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

Diff of /Sprout/Sprout.pm

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

revision 1.90, Fri Sep 29 15:10:05 2006 UTC revision 1.106, Wed Feb 6 23:21:02 2008 UTC
# Line 1  Line 1 
1  package Sprout;  package Sprout;
2    
     require Exporter;  
     use ERDB;  
     @ISA = qw(Exporter ERDB);  
3      use Data::Dumper;      use Data::Dumper;
4      use strict;      use strict;
     use Carp;  
5      use DBKernel;      use DBKernel;
6      use XML::Simple;      use XML::Simple;
7      use DBQuery;      use DBQuery;
8      use DBObject;      use ERDBObject;
9      use Tracer;      use Tracer;
10      use FIGRules;      use FIGRules;
11      use FidCheck;      use FidCheck;
12      use Stats;      use Stats;
13      use POSIX qw(strftime);      use POSIX qw(strftime);
14      use BasicLocation;      use BasicLocation;
15        use CustomAttributes;
16        use RemoteCustomAttributes;
17        use base qw(ERDB);
18    
19  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
20    
# Line 28  Line 27 
27  on the constructor. For example, the following invocation specifies a PostgreSQL database named I<GenDB>  on the constructor. For example, the following invocation specifies a PostgreSQL database named I<GenDB>
28  whose definition and data files are in a co-directory named F<Data>.  whose definition and data files are in a co-directory named F<Data>.
29    
30  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' });
31    
32  Once you have a sprout object, you may use it to re-create the database, load the tables from  Once you have a sprout object, you may use it to re-create the database, load the tables from
33  tab-delimited flat files and perform queries. Several special methods are provided for common  tab-delimited flat files and perform queries. Several special methods are provided for common
34  query tasks. For example, L</genomes> lists the IDs of all the genomes in the database and  query tasks. For example, L</Genomes> lists the IDs of all the genomes in the database and
35  L</dna_seq> returns the DNA sequence for a specified genome location.  L</DNASeq> returns the DNA sequence for a specified genome location.
36    
37  The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.  The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.
38    
# Line 45  Line 44 
44    
45  =head3 new  =head3 new
46    
47  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
48    
49  This is the constructor for a sprout object. It connects to the database and loads the  This is the constructor for a sprout object. It connects to the database and loads the
50  database definition into memory. The positional first parameter specifies the name of the  database definition into memory. The positional first parameter specifies the name of the
# Line 79  Line 78 
78    
79  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
80    
81    * B<host> name of the database host
82    
83  =back  =back
84    
85  For example, the following constructor call specifies a database named I<Sprout> and a user name of  For example, the following constructor call specifies a database named I<Sprout> and a user name of
86  I<fig> with a password of I<admin>. The database load files are in the directory  I<fig> with a password of I<admin>. The database load files are in the directory
87  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
88    
89  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' });
90    
91  =cut  =cut
92    
# Line 109  Line 110 
110                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::dbport,
111                                                          # database connection port                                                          # database connection port
112                         sock         => $FIG_Config::dbsock,                         sock         => $FIG_Config::dbsock,
113                         host         => $FIG_Config::dbhost,                         host         => $FIG_Config::sprout_host,
114                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
115                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
116                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
# Line 122  Line 123 
123      # Connect to the database.      # Connect to the database.
124      my $dbh;      my $dbh;
125      if (! $optionTable->{noDBOpen}) {      if (! $optionTable->{noDBOpen}) {
126            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
127          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
128                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
129      }      }
# Line 133  Line 135 
135      $retVal->{_xmlName} = $xmlFileName;      $retVal->{_xmlName} = $xmlFileName;
136      # Set up space for the group file data.      # Set up space for the group file data.
137      $retVal->{groupHash} = undef;      $retVal->{groupHash} = undef;
138        # Set up space for the genome hash. We use this to identify NMPDR genomes.
139        $retVal->{genomeHash} = undef;
140        # Connect to the attributes.
141        if ($FIG_Config::attrURL) {
142            Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
143            $retVal->{_ca} = RemoteCustomAttributes->new($FIG_Config::attrURL);
144        } elsif ($FIG_Config::attrDbName) {
145            Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
146            my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
147            $retVal->{_ca} = CustomAttributes->new(user => $user);
148        }
149      # Return it.      # Return it.
150      return $retVal;      return $retVal;
151  }  }
152    
153    =head3 RealCoreGenomes
154    
155        my @genomes = $sprout->RealCoreGenomes();
156    
157    Return the IDs of the original core NMPDR genomes. These are the ones
158    in the major groups indicated in the C<@realCoreGroups> member of the
159    B<FIG_Config> file.
160    
161    =cut
162    
163    sub RealCoreGenomes {
164        # Get the parameters.
165        my ($self) = @_;
166        # Declare the return variable.
167        my @retVal = ();
168        # Get the hash of all the genome groups.
169        my %groups = $self->GetGroups();
170        # Loop through the groups, keeping the ones that belong to real core
171        # organisms.
172        for my $group (keys %groups) {
173            if (grep { $group =~ /$_/ } @FIG_Config::realCoreGroups) {
174                push @retVal, @{$groups{$group}};
175            }
176        }
177        # Return the result.
178        return @retVal;
179    }
180    
181  =head3 MaxSegment  =head3 MaxSegment
182    
183  C<< my $length = $sprout->MaxSegment(); >>      my $length = $sprout->MaxSegment();
184    
185  This method returns the maximum permissible length of a feature segment. The length is important  This method returns the maximum permissible length of a feature segment. The length is important
186  because it enables us to make reasonable guesses at how to find features inside a particular  because it enables us to make reasonable guesses at how to find features inside a particular
# Line 156  Line 197 
197    
198  =head3 MaxSequence  =head3 MaxSequence
199    
200  C<< my $length = $sprout->MaxSequence(); >>      my $length = $sprout->MaxSequence();
201    
202  This method returns the maximum permissible length of a contig sequence. A contig is broken  This method returns the maximum permissible length of a contig sequence. A contig is broken
203  into sequences in order to save memory resources. In particular, when manipulating features,  into sequences in order to save memory resources. In particular, when manipulating features,
# Line 171  Line 212 
212    
213  =head3 Load  =head3 Load
214    
215  C<< $sprout->Load($rebuild); >>;      $sprout->Load($rebuild);;
216    
217  Load the database from files in the data directory, optionally re-creating the tables.  Load the database from files in the data directory, optionally re-creating the tables.
218    
# Line 211  Line 252 
252    
253  =head3 LoadUpdate  =head3 LoadUpdate
254    
255  C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
256    
257  Load updates to one or more database tables. This method enables the client to make changes to one  Load updates to one or more database tables. This method enables the client to make changes to one
258  or two tables without reloading the whole database. For each table, there must be a corresponding  or two tables without reloading the whole database. For each table, there must be a corresponding
# Line 257  Line 298 
298              Trace("No load file found for $tableName in $dataDir.") if T(0);              Trace("No load file found for $tableName in $dataDir.") if T(0);
299          } else {          } else {
300              # Attempt to load this table.              # Attempt to load this table.
301              my $result = $self->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
302              # Accumulate the resulting statistics.              # Accumulate the resulting statistics.
303              $retVal->Accumulate($result);              $retVal->Accumulate($result);
304          }          }
# Line 268  Line 309 
309    
310  =head3 GenomeCounts  =head3 GenomeCounts
311    
312  C<< my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete); >>      my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
313    
314  Count the number of genomes in each domain. If I<$complete> is TRUE, only complete  Count the number of genomes in each domain. If I<$complete> is TRUE, only complete
315  genomes will be included in the counts.  genomes will be included in the counts.
# Line 313  Line 354 
354    
355  =head3 ContigCount  =head3 ContigCount
356    
357  C<< my $count = $sprout->ContigCount($genomeID); >>      my $count = $sprout->ContigCount($genomeID);
358    
359  Return the number of contigs for the specified genome ID.  Return the number of contigs for the specified genome ID.
360    
# Line 342  Line 383 
383    
384  =head3 GeneMenu  =head3 GeneMenu
385    
386  C<< my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params, $selected); >>      my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params, $selected);
387    
388  Return an HTML select menu of genomes. Each genome will be an option in the menu,  Return an HTML select menu of genomes. Each genome will be an option in the menu,
389  and will be displayed by name with the ID and a contig count attached. The selection  and will be displayed by name with the ID and a contig count attached. The selection
# Line 423  Line 464 
464    
465  =head3 Build  =head3 Build
466    
467  C<< $sprout->Build(); >>      $sprout->Build();
468    
469  Build the database. The database will be cleared and the tables re-created from the metadata.  Build the database. The database will be cleared and the tables re-created from the metadata.
470  This method is useful when a database is brand new or when the database definition has  This method is useful when a database is brand new or when the database definition has
# Line 440  Line 481 
481    
482  =head3 Genomes  =head3 Genomes
483    
484  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
485    
486  Return a list of all the genome IDs.  Return a list of all the genome IDs.
487    
# Line 457  Line 498 
498    
499  =head3 GenusSpecies  =head3 GenusSpecies
500    
501  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
502    
503  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
504    
# Line 489  Line 530 
530    
531  =head3 FeaturesOf  =head3 FeaturesOf
532    
533  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
534    
535  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
536    
# Line 534  Line 575 
575    
576  =head3 FeatureLocation  =head3 FeatureLocation
577    
578  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
579    
580  Return the location of a feature in its genome's contig segments. In a list context, this method  Return the location of a feature in its genome's contig segments. In a list context, this method
581  will return a list of the locations. In a scalar context, it will return the locations as a space-  will return a list of the locations. In a scalar context, it will return the locations as a space-
# Line 563  Line 604 
604  =back  =back
605    
606  =cut  =cut
607  #: Return Type @;  
 #: Return Type $;  
608  sub FeatureLocation {  sub FeatureLocation {
609      # Get the parameters.      # Get the parameters.
610      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
611      # Create a query for the feature locations.      # Get the feature record.
612      my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",      my $object = $self->GetEntity('Feature', $featureID);
613                             [$featureID]);      Confess("Feature $featureID not found.") if ! defined($object);
614        # Get the location string.
615        my $locString = $object->PrimaryValue('Feature(location-string)');
616      # Create the return list.      # Create the return list.
617      my @retVal = ();      my @retVal = split /\s*,\s*/, $locString;
     # Set up the variables used to determine if we have adjacent segments. This initial setup will  
     # not match anything.  
     my ($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 + $len == $prevBeg) {  
                 # Here we're merging two backward blocks, so we keep the new begin point  
                 # and adjust the length.  
                 $len += $prevLen;  
                 # Pop the old segment off. The new one will replace it later.  
                 pop @retVal;  
             } elsif ($dir eq "+" && $beg == $prevBeg + $prevLen) {  
                 # Here we need to merge two forward blocks. 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);  
         # Compute the initial base pair.  
         my $start = ($dir eq "+" ? $beg : $beg + $len - 1);  
         # Add the specifier to the list.  
         push @retVal, "${contigID}_$start$dir$len";  
     }  
618      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
619      return (wantarray ? @retVal : join(',', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
