--- Sprout.pm 2005/05/04 03:24:43 1.12 +++ Sprout.pm 2008/02/14 19:13:33 1.108 @@ -1,18 +1,20 @@ package Sprout; - use Data::Dumper; - use strict; - use Carp; - use DBKernel; - use XML::Simple; - use DBQuery; - use DBObject; - use ERDB; - use Tracer; - use FIGRules; - use Stats; + use Data::Dumper; + use strict; + use DBKernel; + use XML::Simple; + use DBQuery; + use ERDBObject; + use Tracer; + use FIGRules; + use FidCheck; + use Stats; use POSIX qw(strftime); - + use BasicLocation; + use CustomAttributes; + use RemoteCustomAttributes; + use base qw(ERDB); =head1 Sprout Database Manipulation Object @@ -25,12 +27,14 @@ on the constructor. For example, the following invocation specifies a PostgreSQL database named I whose definition and data files are in a co-directory named F. -C<< my $sprout = Sprout->new('GenDB', { dbType => 'pg', dataDir => '../Data', xmlFileName => '../Data/SproutDBD.xml' }); >> + my $sprout = Sprout->new('GenDB', { dbType => 'pg', dataDir => '../Data', xmlFileName => '../Data/SproutDBD.xml' }); Once you have a sprout object, you may use it to re-create the database, load the tables from tab-delimited flat files and perform queries. Several special methods are provided for common -query tasks. For example, L lists the IDs of all the genomes in the database and -L returns the DNA sequence for a specified genome location. +query tasks. For example, L lists the IDs of all the genomes in the database and +L returns the DNA sequence for a specified genome location. + +The Sprout object is a subclass of the ERDB object and inherits all its properties and methods. =cut @@ -40,7 +44,7 @@ =head3 new -C<< my $sprout = Sprout->new($dbName, \%options); >> + my $sprout = Sprout->new($dbName, \%options); This is the constructor for a sprout object. It connects to the database and loads the database definition into memory. The positional first parameter specifies the name of the @@ -62,280 +66,237 @@ * B name of the XML file containing the database definition (default C) -* B user name and password, delimited by a slash (default C) +* B user name and password, delimited by a slash (default same as SEED) * B connection port (default C<0>) +* B connection socket (default same as SEED) + * B maximum number of residues per feature segment, (default C<4500>) * B maximum number of residues per sequence, (default C<8000>) +* B suppresses the connection to the database if TRUE, else FALSE + +* B name of the database host + =back For example, the following constructor call specifies a database named I and a user name of I with a password of I. The database load files are in the directory F. -C<< my $sprout = Sprout->new('Sprout', { userData =>; 'fig/admin', dataDir => '/usr/fig/SproutData' }); >> + my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' }); =cut sub new { - # Get the parameters. - my ($class, $dbName, $options) = @_; - # Compute the options. We do this by starting with a table of defaults and overwriting with - # the incoming data. - my $optionTable = Tracer::GetOptions({ - dbType => 'mysql', # database type - dataDir => 'Data', # data file directory - xmlFileName => 'SproutDBD.xml', # database definition file name - userData => 'root/', # user name and password - port => 0, # database connection port - maxSegmentLength => 4500, # maximum feature segment length - maxSequenceLength => 8000, # maximum contig sequence length - }, $options); - # Get the data directory. - my $dataDir = $optionTable->{dataDir}; - # Extract the user ID and password. - $optionTable->{userData} =~ m!([^/]*)/(.*)$!; - my ($userName, $password) = ($1, $2); - # Connect to the database. - my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port}); - # Create the ERDB object. - my $xmlFileName = "$optionTable->{xmlFileName}"; - my $erdb = ERDB->new($dbh, $xmlFileName); - # Create this object. - my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName }; - # Bless and return it. - bless $self; - return $self; -} - -=head3 MaxSegment - -C<< my $length = $sprout->MaxSegment(); >> - -This method returns the maximum permissible length of a feature segment. The length is important -because it enables us to make reasonable guesses at how to find features inside a particular -contig region. For example, if the maximum length is 4000 and we're looking for a feature that -overlaps the region from 6000 to 7000 we know that the starting position must be between 2001 -and 10999. - -=cut -#: Return Type $; -sub MaxSegment { - my ($self) = @_; - return $self->{_options}->{maxSegmentLength}; -} - -=head3 MaxSequence - -C<< my $length = $sprout->MaxSequence(); >> - -This method returns the maximum permissible length of a contig sequence. A contig is broken -into sequences in order to save memory resources. In particular, when manipulating features, -we generally only need a few sequences in memory rather than the entire contig. - -=cut -#: Return Type $; -sub MaxSequence { - my ($self) = @_; - return $self->{_options}->{maxSequenceLength}; + # Get the parameters. + my ($class, $dbName, $options) = @_; + # Compute the DBD directory. + my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir : + $FIG_Config::fig ); + # Compute the options. We do this by starting with a table of defaults and overwriting with + # the incoming data. + my $optionTable = Tracer::GetOptions({ + dbType => $FIG_Config::dbms, + # database type + dataDir => $FIG_Config::sproutData, + # data file directory + xmlFileName => "$dbd_dir/SproutDBD.xml", + # database definition file name + userData => "$FIG_Config::dbuser/$FIG_Config::dbpass", + # user name and password + port => $FIG_Config::dbport, + # database connection port + sock => $FIG_Config::dbsock, + host => $FIG_Config::sprout_host, + maxSegmentLength => 4500, # maximum feature segment length + maxSequenceLength => 8000, # maximum contig sequence length + noDBOpen => 0, # 1 to suppress the database open + }, $options); + # Get the data directory. + my $dataDir = $optionTable->{dataDir}; + # Extract the user ID and password. + $optionTable->{userData} =~ m!([^/]*)/(.*)$!; + my ($userName, $password) = ($1, $2); + # Connect to the database. + my $dbh; + if (! $optionTable->{noDBOpen}) { + Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3); + $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, + $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock}); + } + # Create the ERDB object. + my $xmlFileName = "$optionTable->{xmlFileName}"; + my $retVal = ERDB::new($class, $dbh, $xmlFileName); + # Add the option table and XML file name. + $retVal->{_options} = $optionTable; + $retVal->{_xmlName} = $xmlFileName; + # Set up space for the group file data. + $retVal->{groupHash} = undef; + # Set up space for the genome hash. We use this to identify NMPDR genomes. + $retVal->{genomeHash} = undef; + # Connect to the attributes. + if ($FIG_Config::attrURL) { + Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3); + $retVal->{_ca} = RemoteCustomAttributes->new($FIG_Config::attrURL); + } elsif ($FIG_Config::attrDbName) { + Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3); + my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent())); + $retVal->{_ca} = CustomAttributes->new(user => $user); + } + # Return it. + return $retVal; } -=head3 Get - -C<< my $query = $sprout->Get(\@objectNames, $filterClause, \@parameterList); >> - -This method allows a general query against the Sprout data using a specified filter clause. - -The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each -field name represented in the form B(I)>. For example, the -following call requests all B objects for the genus specified in the variable -$genus. - -C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", [$genus]); >> - -The WHERE clause contains a single question mark, so there is a single additional -parameter representing the parameter value. It would also be possible to code - -C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >> - -however, this version of the call would generate a syntax error if there were any quote -characters inside the variable C<$genus>. - -The use of the strange parenthesized notation for field names enables us to distinguish -hyphens contained within field names from minus signs that participate in the computation -of the WHERE clause. All of the methods that manipulate fields will use this same notation. - -It is possible to specify multiple entity and relationship names in order to retrieve more than -one object's data at the same time, which allows highly complex joined queries. For example, - -C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >> - -This query returns all the genomes for a particular genus and allows access to the -sources from which they came. The join clauses to go from Genome to Source are generated -automatically. - -Finally, the filter clause can contain sort information. To do this, simply put an C -clause at the end of the filter. Field references in the ORDER BY section follow the same rules -as they do in the filter itself; in other words, each one must be of the form B(I)>. -For example, the following filter string gets all genomes for a particular genus and sorts -them by species name. - -C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ? ORDER BY Genome(species)", [$genus]); >> +=head3 CoreGenomes -It is also permissible to specify I an ORDER BY clause. For example, the following invocation gets -all genomes ordered by genus and species. + my @genomes = $sprout->CoreGenomes($scope); -C<< $query = $sprout->Get(['Genome'], "ORDER BY Genome(genus), Genome(species)"); >> - -Odd things may happen if one of the ORDER BY fields is in a secondary relation. So, for example, an -attempt to order Bs by alias may (depending on the underlying database engine used) cause -a single feature to appear more than once. - -If multiple names are specified, then the query processor will automatically determine a -join path between the entities and relationships. The algorithm used is very simplistic. -In particular, you can't specify any entity or relationship more than once, and if a -relationship is recursive, the path is determined by the order in which the entity -and the relationship appear. For example, consider a recursive relationship B -which relates B objects to other B objects. If the join path is -coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however, -the join path is C<['IsParentOf', 'People']>, then the people returned will be children. +Return the IDs of NMPDR genomes in the specified scope. =over 4 -=item objectNames - -List containing the names of the entity and relationship objects to be retrieved. - -=item filterClause +=item scope -WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can -be parameterized with parameter markers (C). Each field used must be specified in the standard form -B(I)>. Any parameters specified in the filter clause should be added to the -parameter list as additional parameters. The fields in a filter clause can come from primary -entity relations, relationship relations, or secondary entity relations; however, all of the -entities and relationships involved must be included in the list of object names. - -=item parameterList - -List of the parameters to be substituted in for the parameters marks in the filter clause. +Scope of the desired genomes. C covers the original core genomes, +C covers all genomes in NMPDR groups, and C covers all +genomes in the system. =item RETURN -Returns a B that can be used to iterate through all of the results. +Returns a list of the IDs for the genomes in the specified scope. =back =cut -sub Get { - # Get the parameters. - my ($self, $objectNames, $filterClause, $parameterList) = @_; - # We differ from the ERDB Get method in that the parameter list is passed in as a list reference - # rather than a list of parameters. The next step is to convert the parameters from a reference - # to a real list. We can only do this if the parameters have been specified. - my @parameters; - if ($parameterList) { @parameters = @{$parameterList}; } - return $self->{_erdb}->Get($objectNames, $filterClause, @parameters); +sub CoreGenomes { + # Get the parameters. + my ($self, $scope) = @_; + # Declare the return variable. + my @retVal = (); + # If we want all genomes, then this is easy. + if ($scope eq 'all') { + @retVal = $self->Genomes(); + } else { + # Here we're dealing with groups. Get the hash of all the + # genome groups. + my %groups = $self->GetGroups(); + # Loop through the groups, keeping the ones that we want. + for my $group (keys %groups) { + # Decide if we want to keep this group. + my $keepGroup = 0; + if ($scope eq 'nmpdr') { + # NMPDR mode: keep all groups. + $keepGroup = 1; + } elsif ($scope eq 'core') { + # CORE mode. Only keep real core groups. + if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) { + $keepGroup = 1; + } + } + # Add this group if we're keeping it. + if ($keepGroup) { + push @retVal, @{$groups{$group}}; + } + } + } + # Return the result. + return @retVal; } -=head3 GetEntity +=head3 SuperGroup -C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >> + my $superGroup = $sprout->SuperGroup($groupName); -Return an object describing the entity instance with a specified ID. +Return the name of the super-group containing the specified NMPDR genome +group. If no appropriate super-group can be found, an error will be +thrown. =over 4 -=item entityType - -Entity type name. - -=item ID +=item groupName -ID of the desired entity. +Name of the group whose super-group is desired. =item RETURN -Returns a B representing the desired entity instance, or an undefined value if no -instance is found with the specified key. +Returns the name of the super-group containing the incoming group. =back =cut -sub GetEntity { - # Get the parameters. - my ($self, $entityType, $ID) = @_; - # Call the ERDB method. - return $self->{_erdb}->GetEntity($entityType, $ID); +sub SuperGroup { + # Get the parameters. + my ($self, $groupName) = @_; + # Declare the return variable. + my $retVal; + # Get the group hash. + my %groupHash = $self->CheckGroupFile(); + # Find the super-group genus. + $groupName =~ /([A-Z]\w+)/; + my $nameThing = $1; + # See if it's directly in the group hash. + if (exists $groupHash{$nameThing}) { + # Yes, then it's our result. + $retVal = $nameThing; + } else { + # No, so we have to search. + for my $superGroup (keys %groupHash) { + # Get this super-group's item list. + my $list = $groupHash{$superGroup}->{contents}; + # Search it. + if (grep { $_->[0] eq $nameThing } @{$list}) { + $retVal = $superGroup; + } + } + # Make sure we found something. + if (! $retVal) { + Confess("No super-group found for \"$groupName\"."); + } + } + # Return the result. + return $retVal; } -=head3 GetEntityValues - -C<< my @values = GetEntityValues($entityType, $ID, \@fields); >> - -Return a list of values from a specified entity instance. - -=over 4 - -=item entityType - -Entity type name. - -=item ID - -ID of the desired entity. - -=item fields - -List of field names, each of the form IC<(>IC<)>. - -=item RETURN +=head3 MaxSegment -Returns a flattened list of the values of the specified fields for the specified entity. + my $length = $sprout->MaxSegment(); -=back +This method returns the maximum permissible length of a feature segment. The length is important +because it enables us to make reasonable guesses at how to find features inside a particular +contig region. For example, if the maximum length is 4000 and we're looking for a feature that +overlaps the region from 6000 to 7000 we know that the starting position must be between 2001 +and 10999. =cut -#: Return Type @; -sub GetEntityValues { - # Get the parameters. - my ($self, $entityType, $ID, $fields) = @_; - # Call the ERDB method. - return $self->{_erdb}->GetEntityValues($entityType, $ID, $fields); +#: Return Type $; +sub MaxSegment { + my ($self) = @_; + return $self->{_options}->{maxSegmentLength}; } -=head3 ShowMetaData - -C<< $sprout->ShowMetaData($fileName); >> - -This method outputs a description of the database to an HTML file in the data directory. - -=over 4 - -=item fileName +=head3 MaxSequence -Fully-qualified name to give to the output file. + my $length = $sprout->MaxSequence(); -=back +This method returns the maximum permissible length of a contig sequence. A contig is broken +into sequences in order to save memory resources. In particular, when manipulating features, +we generally only need a few sequences in memory rather than the entire contig. =cut - -sub ShowMetaData { - # Get the parameters. - my ($self, $fileName) = @_; - # Compute the file name. - my $options = $self->{_options}; - # Call the show method on the underlying ERDB object. - $self->{_erdb}->ShowMetaData($fileName); +#: Return Type $; +sub MaxSequence { + my ($self) = @_; + return $self->{_options}->{maxSequenceLength}; } =head3 Load -C<< $sprout->Load($rebuild); >>; + $sprout->Load($rebuild);; Load the database from files in the data directory, optionally re-creating the tables. @@ -365,19 +326,17 @@ =cut #: Return Type %; sub Load { - # Get the parameters. - my ($self, $rebuild) = @_; - # Get the database object. - my $erdb = $self->{_erdb}; - # Load the tables from the data directory. - my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild); - # Return the statistics. - return $retVal; + # Get the parameters. + my ($self, $rebuild) = @_; + # Load the tables from the data directory. + my $retVal = $self->LoadTables($self->{_options}->{dataDir}, $rebuild); + # Return the statistics. + return $retVal; } =head3 LoadUpdate -C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >> + my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); Load updates to one or more database tables. This method enables the client to make changes to one or two tables without reloading the whole database. For each table, there must be a corresponding @@ -408,34 +367,188 @@ =cut #: Return Type $%; sub LoadUpdate { - # Get the parameters. - my ($self, $truncateFlag, $tableList) = @_; - # Get the database object. - my $erdb = $self->{_erdb}; - # Declare the return value. - my $retVal = Stats->new(); - # Get the data directory. - my $optionTable = $self->{_options}; - my $dataDir = $optionTable->{dataDir}; - # Loop through the incoming table names. - for my $tableName (@{$tableList}) { - # Find the table's file. - my $fileName = "$dataDir/$tableName"; - if (! -e $fileName) { - $fileName = "$fileName.dtx"; - } - # Attempt to load this table. - my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag); - # Accumulate the resulting statistics. - $retVal->Accumulate($result); - } - # Return the statistics. - return $retVal; + # Get the parameters. + my ($self, $truncateFlag, $tableList) = @_; + # Declare the return value. + my $retVal = Stats->new(); + # Get the data directory. + my $optionTable = $self->{_options}; + my $dataDir = $optionTable->{dataDir}; + # Loop through the incoming table names. + for my $tableName (@{$tableList}) { + # Find the table's file. + my $fileName = LoadFileName($dataDir, $tableName); + if (! $fileName) { + Trace("No load file found for $tableName in $dataDir.") if T(0); + } else { + # Attempt to load this table. + my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag); + # Accumulate the resulting statistics. + $retVal->Accumulate($result); + } + } + # Return the statistics. + return $retVal; +} + +=head3 GenomeCounts + + my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete); + +Count