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

Diff of /Sprout/Sprout.pm

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

revision 1.75, Sun Jun 25 18:02:35 2006 UTC revision 1.125, Mon Mar 16 00:24:23 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;
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.
116        my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
117                                                      $FIG_Config::fig );
118      # Compute the options. We do this by starting with a table of defaults and overwriting with      # Compute the options. We do this by starting with a table of defaults and overwriting with
119      # the incoming data.      # the incoming data.
120      my $optionTable = Tracer::GetOptions({      my $optionTable = Tracer::GetOptions({
# Line 99  Line 122 
122                                                          # database type                                                          # database type
123                         dataDir      => $FIG_Config::sproutData,                         dataDir      => $FIG_Config::sproutData,
124                                                          # data file directory                                                          # data file directory
125                         xmlFileName  => "$FIG_Config::fig/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::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 118  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}, undef, $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.
157        $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 150  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 165  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 177  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 205  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 251  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 262  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 307  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 334  Line 507 
507      return $retVal;      return $retVal;
508  }  }
509    
510  =head3 GeneMenu  =head3 GenomeMenu
511    
512  C<< my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params); >>      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  Reference to a hash mapping attributes to values for the SELECT tag generated.  Returns the HTML for a genome selection control on a form (sometimes called a popup menu).
527    
528  =item filterString  =back
529    
530  A filter string for use in selecting the genomes. The filter string must conform  The valid options are as follows.
 to the rules for the C<< ERDB->Get >> method.  
531    
532  =item params  =over 4
533    
534  Reference to a list of values to be substituted in for the parameter marks in  =item name
 the filter string.  
535    
536  =item RETURN  Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
537    Terrible things will happen if you have two controls with the same name on the same page.
538    
539    =item filter
540    
541    If specified, a filter for the list of genomes to display. The filter should be in the form of a
542    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 multiSelect
548    
549    If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
550    
551  Returns an HTML select menu with the specified genomes as selectable options.  =item size
552    
553    Number of rows to display in the control. The default is C<10>
554    
555    =item id
556    
557    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, $params) = @_;      my ($self, %options) = @_;
576      # Start the menu.      # Get the control's name and ID.
577      my $retVal = "<select " .      my $menuName = $options{name} || $options{id} || 'myGenomeControl';
578          join(" ", map { "$_=\"$attributes->{$_}\"" } keys %{$attributes}) .      my $menuID = $options{id} || $menuName;
579          ">\n";      Trace("Genome menu name = $menuName with ID $menuID.") if T(3);
580      # Get the genomes.      # Compute the IDs for the status display.
581      my @genomes = $self->GetAll(['Genome'], $filterString, $params, ['Genome(id)',      my $divID = "${menuID}_status";
582                                                                       'Genome(genus)',      my $urlID = "${menuID}_url";
583                                                                       'Genome(species)',      # Compute the code to show selected genomes in the status area.
584                                                                       'Genome(unique-characterization)']);      my $showSelect = "showSelected('$menuID', '$divID', '$urlID', $FIG_Config::genome_control_cap)";
585      # Sort them by name.      # Check for single-select or multi-select.
586      my @sorted = sort { lc("$a->[1] $a->[2]") cmp lc("$b->[1] $b->[2]") } @genomes;      my $multiSelect = $options{multiSelect} || 0;
587      # Loop through the genomes, creating the option tags.      # Get the style data.
588      for my $genomeData (@sorted) {      my $class = $options{class} || '';
589          # Get the data for this genome.      # Get the list of pre-selected items.
590          my ($genomeID, $genus, $species, $strain) = @{$genomeData};      my $selections = $options{selected} || [];
591          # Get the contig count.      if (ref $selections ne 'ARRAY') {
592          my $count = $self->ContigCount($genomeID);          $selections = [ split /\s*,\s*/, $selections ];
593          my $counting = ($count == 1 ? "contig" : "contigs");      }
594          # Build the option tag.      my %selected = map { $_ => 1 } @{$selections};
595          $retVal .= "<option value=\"$genomeID\">$genus $species $strain ($genomeID) [$count $counting]</option>\n";      # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
596          Trace("Option tag built for $genomeID: $genus $species $strain.") if T(3);      # string, a hash reference, or a list reference.
