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

Diff of /Sprout/Sprout.pm

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

revision 1.94, Fri Nov 3 00:42:25 2006 UTC revision 1.126, Thu Apr 2 01:47:00 2009 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 ERDBQuery;
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 CGI qw(-nosticky);
18        use WikiTools;
19        use BioWords;
20        use base qw(ERDB);
21    
22  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
23    
# Line 28  Line 30 
30  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>
31  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>.
32    
33  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' });
34    
35  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
36  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
37  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
38  L</dna_seq> returns the DNA sequence for a specified genome location.  L</DNASeq> returns the DNA sequence for a specified genome location.
39    
40  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.
41    
42  =cut  =cut
43    
 #: Constructor SFXlate->new_sprout_only();  
   
44  =head2 Public Methods  =head2 Public Methods
45    
46  =head3 new  =head3 new
47    
48  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
49    
50  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
51  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 55  Line 55 
55    
56  =item dbName  =item dbName
57    
58  Name of the database.  Name of the database. If omitted, the default Sprout database name is used.
59    
60  =item options  =item options
61    
# Line 79  Line 79 
79    
80  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
81    
82    * B<host> name of the database host
83    
84  =back  =back
85    
86  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
87  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
88  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
89    
90  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' });
91    
92    In order to work properly with [[ERDBGeneratorPl]], the constructor has an alternate
93    form.
94    
95        my $sprout = Sprout->new(dbd => $filename);
96    
97    Where I<$fileName> is the name of the DBD file. This enables us to specify an alternate
98    DBD for the loader, which is important when the database format changes.
99    
100  =cut  =cut
101    
102  sub new {  sub new {
103      # Get the parameters.      # Get the parameters.
104      my ($class, $dbName, $options) = @_;      my ($class, $dbName, $options) = @_;
105        # Check for the alternate signature, and default the database name if it is missing.
106        if ($dbName eq 'dbd') {
107            $dbName = $FIG_Config::sproutDB;
108            $options = { xmlFileName => $options };
109        } elsif (! defined $dbName) {
110            $dbName = $FIG_Config::sproutDB;
111        } elsif (ref $dbName eq 'HASH') {
112            $options = $dbName;
113            $dbName = $FIG_Config::sproutDB;
114        }
115      # Compute the DBD directory.      # Compute the DBD directory.
116      my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :      my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
117                                                    $FIG_Config::fig );                                                    $FIG_Config::fig );
# Line 104  Line 124 
124                                                          # data file directory                                                          # data file directory
125                         xmlFileName  => "$dbd_dir/SproutDBD.xml",                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
126                                                          # database definition file name                                                          # database definition file name
127                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",                         userData     => "$FIG_Config::sproutUser/$FIG_Config::sproutPass",
128                                                          # user name and password                                                          # user name and password
129                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::sproutPort,
130                                                          # database connection port                                                          # database connection port
131                         sock         => $FIG_Config::dbsock,                         sock         => $FIG_Config::sproutSock,
132                         host         => $FIG_Config::dbhost,                         host         => $FIG_Config::sprout_host,
133                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
134                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
135                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
136                           demandDriven => 0,               # 1 for forward-only queries
137                        }, $options);                        }, $options);
138      # Get the data directory.      # Get the data directory.
139      my $dataDir = $optionTable->{dataDir};      my $dataDir = $optionTable->{dataDir};
# Line 122  Line 143 
143      # Connect to the database.      # Connect to the database.
144      my $dbh;      my $dbh;
145      if (! $optionTable->{noDBOpen}) {      if (! $optionTable->{noDBOpen}) {
146            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
147          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
148                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
149      }      }
150      # Create the ERDB object.      # Create the ERDB object.
151      my $xmlFileName = "$optionTable->{xmlFileName}";      my $xmlFileName = "$optionTable->{xmlFileName}";
152      my $retVal = ERDB::new($class, $dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName, %$optionTable);
153      # Add the option table and XML file name.      # Add the option table and XML file name.
154      $retVal->{_options} = $optionTable;      $retVal->{_options} = $optionTable;
155      $retVal->{_xmlName} = $xmlFileName;      $retVal->{_xmlName} = $xmlFileName;
156      # Set up space for the group file data.      # Set up space for the group file data.
157      $retVal->{groupHash} = undef;      $retVal->{groupHash} = undef;
158        # Set up space for the genome hash. We use this to identify NMPDR genomes
159        # and remember genome data.
160        $retVal->{genomeHash} = {};
161        $retVal->{genomeHashFilled} = 0;
162        # Remember the data directory name.
163        $retVal->{dataDir} = $dataDir;
164      # Return it.      # Return it.
165      return $retVal;      return $retVal;
166  }  }
167    
168    =head3 ca
169    
170        my $ca = $sprout->ca():;
171    
172    Return the [[CustomAttributesPm]] object for retrieving object
173    properties.
174    
175    =cut
176    
177    sub ca {
178        # Get the parameters.
179        my ($self) = @_;
180        # Do we already have an attribute object?
181        my $retVal = $self->{_ca};
182        if (! defined $retVal) {
183            # No, create one. How we do it depends on the configuration.
184            if ($FIG_Config::attrURL) {
185                Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
186                $retVal = RemoteCustomAttributes->new($FIG_Config::attrURL);
187            } elsif ($FIG_Config::attrDbName) {
188                Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
189                my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
190                $retVal = CustomAttributes->new(user => $user);
191            }
192            # Save it for next time.
193            $self->{_ca} = $retVal;
194        }
195        # Return the result.
196        return $retVal;
197    }
198    
199    =head3 CoreGenomes
200    
201        my @genomes = $sprout->CoreGenomes($scope);
202    
203    Return the IDs of NMPDR genomes in the specified scope.
204    
205    =over 4
206    
207    =item scope
208    
209    Scope of the desired genomes. C<core> covers the original core genomes,
210    C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
211    genomes in the system.
212    
213    =item RETURN
214    
215    Returns a list of the IDs for the genomes in the specified scope.
216    
217    =back
218    
219    =cut
220    
221    sub CoreGenomes {
222        # Get the parameters.
223        my ($self, $scope) = @_;
224        # Declare the return variable.
225        my @retVal = ();
226        # If we want all genomes, then this is easy.
227        if ($scope eq 'all') {
228            @retVal = $self->Genomes();
229        } else {
230            # Here we're dealing with groups. Get the hash of all the
231            # genome groups.
232            my %groups = $self->GetGroups();
233            # Loop through the groups, keeping the ones that we want.
234            for my $group (keys %groups) {
235                # Decide if we want to keep this group.
236                my $keepGroup = 0;
237                if ($scope eq 'nmpdr') {
238                    # NMPDR mode: keep all groups.
239                    $keepGroup = 1;
240                } elsif ($scope eq 'core') {
241                    # CORE mode. Only keep real core groups.
242                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
243                        $keepGroup = 1;
244                    }
245                }
246                # Add this group if we're keeping it.
247                if ($keepGroup) {
248                    push @retVal, @{$groups{$group}};
249                }
250            }
251        }
252        # Return the result.
253        return @retVal;
254    }
255    
256    =head3 SuperGroup
257    
258        my $superGroup = $sprout->SuperGroup($groupName);
259    
260    Return the name of the super-group containing the specified NMPDR genome
261    group. If no appropriate super-group can be found, an error will be
262    thrown.
263    
264    =over 4
265    
266    =item groupName
267    
268    Name of the group whose super-group is desired.
269    
270    =item RETURN
271    
272    Returns the name of the super-group containing the incoming group.
273    
274    =back
275    
276    =cut
277    
278    sub SuperGroup {
279        # Get the parameters.
280        my ($self, $groupName) = @_;
281        # Declare the return variable.
282        my $retVal;
283        # Get the group hash.
284        my %groupHash = $self->CheckGroupFile();
285        # Find the super-group genus.
286        $groupName =~ /([A-Z]\w+)/;
287        my $nameThing = $1;
288        # See if it's directly in the group hash.
289        if (exists $groupHash{$nameThing}) {
290            # Yes, then it's our result.
291            $retVal = $nameThing;
292        } else {
293            # No, so we have to search.
294            for my $superGroup (keys %groupHash) {
295                # Get this super-group's item list.
296                my $list = $groupHash{$superGroup}->{contents};
297                # Search it.
298                if (grep { $_->[0] eq $nameThing } @{$list}) {
299                    $retVal = $superGroup;
300                }
301            }
302        }
303        # Return the result.
304        return $retVal;
305    }
306    
307  =head3 MaxSegment  =head3 MaxSegment
308    
309  C<< my $length = $sprout->MaxSegment(); >>      my $length = $sprout->MaxSegment();
310    
311  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
312  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 323 
323    
324  =head3 MaxSequence  =head3 MaxSequence
325    
326  C<< my $length = $sprout->MaxSequence(); >>      my $length = $sprout->MaxSequence();
327    
328  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
329  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 338 
338    
339  =head3 Load  =head3 Load
340    
341  C<< $sprout->Load($rebuild); >>;      $sprout->Load($rebuild);;
342    
343  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.
344    
# Line 183  Line 350 
350  The files are loaded based on the presumption that each line of the file is a record in the  The files are loaded based on the presumption that each line of the file is a record in the
351  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside
352  fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must  fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must
353  be presented in the order given in the relation tables produced by the L</ShowMetaData> method.  be presented in the order given in the relation tables produced by the database documentation.
354    
355  =over 4  =over 4
356    
# Line 211  Line 378 
378    
379  =head3 LoadUpdate  =head3 LoadUpdate
380    
381  C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
382    
383  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
384  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 424 
424              Trace("No load file found for $tableName in $dataDir.") if T(0);              Trace("No load file found for $tableName in $dataDir.") if T(0);
425          } else {          } else {
426              # Attempt to load this table.              # Attempt to load this table.
427              my $result = $self->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
428              # Accumulate the resulting statistics.              # Accumulate the resulting statistics.
429              $retVal->Accumulate($result);              $retVal->Accumulate($result);
430          }          }
# Line 268  Line 435 
435    
436  =head3 GenomeCounts  =head3 GenomeCounts
437    
438  C<< my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete); >>      my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
439    
440  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
441  genomes will be included in the counts.  genomes will be included in the counts.
# Line 313  Line 480 
480    
481  =head3 ContigCount  =head3 ContigCount
482    
483  C<< my $count = $sprout->ContigCount($genomeID); >>      my $count = $sprout->ContigCount($genomeID);
484    
485  Return the number of contigs for the specified genome ID.  Return the number of contigs for the specified genome ID.
486    
# Line 340  Line 507 
507      return $retVal;      return $retVal;
508  }  }
509    
510  =head3 GeneMenu  =head3 GenomeMenu
511    
512  C<< my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params, $selected); >>      my $html = $sprout->GenomeMenu(%options);
513    
514  Return an HTML select menu of genomes. Each genome will be an option in the menu,  Generate a genome selection control with the specified name and options.
515  and will be displayed by name with the ID and a contig count attached. The selection  This control is almost but not quite the same as the genome control in the
516  value will be the genome ID. The genomes will be sorted by genus/species name.  B<SearchHelper> class. Eventually, the two will be combined.
517    
518  =over 4  =over 4
519    
520  =item attributes  =item options
521    
522    Optional parameters for the control (see below).
523    
524    =item RETURN
525    
526    Returns the HTML for a genome selection control on a form (sometimes called a popup menu).
527    
528    =back
529    
530  Reference to a hash mapping attributes to values for the SELECT tag generated.  The valid options are as follows.
531    
532  =item filterString  =over 4
533    
534    =item name
535    
536  A filter string for use in selecting the genomes. The filter string must conform  Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
537  to the rules for the C<< ERDB->Get >> method.  Terrible things will happen if you have two controls with the same name on the same page.
538    
539  =item params  =item filter
540    
541  Reference to a list of values to be substituted in for the parameter marks in  If specified, a filter for the list of genomes to display. The filter should be in the form of a
542  the filter string.  list reference, a string, or a hash reference. If it is a list reference, the first element
543    of the list should be the filter string, and the remaining elements the filter parameters. If it is a
544    string, it will be split into a list at each included tab. If it is a hash reference, it should be
545    a hash that maps genomes which should be included to a TRUE value.
546    
547  =item selected (optional)  =item multiSelect
548    
549  ID of the genome to be initially selected.  If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
550    
551  =item fast (optional)  =item size
552    
553  If specified and TRUE, the contig counts will be omitted to improve performance.  Number of rows to display in the control. The default is C<10>
554    
555  =item RETURN  =item id
556    
557  Returns an HTML select menu with the specified genomes as selectable options.  ID to give this control. The default is the value of the C<name> option. Nothing will work correctly
558    unless this ID is unique.
559    
560    =item selected
561    
562    A comma-delimited list of selected genomes, or a reference to a list of selected genomes. The
563    default is none.
564    
565    =item class
566    
567    If specified, a style class to assign to the genome control.
568    
569  =back  =back
570    
571  =cut  =cut
572    
573  sub GeneMenu {  sub GenomeMenu {
574      # Get the parameters.      # Get the parameters.
575      my ($self, $attributes, $filterString, $params, $selected, $fast) = @_;      my ($self, %options) = @_;
576      my $slowMode = ! $fast;      # Get the control's name and ID.
577      # Default to nothing selected. This prevents an execution warning if "$selected"      my $menuName = $options{name} || $options{id} || 'myGenomeControl';
578      # is undefined.      my $menuID = $options{id} || $menuName;