the number of genomes in each domain. If I<$complete> is TRUE, only complete +genomes will be included in the counts. + +=over 4 + +=item complete + +TRUE if only complete genomes are to be counted, FALSE if all genomes are to be +counted + +=item RETURN + +A six-element list containing the number of genomes in each of six categories-- +Archaea, Bacteria, Eukaryota, Viral, Environmental, and Unknown, respectively. + +=back + +=cut + +sub GenomeCounts { + # Get the parameters. + my ($self, $complete) = @_; + # Set the filter based on the completeness flag. + my $filter = ($complete ? "Genome(complete) = 1" : ""); + # Get all the genomes and the related taxonomy information. + my @genomes = $self->GetAll(['Genome'], $filter, [], ['Genome(id)', 'Genome(taxonomy)']); + # Clear the counters. + my ($arch, $bact, $euk, $vir, $env, $unk) = (0, 0, 0, 0, 0, 0); + # Loop through, counting the domains. + for my $genome (@genomes) { + if ($genome->[1] =~ /^archaea/i) { ++$arch } + elsif ($genome->[1] =~ /^bacter/i) { ++$bact } + elsif ($genome->[1] =~ /^eukar/i) { ++$euk } + elsif ($genome->[1] =~ /^vir/i) { ++$vir } + elsif ($genome->[1] =~ /^env/i) { ++$env } + else { ++$unk } + } + # Return the counts. + return ($arch, $bact, $euk, $vir, $env, $unk); +} + +=head3 ContigCount + + my $count = $sprout->ContigCount($genomeID); + +Return the number of contigs for the specified genome ID. + +=over 4 + +=item genomeID + +ID of the genome whose contig count is desired. + +=item RETURN + +Returns the number of contigs for the specified genome. + +=back + +=cut + +sub ContigCount { + # Get the parameters. + my ($self, $genomeID) = @_; + # Get the contig count. + my $retVal = $self->GetCount(['Contig', 'HasContig'], "HasContig(from-link) = ?", [$genomeID]); + # Return the result. + return $retVal; +} + +=head3 GeneMenu + + my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params, $selected); + +Return an HTML select menu of genomes. Each genome will be an option in the menu, +and will be displayed by name with the ID and a contig count attached. The selection +value will be the genome ID. The genomes will be sorted by genus/species name. + +=over 4 + +=item attributes + +Reference to a hash mapping attributes to values for the SELECT tag generated. + +=item filterString + +A filter string for use in selecting the genomes. The filter string must conform +to the rules for the C<< ERDB->Get >> method. + +=item params + +Reference to a list of values to be substituted in for the parameter marks in +the filter string. + +=item selected (optional) + +ID of the genome to be initially selected. + +=item fast (optional) + +If specified and TRUE, the contig counts will be omitted to improve performance. + +=item RETURN + +Returns an HTML select menu with the specified genomes as selectable options. + +=back + +=cut + +sub GeneMenu { + # Get the parameters. + my ($self, $attributes, $filterString, $params, $selected, $fast) = @_; + my $slowMode = ! $fast; + # Default to nothing selected. This prevents an execution warning if "$selected" + # is undefined. + $selected = "" unless defined $selected; + Trace("Gene Menu called with slow mode \"$slowMode\" and selection \"$selected\".") if T(3); + # Start the menu. + my $retVal = "\n"; + # Return the result. + return $retVal; } =head3 Build -C<< $sprout->Build(); >> + $sprout->Build(); Build the database. The database will be cleared and the tables re-created from the metadata. This method is useful when a database is brand new or when the database definition has @@ -444,32 +557,32 @@ =cut #: Return Type ; sub Build { - # Get the parameters. - my ($self) = @_; - # Create the tables. - $self->{_erdb}->CreateTables; + # Get the parameters. + my ($self) = @_; + # Create the tables. + $self->CreateTables(); } =head3 Genomes -C<< my @genomes = $sprout->Genomes(); >> + my @genomes = $sprout->Genomes(); Return a list of all the genome IDs. =cut #: Return Type @; sub Genomes { - # Get the parameters. - my ($self) = @_; - # Get all the genomes. - my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)'); - # Return the list of IDs. - return @retVal; + # Get the parameters. + my ($self) = @_; + # Get all the genomes. + my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)'); + # Return the list of IDs. + return @retVal; } =head3 GenusSpecies -C<< my $infoString = $sprout->GenusSpecies($genomeID); >> + my $infoString = $sprout->GenusSpecies($genomeID); Return the genus, species, and unique characterization for a genome. @@ -489,19 +602,19 @@ =cut #: Return Type $; sub GenusSpecies { - # Get the parameters. - my ($self, $genomeID) = @_; - # Get the data for the specified genome. - my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)', - 'Genome(unique-characterization)']); - # Format the result and return it. - my $retVal = join(' ', @values); - return $retVal; + # Get the parameters. + my ($self, $genomeID) = @_; + # Get the data for the specified genome. + my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)', + 'Genome(unique-characterization)']); + # Format the result and return it. + my $retVal = join(' ', @values); + return $retVal; } =head3 FeaturesOf -C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >> + my @features = $sprout->FeaturesOf($genomeID, $ftype); Return a list of the features relevant to a specified genome. @@ -525,28 +638,28 @@ =cut #: Return Type @; sub FeaturesOf { - # Get the parameters. - my ($self, $genomeID,$ftype) = @_; - # Get the features we want. - my @features; - if (!$ftype) { - @features = $self->GetFlat(['HasContig', 'IsLocatedIn'], "HasContig(from-link) = ?", - [$genomeID], 'IsLocatedIn(from-link)'); - } else { - @features = $self->GetFlat(['HasContig', 'IsLocatedIn', 'Feature'], - "HasContig(from-link) = ? AND Feature(feature-type) = ?", - [$genomeID, $ftype], 'IsLocatedIn(from-link)'); - } - # Return the list with duplicates merged out. We need to merge out duplicates because - # a feature will appear twice if it spans more than one contig. - my @retVal = Tracer::Merge(@features); - # Return the list of feature IDs. - return @retVal; + # Get the parameters. + my ($self, $genomeID,$ftype) = @_; + # Get the features we want. + my @features; + if (!$ftype) { + @features = $self->GetFlat(['HasContig', 'IsLocatedIn'], "HasContig(from-link) = ?", + [$genomeID], 'IsLocatedIn(from-link)'); + } else { + @features = $self->GetFlat(['HasContig', 'IsLocatedIn', 'Feature'], + "HasContig(from-link) = ? AND Feature(feature-type) = ?", + [$genomeID, $ftype], 'IsLocatedIn(from-link)'); + } + # Return the list with duplicates merged out. We need to merge out duplicates because + # a feature will appear twice if it spans more than one contig. + my @retVal = Tracer::Merge(@features); + # Return the list of feature IDs. + return @retVal; } =head3 FeatureLocation -C<< my @locations = $sprout->FeatureLocation($featureID); >> + my @locations = $sprout->FeatureLocation($featureID); Return the location of a feature in its genome's contig segments. In a list context, this method will return a list of the locations. In a scalar context, it will return the locations as a space- @@ -570,55 +683,29 @@ =item RETURN Returns a list of the feature's contig segments. The locations are returned as a list in a list -context and as a space-delimited string in a scalar context. +context and as a comma-delimited string in a scalar context. =back =cut -#: Return Type @; -#: Return Type $; + sub FeatureLocation { - # Get the parameters. - my ($self, $featureID) = @_; - # Create a query for the feature locations. - my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)", - [$featureID]); - # Create the return list. - my @retVal = (); - # Set up the variables used to determine if we have adjacent segments. This initial setup will - # not match anything. - my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0); - # Loop through the query results, creating location specifiers. - while (my $location = $query->Fetch()) { - # Get the location parameters. - my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)', - 'IsLocatedIn(beg)', 'IsLocatedIn(dir)', 'IsLocatedIn(len)']); - # Check to see if we are adjacent to the previous segment. - if ($prevContig eq $contigID && $dir eq $prevDir) { - # Here the new segment is in the same direction on the same contig. Insure the - # new segment's beginning is next to the old segment's end. - if (($dir eq "-" && $beg == $prevBeg - $prevLen) || - ($dir eq "+" && $beg == $prevBeg + $prevLen)) { - # Here we need to merge two segments. Adjust the beginning and length values - # to include both segments. - $beg = $prevBeg; - $len += $prevLen; - # Pop the old segment off. The new one will replace it later. - pop @retVal; - } - } - # Remember this specifier for the adjacent-segment test the next time through. - ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len); - # Add the specifier to the list. - push @retVal, "${contigID}_$beg$dir$len"; - } - # Return the list in the format indicated by the context. - return (wantarray ? @retVal : join(' ', @retVal)); + # Get the parameters. + my ($self, $featureID) = @_; + # Get the feature record. + my $object = $self->GetEntity('Feature', $featureID); + Confess("Feature $featureID not found.") if ! defined($object); + # Get the location string. + my $locString = $object->PrimaryValue('Feature(location-string)'); + # Create the return list. + my @retVal = split /\s*,\s*/, $locString; + # Return the list in the format indicated by the context. + return (wantarray ? @retVal : join(',', @retVal)); } =head3 ParseLocation -C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >> + my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); Split a location specifier into the contig ID, the starting point, the direction, and the length. @@ -637,37 +724,39 @@ =back =cut -#: Return Type @; + sub ParseLocation { - # Get the parameter. Note that if we're called as an instance method, we ignore + # Get the parameter. Note that if we're called as an instance method, we ignore # the first parameter. shift if UNIVERSAL::isa($_[0],__PACKAGE__); - my ($location) = @_; - # Parse it into segments. - $location =~ /^(.*)_(\d*)([+-_])(\d*)$/; - my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4); - # If the direction is an underscore, convert it to a + or -. - if ($dir eq "_") { - if ($start < $len) { - $dir = "+"; - $len = $len - $start + 1; - } else { - $dir = "-"; - $len = $start - $len + 1; - } - } - # Return the result. - return ($contigID, $start, $dir, $len); + my ($location) = @_; + # Parse it into segments. + $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/; + my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4); + # If the direction is an underscore, convert it to a + or -. + if ($dir eq "_") { + if ($start < $len) { + $dir = "+"; + $len = $len - $start + 1; + } else { + $dir = "-"; + $len = $start - $len + 1; + } + } + # Return the result. + return ($contigID, $start, $dir, $len); } + + =head3 PointLocation -C<< my $found = Sprout::PointLocation($location, $point); >> + my $found = Sprout::PointLocation($location, $point); Return the offset into the specified location of the specified point on the contig. If the specified point is before the location, a negative value will be returned. If it is -beyond the location, an undefined value will be returned. It is assumed that the offset -is for the location's contig. The location can either be new-style (using a C<+> or C<-> +beyond the location, an undefined value will be returned. It is assumed that the offset +is for the location's contig. The location can either be new-style (using a C<+> or C<-> and a length) or old-style (using C<_> and start and end positions. =over 4 @@ -691,12 +780,12 @@ =back =cut -#: Return Type $; + sub PointLocation { - # Get the parameter. Note that if we're called as an instance method, we ignore + # Get the parameter. Note that if we're called as an instance method, we ignore # the first parameter. shift if UNIVERSAL::isa($_[0],__PACKAGE__); - my ($location, $point) = @_; + my ($location, $point) = @_; # Parse out the location elements. Note that this works on both old-style and new-style # locations. my ($contigID, $start, $dir, $len) = ParseLocation($location); @@ -714,18 +803,23 @@ =head3 DNASeq -C<< my $sequence = $sprout->DNASeq(\@locationList); >> + my $sequence = $sprout->DNASeq(\@locationList); This method returns the DNA sequence represented by a list of locations. The list of locations should be of the form returned by L when in a list context. In other words, each location is of the form IC<_>III. +For example, the following would return the DNA sequence for contig C<83333.1:NC_000913> +between positions 1401 and 1532, inclusive. + + my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532'); + =over 4 =item locationList -List of location specifiers, each in the form IC<_>III (see -L for more about this format). +List of location specifiers, each in the form IC<_>III or +IC<_>IC<_>I (see L for more about this format). =item RETURN @@ -736,61 +830,64 @@ =cut #: Return Type $; sub DNASeq { - # Get the parameters. - my ($self, $locationList) = @_; - # Create the return string. - my $retVal = ""; - # Loop through the locations. - for my $location (@{$locationList}) { - # Set up a variable to contain the DNA at this location. - my $locationDNA = ""; - # Parse out the contig ID, the beginning point, the direction, and the end point. - my ($contigID, $beg, $dir, $len) = ParseLocation($location); - # Now we must create a query to return all the sequences in the contig relevant to the region - # specified. First, we compute the start and stop points when reading through the sequences. - # For a forward transcription, the start point is the beginning; for a backward transcription, - # the start point is the ending. Note that in the latter case we must reverse the DNA string - # before putting it in the return value. - my ($start, $stop); - if ($dir eq "+") { - $start = $beg; - $stop = $beg + $len - 1; - } else { - $start = $beg + $len + 1; - $stop = $beg; - } - my $query = $self->Get(['IsMadeUpOf','Sequence'], - "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " . - " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)", - [$contigID, $start, $stop]); - # Loop through the sequences. - while (my $sequence = $query->Fetch()) { - # Determine whether the location starts, stops, or continues through this sequence. - my ($startPosition, $sequenceData, $sequenceLength) = - $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)', - 'IsMadeUpOf(len)']); - my $stopPosition = $startPosition + $sequenceLength; - # Figure out the start point and length of the relevant section. - my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition); - my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1; - # Add the relevant data to the location data. - $locationDNA .= substr($sequenceData, $pos1, $len); - } - # Add this location's data to the return string. Note that we may need to reverse it. - if ($dir eq '+') { - $retVal .= $locationDNA; - } else { - $locationDNA = join('', reverse split //, $locationDNA); - $retVal .= $locationDNA; - } - } - # Return the result. - return $retVal; + # Get the parameters. + my ($self, $locationList) = @_; + # Create the return string. + my $retVal = ""; + # Loop through the locations. + for my $location (@{$locationList}) { + # Set up a variable to contain the DNA at this location. + my $locationDNA = ""; + # Parse out the contig ID, the beginning point, the direction, and the end point. + my ($contigID, $beg, $dir, $len) = ParseLocation($location); + # Now we must create a query to return all the sequences in the contig relevant to the region + # specified. First, we compute the start and stop points when reading through the sequences. + # For a forward transcription, the start point is the beginning; for a backward transcription, + # the start point is the ending. Note that in the latter case we must reverse the DNA string + # before putting it in the return value. + my ($start, $stop); + Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4); + if ($dir eq "+") { + $start = $beg; + $stop = $beg + $len - 1; + } else { + $start = $beg - $len + 1; + $stop = $beg; + } + Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4); + my $query = $self->Get(['IsMadeUpOf','Sequence'], + "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " . + " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)", + [$contigID, $start, $stop]); + # Loop through the sequences. + while (my $sequence = $query->Fetch()) { + # Determine whether the location starts, stops, or continues through this sequence. + my ($startPosition, $sequenceData, $sequenceLength) = + $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)', + 'IsMadeUpOf(len)']); + my $stopPosition = $startPosition + $sequenceLength; + Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4); + # Figure out the start point and length of the relevant section. + my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition); + my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1; + Trace("Position is $pos1 for length $len1.") if T(SDNA => 4); + # Add the relevant data to the location data. + $locationDNA .= substr($sequenceData, $pos1, $len1); + } + # Add this location's data to the return string. Note that we may need to reverse it. + if ($dir eq '+') { + $retVal .= $locationDNA; + } else { + $retVal .