620  }  }
621    
622  =head3 ParseLocation  =head3 ParseLocation
623    
624  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
625    
626  Split a location specifier into the contig ID, the starting point, the direction, and the  Split a location specifier into the contig ID, the starting point, the direction, and the
627  length.  length.
# Line 632  Line 640 
640  =back  =back
641    
642  =cut  =cut
643  #: Return Type @;  
644  sub ParseLocation {  sub ParseLocation {
645      # 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
646      # the first parameter.      # the first parameter.
# Line 659  Line 667 
667    
668  =head3 PointLocation  =head3 PointLocation
669    
670  C<< my $found = Sprout::PointLocation($location, $point); >>      my $found = Sprout::PointLocation($location, $point);
671    
672  Return the offset into the specified location of the specified point on the contig. If  Return the offset into the specified location of the specified point on the contig. If
673  the specified point is before the location, a negative value will be returned. If it is  the specified point is before the location, a negative value will be returned. If it is
# Line 688  Line 696 
696  =back  =back
697    
698  =cut  =cut
699  #: Return Type $;  
700  sub PointLocation {  sub PointLocation {
701      # 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
702      # the first parameter.      # the first parameter.
# Line 711  Line 719 
719    
720  =head3 DNASeq  =head3 DNASeq
721    
722  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
723    
724  This method returns the DNA sequence represented by a list of locations. The list of locations  This method returns the DNA sequence represented by a list of locations. The list of locations
725  should be of the form returned by L</featureLocation> when in a list context. In other words,  should be of the form returned by L</featureLocation> when in a list context. In other words,
# Line 795  Line 803 
803    
804  =head3 AllContigs  =head3 AllContigs
805    
806  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
807    
808  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
809    
# Line 825  Line 833 
833    
834  =head3 GenomeLength  =head3 GenomeLength
835    
836  C<< my $length = $sprout->GenomeLength($genomeID); >>      my $length = $sprout->GenomeLength($genomeID);
837    
838  Return the length of the specified genome in base pairs.  Return the length of the specified genome in base pairs.
839    
# Line 860  Line 868 
868    
869  =head3 FeatureCount  =head3 FeatureCount
870    
871  C<< my $count = $sprout->FeatureCount($genomeID, $type); >>      my $count = $sprout->FeatureCount($genomeID, $type);
872    
873  Return the number of features of the specified type in the specified genome.  Return the number of features of the specified type in the specified genome.
874    
# Line 895  Line 903 
903    
904  =head3 GenomeAssignments  =head3 GenomeAssignments
905    
906  C<< my $fidHash = $sprout->GenomeAssignments($genomeID); >>      my $fidHash = $sprout->GenomeAssignments($genomeID);
907    
908  Return a list of a genome's assigned features. The return hash will contain each  Return a list of a genome's assigned features. The return hash will contain each
909  assigned feature of the genome mapped to the text of its most recent functional  assigned feature of the genome mapped to the text of its most recent functional
# Line 921  Line 929 
929      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
930      # Declare the return variable.      # Declare the return variable.
931      my $retVal = {};      my $retVal = {};
932      # Query the genome's features and annotations. We'll put the oldest annotations      # Query the genome's features.
933      # first so that the last assignment to go into the hash will be the correct one.      my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?",
     my $query = $self->Get(['HasFeature', 'IsTargetOfAnnotation', 'Annotation'],  
                            "HasFeature(from-link) = ? ORDER BY Annotation(time)",  
934                             [$genomeID]);                             [$genomeID]);
935      # Loop through the annotations.      # Loop through the features.
936      while (my $data = $query->Fetch) {      while (my $data = $query->Fetch) {
937          # Get the feature ID and annotation text.          # Get the feature ID and assignment.
938          my ($fid, $annotation) = $data->Values(['HasFeature(to-link)',          my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
939                                                  'Annotation(annotation)']);          if ($assignment) {
         # Check to see if this is an assignment. Note that the user really  
         # doesn't matter to us, other than we use it to determine whether or  
         # not this is an assignment.  
         my ($user, $assignment) = _ParseAssignment('fig', $annotation);  
         if ($user) {  
             # Here it's an assignment. We put it in the return hash, overwriting  
             # any older assignment that might be present.  
940              $retVal->{$fid} = $assignment;              $retVal->{$fid} = $assignment;
941          }          }
942      }      }
# Line 947  Line 946 
946    
947  =head3 ContigLength  =head3 ContigLength
948    
949  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->ContigLength($contigID);
950    
951  Compute the length of a contig.  Compute the length of a contig.
952    
# Line 986  Line 985 
985    
986  =head3 ClusterPEGs  =head3 ClusterPEGs
987    
988  C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>      my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
989    
990  Cluster the PEGs in a list according to the cluster coding scheme of the specified  Cluster the PEGs in a list according to the cluster coding scheme of the specified
991  subsystem. In order for this to work properly, the subsystem object must have  subsystem. In order for this to work properly, the subsystem object must have
992  been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.  been used recently to retrieve the PEGs using the B<get_pegs_from_cell> or
993  This causes the cluster numbers to be pulled into the subsystem's color hash.  B<get_row> methods. This causes the cluster numbers to be pulled into the
994  If a PEG is not found in the color hash, it will not appear in the output  subsystem's color hash. If a PEG is not found in the color hash, it will not
995  sequence.  appear in the output sequence.
996    
997  =over 4  =over 4
998    
# Line 1034  Line 1033 
1033    
1034  =head3 GenesInRegion  =head3 GenesInRegion
1035    
1036  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1037    
1038  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1039    
# Line 1063  Line 1062 
1062  =back  =back
1063    
1064  =cut  =cut
1065  #: Return Type @@;  
1066  sub GenesInRegion {  sub GenesInRegion {
1067      # Get the parameters.      # Get the parameters.
1068      my ($self, $contigID, $start, $stop) = @_;      my ($self, $contigID, $start, $stop) = @_;
1069      # Get the maximum segment length.      # Get the maximum segment length.
1070      my $maximumSegmentLength = $self->MaxSegment;      my $maximumSegmentLength = $self->MaxSegment;
     # Create a hash to receive the feature list. We use a hash so that we can eliminate  
     # duplicates easily. The hash key will be the feature ID. The value will be a two-element  
     # containing the minimum and maximum offsets. We will use the offsets to sort the results  
     # when we're building the result set.  
     my %featuresFound = ();  
1071      # Prime the values we'll use for the returned beginning and end.      # Prime the values we'll use for the returned beginning and end.
1072      my @initialMinMax = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
1073      my ($min, $max) = @initialMinMax;      my ($min, $max) = @initialMinMax;
1074      # Create a table of parameters for each query. Each query looks for features travelling in      # Get the overlapping features.
1075        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1076        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1077        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1078        # of the feature's locations.
1079        my %featureMap = ();
1080        # Loop through them to do the begin/end analysis.
1081        for my $featureObject (@featureObjects) {
1082            # Get the feature's location string. This may contain multiple actual locations.
1083            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1084            my @locationSegments = split /\s*,\s*/, $locations;
1085            # Loop through the locations.
1086            for my $locationSegment (@locationSegments) {
1087                # Construct an object for the location.
1088                my $locationObject = BasicLocation->new($locationSegment);
1089                # Merge the current segment's begin and end into the min and max.
1090                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1091                my ($beg, $end);
1092                if (exists $featureMap{$fid}) {
1093                    ($beg, $end) = @{$featureMap{$fid}};
1094                    $beg = $left if $left < $beg;
1095                    $end = $right if $right > $end;
1096                } else {
1097                    ($beg, $end) = ($left, $right);
1098                }
1099                $min = $beg if $beg < $min;
1100                $max = $end if $end > $max;
1101                # Store the feature's new extent back into the hash table.
1102                $featureMap{$fid} = [$beg, $end];
1103            }
1104        }
1105        # Now we must compute the list of the IDs for the features found. We start with a list
1106        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1107        # but the result of the sort will be the same.)
1108        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1109        # Now we sort by midpoint and yank out the feature IDs.
1110        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1111        # Return it along with the min and max.
1112        return (\@retVal, $min, $max);
1113    }
1114    
1115    =head3 GeneDataInRegion
1116    
1117        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1118    
1119    List the features which overlap a specified region in a contig.
1120    
1121    =over 4
1122    
1123    =item contigID
1124    
1125    ID of the contig containing the region of interest.
1126    
1127    =item start
1128    
1129    Offset of the first residue in the region of interest.
1130    
1131    =item stop
1132    
1133    Offset of the last residue in the region of interest.
1134    
1135    =item RETURN
1136    
1137    Returns a list of B<ERDBObjects> for the desired features. Each object will
1138    contain a B<Feature> record.
1139    
1140    =back
1141    
1142    =cut
1143    
1144    sub GeneDataInRegion {
1145        # Get the parameters.
1146        my ($self, $contigID, $start, $stop) = @_;
1147        # Get the maximum segment length.
1148        my $maximumSegmentLength = $self->MaxSegment;
1149        # Create a hash to receive the feature list. We use a hash so that we can eliminate
1150        # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1151        # ERDBObject from the query.
1152        my %featuresFound = ();
1153        # Create a table of parameters for the queries. Each query looks for features travelling in
1154      # a particular direction. The query parameters include the contig ID, the feature direction,      # a particular direction. The query parameters include the contig ID, the feature direction,
1155      # the lowest possible start position, and the highest possible start position. This works      # the lowest possible start position, and the highest possible start position. This works
1156      # because each feature segment length must be no greater than the maximum segment length.      # because each feature segment length must be no greater than the maximum segment length.
# Line 1086  Line 1159 
1159      # Loop through the query parameters.      # Loop through the query parameters.
1160      for my $parms (values %queryParms) {      for my $parms (values %queryParms) {
1161          # Create the query.          # Create the query.
1162          my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1163              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1164              $parms);              $parms);
1165          # Loop through the feature segments found.          # Loop through the feature segments found.
1166          while (my $segment = $query->Fetch) {          while (my $segment = $query->Fetch) {
1167              # Get the data about this segment.              # Get the data about this segment.
1168              my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1169                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1170              # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1171              # this will be the case if the segment is the maximum length, so to fine-tune              # this will be the case if the segment is the maximum length, so to fine-tune
1172              # the results we insure that the inequality from the query holds using the actual              # the results we insure that the inequality from the query holds using the actual
1173              # length.              # length.
1174              my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1175              if ($dir eq '+') {              my $found = $loc->Overlap($start, $stop);
                 $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.  
                     $found = 1;  
                 }  
             }  
1176              if ($found) {              if ($found) {
1177                  # Here we need to record the feature and update the minima and maxima. First,                  # Save this feature in the result list.
1178                  # get the current entry for the specified feature.                  $featuresFound{$featureID} = $segment;
