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; |
163 |
Confess("Invalid subsystem parameter in SproutLoad constructor."); |
Confess("Invalid subsystem parameter in SproutLoad constructor."); |
164 |
} |
} |
165 |
} |
} |
166 |
|
# Go through the subsys hash again, creating the keyword list for each subsystem. |
167 |
|
for my $subsystem (keys %subsystems) { |
168 |
|
my $name = $subsystem; |
169 |
|
$name =~ s/_/ /g; |
170 |
|
my $classes = $fig->subsystem_classification($subsystem); |
171 |
|
my @classList = map { " $_" } @{$classes}; |
172 |
|
$name .= join("", @classList); |
173 |
|
$subsystems{$subsystem} = $name; |
174 |
|
} |
175 |
} |
} |
176 |
# Get the data directory from the Sprout object. |
# Get the data directory from the Sprout object. |
177 |
my ($directory) = $sprout->LoadInfo(); |
my ($directory) = $sprout->LoadInfo(); |
275 |
my $extra = join " ", @extraData; |
my $extra = join " ", @extraData; |
276 |
# Get the full taxonomy. |
# Get the full taxonomy. |
277 |
my $taxonomy = $fig->taxonomy_of($genomeID); |
my $taxonomy = $fig->taxonomy_of($genomeID); |
278 |
|
# Open the NMPDR group file for this genome. |
279 |
|
my $group; |
280 |
|
if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") && |
281 |
|
defined($group = <TMP>)) { |
282 |
|
# Clean the line ending. |
283 |
|
chomp $group; |
284 |
|
} else { |
285 |
|
# No group, so use the default. |
286 |
|
$group = $FIG_Config::otherGroup; |
287 |
|
} |
288 |
|
close TMP; |
289 |
# Output the genome record. |
# Output the genome record. |
290 |
$loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus, |
$loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus, |
291 |
$species, $extra, $taxonomy); |
$group, $species, $extra, $taxonomy); |
292 |
# Now we loop through each of the genome's contigs. |
# Now we loop through each of the genome's contigs. |
293 |
my @contigs = $fig->all_contigs($genomeID); |
my @contigs = $fig->all_contigs($genomeID); |
294 |
for my $contigID (@contigs) { |
for my $contigID (@contigs) { |
469 |
FeatureUpstream |
FeatureUpstream |
470 |
IsLocatedIn |
IsLocatedIn |
471 |
HasFeature |
HasFeature |
472 |
|
HasRoleInSubsystem |
473 |
|
|
474 |
=over 4 |
=over 4 |
475 |
|
|
484 |
sub LoadFeatureData { |
sub LoadFeatureData { |
485 |
# Get this object instance. |
# Get this object instance. |
486 |
my ($self) = @_; |
my ($self) = @_; |
487 |
# Get the FIG object. |
# Get the FIG and Sprout objects. |
488 |
my $fig = $self->{fig}; |
my $fig = $self->{fig}; |
489 |
|
my $sprout = $self->{sprout}; |
490 |
# Get the table of genome IDs. |
# Get the table of genome IDs. |
491 |
my $genomeHash = $self->{genomes}; |
my $genomeHash = $self->{genomes}; |
492 |
# Create load objects for each of the tables we're loading. |
# Create load objects for each of the tables we're loading. |
496 |
my $loadFeatureLink = $self->_TableLoader('FeatureLink'); |
my $loadFeatureLink = $self->_TableLoader('FeatureLink'); |
497 |
my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation'); |
my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation'); |
498 |
my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream'); |
my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream'); |
499 |
my $loadHasFeature = $self->_TableLoader('HasFeature'); |
my $loadHasFeature = $self->_TableLoader('HasFeature', $self->PrimaryOnly); |
500 |
|
my $loadHasRoleInSubsystem = $self->_TableLoader('HasRoleInSubsystem', $self->PrimaryOnly); |
501 |
|
# Get the subsystem hash. |
502 |
|
my $subHash = $self->{subsystems}; |
503 |
# Get the maximum sequence size. We need this later for splitting up the |
# Get the maximum sequence size. We need this later for splitting up the |
504 |
# locations. |
# locations. |
505 |
my $chunkSize = $self->{sprout}->MaxSegment(); |
my $chunkSize = $self->{sprout}->MaxSegment(); |
530 |
$oldFeatureID = $featureID; |
$oldFeatureID = $featureID; |
531 |
# Count this feature. |
# Count this feature. |
532 |
$loadFeature->Add("featureIn"); |
$loadFeature->Add("featureIn"); |
533 |
# Create the feature record. |
# Get the functional assignment. |
534 |
$loadFeature->Put($featureID, 1, $type); |
my $assignment = $fig->function_of($featureID); |
535 |
# Link it to the parent genome. |
# Begin building the keywords. |
536 |
|
my $keywords = "$assignment $genomeID"; |
537 |
|
# Link this feature to the parent genome. |
538 |
$loadHasFeature->Put($genomeID, $featureID, $type); |
$loadHasFeature->Put($genomeID, $featureID, $type); |