= FIG::reverse_comp($locationDNA); + } + } + # Return the result. + return $retVal; } =head3 AllContigs -C<< my @idList = $sprout->AllContigs($genomeID); >> + my @idList = $sprout->AllContigs($genomeID); Return a list of all the contigs for a genome. @@ -809,199 +906,400 @@ =cut #: Return Type @; sub AllContigs { - # Get the parameters. - my ($self, $genomeID) = @_; - # Ask for the genome's Contigs. - my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID], - 'HasContig(to-link)'); - # Return the list of Contigs. - return @retVal; + # Get the parameters. + my ($self, $genomeID) = @_; + # Ask for the genome's Contigs. + my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID], + 'HasContig(to-link)'); + # Return the list of Contigs. + return @retVal; } -=head3 ContigLength +=head3 GenomeLength -C<< my $length = $sprout->ContigLength($contigID); >> + my $length = $sprout->GenomeLength($genomeID); -Compute the length of a contig. +Return the length of the specified genome in base pairs. =over 4 -=item contigID +=item genomeID -ID of the contig whose length is desired. +ID of the genome whose base pair count is desired. =item RETURN -Returns the number of positions in the contig. +Returns the number of base pairs in all the contigs of the specified +genome. =back =cut -#: Return Type $; -sub ContigLength { - # Get the parameters. - my ($self, $contigID) = @_; - # Get the contig's last sequence. - my $query = $self->Get(['IsMadeUpOf'], - "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC", - [$contigID]); - my $sequence = $query->Fetch(); - # Declare the return value. - my $retVal = 0; - # Set it from the sequence data, if any. - if ($sequence) { - my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']); - $retVal = $start + $len; - } - # Return the result. - return $retVal; + +sub GenomeLength { + # Get the parameters. + my ($self, $genomeID) = @_; + # Declare the return variable. + my $retVal = 0; + # Get the genome's contig sequence lengths. + my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?', + [$genomeID], 'IsMadeUpOf(len)'); + # Sum the lengths. + map { $retVal += $_ } @lens; + # Return the result. + return $retVal; } -=head3 GenesInRegion +=head3 FeatureCount -C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >> + my $count = $sprout->FeatureCount($genomeID, $type); -List the features which overlap a specified region in a contig. +Return the number of features of the specified type in the specified genome. =over 4 -=item contigID - -ID of the contig containing the region of interest. - -=item start +=item genomeID -Offset of the first residue in the region of interest. +ID of the genome whose feature count is desired. -=item stop +=item type -Offset of the last residue in the region of interest. +Type of feature to count (eg. C, C, etc.). =item RETURN -Returns a three-element list. The first element is a list of feature IDs for the features that -overlap the region of interest. The second and third elements are the minimum and maximum -locations of the features provided on the specified contig. These may extend outside -the start and stop values. The first element (that is, the list of features) is sorted -roughly by location. +Returns the number of features of the specified type for the specified genome. =back =cut -#: Return Type @@; -sub GenesInRegion { - # Get the parameters. - my ($self, $contigID, $start, $stop) = @_; - # Get the maximum segment length. - my $maximumSegmentLength = $self->MaxSegment; - # Create a hash to receive the feature list. We use a hash so that we can eliminate - # duplicates easily. The hash key will be the feature ID. The value will be a two-element - # containing the minimum and maximum offsets. We will use the offsets to sort the results - # when we're building the result set. - my %featuresFound = (); - # Prime the values we'll use for the returned beginning and end. - my @initialMinMax = ($self->ContigLength($contigID), 0); - my ($min, $max) = @initialMinMax; - # Create a table of parameters for each query. Each query looks for features travelling in - # a particular direction. The query parameters include the contig ID, the feature direction, - # the lowest possible start position, and the highest possible start position. This works - # because each feature segment length must be no greater than the maximum segment length. - my %queryParms = (forward => [$contigID, '+', $start - $maximumSegmentLength + 1, $stop], - reverse => [$contigID, '-', $start, $stop + $maximumSegmentLength - 1]); - # Loop through the query parameters. - for my $parms (values %queryParms) { - # Create the query. - my $query = $self->Get(['IsLocatedIn'], - "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?", - $parms); - # Loop through the feature segments found. - while (my $segment = $query->Fetch) { - # Get the data about this segment. - my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)', - 'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']); - # Determine if this feature actually overlaps the region. The query insures that - # this will be the case if the segment is the maximum length, so to fine-tune - # the results we insure that the inequality from the query holds using the actual - # length. - my ($found, $end) = (0, 0); - if ($dir eq '+') { - $end = $beg + $len; - if ($end >= $start) { - # Denote we found a useful feature. - $found = 1; - } - } elsif ($dir eq '-') { - # Note we switch things around so that the beginning is to the left of the - # ending. - ($beg, $end) = ($beg - $len, $beg); - if ($beg <= $stop) { - # Denote we found a useful feature. - $found = 1; - } - } - if ($found) { - # Here we need to record the feature and update the minima and maxima. First, - # get the current entry for the specified feature. - my ($loc1, $loc2) = (exists $featuresFound{$featureID} ? @{$featuresFound{$featureID}} : - @initialMinMax); - # Merge the current segment's begin and end into the feature begin and end and the - # global min and max. - if ($beg < $loc1) { - $loc1 = $beg; - $min = $beg if $beg < $min; - } - if ($end > $loc2) { - $loc2 = $end; - $max = $end if $end > $max; - } - # Store the entry back into the hash table. - $featuresFound{$featureID} = [$loc1, $loc2]; - } - } - } - # Now we must compute the list of the IDs for the features found. We start with a list - # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint, - # but the result of the sort will be the same.) - my @list = map { [$featuresFound{$_}->[0] + $featuresFound{$_}->[1], $_] } keys %featuresFound; - # Now we sort by midpoint and yank out the feature IDs. - my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list; - # Return it along with the min and max. - return (\@retVal, $min, $max); + +sub FeatureCount { + # Get the parameters. + my ($self, $genomeID, $type) = @_; + # Compute the count. + my $retVal = $self->GetCount(['HasFeature', 'Feature'], + "HasFeature(from-link) = ? AND Feature(feature-type) = ?", + [$genomeID, $type]); + # Return the result. + return $retVal; } -=head3 FType +=head3 GenomeAssignments -C<< my $ftype = $sprout->FType($featureID); >> + my $fidHash = $sprout->GenomeAssignments($genomeID); -Return the type of a feature. +Return a list of a genome's assigned features. The return hash will contain each +assigned feature of the genome mapped to the text of its most recent functional +assignment. =over 4 -=item featureID +=item genomeID -ID of the feature whose type is desired. +ID of the genome whose functional assignments are desired. =item RETURN -A string indicating the type of feature (e.g. peg, rna). If the feature does not exist, returns an -undefined value. +Returns a reference to a hash which maps each feature to its most recent +functional assignment. =back =cut -#: Return Type $; -sub FType { - # Get the parameters. - my ($self, $featureID) = @_; - # Get the specified feature's type. - my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']); - # Return the result. - return $retVal; -} + +sub GenomeAssignments { + # Get the parameters. + my ($self, $genomeID) = @_; + # Declare the return variable. + my $retVal = {}; + # Query the genome's features. + my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?", + [$genomeID]); + # Loop through the features. + while (my $data = $query->Fetch) { + # Get the feature ID and assignment. + my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']); + if ($assignment) { + $retVal->{$fid} = $assignment; + } + } + # Return the result. + return $retVal; +} + +=head3 ContigLength + + my $length = $sprout->ContigLength($contigID); + +Compute the length of a contig. + +=over 4 + +=item contigID + +ID of the contig whose length is desired. + +=item RETURN + +Returns the number of positions in the contig. + +=back + +=cut +#: Return Type $; +sub ContigLength { + # Get the parameters. + my ($self, $contigID) = @_; + # Get the contig's last sequence. + my $query = $self->Get(['IsMadeUpOf'], + "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC", + [$contigID]); + my $sequence = $query->Fetch(); + # Declare the return value. + my $retVal = 0; + # Set it from the sequence data, if any. + if ($sequence) { + my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']); + $retVal = $start + $len - 1; + } + # Return the result. + return $retVal; +} + +=head3 ClusterPEGs + + my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); + +Cluster the PEGs in a list according to the cluster coding scheme of the specified +subsystem. In order for this to work properly, the subsystem object must have +been used recently to retrieve the PEGs using the B or +B methods. This causes the cluster numbers to be pulled into the +subsystem's color hash. If a PEG is not found in the color hash, it will not +appear in the output sequence. + +=over 4 + +=item sub + +Sprout subsystem object for the relevant subsystem, from the L +method. + +=item pegs + +Reference to the list of PEGs to be clustered. + +=item RETURN + +Returns a list of the PEGs, grouped into smaller lists by cluster number. + +=back + +=cut +#: Return Type $@@; +sub ClusterPEGs { + # Get the parameters. + my ($self, $sub, $pegs) = @_; + # Declare the return variable. + my $retVal = []; + # Loop through the PEGs, creating arrays for each cluster. + for my $pegID (@{$pegs}) { + my $clusterNumber = $sub->get_cluster_number($pegID); + # Only proceed if the PEG is in a cluster. + if ($clusterNumber >= 0) { + # Push this PEG onto the sub-list for the specified cluster number. + push @{$retVal->[$clusterNumber]}, $pegID; + } + } + # Return the result. + return $retVal; +} + +=head3 GenesInRegion + + my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); + +List the features which overlap a specified region in a contig. + +=over 4 + +=item contigID + +ID of the contig containing the region of interest. + +=item start + +Offset of the first residue in the region of interest. + +=item stop + +Offset of the last residue in the region of interest. + +=item RETURN + +Returns a three-element list. The first element is a list of feature IDs for the features that +overlap the region of interest. The second and third elements are the minimum and maximum +locations of the features provided on the specified contig. These may extend outside +the start and stop values. The first element (that is, the list of features) is sorted +roughly by location. + +=back + +=cut + +sub GenesInRegion { + # Get the parameters. + my ($self, $contigID, $start, $stop) = @_; + # Get the maximum segment length. + my $maximumSegmentLength = $self->MaxSegment; + # Prime the values we'll use for the returned beginning and end. + my @initialMinMax = ($self->ContigLength($contigID), 0); + my ($min, $max) = @initialMinMax; + # Get the overlapping features. + my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop); + # We'l use this hash to help us track the feature IDs and sort them. The key is the + # feature ID and the value is a [$left,$right] pair indicating the maximum extent + # of the feature's locations. + my %featureMap = (); + # Loop through them to do the begin/end analysis. + for my $featureObject (@featureObjects) { + # Get the feature's location string. This may contain multiple actual locations. + my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]); + my @locationSegments = split /\s*,\s*/, $locations; + # Loop through the locations. + for my $locationSegment (@locationSegments) { + # Construct an object for the location. + my $locationObject = BasicLocation->new($locationSegment); + # Merge the current segment's begin and end into the min and max. + my ($left, $right) = ($locationObject->Left, $locationObject->Right); + my ($beg, $end); + if (exists $featureMap{$fid}) { + ($beg, $end) = @{$featureMap{$fid}}; + $beg = $left if $left < $beg; + $end = $right if $right > $end; + } else { + ($beg, $end) = ($left, $right); + } + $min = $beg if $beg < $min; + $max = $end if $end > $max; + # Store the feature's new extent back into the hash table. + $featureMap{$fid} = [$beg, $end]; + } + } + # Now we must compute the list of the IDs for the features found. We start with a list + # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint, + # but the result of the sort will be the same.) + my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap; + # Now we sort by midpoint and yank out the feature IDs. + my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list; + # Return it along with the min and max. + return (\@retVal, $min, $max); +} + +=head3 GeneDataInRegion + + my @featureList = $sprout->GenesInRegion($contigID, $start, $stop); + +List the features which overlap a specified region in a contig. + +=over 4 + +=item contigID + +ID of the contig containing the region of interest. + +=item start + +Offset of the first residue in the region of interest. + +=item stop + +Offset of the last residue in the region of interest. + +=item RETURN + +Returns a list of B for the desired features. Each object will +contain a B record. + +=back + +=cut + +sub GeneDataInRegion { + # Get the parameters. + my ($self, $contigID, $start, $stop) = @_; + # Get the maximum segment length. + my $maximumSegmentLength = $self->MaxSegment; + # Create a hash to receive the feature list. We use a hash so that we can eliminate + # duplicates easily. The hash key will be the feature ID. The value will be the feature's + # ERDBObject from the query. + my %featuresFound = (); + # Create a table of parameters for the queries. Each query looks for features travelling in + # a particular direction. The query parameters include the contig ID, the feature direction, + # the lowest possible start position, and the highest possible start position. This works + # because each feature segment length must be no greater than the maximum segment length. + my %queryParms = (forward => [$contigID, '+', $start - $maximumSegmentLength + 1, $stop], + reverse => [$contigID, '-', $start, $stop + $maximumSegmentLength - 1]); + # Loop through the query parameters. + for my $parms (values %queryParms) { + # Create the query. + my $query = $self->Get([qw(Feature IsLocatedIn)], + "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?", + $parms); + # Loop through the feature segments found. + while (my $segment = $query->Fetch) { + # Get the data about this segment. + my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link) + IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]); + # Determine if this feature segment actually overlaps the region. The query insures that + # this will be the case if the segment is the maximum length, so to fine-tune + # the results we insure that the inequality from the query holds using the actual + # length. + my $loc = BasicLocation->new($contig, $beg, $dir, $len); + my $found = $loc->Overlap($start, $stop); + if ($found) { + # Save this feature in the result list. + $featuresFound{$featureID} = $segment; + } + } + } + # Return the ERDB objects for the features found. + return values %featuresFound; +} + +=head3 FType + + my $ftype = $sprout->FType($featureID); + +Return the type of a feature. + +=over 4 + +=item featureID + +ID of the feature whose type is desired. + +=item RETURN + +A string indicating the type of feature (e.g. peg, rna). If the feature does not exist, returns an +undefined value. + +=back + +=cut +#: Return Type $; +sub FType { + # Get the parameters. + my ($self, $featureID) = @_; + # Get the specified feature's type. + my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']); + # Return the result. + return $retVal; +} =head3 FeatureAnnotations -C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >> + my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); Return the annotations of a feature. @@ -1011,13 +1309,18 @@ ID of the feature whose annotations are desired. +=item rawFlag + +If TRUE, the annotation timestamps will be returned in raw form; otherwise, they +will be returned in human-readable form. + =item RETURN Returns a list of annotation descriptors. Each descriptor is a hash with the following fields. * B ID of the relevant feature. -* B time the annotation was made, in user-friendly format. +* B time the annotation was made. * B ID of the user who made the annotation @@ -1028,41 +1331,45 @@ =cut #: Return Type @%; sub FeatureAnnotations { - # Get the parameters. - my ($self, $featureID) = @_; - # Create a query to get the feature's annotations and the associated users. - my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'], - "IsTargetOfAnnotation(from-link) = ?", [$featureID]); - # Create the return list. - my @retVal = (); - # Loop through the annotations. - while (my $annotation = $query->Fetch) { - # Get the fields to return. - my ($featureID, $timeStamp, $user, $text) = - $annotation->Values(['IsTargetOfAnnotation(from-link)', - 'Annotation(time)', 'MadeAnnotation(from-link)', - 'Annotation(annotation)']); - # Assemble them into a hash. + # Get the parameters. + my ($self, $featureID, $rawFlag) = @_; + # Create a query to get the feature's annotations and the associated users. + my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'], + "IsTargetOfAnnotation(from-link) = ?", [$featureID]); + # Create the return list. + my @retVal = (); + # Loop through the annotations. + while (my $annotation = $query->Fetch) { + # Get the fields to return. + my ($featureID, $timeStamp, $user, $text) = + $annotation->Values(['IsTargetOfAnnotation(from-link)', + 'Annotation(time)', 'MadeAnnotation(from-link)', + 'Annotation(annotation)']); + # Convert the time, if necessary. + if (! $rawFlag) { + $timeStamp = FriendlyTimestamp($timeStamp); + } + # Assemble them into a hash. my $annotationHash = { featureID => $featureID, - timeStamp => FriendlyTimestamp($timeStamp), - user => $user, text => $text }; - # Add it to the return list. - push @retVal, $annotationHash; - } - # Return the result list. - return @retVal; + timeStamp => $timeStamp, + user => $user, text => $text }; + # Add it to the return list. + push @retVal, $annotationHash; + } + # Return the result list. + return @retVal; } =head3 AllFunctionsOf -C<< my %functions = $sprout->AllFunctionsOf($featureID); >> + my %functions = $sprout->AllFunctionsOf($featureID); Return all of the functional assignments for a particular feature. The data is returned as a hash of functional assignments to user IDs. A functional assignment is a type of annotation, -Functional assignments are described in the L function. Its worth noting that -we cannot filter on the content of the annotation itself because it's a text field; however, -this is not a big problem because most features only have a small number of annotations. -Finally, if a single user has multiple functional assignments, we will only keep the most +Functional assignments are described in the L function. Its worth noting that +we cannot filter on the content of the annotation itself because it's a text field; however, +this is not a big problem because most features only have a small number of annotations. +Finally, if a single user has multiple functional assignments, we will only keep the most recent one. =over 4 @@ -1073,56 +1380,50 @@ =item RETURN -Returns a hash mapping the functional assignment IDs to user IDs. +Returns a hash mapping the user IDs to functional assignment IDs. =back =cut #: Return Type %; sub AllFunctionsOf { - # Get the parameters. - my ($self, $featureID) = @_; - # Get all of the feature's annotations. - my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'], - "IsTargetOfAnnotation(from-link) = ?", - [$featureID], ['Annotation(time)', 'Annotation(annotation)']); - # Declare the return hash. - my %retVal; - # Declare a hash for insuring we only make one assignment per user. - my %timeHash = (); + # Get the parameters. + my ($self, $featureID) = @_; + # Get all of the feature's annotations. + my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'], + "IsTargetOfAnnotation(from-link) = ?", + [$featureID], ['Annotation(time)', 'Annotation(annotation)', + 'MadeAnnotation(from-link)']); + # Declare the return hash. + my %retVal; # Now we sort the assignments by timestamp in reverse. my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query; - # Loop until we run out of annotations. + # Loop until we run out of annotations. for my $annotation (@sortedQuery) { # Get the annotation fields. - my ($timeStamp, $text) = @{$annotation}; - # Check to see if this is a functional assignment. - my ($user, $function) = _ParseAssignment($text); - if ($user && ! exists $timeHash{$user}) { + my ($timeStamp, $text, $user) = @{$annotation}; + # Check to see if this is a functional assignment. + my ($actualUser, $function) = _ParseAssignment($user, $text); + if ($actualUser && ! exists $retVal{$actualUser}) { # Here it is a functional assignment and there has been no # previous assignment for this user, so we stuff it in the # return hash. - $retVal{$function} = $user; - # Insure we don't assign to this user again. - $timeHash{$user} = 1; - } - } - # Return the hash of assignments found. - return %retVal; + $retVal{$actualUser} = $function; + } + } + # Return the hash of assignments found. + return %retVal; } =head3 FunctionOf -C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >> + my $functionText = $sprout->FunctionOf($featureID, $userID); Return the most recently-determined functional assignment of a particular feature. The functional assignment is handled differently depending on the type of feature. If -the feature is identified by a FIG ID (begins with the string C), then a functional -assignment is a type of annotation. The format of an assignment is described in -L. Its worth noting that we cannot filter on the content of the -annotation itself because it's a text field; however, this is not a big problem because -most features only have a small number of annotations. +the feature is identified by a FIG ID (begins with the string C), then the functional +assignment is taken from the B or C table, depending. Each user has an associated list of trusted users. The assignment returned will be the most recent one by at least one of the trusted users. If no trusted user list is available, then @@ -1141,8 +1442,8 @@ =item userID (optional) -ID of the user whose function determination is desired. If omitted, only the latest -C assignment will be returned. +ID of the user whose function determination is desired. If omitted, the primary +functional assignment in the B table will be returned. =item RETURN @@ -1153,67 +1454,146 @@ =cut #: Return Type $; sub FunctionOf { - # Get the parameters. - my ($self, $featureID, $userID) = @_; + # Get the parameters. + my ($self, $featureID, $userID) = @_; # Declare the return value. my $retVal; # Determine the ID type. if ($featureID =~ m/^fig\|/) { - # Here we have a FIG feature ID. We must build the list of trusted - # users. - my %trusteeTable = (); - # Check the user ID. + # Here we have a FIG feature ID. if (!