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

Diff of /Sprout/SproutLoad.pm

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

revision 1.36, Fri May 19 07:26:17 2006 UTC revision 1.61, Sun Jul 30 01:41:34 2006 UTC
# Line 30  Line 30 
30      $stats->Accumulate($spl->LoadFeatureData());      $stats->Accumulate($spl->LoadFeatureData());
31      print $stats->Show();      print $stats->Show();
32    
 This module makes use of the internal Sprout property C<_erdb>.  
   
33  It is worth noting that the FIG object does not need to be a real one. Any object  It is worth noting that the FIG object does not need to be a real one. Any object
34  that implements the FIG methods for data retrieval could be used. So, for example,  that implements the FIG methods for data retrieval could be used. So, for example,
35  this object could be used to copy data from one Sprout database to another, or  this object could be used to copy data from one Sprout database to another, or
# Line 138  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 175  Line 173 
173                    subsystems => \%subsystems,                    subsystems => \%subsystems,
174                    sprout => $sprout,                    sprout => $sprout,
175                    loadDirectory => $directory,                    loadDirectory => $directory,
176                    erdb => $sprout->{_erdb},                    erdb => $sprout,
177                    loaders => [],                    loaders => [],
178                    options => $options                    options => $options
179                   };                   };
# Line 342  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 377  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 413  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 488  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 548  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 636  Line 649 
649  The following relations are loaded by this method.  The following relations are loaded by this method.
650    
651      Subsystem      Subsystem
652        SubsystemClass
653      Role      Role
654      RoleEC      RoleEC
655      SSCell      SSCell
# Line 698  Line 712 
712      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
713      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
714      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
715        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
716      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
717          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
718      } else {      } else {
# 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);
742                    if ($class) {
743                        $loadSubsystemClass->Put($subsysID, $class);
744                    }
745                  # 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.
746                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
747                      # Connect to this role.                      # Connect to this role.
# Line 766  Line 785 
785                          # part of the spreadsheet cell ID.                          # part of the spreadsheet cell ID.
786                          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
787                              # Get the features in the spreadsheet cell for this genome and role.                              # Get the features in the spreadsheet cell for this genome and role.
788                              my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
789                              # Only proceed if features exist.                              # Only proceed if features exist.
790                              if (@pegs > 0) {                              if (@pegs > 0) {
791                                  # Create the spreadsheet cell.                                  # Create the spreadsheet cell.
# Line 787  Line 806 
806                          if ($pegCount > 0) {                          if ($pegCount > 0) {
807                              Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                              Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
808                              $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);                              $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
                             # Partition the PEGs found into clusters.  
                             my @clusters = $fig->compute_clusters(\@pegsFound, $sub);  
809                              # Create a hash mapping PEG IDs to cluster numbers.                              # Create a hash mapping PEG IDs to cluster numbers.
810                              # We default to -1 for all of them.                              # We default to -1 for all of them.
811                              my %clusterOf = map { $_ => -1 } @pegsFound;                              my %clusterOf = map { $_ => -1 } @pegsFound;
812                                # Partition the PEGs found into clusters.
813                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
814                              for (my $i = 0; $i <= $#clusters; $i++) {                              for (my $i = 0; $i <= $#clusters; $i++) {
815                                  my $subList = $clusters[$i];                                  my $subList = $clusters[$i];
816                                  for my $peg (@{$subList}) {                                  for my $peg (@{$subList}) {
# Line 839  Line 858 
858                      }                      }
859                  }                  }
860              }              }
861            }
862              # 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
863              # 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
864              # in subsystems (and therefore appear in the %ecToRoles hash) are              # in subsystems (and therefore appear in the %ecToRoles hash) are
