsystems (and therefore appear in the %ecToRoles hash) are
# Line 876  Line 895 
895                  }                  }
896              }              }
897          }          }
     }  
898      # Finish the load.      # Finish the load.
899      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
900      return $retVal;      return $retVal;
# Line 1211  Line 1229 
1229      } else {      } else {
1230          Trace("Generating external data.") if T(2);          Trace("Generating external data.") if T(2);
1231          # We loop through the files one at a time. First, the organism file.          # We loop through the files one at a time. First, the organism file.
1232          Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1233          my $orgLine;          my $orgLine;
1234          while (defined($orgLine = <ORGS>)) {          while (defined($orgLine = <ORGS>)) {
1235              # Clean the input line.              # Clean the input line.
# Line 1223  Line 1241 
1241          close ORGS;          close ORGS;
1242          # Now the function file.          # Now the function file.
1243          my $funcLine;          my $funcLine;
1244          Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1245          while (defined($funcLine = <FUNCS>)) {          while (defined($funcLine = <FUNCS>)) {
1246              # Clean the line ending.              # Clean the line ending.
1247              chomp $funcLine;              chomp $funcLine;
# Line 1414  Line 1432 
1432      IsSynonymGroupFor      IsSynonymGroupFor
1433    
1434  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
1435  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
1436  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.  
1437    
1438  =over 4  =over 4
1439    
# Line 1443  Line 1459 
1459          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1460      } else {      } else {
1461          Trace("Generating synonym group data.") if T(2);          Trace("Generating synonym group data.") if T(2);
1462            # Get the database handle.
1463            my $dbh = $fig->db_handle();
1464            # Ask for the synonyms.
1465            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1466            my $result = $sth->execute();
1467            if (! defined($result)) {
1468                Confess("Database error in Synonym load: " . $sth->errstr());
1469            } else {
1470                # Remember the current synonym.
1471                my $current_syn = "";
1472                # Count the features.
1473                my $featureCount = 0;
1474                # Loop through the synonym/peg pairs.
1475                while (my @row = $sth->fetchrow()) {
1476                    # Get the synonym ID and feature ID.
1477                    my ($syn_id, $peg) = @row;
1478                    # Insure it's for one of our genomes.
1479                    my $genomeID = FIG::genome_of($peg);
1480                    if (exists $genomeHash->{$genomeID}) {
1481                        # Verify the synonym.
1482                        if ($syn_id ne $current_syn) {
1483                            # It's new, so put it in the group table.
1484                            $loadSynonymGroup->Put($syn_id);
1485                            $current_syn = $syn_id;
1486                        }
1487                        # Connect the synonym to the peg.
1488                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1489                        # Count this feature.
1490                        $featureCount++;
1491                        if ($featureCount % 1000 == 0) {
1492                            Trace("$featureCount features processed.") if T(3);
1493                        }
1494                    }
1495                }
1496            }
1497        }
1498        # Finish the load.
1499        my $retVal = $self->_FinishAll();
1500        return $retVal;
1501    }
1502    
1503    =head3 LoadFamilyData
1504    
1505    C<< my $stats = $spl->LoadFamilyData(); >>
1506    
1507    Load the protein families into Sprout.
1508    
1509    The following relations are loaded by this method.
1510    
1511        Family
1512        IsFamilyForFeature
1513    
1514    The source information for these relations is taken from the C<families_for_protein>,
1515    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1516    
1517    =over 4
1518    
1519    =item RETURNS
1520    
1521    Returns a statistics object for the loads.
1522    
1523    =back
1524    
1525    =cut
1526    #: Return Type $%;
1527    sub LoadFamilyData {
1528        # Get this object instance.
1529        my ($self) = @_;
1530        # Get the FIG object.
1531        my $fig = $self->{fig};
1532        # Get the genome hash.
1533        my $genomeHash = $self->{genomes};
1534        # Create load objects for the tables we're loading.
1535        my $loadFamily = $self->_TableLoader('Family');
1536        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1537        if ($self->{options}->{loadOnly}) {
1538            Trace("Loading from existing files.") if T(2);
1539        } else {
1540            Trace("Generating family data.") if T(2);
1541            # Create a hash for the family IDs.
1542            my %familyHash = ();
1543          # Loop through the genomes.          # Loop through the genomes.
1544          for my $genomeID (sort keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1545              Trace("Processing $genomeID.") if T(3);              Trace("Processing features for $genomeID.") if T(2);
1546              # Get all of the features for this genome. The only method that does this is              # Loop through this genome's PEGs.
1547              # all_features_detailed, which returns extra baggage that we discard.              for my $fid ($fig->all_features($genomeID, "peg")) {
1548              my $featureData = $fig->all_features_detailed($genomeID);                  $loadIsFamilyForFeature->Add("features", 1);
1549              my @fids = map { $_->[0] } @{$featureData};                  # Get this feature's families.
1550              Trace(scalar(@fids) . " features found for genome $genomeID.") if T(3);                  my @families = $fig->families_for_protein($fid);
1551              # Loop through the feature IDs.                  # Loop through the families, connecting them to the feature.
1552              for my $fid (@fids) {                  for my $family (@families) {
1553                  # Get the group for this feature.                      $loadIsFamilyForFeature->Put($family, $fid);
1554                  my $synonym = $fig->maps_to_id($fid);                      # If this is a new family, create a record for it.
1555                  # Only proceed if the synonym is a real group.                      if (! exists $familyHash{$family}) {
1556                  if ($synonym ne $fid) {                          $familyHash{$family} = 1;
1557                      $loadSynonymGroup->Put($synonym);                          $loadFamily->Add("families", 1);
1558                      $loadIsSynonymGroupFor->Put($synonym, $fid);                          my $size = $fig->sz_family($family);
1559                            my $func = $fig->family_function($family);
1560                            $loadFamily->Put($family, $size, $func);
1561                        }
1562                  }                  }
1563              }              }
1564          }          }
# Line 1468  Line 1568 
1568      return $retVal;      return $retVal;
1569  }  }
1570    
   