579      $selected = "" unless defined $selected;      Trace("Genome menu name = $menuName with ID $menuID.") if T(3);
580      Trace("Gene Menu called with slow mode \"$slowMode\" and selection \"$selected\".") if T(3);      # Compute the IDs for the status display.
581      # Start the menu.      my $divID = "${menuID}_status";
582      my $retVal = "<select " .      my $urlID = "${menuID}_url";
583          join(" ", map { "$_=\"$attributes->{$_}\"" } keys %{$attributes}) .      # Compute the code to show selected genomes in the status area.
584          ">\n";      my $showSelect = "showSelected('$menuID', '$divID', '$urlID', $FIG_Config::genome_control_cap)";
585      # Get the genomes.      # Check for single-select or multi-select.
586      my @genomes = $self->GetAll(['Genome'], $filterString, $params, ['Genome(id)',      my $multiSelect = $options{multiSelect} || 0;
587                                                                       'Genome(genus)',      # Get the style data.
588                                                                       'Genome(species)',      my $class = $options{class} || '';
589                                                                       'Genome(unique-characterization)']);      # Get the list of pre-selected items.
590      # Sort them by name.      my $selections = $options{selected} || [];
591      my @sorted = sort { lc("$a->[1] $a->[2]") cmp lc("$b->[1] $b->[2]") } @genomes;      if (ref $selections ne 'ARRAY') {
592      # Loop through the genomes, creating the option tags.          $selections = [ split /\s*,\s*/, $selections ];
593      for my $genomeData (@sorted) {      }
594          # Get the data for this genome.      my %selected = map { $_ => 1 } @{$selections};
595          my ($genomeID, $genus, $species, $strain) = @{$genomeData};      # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
596          # Get the contig count.      # string, a hash reference, or a list reference.
597          my $contigInfo = "";      my ($filterHash, $filterString);
598          if ($slowMode) {      my $filterParms = $options{filter} || "";
599              my $count = $self->ContigCount($genomeID);      if (ref $filterParms eq 'HASH') {
600              my $counting = ($count == 1 ? "contig" : "contigs");          $filterHash = $filterParms;
601              $contigInfo = "[$count $counting]";          $filterParms = [];
602          }          $filterString = "";
603          # Find out if we're selected.      } else {
604          my $selectOption = ($selected eq $genomeID ? " selected" : "");          if (! ref $filterParms) {
605          # Build the option tag.              $filterParms = [split /\t|\\t/, $filterParms];
606          $retVal .= "<option value=\"$genomeID\"$selectOption>$genus $species $strain ($genomeID)$contigInfo</option>\n";          }
607            $filterString = shift @{$filterParms};
608        }
609        # Check for possible subsystem filtering. If there is one, we will tack the
610        # relationship onto the object name list.
611        my @objectNames = qw(Genome);
612        if ($filterString =~ /ParticipatesIn\(/) {
613            push @objectNames, 'ParticipatesIn';
614        }
615        # Get a list of all the genomes in group order. In fact, we only need them ordered
616        # by name (genus,species,strain), but putting primary-group in front enables us to
617        # take advantage of an existing index.
618        my @genomeList = $self->GetAll(\@objectNames, "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
619                                       $filterParms,
620                                       [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
621        # Apply the hash filter (if any).
622        if (defined $filterHash) {
623            @genomeList = grep { $filterHash->{$_->[1]} } @genomeList;
624        }
625        # Create a hash to organize the genomes by group. Each group will contain a list of
626        # 2-tuples, the first element being the genome ID and the second being the genome
627        # name.
628        my %gHash = ();
629        for my $genome (@genomeList) {
630            # Get the genome data.
631            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
632            # Compute its name. This is the genus, species, strain (if any), and the contig count.
633            my $name = "$genus $species ";
634            $name .= "$strain " if $strain;
635            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
636            # Now we get the domain. The domain tells us the display style of the organism.
637            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
638            # Now compute the display group. This is normally the primary group, but if the
639            # organism is supporting, we blank it out.
640            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
641            # Push the genome into the group's list. Note that we use the real group
642            # name for the hash key here, not the display group name.
643            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
644        }
645        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
646        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
647        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
648        # that aren't "other". At some point, we will want to make this less complicated.
649        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
650                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
651        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
652        # Remember the number of NMPDR groups.
653        my $nmpdrGroupCount = scalar @groups;
654        # Are there any supporting genomes?
655        if (exists $gHash{$FIG_Config::otherGroup}) {
656            # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
657            # of the domains found.
658            my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
659            my @domains = ();
660            for my $genomeData (@otherGenomes) {
661                my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
662                if (exists $gHash{$domain}) {
663                    push @{$gHash{$domain}}, $genomeData;
664                } else {
665                    $gHash{$domain} = [$genomeData];
666                    push @domains, $domain;
667                }
668            }
669            # Add the domain groups at the end of the main group list. The main group list will now
670            # contain all the categories we need to display the genomes.
671            push @groups, sort @domains;
672            # Delete the supporting group.
673            delete $gHash{$FIG_Config::otherGroup};
674        }
675        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
676        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
677        # and use that to make the selections.
678        my $nmpdrCount = 0;
679        # Create the type counters.
680        my $groupCount = 1;
681        # Get the number of rows to display.
682        my $rows = $options{size} || 10;
683        # If we're multi-row, create an onChange event.
684        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
685        # Set up the multiple-select flag.
686        my $multipleTag = ($multiSelect ? " multiple" : "" );
687        # Set up the style class.
688        my $classTag = ($class ? " $class" : "" );
689        # Create the SELECT tag and stuff it into the output array.
690        my @lines = qq(<SELECT name="$menuName" id="$menuID" class="genomeSelect $class" $onChangeTag$multipleTag$classTag size="$rows">);
691        # Loop through the groups.
692        for my $group (@groups) {
693            # Get the genomes in the group.
694            for my $genome (@{$gHash{$group}}) {
695                # If this is an NMPDR organism, we add an extra style and count it.
696                my $nmpdrStyle = "";
697                if ($nmpdrGroupCount > 0) {
698                    $nmpdrCount++;
699                    $nmpdrStyle = " Core";
700                }
701                # Get the organism ID, name, contig count, and domain.
702                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
703                # See if we're pre-selected.
704                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
705                # Compute the display name.
706                my $nameString = "$name ($genomeID$contigCount)";
707                # Generate the option tag.
708                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
709                push @lines, "    $optionTag";
710            }
711            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
712            # groups.
713            $nmpdrGroupCount--;
714      }      }
715      # Close the SELECT tag.      # Close the SELECT tag.
716      $retVal .= "</select>\n";      push @lines, "</SELECT>";
717        if ($rows > 1) {
718            # We're in a non-compact mode, so we need to add some selection helpers. First is
719            # the search box. This allows the user to type text and change which genomes are
720            # displayed. For multiple-select mode, we include a button that selects the displayed
721            # genes. For single-select mode, we use a plain label instead.
722            my $searchThingName = "${menuID}_SearchThing";
723            my $searchThingLabel = "Type to narrow selection";
724            my $searchThingButton = "";
725            if ($multiSelect) {
726                $searchThingButton = qq(<INPUT type="button" name="MacroSearch" class="button" value="Go" onClick="selectShowing('$menuID', '$searchThingName'); $showSelect;" />);
727            }
728            push @lines, "<br />$searchThingLabel&nbsp;" .
729                         qq(<INPUT type="text" id="$searchThingName" name="$searchThingName" class="genomeSearchThing" onKeyup="showTyped('$menuID', '$searchThingName');" />) .
730                         $searchThingButton .
731                         Hint("GenomeControl", 28) . "<br />";
732            # For multi-select mode, we also have buttons to set and clear selections.
733            if ($multiSelect) {
734                push @lines, qq(<INPUT type="button" name="ClearAll" class="bigButton genomeButton" value="Clear All" onClick="clearAll(getElementById('$menuID')); $showSelect" />);
735                push @lines, qq(<INPUT type="button" name="SelectAll" class="bigButton genomeButton" value="Select All" onClick="selectAll(getElementById('$menuID')); $showSelect" />);
736                push @lines, qq(<INPUT type="button" name="NMPDROnly" class="bigButton genomeButton" value="Select NMPDR" onClick="selectSome(getElementById('$menuID'), $nmpdrCount, true); $showSelect;" />);
737            }
738            # Add a hidden field we can use to generate organism page hyperlinks.
739            push @lines, qq(<INPUT type="hidden" id="$urlID" value="$FIG_Config::cgi_url/wiki/rest.cgi/NmpdrPlugin/SeedViewer?page=Organism;organism=" />);
740            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
741            push @lines, qq(<DIV id="$divID" class="Panel"></DIV>);
742        }
743        # Assemble all the lines into a string.
744        my $retVal = join("\n", @lines, "");
745      # Return the result.      # Return the result.
746      return $retVal;      return $retVal;
747  }  }
748    
749    =head3 Cleanup
750    
751        $sprout->Cleanup();
752    
753    Release the internal cache structures to free up memory.
754    
755    =cut
756    
757    sub Cleanup {
758        # Get the parameters.
759        my ($self) = @_;
760        # Delete the stemmer.
761        delete $self->{stemmer};
762        # Delete the attribute database.
763        delete $self->{_ca};
764        # Delete the group hash.
765        delete $self->{groupHash};
766        # Is there a FIG object?
767        if (defined $self->{fig}) {
768            # Yes, clear its subsystem cache.
769            $self->{fig}->clear_subsystem_cache();
770        }
771    }
772    
773    
774    =head3 Stem
775    
776        my $stem = $sprout->Stem($word);
777    
778    Return the stem of the specified word, or C<undef> if the word is not
779    stemmable. Note that even if the word is stemmable, the stem may be
780    the same as the original word.
781    
782    =over 4
783    
784    =item word
785    
786    Word to convert into a stem.
787    
788    =item RETURN
789    
790    Returns a stem of the word (which may be the word itself), or C<undef> if
791    the word is not stemmable.
792    
793    =back
794    
795    =cut
796    
797    sub Stem {
798        # Get the parameters.
799        my ($self, $word) = @_;
800        # Get the stemmer object.
801        my $stemmer = $self->{stemmer};
802        if (! defined $stemmer) {
803            # We don't have one pre-built, so we build and save it now.
804            $stemmer = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
805                                     stops => "$FIG_Config::sproutData/StopWords.txt",
806                                     cache => 0);
807            $self->{stemmer} = $stemmer;
808        }
809        # Try to stem the word.
810        my $retVal = $stemmer->Process($word);
811        # Return the result.
812        return $retVal;
813    }
814    
815    
816  =head3 Build  =head3 Build
817    
818  C<< $sprout->Build(); >>      $sprout->Build();
819    
820  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.
821  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 832 
832    
833  =head3 Genomes  =head3 Genomes
834    
835  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
836    
837  Return a list of all the genome IDs.  Return a list of all the genome IDs.
838    
# Line 457  Line 849 
849    
850  =head3 GenusSpecies  =head3 GenusSpecies
851    
852  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
853    
854  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
855    
# Line 479  Line 871 
871  sub GenusSpecies {  sub GenusSpecies {
872      # Get the parameters.      # Get the parameters.
873      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
874      # Get the data for the specified genome.      # Declare the return value.
875      my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',      my $retVal;
876                                                                'Genome(unique-characterization)']);      # Get the genome data.
877      # Format the result and return it.      my $genomeData = $self->_GenomeData($genomeID);
878      my $retVal = join(' ', @values);      # Only proceed if we found the genome.
879        if (defined $genomeData) {
880            $retVal = $genomeData->PrimaryValue('Genome(scientific-name)');
881        }
882        # Return it.
883      return $retVal;      return $retVal;
884  }  }
885    
886  =head3 FeaturesOf  =head3 FeaturesOf
887    
888  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
889    
890  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
891    
# Line 534  Line 930 
930    
931  =head3 FeatureLocation  =head3 FeatureLocation
932    
933  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
934    
935  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
936  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 558  Line 954 
954  =item RETURN  =item RETURN
955    
956  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
957  context and as a comma-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context. An empty list means the feature
958    wasn't found.
959    
960  =back  =back
961    
962  =cut  =cut
963  #: Return Type @;  
 #: Return Type $;  
964  sub FeatureLocation {  sub FeatureLocation {
965      # Get the parameters.      # Get the parameters.
966      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
967      # Create a query for the feature locations.      # Declare the return variable.
     my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",  
                            [$featureID]);  
     # Create the return list.  
968      my @retVal = ();      my @retVal = ();
969      # Set up the variables used to determine if we have adjacent segments. This initial setup will      # Get the feature record.
970      # not match anything.      my $object = $self->GetEntity('Feature', $featureID);
971      my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);      # Only proceed if we found it.
972      # Loop through the query results, creating location specifiers.      if (defined $object) {
973      while (my $location = $query->Fetch()) {          # Get the location string.
974          # Get the location parameters.          my $locString = $object->PrimaryValue('Feature(location-string)');
975          my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',          # Create the return list.
976              'IsLocatedIn(beg)', 'IsLocatedIn(dir)', 'IsLocatedIn(len)']);          @retVal = split /\s*,\s*/, $locString;
         # Check to see if we are adjacent to the previous segment.  
         if ($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$len";  
977      }      }
978      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
979      return (wantarray ? @retVal : join(',', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
# Line 613  Line 981 
981    
982  =head3 ParseLocation  =head3 ParseLocation
983    
984  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
985    
986  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
987  length.  length.
# Line 632  Line 1000 
1000  =back  =back
1001    
1002  =cut  =cut
1003  #: Return Type @;  
1004  sub ParseLocation {  sub ParseLocation {
1005      # 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
1006      # the first parameter.      # the first parameter.
# Line 656  Line 1024 
1024  }  }
1025    
1026    
   
