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

Diff of /Sprout/SproutLoad.pm

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

revision 1.40, Thu Jun 8 15:37:32 2006 UTC revision 1.66, Wed Sep 6 19:30:53 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 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 594  Line 609 
609              Trace("Processing features for genome $genomeID.") if T(3);              Trace("Processing features for genome $genomeID.") if T(3);
610              # Get the feature list for this genome.              # Get the feature list for this genome.
611              my $features = $fig->all_features_detailed($genomeID);              my $features = $fig->all_features_detailed($genomeID);
612                # Count the BBHs we find.
613                my $bbhCount = 0;
614              # Loop through the features.              # Loop through the features.
615              for my $featureData (@{$features}) {              for my $featureData (@{$features}) {
616                  # Split the tuple.                  # Split the tuple.
# Line 609  Line 626 
626                      if ($genomeHash->{$targetGenomeID}) {                      if ($genomeHash->{$targetGenomeID}) {
627                          $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,                          $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,
628                                                             $score);                                                             $score);
629                            $bbhCount++;
630                      }                      }
631                  }                  }
632              }              }
633                Trace("$bbhCount BBHs found for $genomeID.") if T(3);
634          }          }
635      }      }
636      # Finish the loads.      # Finish the loads.
# Line 634  Line 653 
653  The following relations are loaded by this method.  The following relations are loaded by this method.
654    
655      Subsystem      Subsystem
656        SubsystemClass
657      Role      Role
658      RoleEC      RoleEC
659      SSCell      SSCell
# Line 696  Line 716 
716      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
717      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
718      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
719        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
720      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
721          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
722      } else {      } else {
# Line 721  Line 742 
742                  my $curator = $sub->get_curator();                  my $curator = $sub->get_curator();
743                  my $notes = $sub->get_notes();                  my $notes = $sub->get_notes();
744                  $loadSubsystem->Put($subsysID, $curator, $notes);                  $loadSubsystem->Put($subsysID, $curator, $notes);
745                    my $classList = $fig->subsystem_classification($subsysID);
746                    my @classes = @$classList;
747                    if (@classes) {
748                        for my $class (@classes) {
749                            $loadSubsystemClass->Put($subsysID, $class);
750                        }
751                    }
752                  # 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.
753                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
754                      # Connect to this role.                      # Connect to this role.
# Line 785  Line 813 
813                          if ($pegCount > 0) {                          if ($pegCount > 0) {
814                              Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                              Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
815                              $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);                              $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
                             # Partition the PEGs found into clusters.  
                             my @clusters = $fig->compute_clusters(\@pegsFound, $sub);  
816                              # Create a hash mapping PEG IDs to cluster numbers.                              # Create a hash mapping PEG IDs to cluster numbers.
817                              # We default to -1 for all of them.                              # We default to -1 for all of them.
818                              my %clusterOf = map { $_ => -1 } @pegsFound;                              my %clusterOf = map { $_ => -1 } @pegsFound;
819                                # Partition the PEGs found into clusters.
820                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
821                              for (my $i = 0; $i <= $#clusters; $i++) {                              for (my $i = 0; $i <= $#clusters; $i++) {
822                                  my $subList = $clusters[$i];                                  my $subList = $clusters[$i];
823                                  for my $peg (@{$subList}) {                                  for my $peg (@{$subList}) {
# Line 837  Line 865 
865                      }                      }
866                  }                  }
867              }              }
868            }
869              # 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
870              # 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
871              # in subsystems (and therefore appear in the %ecToRoles hash) are              # in subsystems (and therefore appear in the %ecToRoles hash) are
# Line 870  Line 899 
899                  }                  }
900              }              }
901          }          }
     }  
902      # Finish the load.      # Finish the load.
903      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
904      return $retVal;      return $retVal;
# Line 923  Line 951 
951          my %propertyKeys = ();          my %propertyKeys = ();
952          my $nextID = 1;          my $nextID = 1;
953          # Loop through the genomes.          # Loop through the genomes.
954          for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