$userID) { - # No user ID, so only FIG is trusted. - $trusteeTable{FIG} = 1; + # Use the primary assignment. + ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']); } else { - # Add this user's ID. - $trusteeTable{$userID} = 1; - # Look for the trusted users in the database. - my @trustees = $self->GetFlat(['IsTrustedBy'], 'IsTrustedBy(from-link) = ?', [$userID], 'IsTrustedBy(to-link)'); - if (! @trustees) { - # None were found, so build a default list. + # We must build the list of trusted users. + my %trusteeTable = (); + # Check the user ID. + if (!$userID) { + # No user ID, so only FIG is trusted. $trusteeTable{FIG} = 1; } else { - # Otherwise, put all the trustees in. - for my $trustee (@trustees) { - $trusteeTable{$trustee} = 1; + # Add this user's ID. + $trusteeTable{$userID} = 1; + # Look for the trusted users in the database. + my @trustees = $self->GetFlat(['IsTrustedBy'], 'IsTrustedBy(from-link) = ?', [$userID], 'IsTrustedBy(to-link)'); + if (! @trustees) { + # None were found, so build a default list. + $trusteeTable{FIG} = 1; + } else { + # Otherwise, put all the trustees in. + for my $trustee (@trustees) { + $trusteeTable{$trustee} = 1; + } + } + } + # Build a query for all of the feature's annotations, sorted by date. + my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'], + "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC", + [$featureID]); + my $timeSelected = 0; + # Loop until we run out of annotations. + while (my $annotation = $query->Fetch()) { + # Get the annotation text. + my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)', + 'Annotation(time)', 'MadeAnnotation(from-link)']); + # Check to see if this is a functional assignment for a trusted user. + my ($actualUser, $function) = _ParseAssignment($user, $text); + Trace("Assignment user is $actualUser, text is $function.") if T(4); + if ($actualUser) { + # Here it is a functional assignment. Check the time and the user + # name. The time must be recent and the user must be trusted. + if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) { + $retVal = $function; + $timeSelected = $time; + } } } } + } else { + # Here we have a non-FIG feature ID. In this case the user ID does not + # matter. We simply get the information from the External Alias Function + # table. + ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']); + } + # Return the assignment found. + return $retVal; +} + +=head3 FunctionsOf + + my @functionList = $sprout->FunctionOf($featureID, $userID); + +Return the functional assignments of a particular feature. + +The functional assignment is handled differently depending on the type of feature. If +the feature is identified by a FIG ID (begins with the string C), then a functional +assignment is a type of annotation. The format of an assignment is described in +L. Its worth noting that we cannot filter on the content of the +annotation itself because it's a text field; however, this is not a big problem because +most features only have a small number of annotations. + +If the feature is B identified by a FIG ID, then the functional assignment +information is taken from the B table. If the table does +not contain an entry for the feature, an empty list is returned. + +=over 4 + +=item featureID + +ID of the feature whose functional assignments are desired. + +=item RETURN + +Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by +that user. + +=back + +=cut +#: Return Type @@; +sub FunctionsOf { + # Get the parameters. + my ($self, $featureID) = @_; + # Declare the return value. + my @retVal = (); + # Determine the ID type. + if ($featureID =~ m/^fig\|/) { + # Here we have a FIG feature ID. We must build the list of trusted + # users. + my %trusteeTable = (); # Build a query for all of the feature's annotations, sorted by date. - my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'], + my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'], "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC", [$featureID]); my $timeSelected = 0; # Loop until we run out of annotations. while (my $annotation = $query->Fetch()) { # Get the annotation text. - my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']); + my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)', + 'Annotation(time)', + 'MadeAnnotation(user)']); # Check to see if this is a functional assignment for a trusted user. - my ($user, $function) = _ParseAssignment($text); - if ($user) { - # Here it is a functional assignment. Check the time and the user - # name. The time must be recent and the user must be trusted. - if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) { - $retVal = $function; - $timeSelected = $time; - } + my ($actualUser, $function) = _ParseAssignment($user, $text); + if ($actualUser) { + # Here it is a functional assignment. + push @retVal, [$actualUser, $function]; } } } else { # Here we have a non-FIG feature ID. In this case the user ID does not # matter. We simply get the information from the External Alias Function # table. - ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']); + my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID, + ['ExternalAliasFunc(func)']); + push @retVal, map { ['master', $_] } @assignments; } - # Return the assignment found. - return $retVal; + # Return the assignments found. + return @retVal; } =head3 BBHList -C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >> + my $bbhHash = $sprout->BBHList($genomeID, \@featureList); Return a hash mapping the features in a specified list to their bidirectional best hits on a specified target genome. @@ -1230,170 +1610,390 @@ =item RETURN -Returns a reference to a hash that maps the IDs of the incoming features to the IDs of -their best hits. +Returns a reference to a hash that maps the IDs of the incoming features to the best hits +on the target genome. =back =cut #: Return Type %; sub BBHList { - # Get the parameters. - my ($self, $genomeID, $featureList) = @_; - # Create the return structure. - my %retVal = (); - # Loop through the incoming features. - for my $featureID (@{$featureList}) { - # Create a query to get the feature's best hit. - my $query = $self->Get(['IsBidirectionalBestHitOf'], - "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?", - [$featureID, $genomeID]); - # Look for the best hit. - my $bbh = $query->Fetch; - if ($bbh) { - my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)'); - $retVal{$featureID} = $targetFeature; - } - } - # Return the mapping. - return \%retVal; + # Get the parameters. + my ($self, $genomeID, $featureList) = @_; + # Create the return structure. + my %retVal = (); + # Loop through the incoming features. + for my $featureID (@{$featureList}) { + # Ask the server for the feature's best hit. + my @bbhData = FIGRules::BBHData($featureID); + # Peel off the BBHs found. + my @found = (); + for my $bbh (@bbhData) { + my $fid = $bbh->[0]; + my $bbGenome = $self->GenomeOf($fid); + if ($bbGenome eq $genomeID) { + push @found, $fid; + } + } + $retVal{$featureID} = \@found; + } + # Return the mapping. + return \%retVal; } -=head3 FeatureAliases +=head3 SimList -C<< my @aliasList = $sprout->FeatureAliases($featureID); >> + my %similarities = $sprout->SimList($featureID, $count); -Return a list of the aliases for a specified feature. +Return a list of the similarities to the specified feature. + +This method just returns the bidirectional best hits for performance reasons. =over 4 =item featureID -ID of the feature whose aliases are desired. +ID of the feature whose similarities are desired. -=item RETURN +=item count -Returns a list of the feature's aliases. If the feature is not found or has no aliases, it will -return an empty list. +Maximum number of similar features to be returned, or C<0> to return them all. =back =cut -#: Return Type @; -sub FeatureAliases { - # Get the parameters. - my ($self, $featureID) = @_; - # Get the desired feature's aliases - my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']); - # Return the result. - return @retVal; +#: Return Type %; +sub SimList { + # Get the parameters. + my ($self, $featureID, $count) = @_; + # Ask for the best hits. + my @lists = FIGRules::BBHData($featureID); + # Create the return value. + my %retVal = (); + for my $tuple (@lists) { + $retVal{$tuple->[0]} = $tuple->[1]; + } + # Return the result. + return %retVal; } -=head3 GenomeOf +=head3 IsComplete -C<< my $genomeID = $sprout->GenomeOf($featureID); >> + my $flag = $sprout->IsComplete($genomeID); -Return the genome that contains a specified feature. +Return TRUE if the specified genome is complete, else FALSE. =over 4 -=item featureID +=item genomeID -ID of the feature whose genome is desired. +ID of the genome whose completeness status is desired. =item RETURN -Returns the ID of the genome for the specified feature. If the feature is not found, returns -an undefined value. +Returns TRUE if the genome is complete, FALSE if it is incomplete, and C if it is +not found. =back =cut #: Return Type $; -sub GenomeOf { - # Get the parameters. - my ($self, $featureID) = @_; - # Create a query to find the genome associated with the feature. - my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]); - # Declare the return value. - my $retVal; - # Get the genome ID. - if (my $relationship = $query->Fetch()) { - ($retVal) = $relationship->Value('HasContig(from-link)'); - } - # Return the value found. - return $retVal; +sub IsComplete { + # Get the parameters. + my ($self, $genomeID) = @_; + # Declare the return variable. + my $retVal; + # Get the genome's data. + my $genomeData = $self->GetEntity('Genome', $genomeID); + if ($genomeData) { + # The genome exists, so get the completeness flag. + $retVal = $genomeData->PrimaryValue('Genome(complete)'); + } + # Return the result. + return $retVal; } -=head3 CoupledFeatures +=head3 FeatureAliases -C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >> + my @aliasList = $sprout->FeatureAliases($featureID); -Return the features functionally coupled with a specified feature. Features are considered -functionally coupled if they tend to be clustered on the same chromosome. +Return a list of the aliases for a specified feature. =over 4 =item featureID -ID of the feature whose functionally-coupled brethren are desired. +ID of the feature whose aliases are desired. =item RETURN -A hash mapping the functionally-coupled feature IDs to the coupling score. +Returns a list of the feature's aliases. If the feature is not found or has no aliases, it will +return an empty list. =back =cut -#: Return Type %; -sub CoupledFeatures { - # Get the parameters. - my ($self, $featureID) = @_; - # Create a query to retrieve the functionally-coupled features. Note that we depend on the - # fact that the functional coupling is physically paired. If (A,B) is in the database, then - # (B,A) will also be found. - my $query = $self->Get(['IsClusteredOnChromosomeWith'], - "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]); - # This value will be set to TRUE if we find at least one coupled feature. - my $found = 0; - # Create the return hash. - my %retVal = (); - # Retrieve the relationship records and store them in the hash. - while (my $clustering = $query->Fetch()) { - my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)', - 'IsClusteredOnChromosomeWith(score)']); - $retVal{$otherFeatureID} = $score; - $found = 1; - } - # Functional coupling is reflexive. If we found at least one coupled feature, we must add - # the incoming feature as well. - if ($found) { - $retVal{$featureID} = 9999; - } - # Return the hash. - return %retVal; +#: Return Type @; +sub FeatureAliases { + # Get the parameters. + my ($self, $featureID) = @_; + # Get the desired feature's aliases + my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)'); + # Return the result. + return @retVal; } -=head3 GetEntityTypes +=head3 GenomeOf -C<< my @entityList = $sprout->GetEntityTypes(); >> + my $genomeID = $sprout->GenomeOf($featureID); -Return the list of supported entity types. +Return the genome that contains a specified feature or contig. -=cut -#: Return Type @; -sub GetEntityTypes { - # Get the parameters. - my ($self) = @_; - # Get the underlying database object. - my $erdb = $self->{_erdb}; - # Get its entity type list. - my @retVal = $erdb->GetEntityTypes(); +=over 4 + +=item featureID + +ID of the feature or contig whose genome is desired. + +=item RETURN + +Returns the ID of the genome for the specified feature or contig. If the feature or contig is not +found, returns an undefined value. + +=back + +=cut +#: Return Type $; +sub GenomeOf { + # Get the parameters. + my ($self, $featureID) = @_; + # Declare the return value. + my $retVal; + # Parse the genome ID from the feature ID. + if ($featureID =~ /^fig\|(\d+\.\d+)/) { + $retVal = $1; + } else { + Confess("Invalid feature ID $featureID."); + } + # Return the value found. + return $retVal; +} + +=head3 CoupledFeatures + + my %coupleHash = $sprout->CoupledFeatures($featureID); + +Return the features functionally coupled with a specified feature. Features are considered +functionally coupled if they tend to be clustered on the same chromosome. + +=over 4 + +=item featureID + +ID of the feature whose functionally-coupled brethren are desired. + +=item RETURN + +A hash mapping the functionally-coupled feature IDs to the coupling score. + +=back + +=cut +#: Return Type %; +sub CoupledFeatures { + # Get the parameters. + my ($self, $featureID) = @_; + # Ask the coupling server for the data. + Trace("Looking for features coupled to $featureID.") if T(coupling => 3); + my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID); + Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3); + # Form them into a hash. + my %retVal = (); + for my $pair (@rawPairs) { + # Get the feature ID and score. + my ($featureID2, $score) = @{$pair}; + # Only proceed if the feature is in NMPDR. + if ($self->_CheckFeature($featureID2)) { + $retVal{$featureID2} = $score; + } + } + # Functional coupling is reflexive. If we found at least one coupled feature, we must add + # the incoming feature as well. + if (keys %retVal) { + $retVal{$featureID} = 9999; + } + # Return the hash. + return %retVal; +} + +=head3 CouplingEvidence + + my @evidence = $sprout->CouplingEvidence($peg1, $peg2); + +Return the evidence for a functional coupling. + +A pair of features is considered evidence of a coupling between two other +features if they occur close together on a contig and both are similar to +the coupled features. So, if B and B are close together on a contig, +B and B are considered evidence for the coupling if (1) B and +B are close together, (2) B is similar to B, and (3) B is +similar to B. + +The score of a coupling is determined by the number of pieces of evidence +that are considered I. If several evidence items belong to +a group of genomes that are close to each other, only one of those items +is considered representative. The other evidence items are presumed to be +there because of the relationship between the genomes rather than because +the two proteins generated by the features have a related functionality. + +Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,> +I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a> +is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative +and FALSE otherwise. + +=over 4 + +=item peg1 + +ID of the feature of interest. + +=item peg2 + +ID of a feature functionally coupled to the feature of interest. + +=item RETURN + +Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature +of interest, a feature similar to the functionally coupled feature, and a flag +that is TRUE for a representative piece of evidence and FALSE otherwise. + +=back + +=cut +#: Return Type @@; +sub CouplingEvidence { + # Get the parameters. + my ($self, $peg1, $peg2) = @_; + # Declare the return variable. + my @retVal = (); + # Get the coupling and evidence data. + my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2); + # Loop through the raw data, saving the ones that are in NMPDR genomes. + for my $rawTuple (@rawData) { + if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) { + push @retVal, $rawTuple; + } + } + # Return the result. + return @retVal; +} + +=head3 GetSynonymGroup + + my $id = $sprout->GetSynonymGroup($fid); + +Return the synonym group name for the specified feature. + +=over 4 + +=item fid + +ID of the feature whose synonym group is desired. + +=item RETURN + +The name of the synonym group to which the feature belongs. If the feature does +not belong to a synonym group, the feature ID itself is returned. + +=back + +=cut + +sub GetSynonymGroup { + # Get the parameters. + my ($self, $fid) = @_; + # Declare the return variable. + my $retVal; + # Find the synonym group. + my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?", + [$fid], 'IsSynonymGroupFor(from-link)'); + # Check to see if we found anything. + if (@groups) { + $retVal = $groups[0]; + } else { + $retVal = $fid; + } + # Return the result. + return $retVal; +} + +=head3 GetBoundaries + + my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList); + +Determine the begin and end boundaries for the locations in a list. All of the +locations must belong to the same contig and have mostly the same direction in +order for this method to produce a meaningful result. The resulting +begin/end pair will contain all of the bases in any of the locations. + +=over 4 + +=item locList + +List of locations to process. + +=item RETURN + +Returns a 3-tuple consisting of the contig ID, the beginning boundary, +and the ending boundary. The beginning boundary will be left of the +end for mostly-forward locations and right of the end for mostly-backward +locations. + +=back + +=cut + +sub GetBoundaries { + # Get the parameters. + my ($self, @locList) = @_; + # Set up the counters used to determine the most popular direction. + my %counts = ( '+' => 0, '-' => 0 ); + # Get the last location and parse it. + my $locObject = BasicLocation->new(pop @locList); + # Prime the loop with its data. + my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right); + # Count its direction. + $counts{$locObject->Dir}++; + # Loop through the remaining locations. Note that in most situations, this loop + # will not iterate at all, because most of the time we will be dealing with a + # singleton list. + for my $loc (@locList) { + # Create a location object. + my $locObject = BasicLocation->new($loc); + # Count the direction. + $counts{$locObject->Dir}++; + # Get the left end and the right end. + my $left = $locObject->Left; + my $right = $locObject->Right; + # Merge them into the return variables. + if ($left < $beg) { + $beg = $left; + } + if ($right > $end) { + $end = $right; + } + } + # If the most common direction is reverse, flip the begin and end markers. + if ($counts{'-'} > $counts{'+'}) { + ($beg, $end) = ($end, $beg); + } + # Return the result. + return ($contig, $beg, $end); } =head3 ReadFasta -C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >> + my %sequenceData = Sprout::ReadFasta($fileName, $prefix); Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by one or more lines of data. The first line begins with a > character and contains an ID. @@ -1418,53 +2018,53 @@ =cut #: Return Type %; sub ReadFasta { - # Get the parameters. - my ($fileName, $prefix) = @_; - # Create the return hash. - my %retVal = (); - # Open the file for input. - open FASTAFILE, '<', $fileName; - # Declare the ID variable and clear the sequence accumulator. - my $sequence = ""; - my $id = ""; - # Loop through the file. - while () { - # Get the current line. - my $line = $_; - # Check for a header line. - if ($line =~ m/^>\s*(.