# Line 872  Line 892 
892                  }                  }
893              }              }
894          }          }
     }  
895      # Finish the load.      # Finish the load.
896      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
897      return $retVal;      return $retVal;
# Line 1034  Line 1053 
1053          # Loop through the genomes.          # Loop through the genomes.
1054          for my $genomeID (sort keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1055              Trace("Processing $genomeID.") if T(3);              Trace("Processing $genomeID.") if T(3);
1056                # Create a hash of timestamps. We use this to prevent duplicate time stamps
1057                # from showing up for a single PEG's annotations.
1058                my %seenTimestamps = ();
1059              # Get the genome's annotations.              # Get the genome's annotations.
1060              my @annotations = $fig->read_all_annotations($genomeID);              my @annotations = $fig->read_all_annotations($genomeID);
1061              Trace("Processing annotations.") if T(2);              Trace("Processing annotations.") if T(2);
1062              for my $tuple (@annotations) {              for my $tuple (@annotations) {
                 # Create a hash of timestamps. We use this to prevent duplicate time stamps  
                 # from showing up for a single PEG's annotations.  
                 my %seenTimestamps = ();  
1063                  # Get the annotation tuple.                  # Get the annotation tuple.
1064                  my ($peg, $timestamp, $user, $text) = @{$tuple};                  my ($peg, $timestamp, $user, $text) = @{$tuple};
1065                  # Here we fix up the annotation text. "\r" is removed,                  # Here we fix up the annotation text. "\r" is removed,
1066                  # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1067                  # modifier so that new-lines inside the text do not                  # modifier so that new-lines inside the text do not
1068                  # stop the substitution search.                  # stop the substitution search.
1069                  $text =~ s/\r//gs;                  $text =~ s/\r//gs;
# Line 1207  Line 1226 
1226      } else {      } else {
1227          Trace("Generating external data.") if T(2);          Trace("Generating external data.") if T(2);
1228          # We loop through the files one at a time. First, the organism file.          # We loop through the files one at a time. First, the organism file.
1229          Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1230          my $orgLine;          my $orgLine;
1231          while (defined($orgLine = <ORGS>)) {          while (defined($orgLine = <ORGS>)) {
1232              # Clean the input line.              # Clean the input line.
# Line 1219  Line 1238 
1238          close ORGS;          close ORGS;
1239          # Now the function file.          # Now the function file.
1240          my $funcLine;          my $funcLine;
1241          Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1242          while (defined($funcLine = <FUNCS>)) {          while (defined($funcLine = <FUNCS>)) {
1243              # Clean the line ending.              # Clean the line ending.
1244              chomp $funcLine;              chomp $funcLine;
# Line 1398  Line 1417 
1417      return $retVal;      return $retVal;
1418  }  }
1419    
1420    =head3 LoadSynonymData
1421    
1422    C<< my $stats = $spl->LoadSynonymData(); >>
1423    
1424    Load the synonym groups into Sprout.
1425    
1426    The following relations are loaded by this method.
1427    
1428        SynonymGroup
1429        IsSynonymGroupFor
1430    
1431    The source information for these relations is taken from the C<maps_to_id> method
1432    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1433    SQL against the FIG database.
1434    
1435    =over 4
1436    
1437    =item RETURNS
1438    
1439    Returns a statistics object for the loads.
1440    
1441    =back
1442    
1443    =cut
1444    #: Return Type $%;
1445    sub LoadSynonymData {
1446        # Get this object instance.
1447        my ($self) = @_;
1448        # Get the FIG object.
1449        my $fig = $self->{fig};
1450        # Get the genome hash.
1451        my $genomeHash = $self->{genomes};
1452        # Create a load object for the table we're loading.
1453        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1454        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1455        if ($self->{options}->{loadOnly}) {
1456            Trace("Loading from existing files.") if T(2);
1457        } else {
1458            Trace("Generating synonym group data.") if T(2);
1459            # Get the database handle.
1460            my $dbh = $fig->db_handle();
1461            # Ask for the synonyms.
1462            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1463            my $result = $sth->execute();
1464            if (! defined($result)) {
1465                Confess("Database error in Synonym load: " . $sth->errstr());
1466            } else {
1467                # Remember the current synonym.
1468                my $current_syn = "";
1469                # Count the features.
1470                my $featureCount = 0;
1471                # Loop through the synonym/peg pairs.
1472                while (my @row = $sth->fetchrow()) {
1473                    # Get the synonym ID and feature ID.
1474                    my ($syn_id, $peg) = @row;
1475                    # Insure it's for one of our genomes.
1476                    my $genomeID = FIG::genome_of($peg);
1477                    if (exists $genomeHash->{$genomeID}) {
1478                        # Verify the synonym.
1479                        if ($syn_id ne $current_syn) {
1480                            # It's new, so put it in the group table.