1027  =head3 PointLocation  =head3 PointLocation
1028    
1029  C<< my $found = Sprout::PointLocation($location, $point); >>      my $found = Sprout::PointLocation($location, $point);
1030    
1031  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
1032  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 1055 
1055  =back  =back
1056    
1057  =cut  =cut
1058  #: Return Type $;  
1059  sub PointLocation {  sub PointLocation {
1060      # 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
1061      # the first parameter.      # the first parameter.
# Line 711  Line 1078 
1078    
1079  =head3 DNASeq  =head3 DNASeq
1080    
1081  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
1082    
1083  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
1084  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 1162 
1162    
1163  =head3 AllContigs  =head3 AllContigs
1164    
1165  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1166    
1167  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1168    
# Line 825  Line 1192 
1192    
1193  =head3 GenomeLength  =head3 GenomeLength
1194    
1195  C<< my $length = $sprout->GenomeLength($genomeID); >>      my $length = $sprout->GenomeLength($genomeID);
1196    
1197  Return the length of the specified genome in base pairs.  Return the length of the specified genome in base pairs.
1198    
# Line 849  Line 1216 
1216      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
1217      # Declare the return variable.      # Declare the return variable.
1218      my $retVal = 0;      my $retVal = 0;
1219      # Get the genome's contig sequence lengths.      # Get the genome data.
1220      my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',      my $genomeData = $self->_GenomeData($genomeID);
1221                         [$genomeID], 'IsMadeUpOf(len)');      # Only proceed if it exists.
1222      # Sum the lengths.      if (defined $genomeData) {
1223      map { $retVal += $_ } @lens;          $retVal = $genomeData->PrimaryValue('Genome(dna-size)');
1224        }
1225      # Return the result.      # Return the result.
1226      return $retVal;      return $retVal;
1227  }  }
1228    
1229  =head3 FeatureCount  =head3 FeatureCount
1230    
1231  C<< my $count = $sprout->FeatureCount($genomeID, $type); >>      my $count = $sprout->FeatureCount($genomeID, $type);
1232    
1233  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.
1234    
# Line 895  Line 1263 
1263    
1264  =head3 GenomeAssignments  =head3 GenomeAssignments
1265    
1266  C<< my $fidHash = $sprout->GenomeAssignments($genomeID); >>      my $fidHash = $sprout->GenomeAssignments($genomeID);
1267    
1268  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
1269  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 938  Line 1306 
1306    
1307  =head3 ContigLength  =head3 ContigLength
1308    
1309  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->ContigLength($contigID);
1310    
1311  Compute the length of a contig.  Compute the length of a contig.
1312    
# Line 977  Line 1345 
1345    
1346  =head3 ClusterPEGs  =head3 ClusterPEGs
1347    
1348  C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>      my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1349    
1350  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
1351  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
1352  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
1353  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
1354  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
1355  sequence.  appear in the output sequence.
1356    
1357  =over 4  =over 4
1358    
# Line 1025  Line 1393 
1393    
1394  =head3 GenesInRegion  =head3 GenesInRegion
1395    
1396  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1397    
1398  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1399    
# Line 1054  Line 1422 
1422  =back  =back
1423    
1424  =cut  =cut
1425  #: Return Type @@;  
1426  sub GenesInRegion {  sub GenesInRegion {
1427      # Get the parameters.      # Get the parameters.
1428      my ($self, $contigID, $start, $stop) = @_;      my ($self, $contigID, $start, $stop) = @_;
1429      # Get the maximum segment length.      # Get the maximum segment length.
1430      my $maximumSegmentLength = $self->MaxSegment;      my $maximumSegmentLength = $self->MaxSegment;
     # Create a hash to receive the feature list. We use a hash so that we can eliminate  
     # duplicates easily. The hash key will be the feature ID. The value will be a two-element  
     # containing the minimum and maximum offsets. We will use the offsets to sort the results  
     # when we're building the result set.  
     my %featuresFound = ();  
1431      # Prime the values we'll use for the returned beginning and end.      # Prime the values we'll use for the returned beginning and end.
1432      my @initialMinMax = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
1433      my ($min, $max) = @initialMinMax;      my ($min, $max) = @initialMinMax;
1434      # Create a table of parameters for each query. Each query looks for features travelling in      # Get the overlapping features.
1435        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1436        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1437        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1438        # of the feature's locations.
1439        my %featureMap = ();
1440        # Loop through them to do the begin/end analysis.
1441        for my $featureObject (@featureObjects) {
1442            # Get the feature's location string. This may contain multiple actual locations.
1443            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1444            my @locationSegments = split /\s*,\s*/, $locations;
1445            # Loop through the locations.
1446            for my $locationSegment (@locationSegments) {
1447                # Construct an object for the location.
1448                my $locationObject = BasicLocation->new($locationSegment);
1449                # Merge the current segment's begin and end into the min and max.
1450                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1451                my ($beg, $end);
1452                if (exists $featureMap{$fid}) {
1453                    ($beg, $end) = @{$featureMap{$fid}};
1454                    $beg = $left if $left < $beg;
1455                    $end = $right if $right > $end;
1456                } else {
1457                    ($beg, $end) = ($left, $right);
1458                }
1459                $min = $beg if $beg < $min;
1460                $max = $end if $end > $max;
1461                # Store the feature's new extent back into the hash table.
1462                $featureMap{$fid} = [$beg, $end];
1463            }
1464        }
1465        # Now we must compute the list of the IDs for the features found. We start with a list
1466        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1467        # but the result of the sort will be the same.)
1468        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1469        # Now we sort by midpoint and yank out the feature IDs.
1470        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1471        # Return it along with the min and max.
1472        return (\@retVal, $min, $max);
1473    }
1474    
1475    =head3 GeneDataInRegion
1476    
1477        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1478    
1479    List the features which overlap a specified region in a contig.
1480    
1481    =over 4
1482    
1483    =item contigID
1484    
1485    ID of the contig containing the region of interest.
1486    
1487    =item start
1488    
1489    Offset of the first residue in the region of interest.
1490    
1491    =item stop
1492    
1493    Offset of the last residue in the region of interest.
1494    
1495    =item RETURN
1496    
1497    Returns a list of B<ERDBObjects> for the desired features. Each object will
1498    contain a B<Feature> record.
1499    
1500    =back
1501    
1502    =cut
1503    
1504    sub GeneDataInRegion {
1505        # Get the parameters.
1506        my ($self, $contigID, $start, $stop) = @_;
1507        # Get the maximum segment length.
1508        my $maximumSegmentLength = $self->MaxSegment;
1509        # Create a hash to receive the feature list. We use a hash so that we can eliminate
1510        # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1511        # ERDBObject from the query.
1512        my %featuresFound = ();
1513        # Create a table of parameters for the queries. Each query looks for features travelling in
1514      # 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,
1515      # 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
1516      # 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 1077  Line 1519 
1519      # Loop through the query parameters.      # Loop through the query parameters.
1520      for my $parms (values %queryParms) {      for my $parms (values %queryParms) {
1521          # Create the query.          # Create the query.
1522          my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1523              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1524              $parms);              $parms);
1525          # Loop through the feature segments found.          # Loop through the feature segments found.
1526          while (my $segment = $query->Fetch) {          while (my $segment = $query->Fetch) {
1527              # Get the data about this segment.              # Get the data about this segment.
1528              my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1529                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1530              # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1531              # this will be the case if the segment is the maximum length, so to fine-tune              # this will be the case if the segment is the maximum length, so to fine-tune
1532              # the results we insure that the inequality from the query holds using the actual              # the results we insure that the inequality from the query holds using the actual
1533              # length.              # length.
1534              my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1535              if ($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.  
                     $found = 1;  
                 }  
             }  
1536              if ($found) {              if ($found) {
1537                  # Here we need to record the feature and update the minima and maxima. First,                  # Save this feature in the result list.
1538                  # 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 < $min;  
1539                  }                  }
                 if ($end > $loc2) {  
                     $loc2 = $end;  
                     $max = $end if $end > $max;  
                 }  
                 # Store the entry back into the hash table.  
                 $featuresFound{$featureID} = [$loc1, $loc2];  
1540              }              }
1541          }          }
1542      }      # Return the ERDB objects for the features found.
1543      # Now we must compute the list of the IDs for the features found. We start with a list      return values %featuresFound;
     # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,  
     # but the result of the sort will be the same.)  
     my @list = map { [$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);  
1544  }  }
1545    
1546  =head3 FType  =head3 FType
1547    
1548  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1549    
1550  Return the type of a feature.  Return the type of a feature.
1551    
# Line 1167  Line 1575 
1575    
1576  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1577    
1578  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1579    
1580  Return the annotations of a feature.  Return the annotations of a feature.
1581    
# Line 1230  Line 1638 
1638    
1639  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1640    
1641  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1642    
1643  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
1644  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 1285  Line 1693 
1693    
1694  =head3 FunctionOf  =head3 FunctionOf
1695    
1696  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1697    
1698  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1699    
# Line 1298  Line 1706 
1706  the specified user and FIG are considered trusted. If the user ID is omitted, only FIG  the specified user and FIG are considered trusted. If the user ID is omitted, only FIG
1707  is trusted.  is trusted.
1708    
1709  If the feature is B<not> identified by a FIG ID, then the functional assignment  If the feature is B<not> identified by a FIG ID, then we search the aliases for it.
1710  information is taken from the B<ExternalAliasFunc> table. If the table does  If no matching alias is found, we return an undefined value.
 not contain an entry for the feature, an undefined value is returned.  
1711    
1712  =over 4  =over 4
1713    
# Line 1326  Line 1733 
1733      my ($self, $featureID, $userID) = @_;      my ($self, $featureID, $userID) = @_;
1734      # Declare the return value.      # Declare the return value.
1735      my $retVal;      my $retVal;
1736      # Determine the ID type.      # Find a FIG ID for this feature.
1737      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1738        # Only proceed if we have an ID.
1739        if ($fid) {
1740          # Here we have a FIG feature ID.          # Here we have a FIG feature ID.
1741          if (!$userID) {          if (!$userID) {
1742              # Use the primary assignment.              # Use the primary assignment.
1743              ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);              ($retVal) = $self->GetEntityValues('Feature', $fid, ['Feature(assignment)']);
1744          } else {          } else {
1745              # We must build the list of trusted users.              # We must build the list of trusted users.
1746              my %trusteeTable = ();              my %trusteeTable = ();
# Line 1357  Line 1766 
1766              # Build a query for all of the feature's annotations, sorted by date.              # Build a query for all of the feature's annotations, sorted by date.
1767              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1768                                     "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                     "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1769                                     [$featureID]);                                     [$fid]);
1770              my $timeSelected = 0;              my $timeSelected = 0;
1771              # Loop until we run out of annotations.              # Loop until we run out of annotations.
1772              while (my $annotation = $query->Fetch()) {              while (my $annotation = $query->Fetch()) {
# Line 1377  Line 1786 
1786                  }                  }
1787              }              }
1788          }          }
     } else {  
         # Here we have a non-FIG feature ID. In this case the user ID does not  
         # matter. We simply get the information from the External Alias Function  
         # table.  
         ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);  
1789      }      }
1790      # Return the assignment found.      # Return the assignment found.
1791      return $retVal;      return $retVal;
# Line 1389  Line 1793 
1793    
1794  =head3 FunctionsOf  =head3 FunctionsOf
1795    
1796  C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>      my @functionList = $sprout->FunctionOf($featureID, $userID);
1797    
1798  Return the functional assignments of a particular feature.  Return the functional assignments of a particular feature.
1799    
# Line 1400  Line 1804 
1804  annotation itself because it's a text field; however, this is not a big problem because  annotation itself because it's a text field; however, this is not a big problem because
1805  most features only have a small number of annotations.  most features only have a small number of annotations.
1806    
 If the feature is B<not> identified by a FIG ID, then the functional assignment  
 information is taken from the B<ExternalAliasFunc> table. If the table does  
 not contain an entry for the feature, an empty list is returned.  
   