539 |
# Create the aliases. |
# Create the aliases. |
540 |
for my $alias ($fig->feature_aliases($featureID)) { |
for my $alias ($fig->feature_aliases($featureID)) { |
541 |
$loadFeatureAlias->Put($featureID, $alias); |
$loadFeatureAlias->Put($featureID, $alias); |
542 |
|
$keywords .= " $alias"; |
543 |
} |
} |
544 |
# Get the links. |
# Get the links. |
545 |
my @links = $fig->fid_links($featureID); |
my @links = $fig->fid_links($featureID); |
559 |
$loadFeatureUpstream->Put($featureID, $upstream); |
$loadFeatureUpstream->Put($featureID, $upstream); |
560 |
} |
} |
561 |
} |
} |
562 |
|
# Now we need to find the subsystems this feature participates in. |
563 |
|
# We also add the subsystems to the keyword list. Before we do that, |
564 |
|
# we must convert underscores to spaces and tack on the classifications. |
565 |
|
my @subsystems = $fig->peg_to_subsystems($featureID); |
566 |
|
for my $subsystem (@subsystems) { |
567 |
|
# Only proceed if we like this subsystem. |
568 |
|
if (exists $subHash->{$subsystem}) { |
569 |
|
# Store the has-role link. |
570 |
|
$loadHasRoleInSubsystem->Put($featureID, $subsystem, $genomeID, $type); |
571 |
|
# Save the subsystem's keyword data. |
572 |
|
my $subKeywords = $subHash->{$subsystem}; |
573 |
|
$keywords .= " $subKeywords"; |
574 |
|
} |
575 |
|
} |
576 |
|
# The final task is to add virulence and essentiality attributes. |
577 |
|
if ($fig->virulent($featureID)) { |
578 |
|
$keywords .= " virulent"; |
579 |
|
} |
580 |
|
if ($fig->essential($featureID)) { |
581 |
|
$keywords .= " essential"; |
582 |
|
} |
583 |
|
# Clean the keyword list. |
584 |
|
my $cleanWords = $sprout->CleanKeywords($keywords); |
585 |
|
# Create the feature record. |
586 |
|
$loadFeature->Put($featureID, 1, $type, $assignment, $cleanWords); |
587 |
# This part is the roughest. We need to relate the features to contig |
# This part is the roughest. We need to relate the features to contig |
588 |
# locations, and the locations must be split so that none of them exceed |
# locations, and the locations must be split so that none of them exceed |
589 |
# the maximum segment size. This simplifies the genes_in_region processing |
# the maximum segment size. This simplifies the genes_in_region processing |
662 |
Trace("Processing features for genome $genomeID.") if T(3); |
Trace("Processing features for genome $genomeID.") if T(3); |
663 |
# Get the feature list for this genome. |
# Get the feature list for this genome. |
664 |
my $features = $fig->all_features_detailed($genomeID); |
my $features = $fig->all_features_detailed($genomeID); |
665 |
|
# Count the BBHs we find. |
666 |
|
my $bbhCount = 0; |
667 |
# Loop through the features. |
# Loop through the features. |
668 |
for my $featureData (@{$features}) { |
for my $featureData (@{$features}) { |
669 |
# Split the tuple. |
# Split the tuple. |
679 |
if ($genomeHash->{$targetGenomeID}) { |
if ($genomeHash->{$targetGenomeID}) { |
680 |
$loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID, |
$loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID, |
681 |
$score); |
$score); |
682 |
|
$bbhCount++; |
683 |
} |
} |
684 |
} |
} |
685 |
} |
} |
686 |
|
Trace("$bbhCount BBHs found for $genomeID.") if T(3); |
687 |
} |
} |
688 |
} |
} |
689 |
# Finish the loads. |
# Finish the loads. |
795 |
my $curator = $sub->get_curator(); |
my $curator = $sub->get_curator(); |
796 |
my $notes = $sub->get_notes(); |
my $notes = $sub->get_notes(); |
797 |
$loadSubsystem->Put($subsysID, $curator, $notes); |
$loadSubsystem->Put($subsysID, $curator, $notes); |
798 |
my $class = $fig->subsystem_classification($subsysID); |
# Now for the classification string. This comes back as a list |
799 |
if ($class) { |
# reference and we convert it to a space-delimited string. |
800 |
$loadSubsystemClass->Put($subsysID, $class); |
my $classList = $fig->subsystem_classification($subsysID); |
801 |
} |
my $classString = join(" ", grep { $_ } @$classList); |
802 |
|
$loadSubsystemClass->Put($subsysID, $classString); |
803 |
# 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. |
804 |
for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) { |
for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) { |
805 |
# Connect to this role. |
# Connect to this role. |
1002 |
my %propertyKeys = (); |
my %propertyKeys = (); |
1003 |
my $nextID = 1; |
my $nextID = 1; |
1004 |
# Loop through the genomes. |
# Loop through the genomes. |
1005 |