+?)(\s|\n)/) { - # Here we have a new header. Store the current sequence if we have one. - if ($id) { - $retVal{$id} = uc $sequence; - } - # Clear the sequence accumulator and save the new ID. - ($id, $sequence) = ("$prefix$1", ""); - } else { - # Here we have a data line, so we add it to the sequence accumulator. - # First, we get the actual data out. Note that we normalize to upper - # case. - $line =~ /^\s*(.*?)(\s|\n)/; - $sequence .= $1; - } - } - # Flush out the last sequence (if any). - if ($sequence) { - $retVal{$id} = uc $sequence; - } - # Close the file. - close FASTAFILE; - # Return the hash constructed from the file. - return %retVal; + # Get the parameters. + my ($fileName, $prefix) = @_; + # Create the return hash. + my %retVal = (); + # Open the file for input. + open FASTAFILE, '<', $fileName; + # Declare the ID variable and clear the sequence accumulator. + my $sequence = ""; + my $id = ""; + # Loop through the file. + while () { + # Get the current line. + my $line = $_; + # Check for a header line. + if ($line =~ m/^>\s*(.+?)(\s|\n)/) { + # Here we have a new header. Store the current sequence if we have one. + if ($id) { + $retVal{$id} = lc $sequence; + } + # Clear the sequence accumulator and save the new ID. + ($id, $sequence) = ("$prefix$1", ""); + } else { + # Here we have a data line, so we add it to the sequence accumulator. + # First, we get the actual data out. Note that we normalize to lower + # case. + $line =~ /^\s*(.*?)(\s|\n)/; + $sequence .= $1; + } + } + # Flush out the last sequence (if any). + if ($sequence) { + $retVal{$id} = lc $sequence; + } + # Close the file. + close FASTAFILE; + # Return the hash constructed from the file. + return %retVal; } =head3 FormatLocations -C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >> + my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); Insure that a list of feature locations is in the Sprout format. The Sprout feature location format is I_I where I<*> is C<+> for a forward gene and C<-> for a backward gene. The old format is I_I_I. If a feature is in the new format already, -it will not be changed; otherwise, it will be converted. This method can also be used to +it will not be changed; otherwise, it will be converted. This method can also be used to perform the reverse task-- insuring that all the locations are in the old format. =over 4 @@ -1491,70 +2091,151 @@ =cut #: Return Type @; sub FormatLocations { - # Get the parameters. - my ($self, $prefix, $locations, $oldFormat) = @_; - # Create the return list. - my @retVal = (); - # Check to see if any locations were passed in. - if ($locations eq '') { - Confess("No locations specified."); - } else { - # Loop through the locations, converting them to the new format. - for my $location (@{$locations}) { - # Parse the location elements. - my ($contig, $beg, $dir, $len) = ParseLocation($location); - # Process according to the desired output format. - if (!$oldFormat) { - # Here we're producing the new format. Add the location to the return list. - push @retVal, "$prefix${contig}_$beg$dir$len"; - } elsif ($dir eq '+') { - # Here we're producing the old format and it's a forward gene. - my $end = $beg + $len - 1; - push @retVal, "$prefix${contig}_${beg}_$end"; - } else { - # Here we're producting the old format and it's a backward gene. - my $end = $beg - $len + 1; - push @retVal, "$prefix${contig}_${beg}_$end"; - } - } - } - # Return the normalized list. - return @retVal; + # Get the parameters. + my ($self, $prefix, $locations, $oldFormat) = @_; + # Create the return list. + my @retVal = (); + # Check to see if any locations were passed in. + if ($locations eq '') { + Confess("No locations specified."); + } else { + # Loop through the locations, converting them to the new format. + for my $location (@{$locations}) { + # Parse the location elements. + my ($contig, $beg, $dir, $len) = ParseLocation($location); + # Process according to the desired output format. + if (!$oldFormat) { + # Here we're producing the new format. Add the location to the return list. + push @retVal, "$prefix${contig}_$beg$dir$len"; + } elsif ($dir eq '+') { + # Here we're producing the old format and it's a forward gene. + my $end = $beg + $len - 1; + push @retVal, "$prefix${contig}_${beg}_$end"; + } else { + # Here we're producting the old format and it's a backward gene. + my $end = $beg - $len + 1; + push @retVal, "$prefix${contig}_${beg}_$end"; + } + } + } + # Return the normalized list. + return @retVal; } =head3 DumpData -C<< $sprout->DumpData(); >> + $sprout->DumpData(); Dump all the tables to tab-delimited DTX files. The files will be stored in the data directory. =cut sub DumpData { - # Get the parameters. - my ($self) = @_; - # Get the data directory name. - my $outputDirectory = $self->{_options}->{dataDir}; - # Dump the relations. - $self->{_erdb}->DumpRelations($outputDirectory); + # Get the parameters. + my ($self) = @_; + # Get the data directory name. + my $outputDirectory = $self->{_options}->{dataDir}; + # Dump the relations. + $self->DumpRelations($outputDirectory); } =head3 XMLFileName -C<< my $fileName = $sprout->XMLFileName(); >> + my $fileName = $sprout->XMLFileName(); Return the name of this database's XML definition file. =cut #: Return Type $; sub XMLFileName { - my ($self) = @_; - return $self->{_xmlName}; + my ($self) = @_; + return $self->{_xmlName}; +} + +=head3 GetGenomeNameData + + my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID); + +Return the genus, species, and unique characterization for a genome. This +is similar to L, with the exception that it returns the +values in three seperate fields. + +=over 4 + +=item genomeID + +ID of the genome whose name data is desired. + +=item RETURN + +Returns a three-element list, consisting of the genus, species, and strain +of the specified genome. If the genome is not found, an error occurs. + +=back + +=cut + +sub GetGenomeNameData { + # Get the parameters. + my ($self, $genomeID) = @_; + # Get the desired values. + my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID => + [qw(Genome(genus) Genome(species) Genome(unique-characterization))]); + # Throw an error if they were not found. + if (! defined $genus) { + Confess("Genome $genomeID not found in database."); + } + # Return the results. + return ($genus, $species, $strain); +} + +=head3 GetGenomeByNameData + + my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain); + +Return a list of the IDs of the genomes with the specified genus, +species, and strain. In almost every case, there will be either zero or +one IDs returned; however, two or more IDs could be returned if there are +multiple versions of the genome in the database. + +=over 4 + +=item genus + +Genus of the desired genome. + +=item species + +Species of the desired genome. + +=item strain + +Strain (unique characterization) of the desired genome. This may be an empty +string, in which case it is presumed that the desired genome has no strain +specified. + +=item RETURN + +Returns a list of the IDs of the genomes having the specified genus, species, and +strain. + +=back + +=cut + +sub GetGenomeByNameData { + # Get the parameters. + my ($self, $genus, $species, $strain) = @_; + # Try to find the genomes. + my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?", + [$genus, $species, $strain], 'Genome(id)'); + # Return the result. + return @retVal; } =head3 Insert -C<< $sprout->Insert($objectType, \%fieldHash); >> + $sprout->Insert($objectType, \%fieldHash); Insert an entity or relationship instance into the database. The entity or relationship of interest is defined by a type name and then a hash of field names to values. Field values in the primary @@ -1563,12 +2244,12 @@ list references. For example, the following line inserts an inactive PEG feature named C with aliases C and C. -C<< $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >> + $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); The next statement inserts a C relationship between feature C and property C<4> with an evidence URL of C. -C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >> + $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); =over 4 @@ -1585,15 +2266,15 @@ =cut #: Return Type ; sub Insert { - # Get the parameters. - my ($self, $objectType, $fieldHash) = @_; - # Call the underlying method. - $self->{_erdb}->InsertObject($objectType, $fieldHash); + # Get the parameters. + my ($self, $objectType, $fieldHash) = @_; + # Call the underlying method. + $self->InsertObject($objectType, $fieldHash); } =head3 Annotate -C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >> + my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); Annotate a feature. This inserts an Annotation record into the database and links it to the specified feature and user. @@ -1626,28 +2307,28 @@ =cut #: Return Type $; sub Annotate { - # Get the parameters. - my ($self, $fid, $timestamp, $user, $text) = @_; - # Create the annotation ID. - my $aid = "$fid:$timestamp"; - # Insert the Annotation object. - my $retVal = $self->Insert('Annotation', { id => $aid, time => $timestamp, annotation => $text }); - if ($retVal) { - # Connect it to the user. - $retVal = $self->Insert('MadeAnnotation', { 'from-link' => $user, 'to-link' => $aid }); - if ($retVal) { - # Connect it to the feature. - $retVal = $self->Insert('IsTargetOfAnnotation', { 'from-link' => $fid, - 'to-link' => $aid }); - } - } - # Return the success indicator. - return $retVal; + # Get the parameters. + my ($self, $fid, $timestamp, $user, $text) = @_; + # Create the annotation ID. + my $aid = "$fid:$timestamp"; + # Insert the Annotation object. + my $retVal = $self->Insert('Annotation', { id => $aid, time => $timestamp, annotation => $text }); + if ($retVal) { + # Connect it to the user. + $retVal = $self->Insert('MadeAnnotation', { 'from-link' => $user, 'to-link' => $aid }); + if ($retVal) { + # Connect it to the feature. + $retVal = $self->Insert('IsTargetOfAnnotation', { 'from-link' => $fid, + 'to-link' => $aid }); + } + } + # Return the success indicator. + return $retVal; } =head3 AssignFunction -C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >> + my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); This method assigns a function to a feature. Functions are a special type of annotation. The general format is described in L. @@ -1679,35 +2360,35 @@ =cut #: Return Type $; sub AssignFunction { - # Get the parameters. - my ($self, $featureID, $user, $function, $assigningUser) = @_; + # Get the parameters. + my ($self, $featureID, $user, $function, $assigningUser) = @_; # Default the assigning user. if (! $assigningUser) { $assigningUser = $user; } - # Create an annotation string from the parameters. - my $annotationText = "$assigningUser\nset $user function to\n$function"; - # Get the current time. - my $now = time; - # Declare the return variable. - my $retVal = 1; - # Locate the genome containing the feature. - my $genome = $self->GenomeOf($featureID); - if (!$genome) { - # Here the genome was not found. This probably means the feature ID is invalid. - Trace("No genome found for feature $featureID.") if T(0); - $retVal = 0; - } else { - # Here we know we have a feature with a genome. Store the annotation. + # Create an annotation string from the parameters. + my $annotationText = "$assigningUser\nset $user function to\n$function"; + # Get the current time. + my $now = time; + # Declare the return variable. + my $retVal = 1; + # Locate the genome containing the feature. + my $genome = $self->GenomeOf($featureID); + if (!$genome) { + # Here the genome was not found. This probably means the feature ID is invalid. + Trace("No genome found for feature $featureID.") if T(0); + $retVal = 0; + } else { + # Here we know we have a feature with a genome. Store the annotation. $retVal = $self->Annotate($featureID, $now, $user, $annotationText); - } - # Return the success indicator. - return $retVal; + } + # Return the success indicator. + return $retVal; } =head3 FeaturesByAlias -C<< my @features = $sprout->FeaturesByAlias($alias); >> + my @features = $sprout->FeaturesByAlias($alias); Returns a list of features with the specified alias. The alias is parsed to determine the type of the alias. A string of digits is a GenBack ID and a string of exactly 6 @@ -1730,60 +2411,26 @@ =cut #: Return Type @; sub FeaturesByAlias { - # Get the parameters. - my ($self, $alias) = @_; - # Declare the return variable. - my @retVal = (); - # Parse the alias. - my ($mappedAlias, $flag) = FIGRules::NormalizeAlias($alias); - # If it's a FIG alias, we're done. - if ($flag) { - push @retVal, $mappedAlias; - } else { - # Here we have a non-FIG alias. Get the features with the normalized alias. - @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)'); - } - # Return the result. - return @retVal; -} - -=head3 Exists - -C<< my $found = $sprout->Exists($entityName, $entityID); >> - -Return TRUE if an entity exists, else FALSE. - -=over 4 - -=item entityName - -Name of the entity type (e.g. C) relevant to the existence check. - -=item entityID - -ID of the entity instance whose existence is to be checked. - -=item RETURN - -Returns TRUE if the entity instance exists, else FALSE. - -=back - -=cut -#: Return Type $; -sub Exists { - # Get the parameters. - my ($self, $entityName, $entityID) = @_; - # Check for the entity instance. - my $testInstance = $self->GetEntity($entityName, $entityID); - # Return an existence indicator. - my $retVal = ($testInstance ? 1 : 0); - return $retVal; + # Get the parameters. + my ($self, $alias) = @_; + # Declare the return variable. + my @retVal = (); + # Parse the alias. + my ($mappedAlias, $flag) = FIGRules::NormalizeAlias($alias); + # If it's a FIG alias, we're done. + if ($flag) { + push @retVal, $mappedAlias; + } else { + # Here we have a non-FIG alias. Get the features with the normalized alias. + @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)'); + } + # Return the result. + return @retVal; } =head3 FeatureTranslation -C<< my $translation = $sprout->FeatureTranslation($featureID); >> + my $translation = $sprout->FeatureTranslation($featureID); Return the translation of a feature. @@ -1802,22 +2449,22 @@ =cut #: Return Type $; sub FeatureTranslation { - # Get the parameters. - my ($self, $featureID) = @_; - # Get the specified feature's translation. - my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']); - return $retVal; + # Get the parameters. + my ($self, $featureID) = @_; + # Get the specified feature's translation. + my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']); + return $retVal; } =head3 Taxonomy -C<< my @taxonomyList = $sprout->Taxonomy($genome); >> + my @taxonomyList = $sprout->Taxonomy($genome); Return the taxonomy of the specified genome. This will be in the form of a list containing the various classifications in order from domain (eg. C, C, or C) to sub-species. For example, -C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >> + (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) =over 4 @@ -1834,25 +2481,25 @@ =cut #: Return Type @; sub Taxonomy { - # Get the parameters. - my ($self, $genome) = @_; - # Find the specified genome's taxonomy string. - my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']); - # Declare the return variable. - my @retVal = (); - # If we found the genome, return its taxonomy string. - if ($list) { - @retVal = split /\s*;\s*/, $list; - } else { - Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0); - } - # Return the value found. - return @retVal; + # Get the parameters. + my ($self, $genome) = @_; + # Find the specified genome's taxonomy string. + my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']); + # Declare the return variable. + my @retVal = (); + # If we found the genome, return its taxonomy string. + if ($list) { + @retVal = split /\s*;\s*/, $list; + } else { + Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0); + } + # Return the value found. + return @retVal; } =head3 CrudeDistance -C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >> + my $distance = $sprout->CrudeDistance($genome1, $genome2); Returns a crude estimate of the distance between two genomes. The distance is construed so that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains. @@ -1877,34 +2524,34 @@ =cut #: Return Type $; sub CrudeDistance { - # Get the parameters. - my ($self, $genome1, $genome2) = @_; - # Insure that the distance is commutative by sorting the genome IDs. - my ($genomeA, $genomeB); - if ($genome2 < $genome2) { - ($genomeA, $genomeB) = ($genome1, $genome2); - } else { - ($genomeA, $genomeB) = ($genome2, $genome1); - } - my @taxA = $self->Taxonomy($genomeA); - my @taxB = $self->Taxonomy($genomeB); - # Initialize the distance to 1. We'll reduce it each time we find a match between the - # taxonomies. - my $retVal = 1.0; - # Initialize the subtraction amount. This amount determines the distance reduction caused - # by a mismatch at the current level. - my $v = 0.5; - # Loop through the taxonomies. - for (my $i = 0; ($i < @taxA) && ($i < @taxB) && ($taxA[$i] eq $taxB[$i]); $i++) { - $retVal -= $v; - $v /= 2; - } + # Get the parameters. + my ($self, $genome1, $genome2) = @_; + # Insure that the distance is commutative by sorting the genome IDs. + my ($genomeA, $genomeB); + if ($genome2 < $genome2) { + ($genomeA, $genomeB) = ($genome1, $genome2); + } else { + ($genomeA, $genomeB) = ($genome2, $genome1); + } + my @taxA = $self->Taxonomy($genomeA); + my @taxB = $self->Taxonomy($genomeB); + # Initialize the distance to 1. We'll reduce it each time we find a match between the + # taxonomies. + my $retVal = 1.0; + # Initialize the subtraction amount. This amount determines the distance reduction caused + # by a mismatch at the current level. + my $v = 0.5; + # Loop through the taxonomies. + for (my $i = 0; ($i < @taxA) && ($i < @taxB) && ($taxA[$i] eq $taxB[$i]); $i++) { + $retVal -= $v; + $v /= 2; + } return $retVal; } =head3 RoleName -C<< my $roleName = $sprout->RoleName($roleID); >> + my $roleName = $sprout->RoleName($roleID); Return the descriptive name of the role with the specified ID. In general, a role will only have a descriptive name if it is coded as an EC number. @@ -1924,21 +2571,21 @@ =cut #: Return Type $; sub RoleName { - # Get the parameters. - my ($self, $roleID) = @_; - # Get the specified role's name. - my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']); - # Use the ID if the role has no name. - if (!