1807  =over 4  =over 4
1808    
1809  =item featureID  =item featureID
# Line 1424  Line 1824 
1824      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1825      # Declare the return value.      # Declare the return value.
1826      my @retVal = ();      my @retVal = ();
1827      # Determine the ID type.      # Convert to a FIG ID.
1828      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1829        # Only proceed if we found one.
1830        if ($fid) {
1831          # Here we have a FIG feature ID. We must build the list of trusted          # Here we have a FIG feature ID. We must build the list of trusted
1832          # users.          # users.
1833          my %trusteeTable = ();          my %trusteeTable = ();
1834          # Build a query for all of the feature's annotations, sorted by date.          # Build a query for all of the feature's annotations, sorted by date.
1835          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1836                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1837                                 [$featureID]);                                 [$fid]);
1838          my $timeSelected = 0;          my $timeSelected = 0;
1839          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1840          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
# Line 1447  Line 1849 
1849                  push @retVal, [$actualUser, $function];                  push @retVal, [$actualUser, $function];
1850              }              }
1851          }          }
     } else {  
         # Here we have a non-FIG feature ID. In this case the user ID does not  
         # matter. We simply get the information from the External Alias Function  
         # table.  
         my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,  
                                                  ['ExternalAliasFunc(func)']);  
         push @retVal, map { ['master', $_] } @assignments;  
1852      }      }
1853      # Return the assignments found.      # Return the assignments found.
1854      return @retVal;      return @retVal;
# Line 1461  Line 1856 
1856    
1857  =head3 BBHList  =head3 BBHList
1858    
1859  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1860    
1861  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
1862  on a specified target genome.  on a specified target genome.
# Line 1493  Line 1888 
1888      # Loop through the incoming features.      # Loop through the incoming features.
1889      for my $featureID (@{$featureList}) {      for my $featureID (@{$featureList}) {
1890          # Ask the server for the feature's best hit.          # Ask the server for the feature's best hit.
1891          my @bbhData = FIGRules::BBHData($featureID);          my $bbhData = FIGRules::BBHData($featureID);
1892          # Peel off the BBHs found.          # Peel off the BBHs found.
1893          my @found = ();          my @found = ();
1894          for my $bbh (@bbhData) {          for my $bbh (@$bbhData) {
1895              my $fid = $bbh->[0];              my $fid = $bbh->[0];
1896              my $bbGenome = $self->GenomeOf($fid);              my $bbGenome = $self->GenomeOf($fid);
1897              if ($bbGenome eq $genomeID) {              if ($bbGenome eq $genomeID) {
# Line 1511  Line 1906 
1906    
1907  =head3 SimList  =head3 SimList
1908    
1909  C<< my %similarities = $sprout->SimList($featureID, $count); >>      my %similarities = $sprout->SimList($featureID, $count);
1910    
1911  Return a list of the similarities to the specified feature.  Return a list of the similarities to the specified feature.
1912    
# Line 1535  Line 1930 
1930      # Get the parameters.      # Get the parameters.
1931      my ($self, $featureID, $count) = @_;      my ($self, $featureID, $count) = @_;
1932      # Ask for the best hits.      # Ask for the best hits.
1933      my @lists = FIGRules::BBHData($featureID);      my $lists = FIGRules::BBHData($featureID);
1934      # Create the return value.      # Create the return value.
1935      my %retVal = ();      my %retVal = ();
1936      for my $tuple (@lists) {      for my $tuple (@$lists) {
1937          $retVal{$tuple->[0]} = $tuple->[1];          $retVal{$tuple->[0]} = $tuple->[1];
1938      }      }
1939      # Return the result.      # Return the result.
# Line 1547  Line 1942 
1942    
1943  =head3 IsComplete  =head3 IsComplete
1944    
1945  C<< my $flag = $sprout->IsComplete($genomeID); >>      my $flag = $sprout->IsComplete($genomeID);
1946    
1947  Return TRUE if the specified genome is complete, else FALSE.  Return TRUE if the specified genome is complete, else FALSE.
1948    
# Line 1572  Line 1967 
1967      # Declare the return variable.      # Declare the return variable.
1968      my $retVal;      my $retVal;
1969      # Get the genome's data.      # Get the genome's data.
1970      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->_GenomeData($genomeID);
1971      if ($genomeData) {      # Only proceed if it exists.
1972        if (defined $genomeData) {
1973          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1974          ($retVal) = $genomeData->Value('Genome(complete)');          $retVal = $genomeData->PrimaryValue('Genome(complete)');
1975      }      }
1976      # Return the result.      # Return the result.
1977      return $retVal;      return $retVal;
# Line 1583  Line 1979 
1979    
1980  =head3 FeatureAliases  =head3 FeatureAliases
1981    
1982  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1983    
1984  Return a list of the aliases for a specified feature.  Return a list of the aliases for a specified feature.
1985    
# Line 1606  Line 2002 
2002      # Get the parameters.      # Get the parameters.
2003      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2004      # Get the desired feature's aliases      # Get the desired feature's aliases
2005      my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
2006      # Return the result.      # Return the result.
2007      return @retVal;      return @retVal;
2008  }  }
2009    
2010  =head3 GenomeOf  =head3 GenomeOf
2011    
2012  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $genomeID = $sprout->GenomeOf($featureID);
2013    
2014  Return the genome that contains a specified feature or contig.  Return the genome that contains a specified feature or contig.
2015    
# Line 1635  Line 2031 
2031  sub GenomeOf {  sub GenomeOf {
2032      # Get the parameters.      # Get the parameters.
2033      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]);  
2034      # Declare the return value.      # Declare the return value.
2035      my $retVal;      my $retVal;
2036      # Get the genome ID.      # Parse the genome ID from the feature ID.
2037      if (my $relationship = $query->Fetch()) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
2038          ($retVal) = $relationship->Value('HasContig(from-link)');          $retVal = $1;
2039        } else {
2040            # Find the feature by alias.
2041            my ($realFeatureID) = $self->FeaturesByAlias($featureID);
2042            if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {
2043                $retVal = $1;
2044            }
2045      }      }
2046      # Return the value found.      # Return the value found.
2047      return $retVal;      return $retVal;
# Line 1650  Line 2049 
2049    
2050  =head3 CoupledFeatures  =head3 CoupledFeatures
2051    
2052  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
2053    
2054  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
2055  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 1672  Line 2071 
2071  sub CoupledFeatures {  sub CoupledFeatures {
2072      # Get the parameters.      # Get the parameters.
2073      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2074        # Ask the coupling server for the data.
2075      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
2076      # Create a query to retrieve the functionally-coupled features.      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
2077      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
2078                             "ParticipatesInCoupling(from-link) = ?", [$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.  
2079      my %retVal = ();      my %retVal = ();
2080      # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
2081      while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
2082          # Get the ID and score of the coupling.          my ($featureID2, $score) = @{$pair};
2083          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',          # Only proceed if the feature is in NMPDR.
2084                                                          'Coupling(score)']);          if ($self->_CheckFeature($featureID2)) {
2085          Trace("$featureID coupled with score $score to ID $couplingID.") if T(coupling => 4);              $retVal{$featureID2} = $score;
         # Get the other feature that participates in the coupling.  
         my ($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;  
         $found = 1;  
2086      }      }
     # Functional coupling is reflexive. If we found at least one coupled feature, we must add  
     # the incoming feature as well.  
     if ($found) {  
         $retVal{$featureID} = 9999;  
2087      }      }
2088      # Return the hash.      # Return the hash.
2089      return %retVal;      return %retVal;
# Line 1706  Line 2091 
2091    
2092  =head3 CouplingEvidence  =head3 CouplingEvidence
2093    
2094  C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>      my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
2095    
2096  Return the evidence for a functional coupling.  Return the evidence for a functional coupling.
2097    
# Line 1754  Line 2139 
2139      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
2140      # Declare the return variable.      # Declare the return variable.
2141      my @retVal = ();      my @retVal = ();
2142      # Our first task is to find out the nature of the coupling: whether or not      # Get the coupling and evidence data.
2143      # it exists, its score, and whether the features are stored in the same      my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
2144      # order as the ones coming in.      # Loop through the raw data, saving the ones that are in NMPDR genomes.
2145      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);      for my $rawTuple (@rawData) {
2146      # Only proceed if a coupling exists.          if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
2147      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);  
     }  
     # Return the result.  
     return @retVal;  
2148  }  }
   
 =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 $peg1.") if T(Coupling => 4);  
2149      }      }
2150      # Return the result.      # Return the result.
2151      return ($retVal, $inverted, $score);      return @retVal;
2152  }  }
2153    
2154  =head3 GetSynonymGroup  =head3 GetSynonymGroup
2155    
2156  C<< my $id = $sprout->GetSynonymGroup($fid); >>      my $id = $sprout->GetSynonymGroup($fid);
2157    
2158  Return the synonym group name for the specified feature.  Return the synonym group name for the specified feature.
2159    
# Line 1885  Line 2192 
2192    
2193  =head3 GetBoundaries  =head3 GetBoundaries
2194    
2195  C<< my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList); >>      my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2196    
2197  Determine the begin and end boundaries for the locations in a list. All of the  Determine the begin and end boundaries for the locations in a list. All of the
2198  locations must belong to the same contig and have mostly the same direction in  locations must belong to the same contig and have mostly the same direction in
# Line 1947  Line 2254 
2254      return ($contig, $beg, $end);      return ($contig, $beg, $end);
2255  }  }
2256    
2257  =head3 CouplingID  =head3 ReadFasta
   
 C<< my $couplingID = $sprout->CouplingID($peg1, $peg2); >>  
2258    
2259  Return the coupling ID for a pair of feature IDs.      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2260    
2261  The coupling ID is currently computed by joining the feature IDs in  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
2262  sorted order with a space. Client modules (that is, modules which  one or more lines of data. The first line begins with a > character and contains an ID.
2263  use Sprout) should not, however, count on this always being the  The remaining lines contain the sequence data in order.
 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")>.  
2264    
2265  =over 4  =over 4
2266    
2267  =item peg1  =item fileName
2268    
2269  First feature of interest.  Name of the FASTA file.
2270    
2271  =item peg2  =item prefix (optional)
2272    
2273  Second feature of interest.  Prefix to be put in front of each ID found.
2274    
2275  =item RETURN  =item RETURN
2276    
2277  Returns the ID that would be used to represent a functional coupling of  Returns a hash that maps each ID to its sequence.
 the two specified PEGs.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub CouplingID {  
     my ($self, @pegs) = @_;  
     return $self->DigestKey(join " ", sort @pegs);  
 }  
   
 =head3 ReadFasta  
   
 C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>  
   
 Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by  
 one or more lines of data. The first line begins with a > character and contains an ID.  
 The remaining lines contain the sequence data in order.  
   