1571  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1572    
1573  =head3 TableLoader  =head3 TableLoader
# Line 1536  Line 1635 
1635      my $retVal = Stats->new();      my $retVal = Stats->new();
1636      # Get the loader list.      # Get the loader list.
1637      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1638        # Create a hash to hold the statistics objects, keyed on relation name.
1639        my %loaderHash = ();
1640      # 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
1641      # 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.
1642      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1643          # Get the relation name.          # Get the relation name.
1644          my $relName = $loader->RelName;          my $relName = $loader->RelName;
# Line 1548  Line 1649 
1649              # Here we really need to finish.              # Here we really need to finish.
1650              Trace("Finishing $relName.") if T(2);              Trace("Finishing $relName.") if T(2);
1651              my $stats = $loader->Finish();              my $stats = $loader->Finish();
1652                $loaderHash{$relName} = $stats;
1653            }
1654        }
1655        # Now we loop through again, actually loading the tables. We want to finish before
1656        # loading so that if something goes wrong at this point, all the load files are usable
1657        # and we don't have to redo all that work.
1658        for my $relName (sort keys %loaderHash) {
1659            # Get the statistics for this relation.
1660            my $stats = $loaderHash{$relName};
1661            # Check for a database load.
1662              if ($self->{options}->{dbLoad}) {              if ($self->{options}->{dbLoad}) {
1663                  # 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.
1664                  Trace("Loading relation $relName.") if T(2);                  Trace("Loading relation $relName.") if T(2);
# Line 1558  Line 1669 
1669              $retVal->Accumulate($stats);              $retVal->Accumulate($stats);
1670              Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);              Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1671          }          }
     }  
1672      # Return the load statistics.      # Return the load statistics.
1673      return $retVal;      return $retVal;
1674  }  }

Legend:
Removed from v.1.46  
changed lines
  Added in v.1.64

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3