$retVal) { - $retVal = $roleID; - } - # Return the name. - return $retVal; + # Get the parameters. + my ($self, $roleID) = @_; + # Get the specified role's name. + my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']); + # Use the ID if the role has no name. + if (!$retVal) { + $retVal = $roleID; + } + # Return the name. + return $retVal; } =head3 RoleDiagrams -C<< my @diagrams = $sprout->RoleDiagrams($roleID); >> + my @diagrams = $sprout->RoleDiagrams($roleID); Return a list of the diagrams containing a specified functional role. @@ -1957,26 +2604,110 @@ =cut #: Return Type @; sub RoleDiagrams { - # Get the parameters. - my ($self, $roleID) = @_; - # Query for the diagrams. - my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID], - 'RoleOccursIn(to-link)'); - # Return the result. - return @retVal; + # Get the parameters. + my ($self, $roleID) = @_; + # Query for the diagrams. + my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID], + 'RoleOccursIn(to-link)'); + # Return the result. + return @retVal; +} + +=head3 GetProperties + + my @list = $sprout->GetProperties($fid, $key, $value, $url); + +Return a list of the properties with the specified characteristics. + +Properties are the Sprout analog of the FIG attributes. The call is +passed directly to the CustomAttributes or RemoteCustomAttributes object +contained in this object. + +This method returns a series of tuples that match the specified criteria. Each tuple +will contain an object ID, a key, and one or more values. The parameters to this +method therefore correspond structurally to the values expected in each tuple. In +addition, you can ask for a generic search by suffixing a percent sign (C<%>) to any +of the parameters. So, for example, + + my @attributeList = $sprout->GetProperties('fig|100226.1.peg.1004', 'structure%', 1, 2); + +would return something like + + ['fig}100226.1.peg.1004', 'structure', 1, 2] + ['fig}100226.1.peg.1004', 'structure1', 1, 2] + ['fig}100226.1.peg.1004', 'structure2', 1, 2] + ['fig}100226.1.peg.1004', 'structureA', 1, 2] + +Use of C in any position acts as a wild card (all values). You can also specify +a list reference in the ID column. Thus, + + my @attributeList = $sprout->GetProperties(['100226.1', 'fig|100226.1.%'], 'PUBMED'); + +would get the PUBMED attribute data for Streptomyces coelicolor A3(2) and all its +features. + +In addition to values in multiple sections, a single attribute key can have multiple +values, so even + + my @attributeList = $sprout->GetProperties($peg, 'virulent'); + +which has no wildcard in the key or the object ID, may return multiple tuples. + +=over 4 + +=item objectID + +ID of object whose attributes are desired. If the attributes are desired for multiple +objects, this parameter can be specified as a list reference. If the attributes are +desired for all objects, specify C or an empty string. Finally, you can specify +attributes for a range of object IDs by putting a percent sign (C<%>) at the end. + +=item key + +Attribute key name. A value of C or an empty string will match all +attribute keys. If the values are desired for multiple keys, this parameter can be +specified as a list reference. Finally, you can specify attributes for a range of +keys by putting a percent sign (C<%>) at the end. + +=item values + +List of the desired attribute values, section by section. If C +or an empty string is specified, all values in that section will match. A +generic match can be requested by placing a percent sign (C<%>) at the end. +In that case, all values that match up to and not including the percent sign +will match. You may also specify a regular expression enclosed +in slashes. All values that match the regular expression will be returned. For +performance reasons, only values have this extra capability. + +=item RETURN + +Returns a list of tuples. The first element in the tuple is an object ID, the +second is an attribute key, and the remaining elements are the sections of +the attribute value. All of the tuples will match the criteria set forth in +the parameter list. + +=back + +=cut + +sub GetProperties { + # Get the parameters. + my ($self, @parms) = @_; + # Declare the return variable. + my @retVal = $self->{_ca}->GetAttributes(@parms); + # Return the result. + return @retVal; } =head3 FeatureProperties -C<< my @properties = $sprout->FeatureProperties($featureID); >> + my @properties = $sprout->FeatureProperties($featureID); Return a list of the properties for the specified feature. Properties are key-value pairs that specify special characteristics of the feature. For example, a property could indicate that a feature is essential to the survival of the organism or that it has benign influence on the activities of a pathogen. Each property is returned as a triple of the form -C<($key,$value,$url)>, where C<$key> is the property name, C<$value> is its value (commonly -a 1 or a 0, but possibly a string or a floating-point value), and C<$url> is a string describing -the web address or citation in which the property's value for the feature was identified. +C<($key,@values)>, where C<$key> is the property name and C<@values> are its values. =over 4 @@ -1986,27 +2717,30 @@ =item RETURN -Returns a list of triples, each triple containing the property name, its value, and a URL or -citation. +Returns a list of tuples, each tuple containing the property name and its values. =back =cut #: Return Type @@; sub FeatureProperties { - # Get the parameters. - my ($self, $featureID) = @_; - # Get the properties. - my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID], - ['Property(property-name)', 'Property(property-value)', - 'HasProperty(evidence)']); - # Return the resulting list. - return @retVal; + # Get the parameters. + my ($self, $featureID) = @_; + # Get the properties. + my @attributes = $self->{_ca}->GetAttributes($featureID); + # Strip the feature ID off each tuple. + my @retVal = (); + for my $attributeRow (@attributes) { + shift @{$attributeRow}; + push @retVal, $attributeRow; + } + # Return the resulting list. + return @retVal; } =head3 DiagramName -C<< my $diagramName = $sprout->DiagramName($diagramID); >> + my $diagramName = $sprout->DiagramName($diagramID); Return the descriptive name of a diagram. @@ -2025,16 +2759,53 @@ =cut #: Return Type $; sub DiagramName { - # Get the parameters. - my ($self, $diagramID) = @_; - # Get the specified diagram's name and return it. - my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']); - return $retVal; + # Get the parameters. + my ($self, $diagramID) = @_; + # Get the specified diagram's name and return it. + my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']); + return $retVal; +} + +=head3 PropertyID + + my $id = $sprout->PropertyID($propName, $propValue); + +Return the ID of the specified property name and value pair, if the +pair exists. Only a small subset of the FIG attributes are stored as +Sprout properties, mostly for use in search optimization. + +=over 4 + +=item propName + +Name of the desired property. + +=item propValue + +Value expected for the desired property. + +=item RETURN + +Returns the ID of the name/value pair, or C if the pair does not exist. + +=back + +=cut + +sub PropertyID { + # Get the parameters. + my ($self, $propName, $propValue) = @_; + # Try to find the ID. + my ($retVal) = $self->GetFlat(['Property'], + "Property(property-name) = ? AND Property(property-value) = ?", + [$propName, $propValue], 'Property(id)'); + # Return the result. + return $retVal; } =head3 MergedAnnotations -C<< my @annotationList = $sprout->MergedAnnotations(\@list); >> + my @annotationList = $sprout->MergedAnnotations(\@list); Returns a merged list of the annotations for the features in a list. Each annotation is represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where @@ -2057,571 +2828,1085 @@ =cut #: Return Type @; sub MergedAnnotations { - # Get the parameters. - my ($self, $list) = @_; - # Create a list to hold the annotation tuples found. - my @tuples = (); - # Loop through the features in the input list. - for my $fid (@{$list}) { - # Create a list of this feature's annotation tuples. - my @newTuples = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'], - "IsTargetOfAnnotation(from-link) = ?", [$fid], - ['IsTargetOfAnnotation(from-link)', 'Annotation(time)', - 'MadeAnnotation(from-link)', 'Annotation(annotation)']); - # Put it in the result list. - push @tuples, @newTuples; - } - # Sort the result list by timestamp. - my @retVal = sort { $a->[1] <=> $b->[1] } @tuples; + # Get the parameters. + my ($self, $list) = @_; + # Create a list to hold the annotation tuples found. + my @tuples = (); + # Loop through the features in the input list. + for my $fid (@{$list}) { + # Create a list of this feature's annotation tuples. + my @newTuples = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'], + "IsTargetOfAnnotation(from-link) = ?", [$fid], + ['IsTargetOfAnnotation(from-link)', 'Annotation(time)', + 'MadeAnnotation(from-link)', 'Annotation(annotation)']); + # Put it in the result list. + push @tuples, @newTuples; + } + # Sort the result list by timestamp. + my @retVal = sort { $a->[1] <=> $b->[1] } @tuples; # Loop through and make the time stamps friendly. for my $tuple (@retVal) { $tuple->[1] = FriendlyTimestamp($tuple->[1]); } - # Return the sorted list. - return @retVal; + # Return the sorted list. + return @retVal; +} + +=head3 RoleNeighbors + + my @roleList = $sprout->RoleNeighbors($roleID); + +Returns a list of the roles that occur in the same diagram as the specified role. Because +diagrams and roles are in a many-to-many relationship with each other, the list is +essentially the set of roles from all of the maps that contain the incoming role. Such +roles are considered neighbors because they are used together in cellular subsystems. + +=over 4 + +=item roleID + +ID of the role whose neighbors are desired. + +=item RETURN + +Returns a list containing the IDs of the roles that are related to the incoming role. + +=back + +=cut +#: Return Type @; +sub RoleNeighbors { + # Get the parameters. + my ($self, $roleID) = @_; + # Get all the diagrams containing this role. + my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID], + 'RoleOccursIn(to-link)'); + # Create the return list. + my @retVal = (); + # Loop through the diagrams. + for my $diagramID (@diagrams) { + # Get all the roles in this diagram. + my @roles = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(to-link) = ?", [$diagramID], + 'RoleOccursIn(from-link)'); + # Add them to the return list. + push @retVal, @roles; + } + # Merge the duplicates from the list. + return Tracer::Merge(@retVal); +} + +=head3 FeatureLinks + + my @links = $sprout->FeatureLinks($featureID); + +Return a list of the web hyperlinks associated with a feature. The web hyperlinks are +to external websites describing either the feature itself or the organism containing it +and are represented in raw HTML. + +=over 4 + +=item featureID + +ID of the feature whose links are desired. + +=item RETURN + +Returns a list of the web links for this feature. + +=back + +=cut +#: Return Type @; +sub FeatureLinks { + # Get the parameters. + my ($self, $featureID) = @_; + # Get the feature's links. + my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']); + # Return the feature's links. + return @retVal; +} + +=head3 SubsystemsOf + + my %subsystems = $sprout->SubsystemsOf($featureID); + +Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped +to the roles the feature performs. + +=over 4 + +=item featureID + +ID of the feature whose subsystems are desired. + +=item RETURN + +Returns a hash mapping all the feature's subsystems to a list of the feature's roles. + +=back + +=cut +#: Return Type %@; +sub SubsystemsOf { + # Get the parameters. + my ($self, $featureID) = @_; + # Get the subsystem list. + my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'], + "ContainsFeature(to-link) = ?", [$featureID], + ['HasSSCell(from-link)', 'IsRoleOf(from-link)']); + # Create the return value. + my %retVal = (); + # Build a hash to weed out duplicates. Sometimes the same PEG and role appears + # in two spreadsheet cells. + my %dupHash = (); + # Loop through the results, adding them to the hash. + for my $record (@subsystems) { + # Get this subsystem and role. + my ($subsys, $role) = @{$record}; + # Insure it's the first time for both. + my $dupKey = "$subsys\n$role"; + if (! exists $dupHash{"$subsys\n$role"}) { + $dupHash{$dupKey} = 1; + push @{$retVal{$subsys}}, $role; + } + } + # Return the hash. + return %retVal; +} + +=head3 SubsystemList + + my @subsystems = $sprout->SubsystemList($featureID); + +Return a list containing the names of the subsystems in which the specified +feature participates. Unlike L, this method only returns the +subsystem names, not the roles. + +=over 4 + +=item featureID + +ID of the feature whose subsystem names are desired. + +=item RETURN + +Returns a list of the names of the subsystems in which the feature participates. + +=back + +=cut +#: Return Type @; +sub SubsystemList { + # Get the parameters. + my ($self, $featureID) = @_; + # Get the list of names. + my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?", + [$featureID], 'HasRoleInSubsystem(to-link)'); + # Return the result, sorted. + return sort @retVal; +} + +=head3 GenomeSubsystemData + + my %featureData = $sprout->GenomeSubsystemData($genomeID); + +Return a hash mapping genome features to their subsystem roles. + +=over 4 + +=item genomeID + +ID of the genome whose subsystem feature map is desired. + +=item RETURN + +Returns a hash mapping each feature of the genome to a list of 2-tuples. Eacb +2-tuple contains a subsystem name followed by a role ID. + +=back + +=cut + +sub GenomeSubsystemData { + # Get the parameters. + my ($self, $genomeID) = @_; + # Declare the return variable. + my %retVal = (); + # Get a list of the genome features that participate in subsystems. For each + # feature we get its spreadsheet cells and the corresponding roles. + my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'], + "HasFeature(from-link) = ?", [$genomeID], + ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']); + # Now we get a list of the spreadsheet cells and their associated subsystems. Subsystems + # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the + # list. We use it at the beginning to get all the spreadsheet cells for the genome and + # again at the end to filter out participation in subsystems with a negative variant code. + my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'], + "IsGenomeOf(from-link) = ? AND ParticipatesIn(variant-code) >= 0 AND ParticipatesIn(from-link) = ?", + [$genomeID, $genomeID], ['HasSSCell(to-link)', 'HasSSCell(from-link)']); + # Now "@roleData" lists the spreadsheet cell and role for each of the genome's features. + # "@cellData" lists the subsystem name for each of the genome's spreadsheet cells. We + # link these two lists together to create the result. First, we want a hash mapping + # spreadsheet cells to subsystem names. + my %subHash = map { $_->[0] => $_->[1] } @cellData; + # We loop through @cellData to build the hash. + for my $roleEntry (@roleData) { + # Get the data for this feature and cell. + my ($fid, $cellID, $role) = @{$roleEntry}; + # Check for a subsystem name. + my $subsys = $subHash{$cellID}; + if ($subsys) { + # Insure this feature has an entry in the return hash. + if (! exists $retVal{$fid}) { $retVal{$fid} = []; } + # Merge in this new data. + push @{$retVal{$fid}}, [$subsys, $role]; + } + } + # Return the result. + return %retVal; +} + +=head3 RelatedFeatures + + my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); + +Return a list of the features which are bi-directional best hits of the specified feature and +have been assigned the specified function by the specified user. If no such features exists, +an empty list will be returned. + +=over 4 + +=item featureID + +ID of the feature to whom the desired features are related. + +=item function + +Functional assignment (as returned by C) that is used to determine which related +features should be selected. + +=item userID + +ID of the user whose functional assignments are to be used. If omitted, C is assumed. + +=item RETURN + +Returns a list of the related features with the specified function. + +=back + +=cut +#: Return Type @; +sub RelatedFeatures { + # Get the parameters. + my ($self, $featureID, $function, $userID) = @_; + # Get a list of the features that are BBHs of the incoming feature. + my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID); + # Now we loop through the features, pulling out the ones that have the correct + # functional assignment. + my @retVal = (); + for my $bbhFeature (@bbhFeatures) { + # Get this feature's functional assignment. + my $newFunction = $self->FunctionOf($bbhFeature, $userID); + # If it matches, add it to the result list. + if ($newFunction eq $function) { + push @retVal, $bbhFeature; + } + } + # Return the result list. + return @retVal; +} + +=head3 TaxonomySort + + my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); + +Return a list formed by sorting the specified features by the taxonomy of the containing +genome. This will cause genomes from similar organisms to float close to each other. + +This task could almost be handled by the database; however, the taxonomy string in the +database is a text field and can't be indexed. Instead, we create a hash table that maps +taxonomy strings to lists of features. We then process the hash table using a key sort +and merge the feature lists together to create the output. + +=over 4 + +=item $featureIDs + +List of features to be taxonomically sorted. + +=item RETURN + +Returns the list of features sorted by the taxonomies of the containing genomes. + +=back + +=cut +#: Return Type @; +sub TaxonomySort { + # Get the parameters. + my ($self, $featureIDs) = @_; + # Create the working hash table. + my %hashBuffer = (); + # Loop through the features. + for my $fid (@{$featureIDs}) { + # Get the taxonomy of the feature's genome. + my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?", + [$fid], 'Genome(taxonomy)'); + # Add this feature to the hash buffer. + push @{$hashBuffer{$taxonomy}}, $fid; + } + # Sort the keys and get the elements. + my @retVal = (); + for my $taxon (sort keys %hashBuffer) { + push @retVal, @{$hashBuffer{$taxon}}; + } + # Return the result. + return @retVal; +} + +=head3 Protein + + my $protein = Sprout::Protein($sequence, $table); + +Translate a DNA sequence into a protein sequence. + +=over 4 + +=item sequence + +DNA sequence to translate. + +=item table (optional) + +Reference to a Hash that translates DNA triples to proteins. A triple that does not +appear in the hash will be translated automatically to C. + +=item RETURN + +Returns the protein sequence that would be created by the DNA sequence. + +=back + +=cut + +# This is the translation table for protein synthesis. +my $ProteinTable = { AAA => 'K', AAG => 'K', AAT => 'N', AAC => 'N', + AGA => 'R', AGG => 'R', AGT => 'S', AGC => 'S', + ATA => 'I', ATG => 'M', ATT => 'I', ATC => 'I', + ACA => 'T', ACG => 'T', ACT => 'T', ACC => 'T', + GAA => 'E', GAG => 'E', GAT => 'D', GAC => 'D', + GTA => 'V', GTG => 'V', GTT => 'V', GTC => 'V', + GGA => 'G', GGG => 'G', GGT => 'G', GGC => 'G', + GCA => 'A', GCG => 'A', GCT => 'A', GCC => 'A', + CAA => 'Q', CAG => 'Q', CAT => 'H', CAC => 'H', + CTA => 'L', CTG => 'L', CTT => 'L', CTC => 'L', + CGA => 'R', CGG => 'R', CGT => 'R', CGC => 'R', + CCA => 'P', CCG => 'P', CCT => 'P', CCC => 'P', + TAA => '*', TAG => '*', TAT => 'Y', TAC => 'Y', + TGA => '*', TGG => 'W', TGT => 'C', TGC => 'C', + TTA => 'L', TTG => 'L', TTT => 'F', TTC => 'F', + TCA => 'S', TCG => 'S', TCT => 'S', TCC => 'S', + AAR => 'K', AAY => 'N', + AGR => 'R', AGY => 'S', + ATY => 'I', + ACR => 'T', ACY => 'T', 'ACX' => 'T', + GAR => 'E', GAY => 'D', + GTR => 'V', GTY => 'V', GTX => 'V', + GGR => 'G', GGY => 'G', GGX => 'G', + GCR => 'A', GCY => 'A', GCX => 'A', + CAR => 'Q', CAY => 'H', + CTR => 'L', CTY => 'L', CTX => 'L', + CGR => 'R', CGY => 'R', CGX => 'R', + CCR => 'P', CCY => 'P', CCX => 'P', + TAR => '*', TAY => 'Y', + TGY => 'C', + TTR => 'L', TTY => 'F', + TCR => 'S', TCY => 'S', TCX => 'S' + }; + +sub Protein { + # Get the paraeters. + my ($sequence, $table) = @_; + # If no table was specified, use the default. + if (!