                 my ($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;  
1179                  }                  }
                 # Store the entry back into the hash table.  
                 $featuresFound{$featureID} = [$loc1, $loc2];  
1180              }              }
1181          }          }
1182      }      # Return the ERDB objects for the features found.
1183      # Now we must compute the list of the IDs for the features found. We start with a list      return values %featuresFound;
     # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,  
     # but the result of the sort will be the same.)  
     my @list = map { [$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);  
1184  }  }
1185    
1186  =head3 FType  =head3 FType
1187    
1188  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1189    
1190  Return the type of a feature.  Return the type of a feature.
1191    
# Line 1176  Line 1215 
1215    
1216  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1217    
1218  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1219    
1220  Return the annotations of a feature.  Return the annotations of a feature.
1221    
# Line 1239  Line 1278 
1278    
1279  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1280    
1281  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1282    
1283  Return all of the functional assignments for a particular feature. The data is returned as a  Return all of the functional assignments for a particular feature. The data is returned as a
1284  hash of functional assignments to user IDs. A functional assignment is a type of annotation,  hash of functional assignments to user IDs. A functional assignment is a type of annotation,
# Line 1294  Line 1333 
1333    
1334  =head3 FunctionOf  =head3 FunctionOf
1335    
1336  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1337    
1338  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1339    
1340  The functional assignment is handled differently depending on the type of feature. If  The functional assignment is handled differently depending on the type of feature. If
1341  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional  the feature is identified by a FIG ID (begins with the string C<fig|>), then the functional
1342  assignment is a type of annotation. The format of an assignment is described in  assignment is taken from the B<Feature> or C<Annotation> table, depending.
 L</ParseAssignment>. 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.  
1343    
1344  Each user has an associated list of trusted users. The assignment returned will be the most  Each user has an associated list of trusted users. The assignment returned will be the most
1345  recent one by at least one of the trusted users. If no trusted user list is available, then  recent one by at least one of the trusted users. If no trusted user list is available, then
# Line 1322  Line 1358 
1358    
1359  =item userID (optional)  =item userID (optional)
1360    
1361  ID of the user whose function determination is desired. If omitted, only the latest  ID of the user whose function determination is desired. If omitted, the primary
1362  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1363    
1364  =item RETURN  =item RETURN
1365    
# Line 1340  Line 1376 
1376      my $retVal;      my $retVal;
1377      # Determine the ID type.      # Determine the ID type.
1378      if ($featureID =~ m/^fig\|/) {      if ($featureID =~ m/^fig\|/) {
1379          # Here we have a FIG feature ID. We must build the list of trusted          # Here we have a FIG feature ID.
1380          # users.          if (!$userID) {
1381                # Use the primary assignment.
1382                ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);
1383            } else {
1384                # We must build the list of trusted users.
1385          my %trusteeTable = ();          my %trusteeTable = ();
1386          # Check the user ID.          # Check the user ID.
1387          if (!$userID) {          if (!$userID) {
# Line 1384  Line 1424 
1424                  }                  }
1425              }              }
1426          }          }
1427            }
1428      } else {      } else {
1429          # Here we have a non-FIG feature ID. In this case the user ID does not          # Here we have a non-FIG feature ID. In this case the user ID does not
1430          # matter. We simply get the information from the External Alias Function          # matter. We simply get the information from the External Alias Function
# Line 1396  Line 1437 
1437    
1438  =head3 FunctionsOf  =head3 FunctionsOf
1439    
1440  C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>      my @functionList = $sprout->FunctionOf($featureID, $userID);
1441    
1442  Return the functional assignments of a particular feature.  Return the functional assignments of a particular feature.
1443    
# Line 1468  Line 1509 
1509    
1510  =head3 BBHList  =head3 BBHList
1511    
1512  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1513    
1514  Return a hash mapping the features in a specified list to their bidirectional best hits  Return a hash mapping the features in a specified list to their bidirectional best hits
1515  on a specified target genome.  on a specified target genome.
# Line 1504  Line 1545 
1545          # Peel off the BBHs found.          # Peel off the BBHs found.
1546          my @found = ();          my @found = ();
1547          for my $bbh (@bbhData) {          for my $bbh (@bbhData) {
1548              push @found, $bbh->[0];              my $fid = $bbh->[0];
1549                my $bbGenome = $self->GenomeOf($fid);
1550                if ($bbGenome eq $genomeID) {
1551                    push @found, $fid;
1552                }
1553          }          }
1554          $retVal{$featureID} = \@found;          $retVal{$featureID} = \@found;
1555      }      }
# Line 1514  Line 1559 
1559    
1560  =head3 SimList  =head3 SimList
1561    
1562  C<< my %similarities = $sprout->SimList($featureID, $count); >>      my %similarities = $sprout->SimList($featureID, $count);
1563    
1564  Return a list of the similarities to the specified feature.  Return a list of the similarities to the specified feature.
1565    
# Line 1550  Line 1595 
1595    
1596  =head3 IsComplete  =head3 IsComplete
1597    
1598  C<< my $flag = $sprout->IsComplete($genomeID); >>      my $flag = $sprout->IsComplete($genomeID);
1599    
1600  Return TRUE if the specified genome is complete, else FALSE.  Return TRUE if the specified genome is complete, else FALSE.
1601    
# Line 1578  Line 1623 
1623      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->GetEntity('Genome', $genomeID);
1624      if ($genomeData) {      if ($genomeData) {
1625          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1626          ($retVal) = $genomeData->Value('Genome(complete)');          $retVal = $genomeData->PrimaryValue('Genome(complete)');
1627      }      }
1628      # Return the result.      # Return the result.
1629      return $retVal;      return $retVal;
# Line 1586  Line 1631 
1631    
1632  =head3 FeatureAliases  =head3 FeatureAliases
1633    
1634  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1635    
1636  Return a list of the aliases for a specified feature.  Return a list of the aliases for a specified feature.
1637    
# Line 1609  Line 1654 
1654      # Get the parameters.      # Get the parameters.
1655      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1656      # Get the desired feature's aliases      # Get the desired feature's aliases
1657      my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
1658      # Return the result.      # Return the result.
1659      return @retVal;      return @retVal;
1660  }  }
1661    
1662  =head3 GenomeOf  =head3 GenomeOf
1663    
1664  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $genomeID = $sprout->GenomeOf($featureID);
1665    
1666  Return the genome that contains a specified feature or contig.  Return the genome that contains a specified feature or contig.
1667    
# Line 1638  Line 1683 
1683  sub GenomeOf {  sub GenomeOf {
1684      # Get the parameters.      # Get the parameters.
1685      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
     # Create a query to find the genome associated with the incoming ID.  
     my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ? OR HasContig(to-link) = ?",  
                            [$featureID, $featureID]);  
1686      # Declare the return value.      # Declare the return value.
1687      my $retVal;      my $retVal;
1688      # Get the genome ID.      # Parse the genome ID from the feature ID.
1689      if (my $relationship = $query->Fetch()) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
1690          ($retVal) = $relationship->Value('HasContig(from-link)');          $retVal = $1;
1691        } else {
1692            Confess("Invalid feature ID $featureID.");
1693      }      }
1694      # Return the value found.      # Return the value found.
1695      return $retVal;      return $retVal;
# Line 1653  Line 1697 
1697    
1698  =head3 CoupledFeatures  =head3 CoupledFeatures
1699    
1700  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
1701    
1702  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
1703  functionally coupled if they tend to be clustered on the same chromosome.  functionally coupled if they tend to be clustered on the same chromosome.
# Line 1675  Line 1719 
1719  sub CoupledFeatures {  sub CoupledFeatures {
1720      # Get the parameters.      # Get the parameters.
1721      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1722        # Ask the coupling server for the data.
1723      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
1724      # Create a query to retrieve the functionally-coupled features.      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
1725      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
1726                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);      # Form them into a hash.
     # This value will be set to TRUE if we find at least one coupled feature.  
     my $found = 0;  
     # Create the return hash.  
1727      my %retVal = ();      my %retVal = ();
1728      # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
1729      while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
1730          # Get the ID and score of the coupling.          my ($featureID2, $score) = @{$pair};
1731          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',          # Only proceed if the feature is in NMPDR.
1732                                                          'Coupling(score)']);          if ($self->_CheckFeature($featureID2)) {
1733          Trace("$featureID coupled with score $score to ID $couplingID.") if T(coupling => 4);              $retVal{$featureID2} = $score;
1734          # Get the other feature that participates in the coupling.          }
         my ($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;  
         $found = 1;  
1735      }      }
1736      # Functional coupling is reflexive. If we found at least one coupled feature, we must add      # Functional coupling is reflexive. If we found at least one coupled feature, we must add
1737      # the incoming feature as well.      # the incoming feature as well.
1738      if ($found) {      if (keys %retVal) {
1739          $retVal{$featureID} = 9999;          $retVal{$featureID} = 9999;
1740      }      }
1741      # Return the hash.      # Return the hash.
# Line 1709  Line 1744 
1744    
1745  =head3 CouplingEvidence  =head3 CouplingEvidence
1746    
1747  C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>      my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
1748    
1749  Return the evidence for a functional coupling.  Return the evidence for a functional coupling.
1750    
# Line 1757  Line 1792 
1792      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
1793      # Declare the return variable.      # Declare the return variable.
1794      my @retVal = ();      my @retVal = ();
1795      # Our first task is to find out the nature of the coupling: whether or not      # Get the coupling and evidence data.
1796      # it exists, its score, and whether the features are stored in the same      my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
1797      # order as the ones coming in.      # Loop through the raw data, saving the ones that are in NMPDR genomes.
1798      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);      for my $rawTuple (@rawData) {
1799      # Only proceed if a coupling exists.          if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
1800      if ($couplingID) {              push @retVal, $rawTuple;
         # Determine the ordering to place on the evidence items. If we're  
         # inverted, we want to see feature 2 before feature 1 (descending); otherwise,  
         # we want feature 1 before feature 2 (normal).  
         Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);  
         my $ordering = ($inverted ? "DESC" : "");  
         # Get the coupling evidence.  
         my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],  
                                           "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",  
                                           [$couplingID],  
                                           ['PCH(used)', 'UsesAsEvidence(to-link)']);  
         # Loop through the evidence items. Each piece of evidence is represented by two  
         # positions in the evidence list, one for each feature on the other side of the  
         # evidence link. If at some point we want to generalize to couplings with  
         # more than two positions, this section of code will need to be re-done.  
         while (@evidenceList > 0) {  
             my $peg1Data = shift @evidenceList;  
             my $peg2Data = shift @evidenceList;  
             Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);  
             push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];  
         }  
         Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);  
1801      }      }
     # Return the result.  
     return @retVal;  
 }  
   