597        my ($filterHash, $filterString);
598        my $filterParms = $options{filter} || "";
599        if (ref $filterParms eq 'HASH') {
600            $filterHash = $filterParms;
601            $filterParms = [];
602            $filterString = "";
603        } else {
604            if (! ref $filterParms) {
605                $filterParms = [split /\t|\\t/, $filterParms];
606            }
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.
746        return $retVal;
747    }
748    
749    
750    =head3 Stem
751    
752        my $stem = $sprout->Stem($word);
753    
754    Return the stem of the specified word, or C<undef> if the word is not
755    stemmable. Note that even if the word is stemmable, the stem may be
756    the same as the original word.
757    
758    =over 4
759    
760    =item word
761    
762    Word to convert into a stem.
763    
764    =item RETURN
765    
766    Returns a stem of the word (which may be the word itself), or C<undef> if
767    the word is not stemmable.
768    
769    =back
770    
771    =cut
772    
773    sub Stem {
774        # Get the parameters.
775        my ($self, $word) = @_;
776        # Get the stemmer object.
777        my $stemmer = $self->{stemmer};
778        if (! defined $stemmer) {
779            # We don't have one pre-built, so we build and save it now.
780            $stemmer = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
781                                     stops => "$FIG_Config::sproutData/StopWords.txt",
782                                     cache => 0);
783            $self->{stemmer} = $stemmer;
784        }
785        # Try to stem the word.
786        my $retVal = $stemmer->Process($word);
787      # Return the result.      # Return the result.
788      return $retVal;      return $retVal;
789  }  }
790    
791    
792  =head3 Build  =head3 Build
793    
794  C<< $sprout->Build(); >>      $sprout->Build();
795    
796  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.
797  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 415  Line 808 
808    
809  =head3 Genomes  =head3 Genomes
810    
811  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
812    
813  Return a list of all the genome IDs.  Return a list of all the genome IDs.
814    
# Line 432  Line 825 
825    
826  =head3 GenusSpecies  =head3 GenusSpecies
827    
828  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
829    
830  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
831    
# Line 454  Line 847 
847  sub GenusSpecies {  sub GenusSpecies {
848      # Get the parameters.      # Get the parameters.
849      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
850      # Get the data for the specified genome.      # Declare the return value.
851      my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',      my $retVal;
852                                                                'Genome(unique-characterization)']);      # Get the genome data.
853      # Format the result and return it.      my $genomeData = $self->_GenomeData($genomeID);
854      my $retVal = join(' ', @values);      # Only proceed if we found the genome.
855        if (defined $genomeData) {
856            $retVal = $genomeData->PrimaryValue('Genome(scientific-name)');
857        }
858        # Return it.
859      return $retVal;      return $retVal;
860  }  }
861    
862  =head3 FeaturesOf  =head3 FeaturesOf
863    
864  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
865    
866  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
867    
# Line 509  Line 906 
906    
907  =head3 FeatureLocation  =head3 FeatureLocation
908    
909  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
910    
911  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
912  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 533  Line 930 
930  =item RETURN  =item RETURN
931    
932  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
933  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
934    wasn't found.
935    
936  =back  =back
937    
938  =cut  =cut
939  #: Return Type @;  
 #: Return Type $;  
940  sub FeatureLocation {  sub FeatureLocation {
941      # Get the parameters.      # Get the parameters.
942      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
943      # 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.  
944      my @retVal = ();      my @retVal = ();
945      # Set up the variables used to determine if we have adjacent segments. This initial setup will      # Get the feature record.
946      # not match anything.      my $object = $self->GetEntity('Feature', $featureID);
947      my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);      # Only proceed if we found it.
948      # Loop through the query results, creating location specifiers.      if (defined $object) {
949      while (my $location = $query->Fetch()) {          # Get the location string.
