--- Sprout.pm 2006/06/07 01:53:03 1.59 +++ Sprout.pm 2006/11/03 00:42:25 1.94 @@ -12,9 +12,10 @@ use DBObject; use Tracer; use FIGRules; + use FidCheck; use Stats; use POSIX qw(strftime); - + use BasicLocation; =head1 Sprout Database Manipulation Object @@ -91,6 +92,9 @@ sub new { # 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({ @@ -98,13 +102,14 @@ # database type dataDir => $FIG_Config::sproutData, # data file directory - xmlFileName => "$FIG_Config::fig/SproutDBD.xml", + 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, + sock => $FIG_Config::dbsock, + host => $FIG_Config::dbhost, maxSegmentLength => 4500, # maximum feature segment length maxSequenceLength => 8000, # maximum contig sequence length noDBOpen => 0, # 1 to suppress the database open @@ -118,7 +123,7 @@ my $dbh; if (! $optionTable->{noDBOpen}) { $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, - $password, $optionTable->{port}, undef, $optionTable->{sock}); + $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock}); } # Create the ERDB object. my $xmlFileName = "$optionTable->{xmlFileName}"; @@ -126,6 +131,8 @@ # 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; # Return it. return $retVal; } @@ -335,7 +342,7 @@ =head3 GeneMenu -C<< my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params); >> +C<< my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params, $selected); >> Return an HTML select menu of genomes. Each genome will be an option in the menu, and will be displayed by name with the ID and a contig count attached. The selection @@ -357,6 +364,14 @@ Reference to a list of values to be substituted in for the parameter marks in the filter string. +=item selected (optional) + +ID of the genome to be initially selected. + +=item fast (optional) + +If specified and TRUE, the contig counts will be omitted to improve performance. + =item RETURN Returns an HTML select menu with the specified genomes as selectable options. @@ -367,7 +382,12 @@ sub GeneMenu { # Get the parameters. - my ($self, $attributes, $filterString, $params) = @_; + my ($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<< $sprout->Build(); >> @@ -627,6 +655,8 @@ return ($contigID, $start, $dir, $len); } + + =head3 PointLocation C<< my $found = Sprout::PointLocation($location, $point); >> @@ -793,6 +823,119 @@ return @retVal; } +=head3 GenomeLength + +C<< my $length = $sprout->GenomeLength($genomeID); >> + +Return the length of the specified genome in base pairs. + +=over 4 + +=item genomeID + +ID of the genome whose base pair count is desired. + +=item RETURN + +Returns the number of base pairs in all the contigs of the specified +genome. + +=back + +=cut + +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 FeatureCount + +C<< my $count = $sprout->FeatureCount($genomeID, $type); >> + +Return the number of features of the specified type in the specified genome. + +=over 4 + +=item genomeID + +ID of the genome whose feature count is desired. + +=item type + +Type of feature to count (eg. C, C, etc.). + +=item RETURN + +Returns the number of features of the specified type for the specified genome. + +=back + +=cut + +sub FeatureCount { + # Get the parameters. + my ($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 GenomeAssignments + +C<< my $fidHash = $sprout->GenomeAssignments($genomeID); >> + +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 genomeID + +ID of the genome whose functional assignments are desired. + +=item RETURN + +Returns a reference to a hash which maps each feature to its most recent +functional assignment. + +=back + +=cut + +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 C<< my $length = $sprout->ContigLength($contigID); >> @@ -1147,11 +1290,8 @@ 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 @@ -1170,8 +1310,8 @@ =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 @@ -1188,47 +1328,52 @@ 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; + # 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; + } } } } @@ -1347,14 +1492,16 @@ 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, $genomeID]); + # Ask the server for the feature's best hit. + my @bbhData = FIGRules::BBHData($featureID); # Peel off the BBHs found. my @found = (); - while (my $bbh = $query->Fetch) { - push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)'); + for my $bbh (@bbhData) { + my $fid = $bbh->[0]; + my $bbGenome = $self->GenomeOf($fid); + if ($bbGenome eq $genomeID) { + push @found, $fid; + } } $retVal{$featureID} = \@found; } @@ -1368,8 +1515,7 @@ Return a list of the similarities to the specified feature. -Sprout does not support real similarities, so this method just returns the bidirectional -best hits. +This method just returns the bidirectional best hits for performance reasons. =over 4 @@ -1389,10 +1535,7 @@ # Get the parameters. my ($self, $featureID, $count) = @_; # Ask for the best hits. - my @lists = $self->GetAll(['IsBidirectionalBestHitOf'], - "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC", - [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'], - $count); + my @lists = FIGRules::BBHData($featureID); # Create the return value. my %retVal = (); for my $tuple (@lists) { @@ -1402,8 +1545,6 @@ return %retVal; } - - =head3 IsComplete C<< my $flag = $sprout->IsComplete($genomeID); >> @@ -1531,6 +1672,7 @@ sub CoupledFeatures { # Get the parameters. my ($self, $featureID) = @_; + Trace("Looking for features coupled to $featureID.") if T(coupling => 3); # Create a query to retrieve the functionally-coupled features. my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'], "ParticipatesInCoupling(from-link) = ?", [$featureID]); @@ -1543,10 +1685,12 @@ # Get the ID and score of the coupling. my ($couplingID, $score) = $clustering->Values(['Coupling(id)', 'Coupling(score)']); - # The coupling ID contains the two feature IDs separated by a space. We use - # this information to find the ID of the other feature. - my ($fid1, $fid2) = split / /, $couplingID; - my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1); + Trace("$featureID coupled with score $score to ID $couplingID.") if T(coupling => 4); + # Get the other feature that participates in the coupling. + my ($otherFeatureID) = $self->GetFlat(['ParticipatesInCoupling'], + "ParticipatesInCoupling(to-link) = ? AND ParticipatesInCoupling(from-link) <> ?", + [$couplingID, $featureID], 'ParticipatesInCoupling(from-link)'); + Trace("$couplingID target feature is $otherFeatureID.") if T(coupling => 4); # Attach the other feature's score to its ID. $retVal{$otherFeatureID} = $score; $found = 1; @@ -1679,7 +1823,7 @@ my ($self, $peg1, $peg2) = @_; # Declare the return values. We'll start with the coupling ID and undefine the # flag and score until we have more information. - my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef); + my ($retVal, $inverted, $score) = ($self->CouplingID($peg1, $peg2), undef, undef); # Find the coupling data. my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'], "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)", @@ -1700,9 +1844,112 @@ return ($retVal, $inverted, $score); } +=head3 GetSynonymGroup + +C<< 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 $retVal; +} + +=head3 GetBoundaries + +C<< my ($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 CouplingID -C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >> +C<< my $couplingID = $sprout->CouplingID($peg1, $peg2); >> Return the coupling ID for a pair of feature IDs. @@ -1735,7 +1982,8 @@ =cut #: Return Type $; sub CouplingID { - return join " ", sort @_; + my ($self, @pegs) = @_; + return $self->DigestKey(join " ", sort @pegs); } =head3 ReadFasta @@ -2094,41 +2342,6 @@ 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. - Trace("Checking existence of $entityName with ID=$entityID.") if T(4); - my $testInstance = $self->GetEntity($entityName, $entityID); - # Return an existence indicator. - my $retVal = ($testInstance ? 1 : 0); - return $retVal; -} - =head3 FeatureTranslation C<< my $translation = $sprout->FeatureTranslation($featureID); >> @@ -2463,6 +2676,42 @@ return $retVal; } +=head3 PropertyID + +C<< my $id = $sprout->PropertyID($propName, $propValue); >> + +Return the ID of the specified property name and value pair, if the +pair exists. + +=over 4 + +=item propName + +Name of the desired property. + +=item propValue + +Value expected for the desired property. + +=item RETURN + +Returns the ID of the name/value pair, or C if the pair does not exist. + +=back + +=cut + +sub PropertyID { + # Get the parameters. + my ($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 = $sprout->MergedAnnotations(\@list); >> @@ -2660,13 +2909,71 @@ # Get the parameters. my ($self, $featureID) = @_; # Get the list of names. - my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?", - [$featureID], 'HasSSCell(from-link)'); - # Return the result. - return @retVal; + my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?", + [$featureID], 'HasRoleInSubsystem(to-link)'); + # Return the result, sorted. + return sort @retVal; } +=head3 GenomeSubsystemData + +C<< 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, $role]; + } + } + # Return the result. + return %retVal; +} =head3 RelatedFeatures @@ -2703,9 +3010,7 @@ # Get the parameters. my ($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)'); + 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 = (); @@ -2841,8 +3146,9 @@ # 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); + # 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}; } @@ -2906,19 +3212,133 @@ 