$table) { + $table = $ProteinTable; + } + # Create the return value. + my $retVal = ""; + # Loop through the input triples. + my $n = length $sequence; + for (my $i = 0; $i < $n; $i += 3) { + # Get the current triple from the sequence. Note we convert to + # upper case to insure a match. + my $triple = uc substr($sequence, $i, 3); + # Translate it using the table. + my $protein = "X"; + if (exists $table->{$triple}) { $protein = $table->{$triple}; } + $retVal .= $protein; + } + # Remove the stop codon (if any). + $retVal =~ s/\*$//; + # Return the result. + return $retVal; +} + +=head3 LoadInfo + + my ($dirName, @relNames) = $sprout->LoadInfo(); + +Return the name of the directory from which data is to be loaded and a list of the relation +names. This information is useful when trying to analyze what needs to be put where in order +to load the entire database. + +=cut +#: Return Type @; +sub LoadInfo { + # Get the parameters. + my ($self) = @_; + # Create the return list, priming it with the name of the data directory. + my @retVal = ($self->{_options}->{dataDir}); + # Concatenate the table names. + push @retVal, $self->GetTableNames(); + # Return the result. + return @retVal; +} + +=head3 BBHMatrix + + my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets); + +Find all the bidirectional best hits for the features of a genome in a +specified list of target genomes. The return value will be a hash mapping +features in the original genome to their bidirectional best hits in the +target genomes. + +=over 4 + +=item genomeID + +ID of the genome whose features are to be examined for bidirectional best hits. + +=item cutoff + +A cutoff value. Only hits with a score lower than the cutoff will be returned. + +=item targets + +List of target genomes. Only pairs originating in the original +genome and landing in one of the target genomes will be returned. + +=item RETURN + +Returns a hash mapping each feature in the original genome to a hash mapping its +BBH pegs in the target genomes to their scores. + +=back + +=cut + +sub BBHMatrix { + # Get the parameters. + my ($self, $genomeID, $cutoff, @targets) = @_; + # Declare the return variable. + my %retVal = (); + # Ask for the BBHs. + my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets); + # We now have a set of 4-tuples that we need to convert into a hash of hashes. + for my $bbhData (@bbhList) { + my ($peg1, $peg2, $score) = @{$bbhData}; + if (! exists $retVal{$peg1}) { + $retVal{$peg1} = { $peg2 => $score }; + } else { + $retVal{$peg1}->{$peg2} = $score; + } + } + # Return the result. + return %retVal; +} + + +=head3 SimMatrix + + my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets); + +Find all the similarities for the features of a genome in a +specified list of target genomes. The return value will be a hash mapping +features in the original genome to their similarites in the +target genomes. + +=over 4 + +=item genomeID + +ID of the genome whose features are to be examined for similarities. + +=item cutoff + +A cutoff value. Only hits with a score lower than the cutoff will be returned. + +=item targets + +List of target genomes. Only pairs originating in the original +genome and landing in one of the target genomes will be returned. + +=item RETURN + +Returns a hash mapping each feature in the original genome to a hash mapping its +similar pegs in the target genomes to their scores. + +=back + +=cut + +sub SimMatrix { + # Get the parameters. + my ($self, $genomeID, $cutoff, @targets) = @_; + # Declare the return variable. + my %retVal = (); + # Get the list of features in the source organism. + my @fids = $self->FeaturesOf($genomeID); + # Ask for the sims. We only want similarities to fig features. + my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig"); + if (! defined $simList) { + Confess("Unable to retrieve similarities from server."); + } else { + Trace("Processing sims.") if T(3); + # We now have a set of sims that we need to convert into a hash of hashes. First, we + # Create a hash for the target genomes. + my %targetHash = map { $_ => 1 } @targets; + for my $simData (@{$simList}) { + # Get the PEGs and the score. + my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc); + # Insure the second ID is in the target list. + my ($genome2) = FIGRules::ParseFeatureID($peg2); + if (exists $targetHash{$genome2}) { + # Here it is. Now we need to add it to the return hash. How we do that depends + # on whether or not $peg1 is new to us. + if (! exists $retVal{$peg1}) { + $retVal{$peg1} = { $peg2 => $score }; + } else { + $retVal{$peg1}->{$peg2} = $score; + } + } + } + } + # Return the result. + return %retVal; +} + + +=head3 LowBBHs + + my %bbhMap = $sprout->LowBBHs($featureID, $cutoff); + +Return the bidirectional best hits of a feature whose score is no greater than a +specified cutoff value. A higher cutoff value will allow inclusion of hits with +a greater score. The value returned is a map of feature IDs to scores. + +=over 4 + +=item featureID + +ID of the feature whose best hits are desired. + +=item cutoff + +Maximum permissible score for inclusion in the results. + +=item RETURN + +Returns a hash mapping feature IDs to scores. + +=back + +=cut +#: Return Type %; +sub LowBBHs { + # Get the parsameters. + my ($self, $featureID, $cutoff) = @_; + # Create the return hash. + my %retVal = (); + # Query for the desired BBHs. + my @bbhList = FIGRules::BBHData($featureID, $cutoff); + # Form the results into the return hash. + for my $pair (@bbhList) { + my $fid = $pair->[0]; + if ($self->Exists('Feature', $fid)) { + $retVal{$fid} = $pair->[1]; + } + } + # Return the result. + return %retVal; } -=head3 RoleNeighbors +=head3 Sims -C<< my @roleList = $sprout->RoleNeighbors($roleID); >> + my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters); -Returns a list of the roles that occur in the same diagram as the specified role. Because -diagrams and roles are in a many-to-many relationship with each other, the list is -essentially the set of roles from all of the maps that contain the incoming role. Such -roles are considered neighbors because they are used together in cellular subsystems. +Get a list of similarities for a specified feature. Similarity information is not kept in the +Sprout database; rather, they are retrieved from a network server. The similarities are +returned as B objects. A Sim object is actually a list reference that has been blessed +so that its elements can be accessed by name. + +Similarities can be either raw or expanded. The raw similarities are basic +hits between features with similar DNA. Expanding a raw similarity drags in any +features considered substantially identical. So, for example, if features B, +B, and B are all substantially identical to B, then a raw similarity +B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>. =over 4 -=item roleID +=item fid -ID of the role whose neighbors are desired. +ID of the feature whose similarities are desired, or reference to a list of IDs +of features whose similarities are desired. -=item RETURN +=item maxN -Returns a list containing the IDs of the roles that are related to the incoming role. +Maximum number of similarities to return. -=back +=item maxP -=cut -#: Return Type @; -sub RoleNeighbors { - # Get the parameters. - my ($self, $roleID) = @_; - # Get all the diagrams containing this role. - my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID], - 'RoleOccursIn(to-link)'); - # Create the return list. - my @retVal = (); - # Loop through the diagrams. - for my $diagramID (@diagrams) { - # Get all the roles in this diagram. - my @roles = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(to-link) = ?", [$diagramID], - 'RoleOccursIn(from-link)'); - # Add them to the return list. - push @retVal, @roles; - } - # Merge the duplicates from the list. - return Tracer::Merge(@retVal); -} +Minumum allowable similarity score. -=head3 FeatureLinks +=item select -C<< my @links = $sprout->FeatureLinks($featureID); >> +Selection criterion: C means only raw similarities are returned; C +means only similarities to FIG features are returned; C means all expanded +similarities are returned; and C means similarities are expanded until the +number of FIG features equals the maximum. -Return a list of the web hyperlinks associated with a feature. The web hyperlinks are -to external websites describing either the feature itself or the organism containing it -and are represented in raw HTML. +=item max_expand -=over 4 +The maximum number of features to expand. -=item featureID +=item filters -ID of the feature whose links are desired. +Reference to a hash containing filter information, or a subroutine that can be +used to filter the sims. =item RETURN -Returns a list of the web links for this feature. +Returns a reference to a list of similarity objects, or C if an error +occurred. =back =cut -#: Return Type @; -sub FeatureLinks { - # Get the parameters. - my ($self, $featureID) = @_; - # Get the feature's links. - my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']); - # Return the feature's links. - return @retVal; + +sub Sims { + # Get the parameters. + my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_; + # Create the shim object to test for deleted FIDs. + my $shim = FidCheck->new($self); + # Ask the network for sims. + my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters); + # Return the result. + return $retVal; } -=head3 SubsystemsOf +=head3 IsAllGenomes -C<< my %subsystems = $sprout->SubsystemsOf($featureID); >> + my $flag = $sprout->IsAllGenomes(\@list, \@checkList); -Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped -to the role the feature performs. +Return TRUE if all genomes in the second list are represented in the first list at +least one. Otherwise, return FALSE. If the second list is omitted, the first list is +compared to a list of all the genomes. =over 4 -=item featureID +=item list -ID of the feature whose subsystems are desired. +Reference to the list to be compared to the second list. + +=item checkList (optional) + +Reference to the comparison target list. Every genome ID in this list must occur at +least once in the first list. If this parameter is omitted, a list of all the genomes +is used. =item RETURN -Returns a hash mapping all the feature's subsystems to the feature's role. +Returns TRUE if every item in the second list appears at least once in the +first list, else FALSE. =back =cut -#: Return Type %; -sub SubsystemsOf { - # Get the parameters. - my ($self, $featureID) = @_; - # Use the SSCell to connect features to subsystems. - my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'], - "ContainsFeature(to-link) = ?", [$featureID], - ['HasSSCell(from-link)', 'IsRoleOf(from-link)']); - # Create the return value. - my %retVal = (); - # Loop through the results, adding them to the hash. - for my $record (@subsystems) { - $retVal{$record->[0]} = $record->[1]; - } - # Return the hash. - return %retVal; -} -=head3 RelatedFeatures +sub IsAllGenomes { + # Get the parameters. + my ($self, $list, $checkList) = @_; + # Supply the checklist if it was omitted. + $checkList = [$self->Genomes()] if ! defined($checkList); + # Create a hash of the original list. + my %testList = map { $_ => 1 } @{$list}; + # Declare the return variable. We assume that the representation + # is complete and stop at the first failure. + my $retVal = 1; + my $n = scalar @{$checkList}; + for (my $i = 0; $retVal && $i < $n; $i++) { + if (! $testList{$checkList->[$i]}) { + $retVal = 0; + } + } + # Return the result. + return $retVal; +} -C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >> +=head3 GetGroups -Return a list of the features which are bi-directional best hits of the specified feature and -have been assigned the specified function by the specified user. If no such features exists, -an empty list will be returned. + my %groups = $sprout->GetGroups(\@groupList); -=over 4 +Return a hash mapping each group to the IDs of the genomes in the group. +A list of groups may be specified, in which case only those groups will be +shown. Alternatively, if no parameter is supplied, all groups will be +included. Genomes that are not in any group are omitted. -=item featureID +=cut +#: Return Type %@; +sub GetGroups { + # Get the parameters. + my ($self, $groupList) = @_; + # Declare the return value. + my %retVal = (); + # Determine whether we are getting all the groups or just some. + if (defined $groupList) { + # Here we have a group list. Loop through them individually, + # getting a list of the relevant genomes. + for my $group (@{$groupList}) { + my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?", + [$group], "Genome(id)"); + $retVal{$group} = \@genomeIDs; + } + } else { + # Here we need all of the groups. In this case, we run through all + # of the genome records, putting each one found into the appropriate + # group. Note that we use a filter clause to insure that only genomes + # in real NMPDR groups are included in the return set. + my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?", + [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']); + # Loop through the genomes found. + for my $genome (@genomes) { + # Get the genome ID and group, and add this genome to the group's list. + my ($genomeID, $group) = @{$genome}; + push @{$retVal{$group}}, $genomeID; + } + } + # Return the hash we just built. + return %retVal; +} -ID of the feature to whom the desired features are related. +=head3 MyGenomes -=item function + my @genomes = Sprout::MyGenomes($dataDir); -Functional assignment (as returned by C) that is used to determine which related -features should be selected. +Return a list of the genomes to be included in the Sprout. -=item userID +This method is provided for use during the Sprout load. It presumes the Genome load file has +already been created. (It will be in the Sprout data directory and called either C +or C.) Essentially, it reads in the Genome load file and strips out the genome +IDs. -ID of the user whose functional assignments are to be used. If omitted, C is assumed. +=over 4 -=item RETURN +=item dataDir -Returns a list of the related features with the specified function. +Directory containing the Sprout load files. =back =cut #: Return Type @; -sub RelatedFeatures { - # Get the parameters. - my ($self, $featureID, $function, $userID) = @_; - # Get a list of the features that are BBHs of the incoming feature. - my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'], - "IsBidirectionalBestHitOf(from-link) = ?", [$featureID], - 'IsBidirectionalBestHitOf(to-link)'); - # Now we loop through the features, pulling out the ones that have the correct - # functional assignment. - my @retVal = (); - for my $bbhFeature (@bbhFeatures) { - # Get this feature's functional assignment. - my $newFunction = $self->FunctionOf($bbhFeature, $userID); - # If it matches, add it to the result list. - if ($newFunction eq $function) { - push @retVal, $bbhFeature; - } - } - # Return the result list. - return @retVal; +sub MyGenomes { + # Get the parameters. + my ($dataDir) = @_; + # Compute the genome file name. + my $genomeFileName = LoadFileName($dataDir, "Genome"); + # Extract the genome IDs from the files. + my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName); + # Return the result. + return @retVal; } -=head3 TaxonomySort - -C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >> +=head3 LoadFileName -Return a list formed by sorting the specified features by the taxonomy of the containing -genome. This will cause genomes from similar organisms to float close to each other. + my $fileName = Sprout::LoadFileName($dataDir, $tableName); -This task could almost be handled by the database; however, the taxonomy string in the -database is a text field and can't be indexed. Instead, we create a hash table that maps -taxonomy strings to lists of features. We then process the hash table using a key sort -and merge the feature lists together to create the output. +Return the name of the load file for the specified table in the specified data +directory. =over 4 -=item $featureIDs +=item dataDir -List of features to be taxonomically sorted. +Directory containing the Sprout load files. + +=item tableName + +Name of the table whose load file is desired. =item RETURN -Returns the list of features sorted by the taxonomies of the containing genomes. +Returns the name of the file containing the load data for the specified table, or +C if no load file is present. =back =cut -#: Return Type @; -sub TaxonomySort { - # Get the parameters. - my ($self, $featureIDs) = @_; - # Create the working hash table. - my %hashBuffer = (); - # Loop through the features. - for my $fid (@{$featureIDs}) { - # Get the taxonomy of the feature's genome. - my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?", - [$fid], 'Genome(taxonomy)'); - # Add this feature to the hash buffer. - Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid); - } - # Sort the keys and