 =over 4  
   
 =item fileName  
   
 Name of the FASTA file.  
   
 =item prefix (optional)  
   
 Prefix to be put in front of each ID found.  
   
 =item RETURN  
   
 Returns a hash that maps each ID to its sequence.  
2278    
2279  =back  =back
2280    
# Line 2054  Line 2322 
2322    
2323  =head3 FormatLocations  =head3 FormatLocations
2324    
2325  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2326    
2327  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
2328  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 2119  Line 2387 
2387    
2388  =head3 DumpData  =head3 DumpData
2389    
2390  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2391    
2392  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.
2393    
# Line 2136  Line 2404 
2404    
2405  =head3 XMLFileName  =head3 XMLFileName
2406    
2407  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2408    
2409  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2410    
# Line 2147  Line 2415 
2415      return $self->{_xmlName};      return $self->{_xmlName};
2416  }  }
2417    
2418    =head3 GetGenomeNameData
2419    
2420        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2421    
2422    Return the genus, species, and unique characterization for a genome. This
2423    is similar to L</GenusSpecies>, with the exception that it returns the
2424    values in three seperate fields.
2425    
2426    =over 4
2427    
2428    =item genomeID
2429    
2430    ID of the genome whose name data is desired.
2431    
2432    =item RETURN
2433    
2434    Returns a three-element list, consisting of the genus, species, and strain
2435    of the specified genome. If the genome is not found, an error occurs.
2436    
2437    =back
2438    
2439    =cut
2440    
2441    sub GetGenomeNameData {
2442        # Get the parameters.
2443        my ($self, $genomeID) = @_;
2444        # Declare the return variables.
2445        my ($genus, $species, $strain);
2446        # Get the genome's data.
2447        my $genomeData = $self->_GenomeData($genomeID);
2448        # Only proceed if the genome exists.
2449        if (defined $genomeData) {
2450            # Get the desired values.
2451            ($genus, $species, $strain) = $genomeData->Values(['Genome(genus)',
2452                                                               'Genome(species)',
2453                                                               'Genome(unique-characterization)']);
2454        } else {
2455            # Throw an error because they were not found.
2456            Confess("Genome $genomeID not found in database.");
2457        }
2458        # Return the results.
2459        return ($genus, $species, $strain);
2460    }
2461    
2462    =head3 GetGenomeByNameData
2463    
2464        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2465    
2466    Return a list of the IDs of the genomes with the specified genus,
2467    species, and strain. In almost every case, there will be either zero or
2468    one IDs returned; however, two or more IDs could be returned if there are
2469    multiple versions of the genome in the database.
2470    
2471    =over 4
2472    
2473    =item genus
2474    
2475    Genus of the desired genome.
2476    
2477    =item species
2478    
2479    Species of the desired genome.
2480    
2481    =item strain
2482    
2483    Strain (unique characterization) of the desired genome. This may be an empty
2484    string, in which case it is presumed that the desired genome has no strain
2485    specified.
2486    
2487    =item RETURN
2488    
2489    Returns a list of the IDs of the genomes having the specified genus, species, and
2490    strain.
2491    
2492    =back
2493    
2494    =cut
2495    
2496    sub GetGenomeByNameData {
2497        # Get the parameters.
2498        my ($self, $genus, $species, $strain) = @_;
2499        # Try to find the genomes.
2500        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2501                                    [$genus, $species, $strain], 'Genome(id)');
2502        # Return the result.
2503        return @retVal;
2504    }
2505    
2506  =head3 Insert  =head3 Insert
2507    
2508  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2509    
2510  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
2511  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 2158  Line 2514 
2514  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
2515  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>.
2516    
2517  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']});
2518    
2519  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
2520  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>.
2521    
2522  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'});
2523    
2524  =over 4  =over 4
2525    
# Line 2188  Line 2544 
2544    
2545  =head3 Annotate  =head3 Annotate
2546    
2547  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2548    
2549  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
2550  specified feature and user.  specified feature and user.
# Line 2242  Line 2598 
2598    
2599  =head3 AssignFunction  =head3 AssignFunction
2600    
2601  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2602    
2603  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
2604  format is described in L</ParseAssignment>.  format is described in L</ParseAssignment>.
# Line 2302  Line 2658 
2658    
2659  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2660    
2661  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2662    
2663  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
2664  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 2336  Line 2692 
2692          push @retVal, $mappedAlias;          push @retVal, $mappedAlias;
2693      } else {      } else {
2694          # 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.
2695          @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2696      }      }
2697      # Return the result.      # Return the result.
2698      return @retVal;      return @retVal;
# Line 2344  Line 2700 
2700    
2701  =head3 FeatureTranslation  =head3 FeatureTranslation
2702    
2703  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2704    
2705  Return the translation of a feature.  Return the translation of a feature.
2706    
# Line 2372  Line 2728 
2728    
2729  =head3 Taxonomy  =head3 Taxonomy
2730    
2731  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2732    
2733  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
2734  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>,
2735  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2736    
2737  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2738    
2739  =over 4  =over 4
2740    
# Line 2397  Line 2753 
2753  sub Taxonomy {  sub Taxonomy {
2754      # Get the parameters.      # Get the parameters.
2755      my ($self, $genome) = @_;      my ($self, $genome) = @_;
     # Find the specified genome's taxonomy string.  
     my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);  
2756      # Declare the return variable.      # Declare the return variable.
2757      my @retVal = ();      my @retVal = ();
2758      # If we found the genome, return its taxonomy string.      # Get the genome data.
2759      if ($list) {      my $genomeData = $self->_GenomeData($genome);
2760          @retVal = split /\s*;\s*/, $list;      # Only proceed if it exists.
2761        if (defined $genomeData) {
2762            # Create the taxonomy from the taxonomy string.
2763            @retVal = split /\s*;\s*/, $genomeData->PrimaryValue('Genome(taxonomy)');
2764      } else {      } else {
2765            # Genome doesn't exist, so emit a warning.
2766          Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0);          Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0);
2767      }      }
2768      # Return the value found.      # Return the value found.
# Line 2413  Line 2771 
2771    
2772  =head3 CrudeDistance  =head3 CrudeDistance
2773    
2774  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2775    
2776  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
2777  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 2449  Line 2807 
2807      }      }
2808      my @taxA = $self->Taxonomy($genomeA);      my @taxA = $self->Taxonomy($genomeA);
2809      my @taxB = $self->Taxonomy($genomeB);      my @taxB = $self->Taxonomy($genomeB);
2810      # Initialize the distance to 1. We'll reduce it each time we find a match between the      # Compute the distance.
2811      # taxonomies.      my $retVal = FIGRules::CrudeDistanceFormula(\@taxA, \@taxB);
     my $retVal = 1.0;  
     # Initialize the subtraction amount. This amount determines the distance reduction caused  
     # by a mismatch at the current level.  
     my $v = 0.5;  
     # Loop through the taxonomies.  
     for (my $i = 0; ($i < @taxA) && ($i < @taxB) && ($taxA[$i] eq $taxB[$i]); $i++) {  
         $retVal -= $v;  
         $v /= 2;  
     }  
2812      return $retVal;      return $retVal;
2813  }  }
2814    
2815  =head3 RoleName  =head3 RoleName
2816    
2817  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2818    
2819  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
2820  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 2499  Line 2848 
2848    
2849  =head3 RoleDiagrams  =head3 RoleDiagrams
2850    
2851  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2852    
2853  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2854    
# Line 2527  Line 2876 
2876      return @retVal;      return @retVal;
2877  }  }
2878    
 =head3 GetProperties  
   
 C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>  
   
 Return a list of the properties with the specified characteristics.  
   
 Properties are arbitrary key-value pairs associated with a feature. (At some point they  
 will also be associated with genomes.) A property value is represented by a 4-tuple of  
 the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter  
   
 =over 4  
   
 =item fid  
   
 ID of the feature possessing the property.  
   
 =item key  
   
 Name or key of the property.  
   
 =item value  
   
 Value of the property.  
   
 =item url  
   
 URL of the document that indicated the property should have this particular value, or an  
 empty string if no such document exists.  
   
 =back  
   
 The parameters act as a filter for the desired data. Any non-null parameter will  
 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.  
   
 A single property key can have many values, representing different ideas about the  
 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  
   
     my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');  
   
 Here the I<$value> and I<$url> fields are left blank, indicating that those fields are  
 not to be filtered. The tuples returned would be  
   
     ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')  
     ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')  
   
 =cut  
 #: Return Type @@;  
 sub GetProperties {  
     # Get the parameters.  
     my ($self, @parms) = @_;  
     # Declare the return variable.  
     my @retVal = ();  
     # 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;  
     }  
     # Return the result.  
     return @retVal;  
 }  
   