 =head3 GetCoupling  
   
 C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>  
   
 Return the coupling (if any) for the specified pair of PEGs. If a coupling  
 exists, we return the coupling ID along with an indicator of whether the  
 coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.  
 In the second case, we say the coupling is I<inverted>. The importance of an  
 inverted coupling is that the PEGs in the evidence will appear in reverse order.  
   
 =over 4  
   
 =item peg1  
   
 ID of the feature of interest.  
   
 =item peg2  
   
 ID of the potentially coupled feature.  
   
 =item RETURN  
   
 Returns a three-element list. The first element contains the database ID of  
 the coupling. The second element is FALSE if the coupling is stored in the  
 database in the caller specified order and TRUE if it is stored in the  
 inverted order. The third element is the coupling's score. If the coupling  
 does not exist, all three list elements will be C<undef>.  
   
 =back  
   
 =cut  
 #: Return Type $%@;  
 sub GetCoupling {  
     # Get the parameters.  
     my ($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, $score) = ($self->CouplingID($peg1, $peg2), undef, undef);  
     # Find the coupling data.  
     my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],  
                                  "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",  
                                  [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);  
     # Check to see if we found anything.  
     if (!@pegs) {  
         Trace("No coupling found.") if T(Coupling => 4);  
         # No coupling, so undefine the return value.  
         $retVal = undef;  
     } else {  
         # We have a coupling! Get the score and check for inversion.  
         $score = $pegs[0]->[1];  
         my $firstFound = $pegs[0]->[0];  
         $inverted = ($firstFound ne $peg1);  
         Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);  
1802      }      }
1803      # Return the result.      # Return the result.
1804      return ($retVal, $inverted, $score);      return @retVal;
1805  }  }
1806    
1807  =head3 GetSynonymGroup  =head3 GetSynonymGroup
1808    
1809  C<< my $id = $sprout->GetSynonymGroup($fid); >>      my $id = $sprout->GetSynonymGroup($fid);
1810    
1811  Return the synonym group name for the specified feature.  Return the synonym group name for the specified feature.
1812    
# Line 1888  Line 1845 
1845    
1846  =head3 GetBoundaries  =head3 GetBoundaries
1847    
1848  C<< my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList); >>      my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
1849    
1850  Determine the begin and end boundaries for the locations in a list. All of the  Determine the begin and end boundaries for the locations in a list. All of the
1851  locations must belong to the same contig and have mostly the same direction in  locations must belong to the same contig and have mostly the same direction in
# Line 1950  Line 1907 
1907      return ($contig, $beg, $end);      return ($contig, $beg, $end);
1908  }  }
1909    
 =head3 CouplingID  
   
 C<< my $couplingID = $sprout->CouplingID($peg1, $peg2); >>  
   
 Return the coupling ID for a pair of feature IDs.  
   
 The coupling ID is currently computed by joining the feature IDs in  
 sorted order with a space. Client modules (that is, modules which  
 use Sprout) should not, however, count on this always being the  
 case. This method provides a way for abstracting the concept of a  
 coupling ID. All that we know for sure about it is that it can be  
 generated easily from the feature IDs and the order of the IDs  
 in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>  
 will have the same value as C<CouplingID("b1", "a1")>.  
   
 =over 4  
   
 =item peg1  
   
 First feature of interest.  
   
 =item peg2  
   
 Second feature of interest.  
   
 =item RETURN  
   
 Returns the ID that would be used to represent a functional coupling of  
 the two specified PEGs.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub CouplingID {  
     my ($self, @pegs) = @_;  
     return $self->DigestKey(join " ", sort @pegs);  
 }  
   