get the elements. - my @retVal = (); - for my $taxon (sort keys %hashBuffer) { - push @retVal, @{$hashBuffer{$taxon}}; - } - # Return the result. - return @retVal; +#: Return Type $; +sub LoadFileName { + # Get the parameters. + my ($dataDir, $tableName) = @_; + # Declare the return variable. + my $retVal; + # Check for the various file names. + if (-e "$dataDir/$tableName") { + $retVal = "$dataDir/$tableName"; + } elsif (-e "$dataDir/$tableName.dtx") { + $retVal = "$dataDir/$tableName.dtx"; + } + # Return the result. + return $retVal; } -=head3 GetAll +=head3 DeleteGenome + + my $stats = $sprout->DeleteGenome($genomeID, $testFlag); + +Delete a genome from the database. -C<< my @list = $sprout->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >> +=over 4 -Return a list of values taken from the objects returned by a query. The first three -parameters correspond to the parameters of the L method. The final parameter is -a list of the fields desired from each record found by the query. The field name -syntax is the standard syntax used for fields in the B system-- -B(I)>-- where I is the name of the relevant entity -or relationship and I is the name of the field. +=item genomeID -The list returned will be a list of lists. Each element of the list will contain -the values returned for the fields specified in the fourth parameter. If one of the -fields specified returns multiple values, they are flattened in with the rest. For -example, the following call will return a list of the features in a particular -spreadsheet cell, and each feature will be represented by a list containing the -feature ID followed by all of its aliases. +ID of the genome to delete -C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >> +=item testFlag -=over 4 +If TRUE, then the DELETE statements will be traced, but no deletions will occur. -=item objectNames +=item RETURN -List containing the names of the entity and relationship objects to be retrieved. +Returns a statistics object describing the rows deleted. -=item filterClause +=back -WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can -be parameterized with parameter markers (C). Each field used must be specified in the standard form -B(I)>. Any parameters specified in the filter clause should be added to the -parameter list as additional parameters. The fields in a filter clause can come from primary -entity relations, relationship relations, or secondary entity relations; however, all of the -entities and relationships involved must be included in the list of object names. +=cut +#: Return Type $%; +sub DeleteGenome { + # Get the parameters. + my ($self, $genomeID, $testFlag) = @_; + # Perform the delete for the genome's features. + my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag); + # Perform the delete for the primary genome data. + my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag); + $retVal->Accumulate($stats); + # Return the result. + return $retVal; +} -=item parameterList +=head3 Fix -List of the parameters to be substituted in for the parameters marks in the filter clause. + my %fixedHash = $sprout->Fix(%groupHash); -=item fields +Prepare a genome group hash (like that returned by L) for processing. +The groups will be combined into the appropriate super-groups. -List of the fields to be returned in each element of the list returned. +=over 4 -=item count +=item groupHash -Maximum number of records to return. If omitted or 0, all available records will be returned. +Hash to be fixed up. =item RETURN -Returns a list of list references. Each element of the return list contains the values for the -fields specified in the B parameter. +Returns a fixed-up version of the hash. =back =cut -#: Return Type @@; -sub GetAll { - # Get the parameters. - my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_; - # Create the query. - my $query = $self->Get($objectNames, $filterClause, $parameterList); - # Set up a counter of the number of records read. - my $fetched = 0; - # Insure the counter has a value. - if (!defined $count) { - $count = 0; - } - # Loop through the records returned, extracting the fields. Note that if the - # counter is non-zero, we stop when the number of records read hits the count. - my @retVal = (); - while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) { - my @rowData = $row->Values($fields); - push @retVal, \@rowData; - $fetched++; - } - # Return the resulting list. - return @retVal; + +sub Fix { + # Get the parameters. + my ($self, %groupHash) = @_; + # Create the result hash. + my %retVal = (); + # Copy over the genomes. + for my $groupID (keys %groupHash) { + # Get the super-group name. + my $realGroupID = $self->SuperGroup($groupID); + # Append this group's genomes into the result hash + # using the super-group name. + push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}}; + } + # Return the result hash. + return %retVal; } -=head3 GetFlat +=head3 GroupPageName -C<< my @list = $sprout->GetFlat(\@objectNames, $filterClause, $parameterList, $field); >> + my $name = $sprout->GroupPageName($group); -This is a variation of L that asks for only a single field per record and -returns a single flattened list. +Return the name of the page for the specified NMPDR group. =over 4 -=item objectNames - -List containing the names of the entity and relationship objects to be retrieved. - -=item filterClause +=item group -WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can -be parameterized with parameter markers (C). Each field used must be specified in the standard form -B(I)>. Any parameters specified in the filter clause should be added to the -parameter list as additional parameters. The fields in a filter clause can come from primary -entity relations, relationship relations, or secondary entity relations; however, all of the -entities and relationships involved must be included in the list of object names. - -=item parameterList - -List of the parameters to be substituted in for the parameters marks in the filter clause. - -=item field - -Name of the field to be used to get the elements of the list returned. +Name of the relevant group. =item RETURN -Returns a list of values. +Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in +memory it will be read in. =back =cut -#: Return Type @; -sub GetFlat { - # Get the parameters. - my ($self, $objectNames, $filterClause, $parameterList, $field) = @_; - # Construct the query. - my $query = $self->Get($objectNames, $filterClause, $parameterList); - # Create the result list. - my @retVal = (); - # Loop through the records, adding the field values found to the result list. - while (my $row = $query->Fetch()) { - push @retVal, $row->Value($field); - } - # Return the list created. - return @retVal; + +sub GroupPageName { + # Get the parameters. + my ($self, $group) = @_; + # Check for the group file data. + my %superTable = $self->CheckGroupFile(); + # Compute the real group name. + my $realGroup = $self->SuperGroup($group); + # Get the associated page name. + my $retVal = "../content/$superTable{$realGroup}->{page}"; + # Return the result. + return $retVal; } -=head3 Protein -C<< my $protein = Sprout::Protein($sequence, $table); >> +=head3 AddProperty -Translate a DNA sequence into a protein sequence. + $sprout->AddProperty($featureID, $key, @values); + +Add a new attribute value (Property) to a feature. =over 4 -=item sequence +=item peg -DNA sequence to translate. +ID of the feature to which the attribute is to be added. -=item table (optional) +=item key -Reference to a Hash that translates DNA triples to proteins. A triple that does not -appear in the hash will be translated automatically to C. +Name of the attribute (key). -=item RETURN +=item values -Returns the protein sequence that would be created by the DNA sequence. +Values of the attribute. =back =cut +#: Return Type ; +sub AddProperty { + # Get the parameters. + my ($self, $featureID, $key, @values) = @_; + # Add the property using the attached attributes object. + $self->{_ca}->AddAttribute($featureID, $key, @values); +} -# This is the translation table for protein synthesis. -my $ProteinTable = { AAA => 'K', AAG => 'K', AAT => 'N', AAC => 'N', - AGA => 'R', AGG => 'R', AGT => 'S', AGC => 'S', - ATA => 'I', ATG => 'M', ATT => 'I', ATC => 'I', - ACA => 'T', ACG => 'T', ACT => 'T', ACC => 'T', - GAA => 'E', GAG => 'E', GAT => 'D', GAC => 'D', - GTA => 'V', GTG => 'V', GTT => 'V', GTC => 'V', - GGA => 'G', GGG => 'G', GGT => 'G', GGC => 'G', - GCA => 'A', GCG => 'A', GCT => 'A', GCC => 'A', - CAA => 'Q', CAG => 'Q', CAT => 'H', CAC => 'H', - CTA => 'L', CTG => 'L', CTT => 'L', CTC => 'L', - CGA => 'R', CGG => 'R', CGT => 'R', CGC => 'R', - CCA => 'P', CCG => 'P', CCT => 'P', CCC => 'P', - TAA => '*', TAG => '*', TAT => 'Y', TAC => 'Y', - TGA => '*', TGG => 'W', TGT => 'C', TGC => 'C', - TTA => 'L', TTG => 'L', TTT => 'F', TTC => 'F', - TCA => 'S', TCG => 'S', TCT => 'S', TCC => 'S', - AAR => 'K', AAY => 'N', - AGR => 'R', AGY => 'S', - ATY => 'I', - ACR => 'T', ACY => 'T', 'ACX' => 'T', - GAR => 'E', GAY => 'D', - GTR => 'V', GTY => 'V', GTX => 'V', - GGR => 'G', GGY => 'G', GGX => 'G', - GCR => 'A', GCY => 'A', GCX => 'A', - CAR => 'Q', CAY => 'H', - CTR => 'L', CTY => 'L', CTX => 'L', - CGR => 'R', CGY => 'R', CGX => 'R', - CCR => 'P', CCY => 'P', CCX => 'P', - TAR => '*', TAY => 'Y', - TGY => 'C', - TTR => 'L', TTY => 'F', - TCR => 'S', TCY => 'S', TCX => 'S' - }; +=head3 CheckGroupFile -sub Protein { - # Get the paraeters. - my ($sequence, $table) = @_; - # If no table was specified, use the default. - if (!$table) { - $table = $ProteinTable; - } - # Create the return value. - my $retVal = ""; - # Loop through the input triples. - my $n = length $sequence; - for (my $i = 0; $i < $n; $i += 3) { - # Get the current triple from the sequence. - my $triple = substr($sequence, $i, 3); - # Translate it using the table. - my $protein = "X"; - if (exists $table->{$triple}) { $protein = $table->{$triple}; } - $retVal .= $protein; - } - # Remove the stop codon (if any). - $retVal =~ s/\*$//; - # Return the result. - return $retVal; -} + my %groupData = $sprout->CheckGroupFile(); -=head3 LoadInfo +Get the group file hash. The group file hash describes the relationship +between a group and the super-group to which it belongs for purposes of +display. The super-group name is computed from the first capitalized word +in the actual group name. For each super-group, the group file contains +the page name and a list of the species expected to be in the group. +Each species is specified by a genus and a species name. A species name +of C<0> implies an entire genus. -C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >> +This method returns a hash from super-group names to a hash reference. Each +resulting hash reference contains the following fields. -Return the name of the directory from which data is to be loaded and a list of the relation -names. This information is useful when trying to analyze what needs to be put where in order -to load the entire database. +=over 4 -=cut -#: Return Type @; -sub LoadInfo { - # Get the parameters. - my ($self) = @_; - # Create the return list, priming it with the name of the data directory. - my @retVal = ($self->{_options}->{dataDir}); - # Concatenate the table names. - push @retVal, $self->{_erdb}->GetTableNames(); - # Return the result. - return @retVal; -} +=item page -=head3 LowBBHs +The super-group's web page in the NMPDR. -C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >> +=item contents -Return the bidirectional best hits of a feature whose score is no greater than a -specified cutoff value. A higher cutoff value will allow inclusion of hits with -a greater score. The value returned is a map of feature IDs to scores. +A list of 2-tuples, each containing a genus name followed by a species name +(or 0, indicating all species). This list indicates which organisms belong +in the super-group. -=over 4 +=back -=item featureID +=cut -ID of the feature whose best hits are desired. +sub CheckGroupFile{ + # Get the parameters. + my ($self) = @_; + # Check to see if we already have this hash. + if (! defined $self->{groupHash}) { + # We don't, so we need to read it in. + my %groupHash; + # Read the group file. + my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl"); + # Loop through the list of sort-of groups. + for my $groupLine (@groupLines) { + my ($name, $page, @contents) = split /\t/, $groupLine; + $groupHash{$name} = { page => $page, + contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ] + }; + } + # Save the hash. + $self->{groupHash} = \%groupHash; + } + # Return the result. + return %{$self->{groupHash}}; +} -=item cutoff +=head2 Virtual Methods -Maximum permissible score for inclusion in the results. +=head3 CleanKeywords -=item RETURN + my $cleanedString = $sprout->CleanKeywords($searchExpression); -Returns a hash mapping feature IDs to scores. +Clean up a search expression or keyword list. This involves converting the periods +in EC numbers to underscores, converting non-leading minus signs to underscores, +a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic +characters. In addition, any extra spaces are removed. -=back +=over 4 -=cut -#: Return Type %; -sub LowBBHs { - # Get the parsameters. - my ($self, $featureID, $cutoff) = @_; - # Create the return hash. - my %retVal = (); - # Create a query to get the desired BBHs. - my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'], - 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?', - [$cutoff, $featureID], - ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']); - # Form the results into the return hash. - for my $pair (@bbhList) { - $retVal{$pair->[0]} = $pair->[1]; - } - # Return the result. - return %retVal; -} +=item searchExpression -=head3 GetGroups +Search expression or keyword list to clean. Note that a search expression may +contain boolean operators which need to be preserved. This includes leading +minus signs. -C<< my %groups = $sprout->GetGroups(\@groupList); >> +=item RETURN -Return a hash mapping each group to the IDs of the genomes in the group. -A list of groups may be specified, in which case only those groups will be -shown. Alternatively, if no parameter is supplied, all groups will be -included. Genomes that are not in any group are omitted. +Cleaned expression or keyword list. + +=back =cut -#: Return Type %@; -sub GetGroups { + +sub CleanKeywords { # Get the parameters. - my ($self, $groupList) = @_; - # Declare the return value. - my %retVal = (); - # Determine whether we are getting all the groups or just some. - if (defined $groupList) { - # Here we have a group list. Loop through them individually, - # getting a list of the relevant genomes. - for my $group (@{$groupList}) { - my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?", - [$group], "Genome(id)"); - $retVal{$group} = \@genomeIDs; - } - } else { - # Here we need all of the groups. In this case, we run through all - # of the genome records, putting each one found into the appropriate - # group. Note that we use a filter clause to insure that only genomes - # in groups are included in the return set. - my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [], - ['Genome(id)', 'Genome(group-name)']); - # Loop through the genomes found. - for my $genome (@genomes) { - # Pop this genome's ID off the current list. - my @groups = @{$genome}; - my $genomeID = shift @groups; - # Loop through the groups, adding the genome ID to each group's - # list. - for my $group (@groups) { - Tracer::AddToListMap(\%retVal, $group, $genomeID); - } - } - } - # Return the hash we just built. - return %retVal; + my ($self, $searchExpression) = @_; + # Perform the standard cleanup. + my $retVal = $self->ERDB::CleanKeywords($searchExpression); + # Fix the periods in EC and TC numbers. + $retVal =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g; + # Fix non-trailing periods. + $retVal =~ s/\.(\w)/_$1/g; + # Fix non-leading minus signs. + $retVal =~ s/(\w)[\-]/$1_/g; + # Fix the vertical bars and colons + $retVal =~ s/(\w)[|:](\w)/$1'$2/g; + # Return the result. + return $retVal; } =head2 Internal Utility Methods @@ -2629,21 +3914,29 @@ =head3 ParseAssignment Parse annotation text to determine whether or not it is a functional assignment. If it is, -the user, function text, and assigning user will be returned as a 3-element list. If it +the user, function text, and assigning user will be returned as a 3-element list. If it isn't, an empty list will be returned. A functional assignment is always of the form - IC<\nset >IC< function to\n>I - -where I is the B, I is the B, and I is the -actual functional role. In most cases, the user and the assigning user will be the -same, but that is not always the case. + set YYYY function to + ZZZZ + +where I is the B, and I is the actual functional role. In most cases, +the user and the assigning user (from MadeAnnotation) will be the same, but that is +not always the case. + +In addition, the functional role may contain extra data that is stripped, such as +terminating spaces or a comment separated from the rest of the text by a tab. This is a static method. =over 4 +=item user + +Name of the assigning user. + =item text Text of the annotation. @@ -2658,19 +3951,60 @@ =cut sub _ParseAssignment { - # Get the parameters. - my ($text) = @_; - # Declare the return value. - my @retVal = (); - # Check to see if this is a functional assignment. - my ($user, $type, $function) = split(/\n/, $text); - if ($type =~ m/^set ([^ ]+) function to$/i) { - # Here it is, so we return the user name (which is in $1), the functional role text, - # and the assigning user. - @retVal = ($1, $function, $user); - } - # Return the result list. - return @retVal; + # Get the parameters. + my ($user, $text) = @_; + # Declare the return value. + my @retVal = (); + # Check to see if this is a functional assignment. + my ($type, $function) = split(/\n/, $text); + if ($type =~ m/^set function to$/i) { + # Here we have an assignment without a user, so we use the incoming user ID. + @retVal = ($user, $function); + } elsif ($type =~ m/^set (\S+) function to$/i) { + # Here we have an assignment with a user that is passed back to the caller. + @retVal = ($1, $function); + } + # If we have an assignment, we need to clean the function text. There may be + # extra junk at the end added as a note from the user. + if (defined( $retVal[1] )) { + $retVal[1] =~ s/(\t\S)?\s*$//; + } + # Return the result list. + return @retVal; +} + +=head3 _CheckFeature + + my $flag = $sprout->_CheckFeature($fid); + +Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE. + +=over 4 + +=item fid + +Feature ID to check. + +=item RETURN + +Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE. + +=back + +=cut + +sub _CheckFeature { + # Get the parameters. + my ($self, $fid) = @_; + # Insure we have a genome hash. + if (! defined $self->{genomeHash}) { + my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)'); + $self->{genomeHash} = \%genomeHash; + } + # Get the feature's genome ID. + my ($genomeID) = FIGRules::ParseFeatureID($fid); + # Return an indicator of whether or not the genome ID is in the hash. + return ($self->{genomeHash}->{$genomeID} ? 1 : 0); } =head3 FriendlyTimestamp @@ -2695,8 +4029,9 @@ sub FriendlyTimestamp { my ($timeValue) = @_; - my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue)); + my $retVal = localtime($timeValue); return $retVal; } + 1; \ No newline at end of file