1481                            $loadSynonymGroup->Put($syn_id);
1482                            $current_syn = $syn_id;
1483                        }
1484                        # Connect the synonym to the peg.
1485                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1486                        # Count this feature.
1487                        $featureCount++;
1488                        if ($featureCount % 1000 == 0) {
1489                            Trace("$featureCount features processed.") if T(3);
1490                        }
1491                    }
1492                }
1493            }
1494        }
1495        # Finish the load.
1496        my $retVal = $self->_FinishAll();
1497        return $retVal;
1498    }
1499    
1500    =head3 LoadFamilyData
1501    
1502    C<< my $stats = $spl->LoadFamilyData(); >>
1503    
1504    Load the protein families into Sprout.
1505    
1506    The following relations are loaded by this method.
1507    
1508        Family
1509        ContainsFeature
1510    
1511    The source information for these relations is taken from the C<families_for_protein>,
1512    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1513    
1514    =over 4
1515    
1516    =item RETURNS
1517    
1518    Returns a statistics object for the loads.
1519    
1520    =back
1521    
1522    =cut
1523    #: Return Type $%;
1524    sub LoadFamilyData {
1525        # Get this object instance.
1526        my ($self) = @_;
1527        # Get the FIG object.
1528        my $fig = $self->{fig};
1529        # Get the genome hash.
1530        my $genomeHash = $self->{genomes};
1531        # Create load objects for the tables we're loading.
1532        my $loadFamily = $self->_TableLoader('Family');
1533        my $loadContainsFeature = $self->_TableLoader('ContainsFeature');
1534        if ($self->{options}->{loadOnly}) {
1535            Trace("Loading from existing files.") if T(2);
1536        } else {
1537            Trace("Generating family data.") if T(2);
1538            # Create a hash for the family IDs.
1539            my %familyHash = ();
1540            # Loop through the genomes.
1541            for my $genomeID (sort keys %{$genomeHash}) {
1542                Trace("Processing features for $genomeID.") if T(2);
1543                # Loop through this genome's PEGs.
1544                for my $fid ($fig->all_features($genomeID, "peg")) {
1545                    $loadContainsFeature->Add("features", 1);
1546                    # Get this feature's families.
1547                    my @families = $fig->families_for_protein($fid);
1548                    # Loop through the families, connecting them to the feature.
1549                    for my $family (@families) {
1550                        $loadContainsFeature->Put($family, $fid);
1551                        # If this is a new family, create a record for it.
1552                        if (! exists $familyHash{$family}) {
1553                            $loadFamily->Add("families", 1);
1554                            my $size = $fig->sz_family($family);
1555                            my $func = $fig->family_function($family);
1556                            $loadFamily->Put($family, $size, $func);
1557                        }
1558                    }
1559                }
1560            }
1561        }
1562        # Finish the load.
1563        my $retVal = $self->_FinishAll();
1564        return $retVal;
1565    }
1566    
1567  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1568    
1569  =head3 TableLoader  =head3 TableLoader
# Line 1465  Line 1631 
1631      my $retVal = Stats->new();      my $retVal = Stats->new();
1632      # Get the loader list.      # Get the loader list.
1633      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1634        # Create a hash to hold the statistics objects, keyed on relation name.
1635        my %loaderHash = ();
1636      # 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
1637      # 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.
1638      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1639          # Get the relation name.          # Get the relation name.
1640          my $relName = $loader->RelName;          my $relName = $loader->RelName;
# Line 1477  Line 1645 
1645              # Here we really need to finish.              # Here we really need to finish.
1646              Trace("Finishing $relName.") if T(2);              Trace("Finishing $relName.") if T(2);
1647              my $stats = $loader->Finish();              my $stats = $loader->Finish();
1648                $loaderHash{$relName} = $stats;
1649            }
1650        }
1651        # Now we loop through again, actually loading the tables. We want to finish before
1652        # loading so that if something goes wrong at this point, all the load files are usable
1653        # and we don't have to redo all that work.
1654        for my $relName (sort keys %loaderHash) {
1655            # Get the statistics for this relation.
1656            my $stats = $loaderHash{$relName};
1657            # Check for a database load.
1658              if ($self->{options}->{dbLoad}) {              if ($self->{options}->{dbLoad}) {
1659                  # 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.
1660                  Trace("Loading relation $relName.") if T(2);                  Trace("Loading relation $relName.") if T(2);
# Line 1487  Line 1665 
1665              $retVal->Accumulate($stats);              $retVal->Accumulate($stats);
1666              Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);              Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1667          }          }
     }  
1668      # Return the load statistics.      # Return the load statistics.
1669      return $retVal;      return $retVal;
1670  }  }

Legend:
Removed from v.1.36  
changed lines
  Added in v.1.61

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3