1910  =head3 ReadFasta  =head3 ReadFasta
1911    
1912  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
1913    
1914  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
1915  one or more lines of data. The first line begins with a > character and contains an ID.  one or more lines of data. The first line begins with a > character and contains an ID.
# Line 2057  Line 1975 
1975    
1976  =head3 FormatLocations  =head3 FormatLocations
1977    
1978  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
1979    
1980  Insure that a list of feature locations is in the Sprout format. The Sprout feature location  Insure that a list of feature locations is in the Sprout format. The Sprout feature location
1981  format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward  format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward
# Line 2122  Line 2040 
2040    
2041  =head3 DumpData  =head3 DumpData
2042    
2043  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2044    
2045  Dump all the tables to tab-delimited DTX files. The files will be stored in the data directory.  Dump all the tables to tab-delimited DTX files. The files will be stored in the data directory.
2046    
# Line 2139  Line 2057 
2057    
2058  =head3 XMLFileName  =head3 XMLFileName
2059    
2060  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2061    
2062  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2063    
# Line 2150  Line 2068 
2068      return $self->{_xmlName};      return $self->{_xmlName};
2069  }  }
2070    
2071    =head3 GetGenomeNameData
2072    
2073        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2074    
2075    Return the genus, species, and unique characterization for a genome. This
2076    is similar to L</GenusSpecies>, with the exception that it returns the
2077    values in three seperate fields.
2078    
2079    =over 4
2080    
2081    =item genomeID
2082    
2083    ID of the genome whose name data is desired.
2084    
2085    =item RETURN
2086    
2087    Returns a three-element list, consisting of the genus, species, and strain
2088    of the specified genome. If the genome is not found, an error occurs.
2089    
2090    =back
2091    
2092    =cut
2093    
2094    sub GetGenomeNameData {
2095        # Get the parameters.
2096        my ($self, $genomeID) = @_;
2097        # Get the desired values.
2098        my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>
2099                                                                [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);
2100        # Throw an error if they were not found.
2101        if (! defined $genus) {
2102            Confess("Genome $genomeID not found in database.");
2103        }
2104        # Return the results.
2105        return ($genus, $species, $strain);
2106    }
2107    
2108    =head3 GetGenomeByNameData
2109    
2110        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2111    
2112    Return a list of the IDs of the genomes with the specified genus,
2113    species, and strain. In almost every case, there will be either zero or
2114    one IDs returned; however, two or more IDs could be returned if there are
2115    multiple versions of the genome in the database.
2116    
2117    =over 4
2118    
2119    =item genus
2120    
2121    Genus of the desired genome.
2122    
2123    =item species
2124    
2125    Species of the desired genome.
2126    
2127    =item strain
2128    
2129    Strain (unique characterization) of the desired genome. This may be an empty
2130    string, in which case it is presumed that the desired genome has no strain
2131    specified.
2132    
2133    =item RETURN
2134    
2135    Returns a list of the IDs of the genomes having the specified genus, species, and
2136    strain.
2137    
2138    =back
2139    
2140    =cut
2141    
2142    sub GetGenomeByNameData {
2143        # Get the parameters.
2144        my ($self, $genus, $species, $strain) = @_;
2145        # Try to find the genomes.
2146        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2147                                    [$genus, $species, $strain], 'Genome(id)');
2148        # Return the result.
2149        return @retVal;
2150    }
2151    
2152  =head3 Insert  =head3 Insert
2153    
2154  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2155    
2156  Insert an entity or relationship instance into the database. The entity or relationship of interest  Insert an entity or relationship instance into the database. The entity or relationship of interest
2157  is defined by a type name and then a hash of field names to values. Field values in the primary  is defined by a type name and then a hash of field names to values. Field values in the primary
# Line 2161  Line 2160 
2160  list references. For example, the following line inserts an inactive PEG feature named  list references. For example, the following line inserts an inactive PEG feature named
2161  C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.  C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.
2162    
2163  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']});
2164    
2165  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2166  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2167    
2168  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'});
2169    
2170  =over 4  =over 4
2171    
# Line 2191  Line 2190 
2190    
2191  =head3 Annotate  =head3 Annotate
2192    
2193  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2194    
2195  Annotate a feature. This inserts an Annotation record into the database and links it to the  Annotate a feature. This inserts an Annotation record into the database and links it to the
2196  specified feature and user.  specified feature and user.
# Line 2245  Line 2244 
2244    
2245  =head3 AssignFunction  =head3 AssignFunction
2246    
2247  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2248    
2249  This method assigns a function to a feature. Functions are a special type of annotation. The general  This method assigns a function to a feature. Functions are a special type of annotation. The general
2250  format is described in L</ParseAssignment>.  format is described in L</ParseAssignment>.
# Line 2305  Line 2304 
2304    
2305  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2306    
2307  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2308    
2309  Returns a list of features with the specified alias. The alias is parsed to determine  Returns a list of features with the specified alias. The alias is parsed to determine
2310  the type of the alias. A string of digits is a GenBack ID and a string of exactly 6  the type of the alias. A string of digits is a GenBack ID and a string of exactly 6
# Line 2339  Line 2338 
2338          push @retVal, $mappedAlias;          push @retVal, $mappedAlias;
2339      } else {      } else {
2340          # Here we have a non-FIG alias. Get the features with the normalized alias.          # Here we have a non-FIG alias. Get the features with the normalized alias.
2341          @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2342      }      }
2343      # Return the result.      # Return the result.
2344      return @retVal;      return @retVal;
# Line 2347  Line 2346 
2346    
2347  =head3 FeatureTranslation  =head3 FeatureTranslation
2348    
2349  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2350    
2351  Return the translation of a feature.  Return the translation of a feature.
2352    
# Line 2375  Line 2374 
2374    
2375  =head3 Taxonomy  =head3 Taxonomy
2376    
2377  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2378    
2379  Return the taxonomy of the specified genome. This will be in the form of a list  Return the taxonomy of the specified genome. This will be in the form of a list
2380  containing the various classifications in order from domain (eg. C<Bacteria>, C<Archaea>,  containing the various classifications in order from domain (eg. C<Bacteria>, C<Archaea>,
2381  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2382    
2383  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2384    
2385  =over 4  =over 4
2386    
# Line 2416  Line 2415 
2415    
2416  =head3 CrudeDistance  =head3 CrudeDistance
2417    
2418  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2419    
2420  Returns a crude estimate of the distance between two genomes. The distance is construed so  Returns a crude estimate of the distance between two genomes. The distance is construed so
2421  that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.  that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.
# Line 2468  Line 2467 
2467    
2468  =head3 RoleName  =head3 RoleName
2469    
2470  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2471    
2472  Return the descriptive name of the role with the specified ID. In general, a role  Return the descriptive name of the role with the specified ID. In general, a role
2473  will only have a descriptive name if it is coded as an EC number.  will only have a descriptive name if it is coded as an EC number.
# Line 2502  Line 2501 
2501    
2502  =head3 RoleDiagrams  =head3 RoleDiagrams
2503    
2504  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2505    
2506  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2507    
# Line 2532  Line 2531 
2531    
2532  =head3 GetProperties  =head3 GetProperties
2533    
2534  C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>      my @list = $sprout->GetProperties($fid, $key, $value, $url);
2535    
2536  Return a list of the properties with the specified characteristics.  Return a list of the properties with the specified characteristics.
2537    
2538  Properties are arbitrary key-value pairs associated with a feature. (At some point they  Properties are the Sprout analog of the FIG attributes. The call is
2539  will also be associated with genomes.) A property value is represented by a 4-tuple of  passed directly to the CustomAttributes or RemoteCustomAttributes object
2540  the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter  contained in this object.
2541    
2542  =over 4  This method returns a series of tuples that match the specified criteria. Each tuple
2543    will contain an object ID, a key, and one or more values. The parameters to this
2544    method therefore correspond structurally to the values expected in each tuple. In
2545    addition, you can ask for a generic search by suffixing a percent sign (C<%>) to any
2546    of the parameters. So, for example,
2547    
2548  =item fid      my @attributeList = $sprout->GetProperties('fig|100226.1.peg.1004', 'structure%', 1, 2);
2549    
2550  ID of the feature possessing the property.  would return something like
2551    
2552  =item key      ['fig}100226.1.peg.1004', 'structure', 1, 2]
2553        ['fig}100226.1.peg.1004', 'structure1', 1, 2]
2554        ['fig}100226.1.peg.1004', 'structure2', 1, 2]
2555        ['fig}100226.1.peg.1004', 'structureA', 1, 2]
2556    
2557  Name or key of the property.  Use of C<undef> in any position acts as a wild card (all values). You can also specify
2558    a list reference in the ID column. Thus,
2559    
2560  =item value      my @attributeList = $sprout->GetProperties(['100226.1', 'fig|100226.1.%'], 'PUBMED');
2561    
2562  Value of the property.  would get the PUBMED attribute data for Streptomyces coelicolor A3(2) and all its
2563    features.
2564    
2565  =item url  In addition to values in multiple sections, a single attribute key can have multiple
2566    values, so even
2567    
2568  URL of the document that indicated the property should have this particular value, or an      my @attributeList = $sprout->GetProperties($peg, 'virulent');
 empty string if no such document exists.  
2569    
2570  =back  which has no wildcard in the key or the object ID, may return multiple tuples.
2571    
2572  The parameters act as a filter for the desired data. Any non-null parameter will  =over 4
 automatically match all the tuples returned. So, specifying just the I<$fid> will  
 return all the properties of the specified feature; similarly, specifying the I<$key>  
 and I<$value> parameters will return all the features having the specified property  
 value.  
2573    
2574  A single property key can have many values, representing different ideas about the  =item objectID
 feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is  
 virulent, and another may declare that it is not virulent. A query about the virulence of  
 C<fig|83333.1.peg.10> would be coded as  
2575    
2576      my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');  ID of object whose attributes are desired. If the attributes are desired for multiple
2577    objects, this parameter can be specified as a list reference. If the attributes are
2578    desired for all objects, specify C<undef> or an empty string. Finally, you can specify
2579    attributes for a range of object IDs by putting a percent sign (C<%>) at the end.
2580    
2581  Here the I<$value> and I<$url> fields are left blank, indicating that those fields are  =item key
 not to be filtered. The tuples returned would be  
2582    
2583      ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')  Attribute key name. A value of C<undef> or an empty string will match all
2584      ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')  attribute keys. If the values are desired for multiple keys, this parameter can be
2585    specified as a list reference. Finally, you can specify attributes for a range of
2586    keys by putting a percent sign (C<%>) at the end.
2587    
2588    =item values
2589    
2590    List of the desired attribute values, section by section. If C<undef>
2591    or an empty string is specified, all values in that section will match. A
2592    generic match can be requested by placing a percent sign (C<%>) at the end.
2593    In that case, all values that match up to and not including the percent sign
2594    will match. You may also specify a regular expression enclosed
2595    in slashes. All values that match the regular expression will be returned. For
2596    performance reasons, only values have this extra capability.
2597    
2598    =item RETURN
2599    
2600    Returns a list of tuples. The first element in the tuple is an object ID, the
2601    second is an attribute key, and the remaining elements are the sections of
2602    the attribute value. All of the tuples will match the criteria set forth in
2603    the parameter list.
2604    
2605    =back
2606    
2607  =cut  =cut
2608  #: Return Type @@;  
2609  sub GetProperties {  sub GetProperties {