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, $featureID], - ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']); + # Query for the desired BBHs. + my @bbhList = FIGRules::BBHData($featureID, $cutoff); # Form the results into the return hash. for my $pair (@bbhList) { - $retVal{$pair->[0]} = $pair->[1]; + my $fid = $pair->[0]; + if ($self->Exists('Feature', $fid)) { + $retVal{$fid} = $pair->[1]; + } } # Return the result. return %retVal; } +=head3 Sims + +C<< my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters); >> + +Get a list of similarities for a specified feature. Similarity information is not kept in the +Sprout database; rather, they are retrieved from a network server. The similarities are +returned as B objects. A Sim object is actually a list reference that has been blessed +so that its elements can be accessed by name. + +Similarities can be either raw or expanded. The raw similarities are basic +hits between features with similar DNA. Expanding a raw similarity drags in any +features considered substantially identical. So, for example, if features B, +B, and B are all substatially identical to B, then a raw similarity +B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>. + +=over 4 + +=item fid + +ID of the feature whose similarities are desired. + +=item maxN + +Maximum number of similarities to return. + +=item maxP + +Minumum allowable similarity score. + +=item select + +Selection criterion: C means only raw similarities are returned; C +means only similarities to FIG features are returned; C means all expanded +similarities are returned; and C means similarities are expanded until the +number of FIG features equals the maximum. + +=item max_expand + +The maximum number of features to expand. + +=item filters + +Reference to a hash containing filter information, or a subroutine that can be +used to filter the sims. + +=item RETURN + +Returns a reference to a list of similarity objects, or C if an error +occurred. + +=back + +=cut + +sub Sims { + # Get the parameters. + my ($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 IsAllGenomes + +C<< my $flag = $sprout->IsAllGenomes(\@list, \@checkList); >> + +Return TRUE if all genomes in the second list are represented in the first list at +least one. Otherwise, return FALSE. If the second list is omitted, the first list is +compared to a list of all the genomes. + +=over 4 + +=item list + +Reference to the list to be compared to the second list. + +=item checkList (optional) + +Reference to the comparison target list. Every genome ID in this list must occur at +least once in the first list. If this parameter is omitted, a list of all the genomes +is used. + +=item RETURN + +Returns TRUE if every item in the second list appears at least once in the +first list, else FALSE. + +=back + +=cut + +sub IsAllGenomes { + # Get the parameters. + my ($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; +} + =head3 GetGroups C<< my %groups = $sprout->GetGroups(\@groupList); >> @@ -2940,7 +3360,7 @@ # 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) = ?", + my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?", [$group], "Genome(id)"); $retVal{$group} = \@genomeIDs; } @@ -2948,9 +3368,9 @@ # 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)']); + # 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) { # Pop this genome's ID off the current list. @@ -3076,93 +3496,151 @@ return $retVal; } -=head2 Internal Utility Methods +=head3 Fix -=head3 ParseAssignment +C<< my %fixedHash = Sprout::Fix(%groupHash); >> -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 -isn't, an empty list will be returned. +Prepare a genome group hash (like that returned by L for processing. +Groups with the same primary name will be combined. The primary name is the +first capitalized word in the group name. -A functional assignment is always of the form +=over 4 - CIC< function to\n>I +=item groupHash -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. +Hash to be fixed up. -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. +=item RETURN -This is a static method. +Returns a fixed-up version of the hash. -=over 4 +=back -=item user +=cut -Name of the assigning user. +sub Fix { + # Get the parameters. + my (%groupHash) = @_; + # Create the result hash. + my %retVal = (); + # Copy over the genomes. + for my $groupID (keys %groupHash) { + # Make a safety copy of the group ID. + my $realGroupID = $groupID; + # Yank the primary name. + if ($groupID =~ /([A-Z]\w+)/) { + $realGroupID = $1; + } + # Append this group's genomes into the result hash. + Tracer::AddToListMap(\%retVal, $realGroupID, @{$groupHash{$groupID}}); + } + # Return the result hash. + return %retVal; +} -=item text +=head3 GroupPageName -Text of the annotation. +C<< my $name = $sprout->GroupPageName($group); >> + +Return