2879  =head3 FeatureProperties  =head3 FeatureProperties
2880    
2881  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2882    
2883  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
2884  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
2885  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
2886  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
2887  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.  
2888    
2889  =over 4  =over 4
2890    
# Line 2630  Line 2894 
2894    
2895  =item RETURN  =item RETURN
2896    
2897  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.  
2898    
2899  =back  =back
2900    
# Line 2641  Line 2904 
2904      # Get the parameters.      # Get the parameters.
2905      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2906      # Get the properties.      # Get the properties.
2907      my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->ca->GetAttributes($featureID);
2908                              ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2909                               'HasProperty(evidence)']);      my @retVal = ();
2910        for my $attributeRow (@attributes) {
2911            shift @{$attributeRow};
2912            push @retVal, $attributeRow;
2913        }
2914      # Return the resulting list.      # Return the resulting list.
2915      return @retVal;      return @retVal;
2916  }  }
2917    
2918  =head3 DiagramName  =head3 DiagramName
2919    
2920  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2921    
2922  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2923    
# Line 2678  Line 2945 
2945    
2946  =head3 PropertyID  =head3 PropertyID
2947    
2948  C<< my $id = $sprout->PropertyID($propName, $propValue); >>      my $id = $sprout->PropertyID($propName, $propValue);
2949    
2950  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
2951  pair exists.  pair exists. Only a small subset of the FIG attributes are stored as
2952    Sprout properties, mostly for use in search optimization.
2953    
2954  =over 4  =over 4
2955    
# Line 2714  Line 2982 
2982    
2983  =head3 MergedAnnotations  =head3 MergedAnnotations
2984    
2985  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2986    
2987  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2988  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2763  Line 3031 
3031    
3032  =head3 RoleNeighbors  =head3 RoleNeighbors
3033    
3034  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
3035    
3036  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
3037  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 2806  Line 3074 
3074    
3075  =head3 FeatureLinks  =head3 FeatureLinks
3076    
3077  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
3078    
3079  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
3080  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 2837  Line 3105 
3105    
3106  =head3 SubsystemsOf  =head3 SubsystemsOf
3107    
3108  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3109    
3110  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
3111  to the roles the feature performs.  to the roles the feature performs.
# Line 2885  Line 3153 
3153    
3154  =head3 SubsystemList  =head3 SubsystemList
3155    
3156  C<< my @subsystems = $sprout->SubsystemList($featureID); >>      my @subsystems = $sprout->SubsystemList($featureID);
3157    
3158  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
3159  feature participates. Unlike L</SubsystemsOf>, this method only returns the  feature participates. Unlike L</SubsystemsOf>, this method only returns the
# Line 2908  Line 3176 
3176  sub SubsystemList {  sub SubsystemList {
3177      # Get the parameters.      # Get the parameters.
3178      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
3179      # Get the list of names.      # Get the list of names. We do a join to the Subsystem table because we have missing subsystems in
3180      my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?",      # the Sprout database!
3181        my @retVal = $self->GetFlat(['HasRoleInSubsystem', 'Subsystem'], "HasRoleInSubsystem(from-link) = ?",
3182                                  [$featureID], 'HasRoleInSubsystem(to-link)');                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3183      # Return the result, sorted.      # Return the result, sorted.
3184      return sort @retVal;      return sort @retVal;
# Line 2917  Line 3186 
3186    
3187  =head3 GenomeSubsystemData  =head3 GenomeSubsystemData
3188    
3189  C<< my %featureData = $sprout->GenomeSubsystemData($genomeID); >>      my %featureData = $sprout->GenomeSubsystemData($genomeID);
3190    
3191  Return a hash mapping genome features to their subsystem roles.  Return a hash mapping genome features to their subsystem roles.
3192    
# Line 2942  Line 3211 
3211      # Declare the return variable.      # Declare the return variable.
3212      my %retVal = ();      my %retVal = ();
3213      # Get a list of the genome features that participate in subsystems. For each      # Get a list of the genome features that participate in subsystems. For each
3214      # feature we get its spreadsheet cells and the corresponding roles.      # feature we get its subsystem ID and the corresponding roles.
3215      my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'],      my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf', 'HasSSCell'],
3216                               "HasFeature(from-link) = ?", [$genomeID],                               "HasFeature(from-link) = ?", [$genomeID],
3217                               ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']);                                   ['HasFeature(to-link)', 'IsRoleOf(from-link)',  'HasSSCell(from-link)']);
3218      # Now we get a list of the spreadsheet cells and their associated subsystems. Subsystems      # Now we get a list of valid subsystems. These are the subsystems connected to the genome with
3219      # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the      # a non-negative variant code.
3220      # list. We use it at the beginning to get all the spreadsheet cells for the genome and      my %subs = map { $_ => 1 } $self->GetFlat(['ParticipatesIn'],
3221      # again at the end to filter out participation in subsystems with a negative variant code.                                                  "ParticipatesIn(from-link) = ? AND ParticipatesIn(variant-code) >= 0",
3222      my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'],                                                  [$genomeID], 'ParticipatesIn(to-link)');
3223                                   "IsGenomeOf(from-link) = ? AND ParticipatesIn(variant-code) >= 0 AND ParticipatesIn(from-link) = ?",      # We loop through @roleData to build the hash.
                                  [$genomeID, $genomeID], ['HasSSCell(to-link)', 'HasSSCell(from-link)']);  
     # Now "@roleData" lists the spreadsheet cell and role for each of the genome's features.  
     # "@cellData" lists the subsystem name for each of the genome's spreadsheet cells. We  
     # link these two lists together to create the result. First, we want a hash mapping  
     # spreadsheet cells to subsystem names.  
     my %subHash = map { $_->[0] => $_->[1] } @cellData;  
     # We loop through @cellData to build the hash.  
3224      for my $roleEntry (@roleData) {      for my $roleEntry (@roleData) {
3225          # Get the data for this feature and cell.          # Get the data for this feature and cell.
3226          my ($fid, $cellID, $role) = @{$roleEntry};          my ($fid, $role, $subsys) = @{$roleEntry};
3227          # Check for a subsystem name.          Trace("Subsystem for $fid is $subsys.") if T(4);
3228          my $subsys = $subHash{$cellID};          # Check the subsystem;
3229          if ($subsys) {          if ($subs{$subsys}) {
3230                Trace("Subsystem found.") if T(4);
3231              # Insure this feature has an entry in the return hash.              # Insure this feature has an entry in the return hash.
3232              if (! exists $retVal{$fid}) { $retVal{$fid} = []; }              if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3233              # Merge in this new data.              # Merge in this new data.
# Line 2977  Line 3240 
3240    
3241  =head3 RelatedFeatures  =head3 RelatedFeatures
3242    
3243  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
3244    
3245  Return a list of the features which are bi-directional best hits of the specified feature and  Return a list of the features which are bi-directional best hits of the specified feature and
3246  have been assigned the specified function by the specified user. If no such features exists,  have been assigned the specified function by the specified user. If no such features exists,
# Line 3010  Line 3273 
3273      # Get the parameters.      # Get the parameters.
3274      my ($self, $featureID, $function, $userID) = @_;      my ($self, $featureID, $function, $userID) = @_;
3275      # Get a list of the features that are BBHs of the incoming feature.      # Get a list of the features that are BBHs of the incoming feature.
3276      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);      my $bbhData = FIGRules::BBHData($featureID);
3277        my @bbhFeatures = map { $_->[0] } @$bbhData;
3278      # Now we loop through the features, pulling out the ones that have the correct      # Now we loop through the features, pulling out the ones that have the correct
3279      # functional assignment.      # functional assignment.
3280      my @retVal = ();      my @retVal = ();
# Line 3028  Line 3292 
3292    
3293  =head3 TaxonomySort  =head3 TaxonomySort
3294    
3295  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3296    
3297  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a list formed by sorting the specified features by the taxonomy of the containing
3298  genome. This will cause genomes from similar organisms to float close to each other.  genome. This will cause genomes from similar organisms to float close to each other.
# Line 3063  Line 3327 
3327          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3328                                          [$fid], 'Genome(taxonomy)');                                          [$fid], 'Genome(taxonomy)');
3329          # Add this feature to the hash buffer.          # Add this feature to the hash buffer.
3330          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);          push @{$hashBuffer{$taxonomy}}, $fid;
3331      }      }
3332      # Sort the keys and get the elements.      # Sort the keys and get the elements.
3333      my @retVal = ();      my @retVal = ();
# Line 3076  Line 3340 
3340    
3341  =head3 Protein  =head3 Protein
3342    
3343  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3344    
3345  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3346    
# Line 3162  Line 3426 
3426    
3427  =head3 LoadInfo  =head3 LoadInfo
3428    
3429  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3430    
3431  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
3432  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 3181  Line 3445 
3445      return @retVal;      return @retVal;
3446  }  }
3447    
3448    =head3 BBHMatrix
3449    
3450        my $bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3451    
3452    Find all the bidirectional best hits for the features of a genome in a
3453    specified list of target genomes. The return value will be a hash mapping
3454    features in the original genome to their bidirectional best hits in the
3455    target genomes.
3456    
3457    =over 4
3458    
3459    =item genomeID
3460    
3461    ID of the genome whose features are to be examined for bidirectional best hits.
3462    
3463    =item cutoff
3464    
3465    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3466    
3467    =item targets
3468    
3469    List of target genomes. Only pairs originating in the original
3470    genome and landing in one of the target genomes will be returned.
3471    
3472    =item RETURN
3473    
3474    Returns a reference to a hash mapping each feature in the original genome
3475    to a sub-hash mapping its BBH pegs in the target genomes to their scores.
3476    
3477    =back
3478    
3479    =cut
3480    
3481    sub BBHMatrix {
3482        # Get the parameters.
3483        my ($self, $genomeID, $cutoff, @targets) = @_;
3484        # Declare the return variable.
3485        my %retVal = ();
3486        # Ask for the BBHs.
3487        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3488        Trace("Retrieved " . scalar(@bbhList) . " BBH results.") if T(3);
3489        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3490        for my $bbhData (@bbhList) {
3491            my ($peg1, $peg2, $score) = @{$bbhData};
3492            if (! exists $retVal{$peg1}) {
3493                $retVal{$peg1} = { $peg2 => $score };
3494            } else {
3495                $retVal{$peg1}->{$peg2} = $score;
3496            }
3497        }
3498        # Return the result.
3499        return \%retVal;
3500    }
3501    
3502    
3503    =head3 SimMatrix
3504    
3505        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3506    
3507    Find all the similarities for the features of a genome in a
3508    specified list of target genomes. The return value will be a hash mapping
3509    features in the original genome to their similarites in the
3510    target genomes.
3511    
3512    =over 4
3513    
3514    =item genomeID
3515    
3516    ID of the genome whose features are to be examined for similarities.
3517    
3518    =item cutoff
3519    
3520    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3521    
3522    =item targets
3523    
3524    List of target genomes. Only pairs originating in the original
3525    genome and landing in one of the target genomes will be returned.
3526    
3527    =item RETURN
3528    
3529    Returns a hash mapping each feature in the original genome to a hash mapping its
3530    similar pegs in the target genomes to their scores.
3531    
3532    =back
3533    
3534    =cut
3535    
3536    sub SimMatrix {
3537        # Get the parameters.
3538        my ($self, $genomeID, $cutoff, @targets) = @_;
3539        # Declare the return variable.
3540        my %retVal = ();
3541        # Get the list of features in the source organism.
3542        my @fids = $self->FeaturesOf($genomeID);
3543        # Ask for the sims. We only want similarities to fig features.
3544        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3545        if (! defined $simList) {
3546            Confess("Unable to retrieve similarities from server.");
3547        } else {
3548            Trace("Processing sims.") if T(3);
3549            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3550            # Create a hash for the target genomes.
3551            my %targetHash = map { $_ => 1 } @targets;