2610      # Get the parameters.      # Get the parameters.
2611      my ($self, @parms) = @_;      my ($self, @parms) = @_;
2612      # Declare the return variable.      # Declare the return variable.
2613      my @retVal = ();      my @retVal = $self->{_ca}->GetAttributes(@parms);
     # Now we need to create a WHERE clause that will get us the data we want. First,  
     # we create a list of the columns containing the data for each parameter.  
     my @colNames = ('HasProperty(from-link)', 'Property(property-name)',  
                     'Property(property-value)', 'HasProperty(evidence)');  
     # Now we build the WHERE clause and the list of parameter values.  
     my @where = ();  
     my @values = ();  
     for (my $i = 0; $i <= $#colNames; $i++) {  
         my $parm = $parms[$i];  
         if (defined $parm && ($parm ne '')) {  
             push @where, "$colNames[$i] = ?";  
             push @values, $parm;  
         }  
     }  
     # Format the WHERE clause.  
     my $filter = (@values > 0 ? (join " AND ", @where) : undef);  
     # Ask for all the propertie values with the desired characteristics.  
     my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);  
     while (my $valueObject = $query->Fetch()) {  
         my @tuple = $valueObject->Values(\@colNames);  
         push @retVal, \@tuple;  
     }  
2614      # Return the result.      # Return the result.
2615      return @retVal;      return @retVal;
2616  }  }
2617    
2618  =head3 FeatureProperties  =head3 FeatureProperties
2619    
2620  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2621    
2622  Return a list of the properties for the specified feature. Properties are key-value pairs  Return a list of the properties for the specified feature. Properties are key-value pairs
2623  that specify special characteristics of the feature. For example, a property could indicate  that specify special characteristics of the feature. For example, a property could indicate
2624  that a feature is essential to the survival of the organism or that it has benign influence  that a feature is essential to the survival of the organism or that it has benign influence
2625  on the activities of a pathogen. Each property is returned as a triple of the form  on the activities of a pathogen. Each property is returned as a triple of the form
2626  C<($key,$value,$url)>, where C<$key> is the property name, C<$value> is its value (commonly  C<($key,@values)>, where C<$key> is the property name and  C<@values> are its values.
 a 1 or a 0, but possibly a string or a floating-point value), and C<$url> is a string describing  
 the web address or citation in which the property's value for the feature was identified.  
2627    
2628  =over 4  =over 4
2629    
# Line 2633  Line 2633 
2633    
2634  =item RETURN  =item RETURN
2635    
2636  Returns a list of triples, each triple containing the property name, its value, and a URL or  Returns a list of tuples, each tuple containing the property name and its values.
 citation.  
2637    
2638  =back  =back
2639    
# Line 2644  Line 2643 
2643      # Get the parameters.      # Get the parameters.
2644      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2645      # Get the properties.      # Get the properties.
2646      my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->{_ca}->GetAttributes($featureID);
2647                              ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2648                               'HasProperty(evidence)']);      my @retVal = ();
2649        for my $attributeRow (@attributes) {
2650            shift @{$attributeRow};
2651            push @retVal, $attributeRow;
2652        }
2653      # Return the resulting list.      # Return the resulting list.
2654      return @retVal;      return @retVal;
2655  }  }
2656    
2657  =head3 DiagramName  =head3 DiagramName
2658    
2659  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2660    
2661  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2662    
# Line 2681  Line 2684 
2684    
2685  =head3 PropertyID  =head3 PropertyID
2686    
2687  C<< my $id = $sprout->PropertyID($propName, $propValue); >>      my $id = $sprout->PropertyID($propName, $propValue);
2688    
2689  Return the ID of the specified property name and value pair, if the  Return the ID of the specified property name and value pair, if the
2690  pair exists.  pair exists. Only a small subset of the FIG attributes are stored as
2691    Sprout properties, mostly for use in search optimization.
2692    
2693  =over 4  =over 4
2694    
# Line 2717  Line 2721 
2721    
2722  =head3 MergedAnnotations  =head3 MergedAnnotations
2723    
2724  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2725    
2726  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2727  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2766  Line 2770 
2770    
2771  =head3 RoleNeighbors  =head3 RoleNeighbors
2772    
2773  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
2774    
2775  Returns a list of the roles that occur in the same diagram as the specified role. Because  Returns a list of the roles that occur in the same diagram as the specified role. Because
2776  diagrams and roles are in a many-to-many relationship with each other, the list is  diagrams and roles are in a many-to-many relationship with each other, the list is
# Line 2809  Line 2813 
2813    
2814  =head3 FeatureLinks  =head3 FeatureLinks
2815    
2816  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
2817    
2818  Return a list of the web hyperlinks associated with a feature. The web hyperlinks are  Return a list of the web hyperlinks associated with a feature. The web hyperlinks are
2819  to external websites describing either the feature itself or the organism containing it  to external websites describing either the feature itself or the organism containing it
# Line 2840  Line 2844 
2844    
2845  =head3 SubsystemsOf  =head3 SubsystemsOf
2846    
2847  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
2848    
2849  Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped  Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped
2850  to the roles the feature performs.  to the roles the feature performs.
# Line 2888  Line 2892 
2892    
2893  =head3 SubsystemList  =head3 SubsystemList
2894    
2895  C<< my @subsystems = $sprout->SubsystemList($featureID); >>      my @subsystems = $sprout->SubsystemList($featureID);
2896    
2897  Return a list containing the names of the subsystems in which the specified  Return a list containing the names of the subsystems in which the specified
2898  feature participates. Unlike L</SubsystemsOf>, this method only returns the  feature participates. Unlike L</SubsystemsOf>, this method only returns the
# Line 2920  Line 2924 
2924    
2925  =head3 GenomeSubsystemData  =head3 GenomeSubsystemData
2926    
2927  C<< my %featureData = $sprout->GenomeSubsystemData($genomeID); >>      my %featureData = $sprout->GenomeSubsystemData($genomeID);
2928    
2929  Return a hash mapping genome features to their subsystem roles.  Return a hash mapping genome features to their subsystem roles.
2930    
# Line 2980  Line 2984 
2984    
2985  =head3 RelatedFeatures  =head3 RelatedFeatures
2986    
2987  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
2988    
2989  Return a list of the features which are bi-directional best hits of the specified feature and  Return a list of the features which are bi-directional best hits of the specified feature and
2990  have been assigned the specified function by the specified user. If no such features exists,  have been assigned the specified function by the specified user. If no such features exists,
# Line 3031  Line 3035 
3035    
3036  =head3 TaxonomySort  =head3 TaxonomySort
3037    
3038  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3039    
3040  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a list formed by sorting the specified features by the taxonomy of the containing
3041  genome. This will cause genomes from similar organisms to float close to each other.  genome. This will cause genomes from similar organisms to float close to each other.
# Line 3066  Line 3070 
3070          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3071                                          [$fid], 'Genome(taxonomy)');                                          [$fid], 'Genome(taxonomy)');
3072          # Add this feature to the hash buffer.          # Add this feature to the hash buffer.
3073          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);          push @{$hashBuffer{$taxonomy}}, $fid;
3074      }      }
3075      # Sort the keys and get the elements.      # Sort the keys and get the elements.
3076      my @retVal = ();      my @retVal = ();
# Line 3079  Line 3083 
3083    
3084  =head3 Protein  =head3 Protein
3085    
3086  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3087    
3088  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3089    
# Line 3149  Line 3153 
3153      # Loop through the input triples.      # Loop through the input triples.
3154      my $n = length $sequence;      my $n = length $sequence;
3155      for (my $i = 0; $i < $n; $i += 3) {      for (my $i = 0; $i < $n; $i += 3) {
3156          # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3157          my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3158            my $triple = uc substr($sequence, $i, 3);
3159          # Translate it using the table.          # Translate it using the table.
3160          my $protein = "X";          my $protein = "X";
3161          if (exists $table->{$triple}) { $protein = $table->{$triple}; }          if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 3164  Line 3169 
3169    
3170  =head3 LoadInfo  =head3 LoadInfo
3171    
3172  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3173    
3174  Return the name of the directory from which data is to be loaded and a list of the relation  Return the name of the directory from which data is to be loaded and a list of the relation
3175  names. This information is useful when trying to analyze what needs to be put where in order  names. This information is useful when trying to analyze what needs to be put where in order
# Line 3183  Line 3188 
3188      return @retVal;      return @retVal;
3189  }  }
3190    
3191    =head3 BBHMatrix
3192    
3193        my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3194    
3195    Find all the bidirectional best hits for the features of a genome in a
3196    specified list of target genomes. The return value will be a hash mapping
3197    features in the original genome to their bidirectional best hits in the
3198    target genomes.
3199    
3200    =over 4
3201    
3202    =item genomeID
3203    
3204    ID of the genome whose features are to be examined for bidirectional best hits.
3205    
3206    =item cutoff
3207    
3208    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3209    
3210    =item targets
3211    
3212    List of target genomes. Only pairs originating in the original
3213    genome and landing in one of the target genomes will be returned.
3214    
3215    =item RETURN
3216    
3217    Returns a hash mapping each feature in the original genome to a hash mapping its
3218    BBH pegs in the target genomes to their scores.
3219    
3220    =back
3221    
3222    =cut
3223    
3224    sub BBHMatrix {
3225        # Get the parameters.
3226        my ($self, $genomeID, $cutoff, @targets) = @_;
3227        # Declare the return variable.
3228        my %retVal = ();
3229        # Ask for the BBHs.
3230        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3231        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3232        for my $bbhData (@bbhList) {
3233            my ($peg1, $peg2, $score) = @{$bbhData};
3234            if (! exists $retVal{$peg1}) {
3235                $retVal{$peg1} = { $peg2 => $score };
3236            } else {
3237                $retVal{$peg1}->{$peg2} = $score;
3238            }
3239        }
3240        # Return the result.
3241        return %retVal;
3242    }
3243    
3244    
3245    =head3 SimMatrix
3246    
3247        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3248    
3249    Find all the similarities for the features of a genome in a
3250    specified list of target genomes. The return value will be a hash mapping
3251    features in the original genome to their similarites in the
3252    target genomes.
3253    
3254    =over 4
3255    
3256    =item genomeID
3257    
3258    ID of the genome whose features are to be examined for similarities.
3259    
3260    =item cutoff
3261    
3262    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3263    
3264    =item targets
3265    
3266    List of target genomes. Only pairs originating in the original
3267    genome and landing in one of the target genomes will be returned.
3268    
3269    =item RETURN
3270    
3271    Returns a hash mapping each feature in the original genome to a hash mapping its
3272    similar pegs in the target genomes to their scores.
3273    
3274    =back
3275    
3276    =cut
3277    
3278    sub SimMatrix {
3279        # Get the parameters.
3280        my ($self, $genomeID, $cutoff, @targets) = @_;
3281        # Declare the return variable.
3282        my %retVal = ();
3283        # Get the list of features in the source organism.
3284        my @fids = $self->FeaturesOf($genomeID);
3285        # Ask for the sims. We only want similarities to fig features.
3286        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3287        if (! defined $simList) {
3288            Confess("Unable to retrieve similarities from server.");
3289        } else {
3290            Trace("Processing sims.") if T(3);
3291            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3292            # Create a hash for the target genomes.
3293            my %targetHash = map { $_ => 1 } @targets;
3294            for my $simData (@{$simList}) {
3295                # Get the PEGs and the score.
3296                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3297                # Insure the second ID is in the target list.
3298                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3299                if (exists $targetHash{$genome2}) {
3300                    # Here it is. Now we need to add it to the return hash. How we do that depends
3301                    # on whether or not $peg1 is new to us.
3302                    if (! exists $retVal{$peg1}) {
3303                        $retVal{$peg1} = { $peg2 => $score };