950          # Get the location parameters.          my $locString = $object->PrimaryValue('Feature(location-string)');
951          my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',          # Create the return list.
952              '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$len";  
953      }      }
954      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
955      return (wantarray ? @retVal : join(',', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
# Line 588  Line 957 
957    
958  =head3 ParseLocation  =head3 ParseLocation
959    
960  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
961    
962  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
963  length.  length.
# Line 607  Line 976 
976  =back  =back
977    
978  =cut  =cut
979  #: Return Type @;  
980  sub ParseLocation {  sub ParseLocation {
981      # 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
982      # the first parameter.      # the first parameter.
# Line 630  Line 999 
999      return ($contigID, $start, $dir, $len);      return ($contigID, $start, $dir, $len);
1000  }  }
1001    
1002    
1003    
1004  =head3 PointLocation  =head3 PointLocation
1005    
1006  C<< my $found = Sprout::PointLocation($location, $point); >>      my $found = Sprout::PointLocation($location, $point);
1007    
1008  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
1009  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 661  Line 1032 
1032  =back  =back
1033    
1034  =cut  =cut
1035  #: Return Type $;  
1036  sub PointLocation {  sub PointLocation {
1037      # 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
1038      # the first parameter.      # the first parameter.
# Line 684  Line 1055 
1055    
1056  =head3 DNASeq  =head3 DNASeq
1057    
1058  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
1059    
1060  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
1061  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 768  Line 1139 
1139    
1140  =head3 AllContigs  =head3 AllContigs
1141    
1142  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1143    
1144  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1145    
# Line 798  Line 1169 
1169    
1170  =head3 GenomeLength  =head3 GenomeLength
1171    
1172  C<< my $length = $sprout->GenomeLength($genomeID); >>      my $length = $sprout->GenomeLength($genomeID);
1173    
1174  Return the length of the specified genome in base pairs.  Return the length of the specified genome in base pairs.
1175    
# Line 822  Line 1193 
1193      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
1194      # Declare the return variable.      # Declare the return variable.
1195      my $retVal = 0;      my $retVal = 0;
1196      # Get the genome's contig sequence lengths.      # Get the genome data.
1197      my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',      my $genomeData = $self->_GenomeData($genomeID);
1198                         [$genomeID], 'IsMadeUpOf(len)');      # Only proceed if it exists.
1199      # Sum the lengths.      if (defined $genomeData) {
1200      map { $retVal += $_ } @lens;          $retVal = $genomeData->PrimaryValue('Genome(dna-size)');
1201        }
1202      # Return the result.      # Return the result.
1203      return $retVal;      return $retVal;
1204  }  }
1205    
1206  =head3 FeatureCount  =head3 FeatureCount
1207    
1208  C<< my $count = $sprout->FeatureCount($genomeID, $type); >>      my $count = $sprout->FeatureCount($genomeID, $type);
1209    
1210  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.
1211    
# Line 868  Line 1240 
1240    
1241  =head3 GenomeAssignments  =head3 GenomeAssignments
1242    
1243  C<< my $fidHash = $sprout->GenomeAssignments($genomeID); >>      my $fidHash = $sprout->GenomeAssignments($genomeID);
1244    
1245  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
1246  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 894  Line 1266 
1266      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
1267      # Declare the return variable.      # Declare the return variable.
1268      my $retVal = {};      my $retVal = {};
1269      # Query the genome's features and annotations. We'll put the oldest annotations      # Query the genome's features.
1270      # first so that the last assignment to go into the hash will be the correct one.      my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?",
     my $query = $self->Get(['HasFeature', 'IsTargetOfAnnotation', 'Annotation'],  
                            "HasFeature(from-link) = ? ORDER BY Annotation(time)",  
1271                             [$genomeID]);                             [$genomeID]);
1272      # Loop through the annotations.      # Loop through the features.
1273      while (my $data = $query->Fetch) {      while (my $data = $query->Fetch) {
1274          # Get the feature ID and annotation text.          # Get the feature ID and assignment.