3552            for my $simData (@{$simList}) {
3553                # Get the PEGs and the score.
3554                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3555                # Insure the second ID is in the target list.
3556                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3557                if (exists $targetHash{$genome2}) {
3558                    # Here it is. Now we need to add it to the return hash. How we do that depends
3559                    # on whether or not $peg1 is new to us.
3560                    if (! exists $retVal{$peg1}) {
3561                        $retVal{$peg1} = { $peg2 => $score };
3562                    } else {
3563                        $retVal{$peg1}->{$peg2} = $score;
3564                    }
3565                }
3566            }
3567        }
3568        # Return the result.
3569        return %retVal;
3570    }
3571    
3572    
3573  =head3 LowBBHs  =head3 LowBBHs
3574    
3575  C<< my %bbhMap = $sprout->LowBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3576    
3577  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3578  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 3213  Line 3602 
3602      # Create the return hash.      # Create the return hash.
3603      my %retVal = ();      my %retVal = ();
3604      # Query for the desired BBHs.      # Query for the desired BBHs.
3605      my @bbhList = FIGRules::BBHData($featureID, $cutoff);      my $bbhList = FIGRules::BBHData($featureID, $cutoff);
3606      # Form the results into the return hash.      # Form the results into the return hash.
3607      for my $pair (@bbhList) {      for my $pair (@$bbhList) {
3608          my $fid = $pair->[0];          my $fid = $pair->[0];
3609          if ($self->Exists('Feature', $fid)) {          if ($self->Exists('Feature', $fid)) {
3610              $retVal{$fid} = $pair->[1];              $retVal{$fid} = $pair->[1];
# Line 3227  Line 3616 
3616    
3617  =head3 Sims  =head3 Sims
3618    
3619  C<< my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters); >>      my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3620    
3621  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
3622  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 3237  Line 3626 
3626  Similarities can be either raw or expanded. The raw similarities are basic  Similarities can be either raw or expanded. The raw similarities are basic
3627  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
3628  features considered substantially identical. So, for example, if features B<A1>,  features considered substantially identical. So, for example, if features B<A1>,
3629  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
3630  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]>.
3631    
3632  =over 4  =over 4
3633    
3634  =item fid  =item fid
3635    
3636  ID of the feature whose similarities are desired.  ID of the feature whose similarities are desired, or reference to a list of IDs
3637    of features whose similarities are desired.
3638    
3639  =item maxN  =item maxN
3640    
# Line 3292  Line 3682 
3682    
3683  =head3 IsAllGenomes  =head3 IsAllGenomes
3684    
3685  C<< my $flag = $sprout->IsAllGenomes(\@list, \@checkList); >>      my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3686    
3687  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
3688  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 3341  Line 3731 
3731    
3732  =head3 GetGroups  =head3 GetGroups
3733    
3734  C<< my %groups = $sprout->GetGroups(\@groupList); >>      my %groups = $sprout->GetGroups(\@groupList);
3735    
3736  Return a hash mapping each group to the IDs of the genomes in the group.  Return a hash mapping each group to the IDs of the genomes in the group.
3737  A list of groups may be specified, in which case only those groups will be  A list of groups may be specified, in which case only those groups will be
# Line 3373  Line 3763 
3763                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3764          # Loop through the genomes found.          # Loop through the genomes found.
3765          for my $genome (@genomes) {          for my $genome (@genomes) {
3766              # Pop this genome's ID off the current list.              # Get the genome ID and group, and add this genome to the group's list.
3767              my @groups = @{$genome};              my ($genomeID, $group) = @{$genome};
3768              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, $genomeID);  
             }  
3769          }          }
3770      }      }
3771      # Return the hash we just built.      # Return the hash we just built.
# Line 3389  Line 3774 
3774    
3775  =head3 MyGenomes  =head3 MyGenomes
3776    
3777  C<< my @genomes = Sprout::MyGenomes($dataDir); >>      my @genomes = Sprout::MyGenomes($dataDir);
3778    
3779  Return a list of the genomes to be included in the Sprout.  Return a list of the genomes to be included in the Sprout.
3780    
# Line 3421  Line 3806 
3806    
3807  =head3 LoadFileName  =head3 LoadFileName
3808    
3809  C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>      my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3810    
3811  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
3812  directory.  directory.
# Line 3462  Line 3847 
3847    
3848  =head3 DeleteGenome  =head3 DeleteGenome
3849    
3850  C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>      my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3851    
3852  Delete a genome from the database.  Delete a genome from the database.
3853    
# Line 3488  Line 3873 
3873      # Get the parameters.      # Get the parameters.
3874      my ($self, $genomeID, $testFlag) = @_;      my ($self, $genomeID, $testFlag) = @_;
3875      # Perform the delete for the genome's features.      # Perform the delete for the genome's features.
3876      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", $testFlag);      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3877      # Perform the delete for the primary genome data.      # Perform the delete for the primary genome data.
3878      my $stats = $self->Delete('Genome', $genomeID, $testFlag);      my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3879      $retVal->Accumulate($stats);      $retVal->Accumulate($stats);
3880      # Return the result.      # Return the result.
3881      return $retVal;      return $retVal;
# Line 3498  Line 3883 
3883    
3884  =head3 Fix  =head3 Fix
3885    
3886  C<< my %fixedHash = Sprout::Fix(%groupHash); >>      my %fixedHash = $sprout->Fix(%groupHash);
3887    
3888  Prepare a genome group hash (like that returned by L</GetGroups> for processing.  Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3889  Groups with the same primary name will be combined. The primary name is the  The groups will be combined into the appropriate super-groups.
 first capitalized word in the group name.  
3890    
3891  =over 4  =over 4
3892    
# Line 3520  Line 3904 
3904    
3905  sub Fix {  sub Fix {
3906      # Get the parameters.      # Get the parameters.
3907      my (%groupHash) = @_;      my ($self, %groupHash) = @_;
3908      # Create the result hash.      # Create the result hash.
3909      my %retVal = ();      my %retVal = ();
3910      # Copy over the genomes.      # Copy over the genomes.
3911      for my $groupID (keys %groupHash) {      for my $groupID (keys %groupHash) {
3912          # Make a safety copy of the group ID.          # Get the super-group name.
3913          my $realGroupID = $groupID;          my $realGroupID = $self->SuperGroup($groupID);
3914          # Yank the primary name.          # Append this group's genomes into the result hash
3915          if ($groupID =~ /([A-Z]\w+)/) {          # using the super-group name.
3916              $realGroupID = $1;          push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
         }  
         # Append this group's genomes into the result hash.  
         Tracer::AddToListMap(\%retVal, $realGroupID, @{$groupHash{$groupID}});  
3917      }      }
3918      # Return the result hash.      # Return the result hash.
3919      return %retVal;      return %retVal;
# Line 3540  Line 3921 
3921    
3922  =head3 GroupPageName  =head3 GroupPageName
3923    
3924  C<< my $name = $sprout->GroupPageName($group); >>      my $name = $sprout->GroupPageName($group);
3925    
3926  Return the name of the page for the specified NMPDR group.  Return the name of the page for the specified NMPDR group.
3927    
# Line 3562  Line 3943 
3943  sub GroupPageName {  sub GroupPageName {
3944      # Get the parameters.      # Get the parameters.
3945      my ($self, $group) = @_;      my ($self, $group) = @_;
     # Declare the return variable.  
     my $retVal;  
3946      # Check for the group file data.      # Check for the group file data.
3947      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;  
     }  
3948      # Compute the real group name.      # Compute the real group name.
3949      my $realGroup = $group;      my $realGroup = $self->SuperGroup($group);
3950      if ($group =~ /([A-Z]\w+)/) {      # Get the associated page name.
3951          $realGroup = $1;      my $retVal = "../content/$superTable{$realGroup}->{page}";
     }  
     # Return the page name.  
     $retVal = "../content/" . $self->{groupHash}->{$realGroup}->[1];  
3952      # Return the result.      # Return the result.
3953      return $retVal;      return $retVal;
3954  }  }
3955    
 =head3 ReadGroupFile  
3956    
3957  C<< my %groupData = Sprout::ReadGroupFile($groupFileName); >>  =head3 AddProperty
3958    
3959        $sprout->AddProperty($featureID, $key, @values);
3960    
3961  Read in the data from the specified group file. The group file contains information  Add a new attribute value (Property) to a feature.
 about each of the NMPDR groups.  
3962    
3963  =over 4  =over 4
3964    
3965  =item name  =item peg
3966    
3967  Name of the group.  ID of the feature to which the attribute is to be added.
3968    
3969  =item page  =item key
3970    
3971  Name of the group's page on the web site (e.g. C<campy.php> for  Name of the attribute (key).
 Campylobacter)  
3972    
3973  =item genus  =item values
3974    
3975  Genus of the group  Values of the attribute.
3976    
3977  =item species  =back
3978    
3979    =cut
3980    #: Return Type ;
3981    sub AddProperty {
3982        # Get the parameters.
3983        my ($self, $featureID, $key, @values) = @_;
3984        # Add the property using the attached attributes object.
3985        $self->ca->AddAttribute($featureID, $key, @values);
3986    }
3987    
3988  Species of the group, or an empty string if the group is for an entire  =head3 CheckGroupFile
 genus. If the group contains more than one species, the species names  
 should be separated by commas.  
3989    
3990  =back      my %groupData = $sprout->CheckGroupFile();
3991    
3992    Get the group file hash. The group file hash describes the relationship
3993    between a group and the super-group to which it belongs for purposes of
3994    display. The super-group name is computed from the first capitalized word
3995    in the actual group name. For each super-group, the group file contains
3996    the page name and a list of the species expected to be in the group.
3997    Each species is specified by a genus and a species name. A species name
3998    of C<0> implies an entire genus.
3999    
4000  The parameters to this method are as follows  This method returns a hash from super-group names to a hash reference. Each
4001    resulting hash reference contains the following fields.
4002    
4003  =over 4  =over 4
4004    
4005  =item groupFile  =item specials
4006    
4007  Name of the file containing the group data.  Reference to a hash whose keys are the names of special species.
4008    
4009  =item RETURN  =item contents
4010    
4011  Returns a hash keyed on group name. The value of each hash  A list of 2-tuples, each containing a genus name followed by a species name
4012    (or 0, indicating all species). This list indicates which organisms belong
4013    in the super-group.
4014    
4015  =back  =back
4016    
4017  =cut  =cut
4018    
4019  sub ReadGroupFile {  sub CheckGroupFile {
4020      # Get the parameters.      # Get the parameters.
4021      my ($groupFileName) = @_;      my ($self) = @_;
4022      # Declare the return variable.      # Check to see if we already have this hash.
4023      my %retVal;      if (! defined $self->{groupHash}) {
4024            # We don't, so we need to read it in.
4025            my %groupHash;
4026      # Read the group file.      # Read the group file.
4027      my @groupLines = Tracer::GetFile($groupFileName);          my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
4028            # Loop through the list of sort-of groups.
4029      for my $groupLine (@groupLines) {      for my $groupLine (@groupLines) {
4030          my ($name, $page, $genus, $species) = split(/\t/, $groupLine);              my ($name, $specials, @contents) = split /\t/, $groupLine;
4031          $retVal{$name} = [$page, $genus, $species];              $groupHash{$name} = { specials => { map { $_ => 1 } split /\s*,\s*/, $specials },
4032                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
4033                                    };
4034            }
4035            # Save the hash.
4036            $self->{groupHash} = \%groupHash;
4037      }      }
4038      # Return the result.      # Return the result.
4039      return %retVal;      return %{$self->{groupHash}};
4040  }  }
4041    
4042  =head3 AddProperty  =head2 Virtual Methods
4043    
4044    =head3 CleanKeywords
4045    
4046  C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>      my $cleanedString = $sprout->CleanKeywords($searchExpression);
4047    
4048  Add a new attribute value (Property) to a feature. In the SEED system, attributes can  Clean up a search expression or keyword list. This involves converting the periods
4049  be added to almost any object. In Sprout, they can only be added to features. In  in EC numbers to underscores, converting non-leading minus signs to underscores,
4050  Sprout, attributes are implemented using I<properties>. A property represents a key/value  a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
4051  pair. If the particular key/value pair coming in is not already in the database, a new  characters. In addition, any extra spaces are removed.
 B<Property> record is created to hold it.  
4052    
4053  =over 4  =over 4
4054    
4055  =item peg  =item searchExpression
4056    
4057    Search expression or keyword list to clean. Note that a search expression may
4058    contain boolean operators which need to be preserved. This includes leading
4059    minus signs.
4060    
4061  ID of the feature to which the attribute is to be replied.  =item RETURN
4062    
4063  =item key  Cleaned expression or keyword list.
4064    
4065  Name of the attribute (key).  =back
4066    