3304                    } else {
3305                        $retVal{$peg1}->{$peg2} = $score;
3306                    }
3307                }
3308            }
3309        }
3310        # Return the result.
3311        return %retVal;
3312    }
3313    
3314    
3315  =head3 LowBBHs  =head3 LowBBHs
3316    
3317  C<< my %bbhMap = $sprout->LowBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3318    
3319  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3320  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 3218  Line 3347 
3347      my @bbhList = FIGRules::BBHData($featureID, $cutoff);      my @bbhList = FIGRules::BBHData($featureID, $cutoff);
3348      # Form the results into the return hash.      # Form the results into the return hash.
3349      for my $pair (@bbhList) {      for my $pair (@bbhList) {
3350          $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3351            if ($self->Exists('Feature', $fid)) {
3352                $retVal{$fid} = $pair->[1];
3353            }
3354      }      }
3355      # Return the result.      # Return the result.
3356      return %retVal;      return %retVal;
# Line 3226  Line 3358 
3358    
3359  =head3 Sims  =head3 Sims
3360    
3361  C<< my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters); >>      my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3362    
3363  Get a list of similarities for a specified feature. Similarity information is not kept in the  Get a list of similarities for a specified feature. Similarity information is not kept in the
3364  Sprout database; rather, they are retrieved from a network server. The similarities are  Sprout database; rather, they are retrieved from a network server. The similarities are
# Line 3236  Line 3368 
3368  Similarities can be either raw or expanded. The raw similarities are basic  Similarities can be either raw or expanded. The raw similarities are basic
3369  hits between features with similar DNA. Expanding a raw similarity drags in any  hits between features with similar DNA. Expanding a raw similarity drags in any
3370  features considered substantially identical. So, for example, if features B<A1>,  features considered substantially identical. So, for example, if features B<A1>,
3371  B<A2>, and B<A3> are all substatially identical to B<A>, then a raw similarity  B<A2>, and B<A3> are all substantially identical to B<A>, then a raw similarity
3372  B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.  B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3373    
3374  =over 4  =over 4
3375    
3376  =item fid  =item fid
3377    
3378  ID of the feature whose similarities are desired.  ID of the feature whose similarities are desired, or reference to a list of IDs
3379    of features whose similarities are desired.
3380    
3381  =item maxN  =item maxN
3382    
# Line 3291  Line 3424 
3424    
3425  =head3 IsAllGenomes  =head3 IsAllGenomes
3426    
3427  C<< my $flag = $sprout->IsAllGenomes(\@list, \@checkList); >>      my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3428    
3429  Return TRUE if all genomes in the second list are represented in the first list at  Return TRUE if all genomes in the second list are represented in the first list at
3430  least one. Otherwise, return FALSE. If the second list is omitted, the first list is  least one. Otherwise, return FALSE. If the second list is omitted, the first list is
# Line 3340  Line 3473 
3473    
3474  =head3 GetGroups  =head3 GetGroups
3475    
3476  C<< my %groups = $sprout->GetGroups(\@groupList); >>      my %groups = $sprout->GetGroups(\@groupList);
3477    
3478  Return a hash mapping each group to the IDs of the genomes in the group.  Return a hash mapping each group to the IDs of the genomes in the group.
3479  A list of groups may be specified, in which case only those groups will be  A list of groups may be specified, in which case only those groups will be
# Line 3372  Line 3505 
3505                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3506          # Loop through the genomes found.          # Loop through the genomes found.
3507          for my $genome (@genomes) {          for my $genome (@genomes) {
3508              # Pop this genome's ID off the current list.              # Get the genome ID and group, and add this genome to the group's list.
3509              my @groups = @{$genome};              my ($genomeID, $group) = @{$genome};
3510              my $genomeID = shift @groups;              push @{$retVal{$group}}, $genomeID;
             # Loop through the groups, adding the genome ID to each group's  
             # list.  
             for my $group (@groups) {  
                 Tracer::AddToListMap(\%retVal, $group, $genomeID);  
             }  
3511          }          }
3512      }      }
3513      # Return the hash we just built.      # Return the hash we just built.
# Line 3388  Line 3516 
3516    
3517  =head3 MyGenomes  =head3 MyGenomes
3518    
3519  C<< my @genomes = Sprout::MyGenomes($dataDir); >>      my @genomes = Sprout::MyGenomes($dataDir);
3520    
3521  Return a list of the genomes to be included in the Sprout.  Return a list of the genomes to be included in the Sprout.
3522    
# Line 3420  Line 3548 
3548    
3549  =head3 LoadFileName  =head3 LoadFileName
3550    
3551  C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>      my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3552    
3553  Return the name of the load file for the specified table in the specified data  Return the name of the load file for the specified table in the specified data
3554  directory.  directory.
# Line 3461  Line 3589 
3589    
3590  =head3 DeleteGenome  =head3 DeleteGenome
3591    
3592  C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>      my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3593    
3594  Delete a genome from the database.  Delete a genome from the database.
3595    
# Line 3487  Line 3615 
3615      # Get the parameters.      # Get the parameters.
3616      my ($self, $genomeID, $testFlag) = @_;      my ($self, $genomeID, $testFlag) = @_;
3617      # Perform the delete for the genome's features.      # Perform the delete for the genome's features.
3618      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", $testFlag);      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3619      # Perform the delete for the primary genome data.      # Perform the delete for the primary genome data.
3620      my $stats = $self->Delete('Genome', $genomeID, $testFlag);      my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3621      $retVal->Accumulate($stats);      $retVal->Accumulate($stats);
3622      # Return the result.      # Return the result.
3623      return $retVal;      return $retVal;
# Line 3497  Line 3625 
3625    
3626  =head3 Fix  =head3 Fix
3627    
3628  C<< my %fixedHash = Sprout::Fix(%groupHash); >>      my %fixedHash = $sprout->Fix(%groupHash);
3629    
3630  Prepare a genome group hash (like that returned by L</GetGroups> for processing.  Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3631  Groups with the same primary name will be combined. The primary name is the  The groups will be combined into the appropriate super-groups.
 first capitalized word in the group name.  
3632    
3633  =over 4  =over 4
3634    
# Line 3519  Line 3646 
3646    
3647  sub Fix {  sub Fix {
3648      # Get the parameters.      # Get the parameters.
3649      my (%groupHash) = @_;      my ($self, %groupHash) = @_;
3650      # Create the result hash.      # Create the result hash.
3651      my %retVal = ();      my %retVal = ();
3652        # Get the super-group table.
3653        my %superTable = $self->CheckGroupFile();
3654      # Copy over the genomes.      # Copy over the genomes.
3655      for my $groupID (keys %groupHash) {      for my $groupID (keys %groupHash) {
3656          # Make a safety copy of the group ID.          # Get the super-group name.
3657          my $realGroupID = $groupID;          my $realGroupID;
         # Yank the primary name.  
3658          if ($groupID =~ /([A-Z]\w+)/) {          if ($groupID =~ /([A-Z]\w+)/) {
3659                if (! defined($superTable{$1})) {
3660                    Confess("Super-group name not found for group $groupID.");
3661                } else {
3662              $realGroupID = $1;              $realGroupID = $1;
3663          }          }
3664            } else {
3665                Confess("Invalid group name $groupID.");
3666            }
3667          # Append this group's genomes into the result hash.          # Append this group's genomes into the result hash.
3668          Tracer::AddToListMap(\%retVal, $realGroupID, @{$groupHash{$groupID}});          push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3669      }      }
3670      # Return the result hash.      # Return the result hash.
3671      return %retVal;      return %retVal;
# Line 3539  Line 3673 
3673    
3674  =head3 GroupPageName  =head3 GroupPageName
3675    
3676  C<< my $name = $sprout->GroupPageName($group); >>      my $name = $sprout->GroupPageName($group);
3677    
3678  Return the name of the page for the specified NMPDR group.  Return the name of the page for the specified NMPDR group.
3679    
# Line 3564  Line 3698 
3698      # Declare the return variable.      # Declare the return variable.
3699      my $retVal;      my $retVal;
3700      # Check for the group file data.      # Check for the group file data.
3701      if (! defined $self->{groupHash}) {      my %superTable = $self->CheckGroupFile();
         # Read the group file.  
         my %groupData = Sprout::ReadGroupFile($self->{_options}->{dataDir} . "/groups.tbl");  
         # Store it in our object.  
         $self->{groupHash} = \%groupData;  
     }  
3702      # Compute the real group name.      # Compute the real group name.
     my $realGroup = $group;  
3703      if ($group =~ /([A-Z]\w+)/) {      if ($group =~ /([A-Z]\w+)/) {
3704          $realGroup = $1;          my $realGroup = $1;
3705            if (! defined($superTable{$1})) {
3706                Confess("No super-group found for \"$group\".");
3707            } else {
3708                $retVal = "../content/$superTable{$1}->{page}";
3709            }
3710        } else {
3711            Confess("\"group\" is not a valid group name.");
3712      }      }
     # Return the page name.  
     $retVal = "../content/" . $self->{groupHash}->{$realGroup}->[1];  
3713      # Return the result.      # Return the result.
3714      return $retVal;      return $retVal;
3715  }  }
3716    
 =head3 ReadGroupFile  
3717    
3718  C<< my %groupData = Sprout::ReadGroupFile($groupFileName); >>  =head3 AddProperty
3719    
3720        $sprout->AddProperty($featureID, $key, @values);
3721    
3722  Read in the data from the specified group file. The group file contains information  Add a new attribute value (Property) to a feature.
 about each of the NMPDR groups.  
3723    
3724  =over 4  =over 4
3725    
3726  =item name  =item peg
3727    
3728  Name of the group.  ID of the feature to which the attribute is to be added.
3729    
3730  =item page  =item key
3731    
3732  Name of the group's page on the web site (e.g. C<campy.php> for  Name of the attribute (key).
 Campylobacter)  
3733    
3734  =item genus  =item values
3735    
3736  Genus of the group  Values of the attribute.
3737    
3738  =item species  =back
3739    
3740  Species of the group, or an empty string if the group is for an entire  =cut
3741  genus. If the group contains more than one species, the species names  #: Return Type ;
3742  should be separated by commas.  sub AddProperty {
3743        # Get the parameters.
3744        my ($self, $featureID, $key, @values) = @_;
3745        # Add the property using the attached attributes object.
3746        $self->{_ca}->AddAttribute($featureID, $key, @values);
3747    }
3748    
3749  =back  =head3 CheckGroupFile
3750    
3751        my %groupData = $sprout->CheckGroupFile();
3752    
3753  The parameters to this method are as follows  Get the group file hash. The group file hash describes the relationship
3754    between a group and the super-group to which it belongs for purposes of
3755    display. The super-group name is computed from the first capitalized word
3756    in the actual group name. For each super-group, the group file contains
3757    the page name and a list of the species expected to be in the group.
3758    Each species is specified by a genus and a species name. A species name
3759    of C<0> implies an entire genus.
3760    
3761    This method returns a hash from super-group names to a hash reference. Each
3762    resulting hash reference contains the following fields.
3763    
3764  =over 4  =over 4
3765    
3766  =item groupFile  =item page
3767    
3768  Name of the file containing the group data.  The super-group's web page in the NMPDR.
3769    
3770  =item RETURN  =item contents
3771    
3772  Returns a hash keyed on group name. The value of each hash  A list of 2-tuples, each containing a genus name followed by a species name
3773    (or 0, indicating all species). This list indicates which organisms belong
3774    in the super-group.
3775    
3776  =back  =back
3777    
3778  =cut  =cut
3779    
3780  sub ReadGroupFile {  sub CheckGroupFile{
3781      # Get the parameters.      # Get the parameters.
3782      my ($groupFileName) = @_;      my ($self) = @_;
3783      # Declare the return variable.      # Check to see if we already have this hash.
3784      my %retVal;      if (! defined $self->{groupHash}) {
3785            # We don't, so we need to read it in.
3786            my %groupHash;
3787      # Read the group file.      # Read the group file.
3788      my @groupLines = Tracer::GetFile($groupFileName);          my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
3789            # Loop through the list of sort-of groups.
3790      for my $groupLine (@groupLines) {      for my $groupLine (@groupLines) {
3791          my ($name, $page, $genus, $species) = split(/\t/, $groupLine);              my ($name, $page, @contents) = split /\t/, $groupLine;
3792          $retVal{$name} = [$page, $genus, $species];              $groupHash{$name} = { page => $page,
3793                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
3794                                    };
3795            }
3796            # Save the hash.
3797            $self->{groupHash} = \%groupHash;
3798      }      }
3799      # Return the result.      # Return the result.
3800      return %retVal;      return %{$self->{groupHash}};
3801  }  }
3802    
3803  =head3 AddProperty  =head2 Virtual Methods
   