the name of the page for the specified NMPDR group. + +=over 4 + +=item group + +Name of the relevant group. =item RETURN -Returns an empty list if the annotation is not a functional assignment; otherwise, returns -a two-element list containing the user name and the function text. +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 -sub _ParseAssignment { +sub GroupPageName { # 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, $function); + my ($self, $group) = @_; + # Declare the return variable. + my $retVal; + # Check for the group file data. + if (! defined $self->{groupHash}) { + # Read the group file. + my %groupData = Sprout::ReadGroupFile($self->{_options}->{dataDir} . "/groups.tbl"); + # Store it in our object. + $self->{groupHash} = \%groupData; } - # 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 (@retVal) { - $retVal[1] =~ s/(\t\S)?\s*$//; + # Compute the real group name. + my $realGroup = $group; + if ($group =~ /([A-Z]\w+)/) { + $realGroup = $1; } - # Return the result list. - return @retVal; + # Return the page name. + $retVal = "../content/" . $self->{groupHash}->{$realGroup}->[1]; + # Return the result. + return $retVal; } -=head3 FriendlyTimestamp +=head3 ReadGroupFile -Convert a time number to a user-friendly time stamp for display. +C<< my %groupData = Sprout::ReadGroupFile($groupFileName); >> -This is a static method. +Read in the data from the specified group file. The group file contains information +about each of the NMPDR groups. =over 4 -=item timeValue +=item name -Numeric time value. +Name of the group. + +=item page + +Name of the group's page on the web site (e.g. C for +Campylobacter) + +=item genus + +Genus of the group + +=item species + +Species of the group, or an empty string if the group is for an entire +genus. If the group contains more than one species, the species names +should be separated by commas. + +=back + +The parameters to this method are as follows + +=over 4 + +=item groupFile + +Name of the file containing the group data. =item RETURN -Returns a string containing the same time in user-readable format. +Returns a hash keyed on group name. The value of each hash =back =cut -sub FriendlyTimestamp { - my ($timeValue) = @_; - my $retVal = localtime($timeValue); - return $retVal; +sub ReadGroupFile { + # Get the parameters. + my ($groupFileName) = @_; + # Declare the return variable. + my %retVal; + # Read the group file. + my @groupLines = Tracer::GetFile($groupFileName); + for my $groupLine (@groupLines) { + my ($name, $page, $genus, $species) = split(/\t/, $groupLine); + $retVal{$name} = [$page, $genus, $species]; + } + # Return the result. + return %retVal; } =head3 AddProperty @@ -3222,5 +3700,138 @@ $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url }); } +=head2 Virtual Methods + +=head3 CleanKeywords + +C<< my $cleanedString = $sprout->CleanKeywords($searchExpression); >> + +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. + +=over 4 + +=item searchExpression + +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. + +=item RETURN + +Cleaned expression or keyword list. + +=back + +=cut + +sub CleanKeywords { + # Get the parameters. + 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 $retVal; +} + +=head2 Internal Utility Methods + +=head3 ParseAssignment + +Parse annotation text to determine whether or not it is a functional assignment. If it is, +the user, function text, and assigning user will be returned as a 3-element list. If it +isn't, an empty list will be returned. + +A functional assignment is always of the form + + CIC< function to\n>I + +where I is the B, and I is the actual functional role. In most cases, +the user and the assigning user (from MadeAnnotation) will be the same, but that is +not always the case. + +In addition, the functional role may contain extra data that is stripped, such as +terminating spaces or a comment separated from the rest of the text by a tab. + +This is a static method. + +=over 4 + +=item user + +Name of the assigning user. + +=item text + +Text of the annotation. + +=item RETURN + +Returns an empty list if the annotation is not a functional assignment; otherwise, returns +a two-element list containing the user name and the function text. + +=back + +=cut + +sub _ParseAssignment { + # Get the parameters. + my ($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 FriendlyTimestamp + +Convert a time number to a user-friendly time stamp for display. + +This is a static method. + +=over 4 + +=item timeValue + +Numeric time value. + +=item RETURN + +Returns a string containing the same time in user-readable format. + +=back + +=cut + +sub FriendlyTimestamp { + my ($timeValue) = @_; + my $retVal = localtime($timeValue); + return $retVal; +} + -1; \ No newline at end of file +1;