955              $loadProperty->Add("genomeIn");              $loadProperty->Add("genomeIn");
956              Trace("Generating properties for $genomeID.") if T(3);              Trace("Generating properties for $genomeID.") if T(3);
957              # Get the genome's features. The feature ID is the first field in the              # Get the genome's features. The feature ID is the first field in the
# Line 1042  Line 1070 
1070                  # Get the annotation tuple.                  # Get the annotation tuple.
1071                  my ($peg, $timestamp, $user, $text) = @{$tuple};                  my ($peg, $timestamp, $user, $text) = @{$tuple};
1072                  # Here we fix up the annotation text. "\r" is removed,                  # Here we fix up the annotation text. "\r" is removed,
1073                  # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1074                  # modifier so that new-lines inside the text do not                  # modifier so that new-lines inside the text do not
1075                  # stop the substitution search.                  # stop the substitution search.
1076                  $text =~ s/\r//gs;                  $text =~ s/\r//gs;
# Line 1205  Line 1233 
1233      } else {      } else {
1234          Trace("Generating external data.") if T(2);          Trace("Generating external data.") if T(2);
1235          # We loop through the files one at a time. First, the organism file.          # We loop through the files one at a time. First, the organism file.
1236          Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1237          my $orgLine;          my $orgLine;
1238          while (defined($orgLine = <ORGS>)) {          while (defined($orgLine = <ORGS>)) {
1239              # Clean the input line.              # Clean the input line.
# Line 1217  Line 1245 
1245          close ORGS;          close ORGS;
1246          # Now the function file.          # Now the function file.
1247          my $funcLine;          my $funcLine;
1248          Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1249          while (defined($funcLine = <FUNCS>)) {          while (defined($funcLine = <FUNCS>)) {
1250              # Clean the line ending.              # Clean the line ending.
1251              chomp $funcLine;              chomp $funcLine;
# Line 1377  Line 1405 
1405          Trace("Generating group data.") if T(2);          Trace("Generating group data.") if T(2);
1406          # Loop through the genomes.          # Loop through the genomes.
1407          my $line;          my $line;
1408          for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1409              Trace("Processing $genomeID.") if T(3);              Trace("Processing $genomeID.") if T(3);
1410              # Open the NMPDR group file for this genome.              # Open the NMPDR group file for this genome.
1411              if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&              if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&
# Line 1396  Line 1424 
1424      return $retVal;      return $retVal;
1425  }  }
1426    
1427    =head3 LoadSynonymData
1428    
1429    C<< my $stats = $spl->LoadSynonymData(); >>
1430    
1431    Load the synonym groups into Sprout.
1432    
1433    The following relations are loaded by this method.
1434    
1435        SynonymGroup
1436        IsSynonymGroupFor
1437    
1438    The source information for these relations is taken from the C<maps_to_id> method
1439    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1440    SQL against the FIG database.
1441    
1442    =over 4
1443    
1444    =item RETURNS
1445    
1446    Returns a statistics object for the loads.
1447    
1448    =back
1449    
1450    =cut
1451    #: Return Type $%;
1452    sub LoadSynonymData {
1453        # Get this object instance.
1454        my ($self) = @_;
1455        # Get the FIG object.
1456        my $fig = $self->{fig};
1457        # Get the genome hash.
1458        my $genomeHash = $self->{genomes};
1459        # Create a load object for the table we're loading.
1460        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1461        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1462        if ($self->{options}->{loadOnly}) {
1463            Trace("Loading from existing files.") if T(2);
1464        } else {
1465            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.
1548            for my $genomeID (sort keys %{$genomeHash}) {
1549                Trace("Processing features for $genomeID.") if T(2);
1550                # Loop through this genome's PEGs.
1551                for my $fid ($fig->all_features($genomeID, "peg")) {
1552                    $loadIsFamilyForFeature->Add("features", 1);
1553                    # Get this feature's families.
1554                    my @families = $fig->families_for_protein($fid);
1555                    # Loop through the families, connecting them to the feature.
1556                    for my $family (@families) {
1557                        $loadIsFamilyForFeature->Put($family, $fid);
1558                        # If this is a new family, create a record for it.
1559                        if (! exists $familyHash{$family}) {
1560                            $familyHash{$family} = 1;
1561                            $loadFamily->Add("families", 1);
1562                            my $size = $fig->sz_family($family);
1563                            my $func = $fig->family_function($family);
1564                            $loadFamily->Put($family, $size, $func);
1565                        }
1566                    }
1567                }
1568            }
1569        }
1570        # Finish the load.
1571        my $retVal = $self->_FinishAll();
1572        return $retVal;
1573    }
1574    
1575  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1576    
1577  =head3 TableLoader  =head3 TableLoader
# Line 1463  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 1475  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 1485  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.1.40  
changed lines
  Added in v.1.66

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3