 C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>  
   
 Add a new attribute value (Property) to a feature. In the SEED system, attributes can  
 be added to almost any object. In Sprout, they can only be added to features. In  
 Sprout, attributes are implemented using I<properties>. A property represents a key/value  
 pair. If the particular key/value pair coming in is not already in the database, a new  
 B<Property> record is created to hold it.  
3804    
3805  =over 4  =head3 CleanKeywords
   
 =item peg  
3806    
3807  ID of the feature to which the attribute is to be replied.      my $cleanedString = $sprout->CleanKeywords($searchExpression);
3808    
3809  =item key  Clean up a search expression or keyword list. This involves converting the periods
3810    in EC numbers to underscores, converting non-leading minus signs to underscores,
3811    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
3812    characters. In addition, any extra spaces are removed.
3813    
3814  Name of the attribute (key).  =over 4
3815    
3816  =item value  =item searchExpression
3817    
3818  Value of the attribute.  Search expression or keyword list to clean. Note that a search expression may
3819    contain boolean operators which need to be preserved. This includes leading
3820    minus signs.
3821    
3822  =item url  =item RETURN
3823    
3824  URL or text citation from which the property was obtained.  Cleaned expression or keyword list.
3825    
3826  =back  =back
3827    
3828  =cut  =cut
3829  #: Return Type ;  
3830  sub AddProperty {  sub CleanKeywords {
3831      # Get the parameters.      # Get the parameters.
3832      my ($self, $featureID, $key, $value, $url) = @_;      my ($self, $searchExpression) = @_;
3833      # Declare the variable to hold the desired property ID.      # Perform the standard cleanup.
3834      my $propID;      my $retVal = $self->ERDB::CleanKeywords($searchExpression);
3835      # Attempt to find a property record for this key/value pair.      # Fix the periods in EC and TC numbers.
3836      my @properties = $self->GetFlat(['Property'],      $retVal =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;
3837                                     "Property(property-name) = ? AND Property(property-value) = ?",      # Fix non-trailing periods.
3838                                     [$key, $value], 'Property(id)');      $retVal =~ s/\.(\w)/_$1/g;
3839      if (@properties) {      # Fix non-leading minus signs.
3840          # Here the property is already in the database. We save its ID.      $retVal =~ s/(\w)[\-]/$1_/g;
3841          $propID = $properties[0];      # Fix the vertical bars and colons
3842          # Here the property value does not exist. We need to generate an ID. It will be set      $retVal =~ s/(\w)[|:](\w)/$1'$2/g;
3843          # to a number one greater than the maximum value in the database. This call to      # Return the result.
3844          # GetAll will stop after one record.      return $retVal;
         my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],  
                                         1);  
         $propID = $maxProperty[0]->[0] + 1;  
         # Insert the new property value.  
         $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });  
     }  
     # Now we connect the incoming feature to the property.  
     $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });  
3845  }  }
3846    
3847  =head2 Internal Utility Methods  =head2 Internal Utility Methods
# Line 3709  Line 3854 
3854    
3855  A functional assignment is always of the form  A functional assignment is always of the form
3856    
3857      C<set >I<YYYY>C< function to\n>I<ZZZZZ>      set YYYY function to
3858        ZZZZ
3859    
3860  where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,  where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
3861  the user and the assigning user (from MadeAnnotation) will be the same, but that is  the user and the assigning user (from MadeAnnotation) will be the same, but that is
# Line 3762  Line 3908 
3908      return @retVal;      return @retVal;
3909  }  }
3910    
3911    =head3 _CheckFeature
3912    
3913        my $flag = $sprout->_CheckFeature($fid);
3914    
3915    Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
3916    
3917    =over 4
3918    
3919    =item fid
3920    
3921    Feature ID to check.
3922    
3923    =item RETURN
3924    
3925    Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE.
3926    
3927    =back
3928    
3929    =cut
3930    
3931    sub _CheckFeature {
3932        # Get the parameters.
3933        my ($self, $fid) = @_;
3934        # Insure we have a genome hash.
3935        if (! defined $self->{genomeHash}) {
3936            my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');
3937            $self->{genomeHash} = \%genomeHash;
3938        }
3939        # Get the feature's genome ID.
3940        my ($genomeID) = FIGRules::ParseFeatureID($fid);
3941        # Return an indicator of whether or not the genome ID is in the hash.
3942        return ($self->{genomeHash}->{$genomeID} ? 1 : 0);
3943    }
3944    
3945  =head3 FriendlyTimestamp  =head3 FriendlyTimestamp
3946    
3947  Convert a time number to a user-friendly time stamp for display.  Convert a time number to a user-friendly time stamp for display.

Legend:
Removed from v.1.90  
changed lines
  Added in v.1.106

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3