4067  =item value  =cut
4068    
4069  Value of the attribute.  sub CleanKeywords {
4070        # Get the parameters.
4071        my ($self, $searchExpression) = @_;
4072        # Get the stemmer.
4073        my $stemmer = $self->GetStemmer();
4074        # Convert the search expression using the stemmer.
4075        my $retVal = $stemmer->PrepareSearchExpression($searchExpression);
4076        Trace("Cleaned keyword list for \"$searchExpression\" is \"$retVal\".") if T(3);
4077        # Return the result.
4078        return $retVal;
4079    }
4080    
4081  =item url  =head3 GetSourceObject
4082    
4083  URL or text citation from which the property was obtained.      my $source = $erdb->GetSourceObject();
4084    
4085  =back  Return the object to be used in creating load files for this database.
4086    
4087  =cut  =cut
4088  #: Return Type ;  
4089  sub AddProperty {  sub GetSourceObject {
4090      # Get the parameters.      # Get the parameters.
4091      my ($self, $featureID, $key, $value, $url) = @_;      my ($self) = @_;
4092      # Declare the variable to hold the desired property ID.      # Do we already have one?
4093      my $propID;      my $retVal = $self->{fig};
4094      # Attempt to find a property record for this key/value pair.      if (! defined $retVal) {
4095      my @properties = $self->GetFlat(['Property'],          # Create the object.
4096                                     "Property(property-name) = ? AND Property(property-value) = ?",          require FIG;
4097                                     [$key, $value], 'Property(id)');          $retVal = FIG->new();
4098      if (@properties) {          Trace("FIG source object created for process $$.") if T(ERDBLoadGroup => 3);
4099          # Here the property is already in the database. We save its ID.          # Set up retries to prevent the lost-connection error when harvesting
4100          $propID = $properties[0];          # the feature data.
4101          # Here the property value does not exist. We need to generate an ID. It will be set          my $dbh = $retVal->db_handle();
4102          # to a number one greater than the maximum value in the database. This call to          $dbh->set_retries(5);
4103          # GetAll will stop after one record.          # Save it for other times.
4104          my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],          $self->{fig} = $retVal;
                                         1);  
         $propID = $maxProperty[0]->[0] + 1;  
         # Insert the new property value.  
         $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });  
4105      }      }
4106      # Now we connect the incoming feature to the property.      # Return the object.
4107      $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });      return $retVal;
4108  }  }
4109    
4110  =head2 Virtual Methods  =head3 SectionList
4111    
4112  =head3 CleanKeywords      my @sections = $erdb->SectionList($fig);
4113    
4114  C<< my $cleanedString = $sprout->CleanKeywords($searchExpression); >>  Return a list of the names for the different data sections used when loading this database.
4115    The default is a single string, in which case there is only one section representing the
4116    entire database.
4117    
4118  Clean up a search expression or keyword list. This involves converting the periods  =cut
4119  in EC numbers to underscores, converting non-leading minus signs to underscores,  
4120  a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic  sub SectionList {
4121  characters. In addition, any extra spaces are removed.      # Get the parameters.
4122        my ($self, $source) = @_;
4123        # Ask the BaseSproutLoader for a section list.
4124        require BaseSproutLoader;
4125        my @retVal = BaseSproutLoader::GetSectionList($self, $source);
4126        # Return the list.
4127        return @retVal;
4128    }
4129    
4130    =head3 Loader
4131    
4132        my $groupLoader = $erdb->Loader($groupName, $options);
4133    
4134    Return an [[ERDBLoadGroupPm]] object for the specified load group. This method is used
4135    by [[ERDBGeneratorPl]] to create the load group objects. If you are not using
4136    [[ERDBGeneratorPl]], you don't need to override this method.
4137    
4138  =over 4  =over 4
4139    
4140  =item searchExpression  =item groupName
4141    
4142  Search expression or keyword list to clean. Note that a search expression may  Name of the load group whose object is to be returned. The group name is
4143  contain boolean operators which need to be preserved. This includes leading  guaranteed to be a single word with only the first letter capitalized.
4144  minus signs.  
4145    =item options
4146    
4147    Reference to a hash of command-line options.
4148    
4149  =item RETURN  =item RETURN
4150    
4151  Cleaned expression or keyword list.  Returns an [[ERDBLoadGroupPm]] object that can be used to process the specified load group
4152    for this database.
4153    
4154  =back  =back
4155    
4156  =cut  =cut
4157    
4158  sub CleanKeywords {  sub Loader {
4159      # Get the parameters.      # Get the parameters.
4160      my ($self, $searchExpression) = @_;      my ($self, $groupName, $options) = @_;
4161      # Perform the standard cleanup.      # Compute the loader name.
4162      my $retVal = $self->ERDB::CleanKeywords($searchExpression);      my $loaderClass = "${groupName}SproutLoader";
4163      # Fix the periods in EC and TC numbers.      # Pull in its definition.
4164      $retVal =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;      require "$loaderClass.pm";
4165      # Fix non-trailing periods.      # Create an object for it.
4166      $retVal =~ s/\.(\w)/_$1/g;      my $retVal = eval("$loaderClass->new(\$self, \$options)");
4167      # Fix non-leading minus signs.      # Insure it worked.
4168      $retVal =~ s/(\w)[\-]/$1_/g;      Confess("Could not create $loaderClass object: $@") if $@;
4169      # Fix the vertical bars and colons      # Return it to the caller.
     $retVal =~ s/(\w)[|:](\w)/$1'$2/g;  
     # Return the result.  
4170      return $retVal;      return $retVal;
4171  }  }
4172    
4173    
4174    =head3 LoadGroupList
4175    
4176        my @groups = $erdb->LoadGroupList();
4177    
4178    Returns a list of the names for this database's load groups. This method is used
4179    by [[ERDBGeneratorPl]] when the user wishes to load all table groups. The default
4180    is a single group called 'All' that loads everything.
4181    
4182    =cut
4183    
4184    sub LoadGroupList {
4185        # Return the list.
4186        return qw(Feature Subsystem Genome Annotation Property Source Reaction Synonym Drug);
4187    }
4188    
4189    =head3 LoadDirectory
4190    
4191        my $dirName = $erdb->LoadDirectory();
4192    
4193    Return the name of the directory in which load files are kept. The default is
4194    the FIG temporary directory, which is a really bad choice, but it's always there.
4195    
4196    =cut
4197    
4198    sub LoadDirectory {
4199        # Get the parameters.
4200        my ($self) = @_;
4201        # Return the directory name.
4202        return $self->{dataDir};
4203    }
4204    
4205  =head2 Internal Utility Methods  =head2 Internal Utility Methods
4206    
4207    =head3 GetStemmer
4208    
4209        my $stermmer = $sprout->GetStemmer();
4210    
4211    Return the stemmer object for this database.
4212    
4213    =cut
4214    
4215    sub GetStemmer {
4216        # Get the parameters.
4217        my ($self) = @_;
4218        # Declare the return variable.
4219        my $retVal = $self->{stemmer};
4220        if (! defined $retVal) {
4221            # We don't have one pre-built, so we build and save it now.
4222            $retVal = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
4223                                     stops => "$FIG_Config::sproutData/StopWords.txt",
4224                                     cache => 0);
4225            $self->{stemmer} = $retVal;
4226        }
4227        # Return the result.
4228        return $retVal;
4229    }
4230    
4231  =head3 ParseAssignment  =head3 ParseAssignment
4232    
4233  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
# Line 3754  Line 4236 
4236    
4237  A functional assignment is always of the form  A functional assignment is always of the form
4238    
4239      C<set >I<YYYY>C< function to\n>I<ZZZZZ>      set YYYY function to
4240        ZZZZ
4241    
4242  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,
4243  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 3807  Line 4290 
4290      return @retVal;      return @retVal;
4291  }  }
4292    
4293    =head3 _CheckFeature
4294    
4295        my $flag = $sprout->_CheckFeature($fid);
4296    
4297    Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
4298    
4299    =over 4
4300    
4301    =item fid
4302    
4303    Feature ID to check.
4304    
4305    =item RETURN
4306    
4307    Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE.
4308    
4309    =back
4310    
4311    =cut
4312    
4313    sub _CheckFeature {
4314        # Get the parameters.
4315        my ($self, $fid) = @_;
4316        # Insure we have a genome hash.
4317        my $genomes = $self->_GenomeHash();
4318        # Get the feature's genome ID.
4319        my ($genomeID) = FIGRules::ParseFeatureID($fid);
4320        # Return an indicator of whether or not the genome ID is in the hash.
4321        return ($self->{genomeHash}->{$genomeID} ? 1 : 0);
4322    }
4323    
4324  =head3 FriendlyTimestamp  =head3 FriendlyTimestamp
4325    
4326  Convert a time number to a user-friendly time stamp for display.  Convert a time number to a user-friendly time stamp for display.
# Line 3834  Line 4348 
4348  }  }
4349    
4350    
4351    =head3 Hint
4352    
4353        my $htmlText = Sprout::Hint($wikiPage, $hintID);
4354    
4355    Return the HTML for a help link that displays the specified hint text when it is clicked.
4356    This HTML can be put in forms to provide a useful hinting mechanism.
4357    
4358    =over 4
4359    
4360    =item wikiPage
4361    
4362    Name of the wiki page to be popped up when the hint mark is clicked.
4363    
4364    =item hintID
4365    
4366    ID of the text to display for the hint. This should correspond to a tip number
4367    in the Wiki.
4368    
4369    =item RETURN
4370    
4371    Returns the html for the hint facility. The resulting html shows the word "help" and
4372    uses the standard FIG popup technology.
4373    
4374    =back
4375    
4376    =cut
4377    
4378    sub Hint {
4379        # Get the parameters.
4380        my ($wikiPage, $hintID) = @_;
4381        # Declare the return variable.
4382        my $retVal;
4383        # Convert the wiki page name to a URL.
4384        my $wikiURL;
4385        if ($wikiPage =~ m#/#) {
4386            # Here it's a URL of some sort.
4387            $wikiURL = $wikiPage;
4388        } else {
4389            # Here it's a wiki page.
4390            my $page = join("", map { ucfirst $_ } split /\s+/, $wikiPage);
4391            if ($page =~ /^(.+?)\.(.+)$/) {
4392                $page = "$1/$2";
4393            } else {
4394                $page = "FIG/$page";
4395            }
4396            $wikiURL = "$FIG_Config::cgi_url/wiki/view.cgi/$page";
4397        }
4398        # Is there hint text?
4399        if (! $hintID) {
4400            # No. Create a new-page hint.
4401            $retVal = qq(&nbsp;<a class="hint" onclick="doPagePopup(this, '$wikiURL')">(help)</a>);
4402        } else {
4403            # With hint text, we create a popup window hint. We need to compute the hint URL.
4404            my $tipURL = "$FIG_Config::cgi_url/wiki/view.cgi/FIG/TWikiCustomTip" .
4405                Tracer::Pad($hintID, 3, 1, "0");
4406            # Create a hint pop-up link.
4407            $retVal = qq(&nbsp;<a class="hint" onclick="doHintPopup(this, '$wikiURL', '$tipURL')">(help)</a>);
4408        }
4409        # Return the HTML.
4410        return $retVal;
4411    }
4412    
4413    =head3 _GenomeHash
4414    
4415        my $gHash = $sprout->_GenomeHash();
4416    
4417    Return a hash mapping all NMPDR genome IDs to [[ERDBObjectPm]] genome objects.
4418    
4419    =cut
4420    
4421    sub _GenomeHash {
4422        # Get the parameters.
4423        my ($self) = @_;
4424        # Do we already have a filled hash?
4425        if (! $self->{genomeHashFilled}) {
4426            # No, create it.
4427            my %gHash = map { $_->PrimaryValue('id') => $_ } $self->GetList("Genome", "", []);
4428            $self->{genomeHash} = \%gHash;
4429            # Denote we have it.
4430            $self->{genomeHashFilled} = 1;
4431        }
4432        # Return the hash.
4433        return $self->{genomeHash};
4434    }
4435    
4436    =head3 _GenomeData
4437    
4438        my $genomeData = $sprout->_GenomeData($genomeID);
4439    
4440    Return an [[ERDBObjectPm]] object for the specified genome, or an undefined
4441    value if the genome does not exist.
4442    
4443    =over 4
4444    
4445    =item genomeID
4446    
4447    ID of the desired genome.
4448    
4449    =item RETURN
4450    
4451    Returns either an [[ERDBObjectPm]] containing the genome, or an undefined value.
4452    If the genome exists, it will have been read into the genome cache.
4453    
4454    =back
4455    
4456    =cut
4457    
4458    sub _GenomeData {
4459        # Get the parameters.
4460        my ($self, $genomeID) = @_;
4461        # Are we in the genome hash?
4462        if (! exists $self->{genomeHash}->{$genomeID} && ! $self->{genomeHashFilled}) {
4463            # The genome isn't in the hash, and the hash is not complete, so we try to
4464            # read it.
4465            $self->{genomeHash}->{$genomeID} = $self->GetEntity(Genome => $genomeID);
4466        }
4467        # Return the result.
4468        return $self->{genomeHash}->{$genomeID};
4469    }
4470    
4471    =head3 _CacheGenome
4472    
4473        $sprout->_CacheGenome($genomeID, $genomeData);
4474    
4475    Store the specified genome object in the genome cache if it is already there.
4476    
4477    =over 4
4478    
4479    =item genomeID
4480    
4481    ID of the genome to store in the cache.
4482    
4483    =item genomeData
4484    
4485    An [[ERDBObjectPm]] containing at least the data for the specified genome.
4486    Note that the Genome may not be the primary object in it, so a fully-qualified
4487    field name has to be used to retrieve data from it.
4488    
4489    =back
4490    
4491    =cut
4492    
4493    sub _CacheGenome {
4494        # Get the parameters.
4495        my ($self, $genomeID, $genomeData) = @_;
4496        # Only proceed if we don't already have the genome.
4497        if (! exists $self->{genomeHash}->{$genomeID}) {
4498            $self->{genomeHash}->{$genomeID} = $genomeData;
4499        }
4500    }
4501    
4502  1;  1;

Legend:
Removed from v.1.94  
changed lines
  Added in v.1.126

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3