for my $genomeID (keys %{$genomeHash}) { |
for my $genomeID (sort keys %{$genomeHash}) { |
1006 |
$loadProperty->Add("genomeIn"); |
$loadProperty->Add("genomeIn"); |
1007 |
Trace("Generating properties for $genomeID.") if T(3); |
Trace("Generating properties for $genomeID.") if T(3); |
1008 |
# 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 |
1016 |
# Get all attributes for this feature. We do this one feature at a time |
# Get all attributes for this feature. We do this one feature at a time |
1017 |
# to insure we do not get any genome attributes. |
# to insure we do not get any genome attributes. |
1018 |
my @attributeList = $fig->get_attributes($fid, '', '', ''); |
my @attributeList = $fig->get_attributes($fid, '', '', ''); |
1019 |
|
# Add essentiality and virulence attributes. |
1020 |
|
if ($fig->essential($fid)) { |
1021 |
|
push @attributeList, [$fid, 'essential', 1, '']; |
1022 |
|
} |
1023 |
|
if ($fig->virulent($fid)) { |
1024 |
|
push @attributeList, [$fid, 'virulent', 1, '']; |
1025 |
|
} |
1026 |
if (scalar @attributeList) { |
if (scalar @attributeList) { |
1027 |
$featureCount++; |
$featureCount++; |
1028 |
} |
} |
1435 |
|
|
1436 |
GenomeGroups |
GenomeGroups |
1437 |
|
|
1438 |
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, |
1439 |
|
butThere is no direct support for genome groups in FIG, so we access the SEED |
1440 |
files directly. |
files directly. |
1441 |
|
|
1442 |
=over 4 |
=over 4 |
1462 |
Trace("Loading from existing files.") if T(2); |
Trace("Loading from existing files.") if T(2); |
1463 |
} else { |
} else { |
1464 |
Trace("Generating group data.") if T(2); |
Trace("Generating group data.") if T(2); |
1465 |
# 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; |
|
|
} |
|
1466 |
} |
} |
1467 |
# Finish the load. |
# Finish the load. |
1468 |
my $retVal = $self->_FinishAll(); |
my $retVal = $self->_FinishAll(); |
1558 |
The following relations are loaded by this method. |
The following relations are loaded by this method. |
1559 |
|
|
1560 |
Family |
Family |
1561 |
ContainsFeature |
IsFamilyForFeature |
1562 |
|
|
1563 |
The source information for these relations is taken from the C<families_for_protein>, |
The source information for these relations is taken from the C<families_for_protein>, |
1564 |
C<family_function>, and C<sz_family> methods of the B<FIG> object. |
C<family_function>, and C<sz_family> methods of the B<FIG> object. |
1582 |
my $genomeHash = $self->{genomes}; |
my $genomeHash = $self->{genomes}; |
1583 |
# Create load objects for the tables we're loading. |
# Create load objects for the tables we're loading. |
1584 |
my $loadFamily = $self->_TableLoader('Family'); |
my $loadFamily = $self->_TableLoader('Family'); |
1585 |
my $loadContainsFeature = $self->_TableLoader('ContainsFeature'); |
my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature'); |
1586 |
if ($self->{options}->{loadOnly}) { |
if ($self->{options}->{loadOnly}) { |
1587 |
Trace("Loading from existing files.") if T(2); |
Trace("Loading from existing files.") if T(2); |
1588 |
} else { |
} else { |
1594 |
Trace("Processing features for $genomeID.") if T(2); |
Trace("Processing features for $genomeID.") if T(2); |
1595 |
# Loop through this genome's PEGs. |
# Loop through this genome's PEGs. |
1596 |
for my $fid ($fig->all_features($genomeID, "peg")) { |
for my $fid ($fig->all_features($genomeID, "peg")) { |
1597 |
$loadContainsFeature->Add("features", 1); |
$loadIsFamilyForFeature->Add("features", 1); |
1598 |
# Get this feature's families. |
# Get this feature's families. |
1599 |
my @families = $fig->families_for_protein($fid); |
my @families = $fig->families_for_protein($fid); |
1600 |
# Loop through the families, connecting them to the feature. |
# Loop through the families, connecting them to the feature. |
1601 |
for my $family (@families) { |
for my $family (@families) { |
1602 |
$loadContainsFeature->Put($family, $fid); |
$loadIsFamilyForFeature->Put($family, $fid); |
1603 |
# If this is a new family, create a record for it. |
# If this is a new family, create a record for it. |
1604 |
if (! exists $familyHash{$family}) { |
if (! exists $familyHash{$family}) { |
1605 |
$familyHash{$family} = 1; |
$familyHash{$family} = 1; |
1617 |
return $retVal; |
return $retVal; |
1618 |
} |
} |
1619 |
|
|
1620 |
|
|
1621 |
|
|
1622 |
=head2 Internal Utility Methods |
=head2 Internal Utility Methods |
1623 |
|
|
1624 |
=head3 TableLoader |
=head3 TableLoader |