1275          my ($fid, $annotation) = $data->Values(['HasFeature(to-link)',          my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
1276                                                  'Annotation(annotation)']);          if ($assignment) {
         # Check to see if this is an assignment. Note that the user really  
         # doesn't matter to us, other than we use it to determine whether or  
         # not this is an assignment.  
         my ($user, $assignment) = _ParseAssignment('fig', $annotation);  
         if ($user) {  
             # Here it's an assignment. We put it in the return hash, overwriting  
             # any older assignment that might be present.  
1277              $retVal->{$fid} = $assignment;              $retVal->{$fid} = $assignment;
1278          }          }
1279      }      }
# Line 920  Line 1283 
1283    
1284  =head3 ContigLength  =head3 ContigLength
1285    
1286  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->ContigLength($contigID);
1287    
1288  Compute the length of a contig.  Compute the length of a contig.
1289    
# Line 959  Line 1322 
1322    
1323  =head3 ClusterPEGs  =head3 ClusterPEGs
1324    
1325  C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>      my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1326    
1327  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
1328  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
1329  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
1330  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
1331  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
1332  sequence.  appear in the output sequence.
1333    
1334  =over 4  =over 4
1335    
# Line 1007  Line 1370 
1370    
1371  =head3 GenesInRegion  =head3 GenesInRegion
1372    
1373  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1374    
1375  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1376    
# Line 1036  Line 1399 
1399  =back  =back
1400    
1401  =cut  =cut
1402  #: Return Type @@;  
1403  sub GenesInRegion {  sub GenesInRegion {
1404      # Get the parameters.      # Get the parameters.
1405      my ($self, $contigID, $start, $stop) = @_;      my ($self, $contigID, $start, $stop) = @_;
1406      # Get the maximum segment length.      # Get the maximum segment length.
1407      my $maximumSegmentLength = $self->MaxSegment;      my $maximumSegmentLength = $self->MaxSegment;
     # Create a hash to receive the feature list. We use a hash so that we can eliminate  
     # duplicates easily. The hash key will be the feature ID. The value will be a two-element  
     # containing the minimum and maximum offsets. We will use the offsets to sort the results  
     # when we're building the result set.  
     my %featuresFound = ();  
1408      # Prime the values we'll use for the returned beginning and end.      # Prime the values we'll use for the returned beginning and end.
1409      my @initialMinMax = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
1410      my ($min, $max) = @initialMinMax;      my ($min, $max) = @initialMinMax;
1411      # Create a table of parameters for each query. Each query looks for features travelling in      # Get the overlapping features.
1412        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1413        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1414        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1415        # of the feature's locations.
1416        my %featureMap = ();
1417        # Loop through them to do the begin/end analysis.
1418        for my $featureObject (@featureObjects) {
1419            # Get the feature's location string. This may contain multiple actual locations.
1420            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1421            my @locationSegments = split /\s*,\s*/, $locations;
1422            # Loop through the locations.
1423            for my $locationSegment (@locationSegments) {
1424                # Construct an object for the location.
1425                my $locationObject = BasicLocation->new($locationSegment);
1426                # Merge the current segment's begin and end into the min and max.
1427                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1428                my ($beg, $end);
1429                if (exists $featureMap{$fid}) {
1430                    ($beg, $end) = @{$featureMap{$fid}};
1431                    $beg = $left if $left < $beg;
1432                    $end = $right if $right > $end;
1433                } else {
1434                    ($beg, $end) = ($left, $right);
1435                }
1436                $min = $beg if $beg < $min;
1437                $max = $end if $end > $max;
1438                # Store the feature's new extent back into the hash table.
1439                $featureMap{$fid} = [$beg, $end];
1440            }
1441        }
1442        # Now we must compute the list of the IDs for the features found. We start with a list
1443        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1444        # but the result of the sort will be the same.)
1445        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1446        # Now we sort by midpoint and yank out the feature IDs.
1447        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1448        # Return it along with the min and max.
1449        return (\@retVal, $min, $max);
1450    }
1451    
1452    =head3 GeneDataInRegion
1453    
1454        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1455    
1456    List the features which overlap a specified region in a contig.
1457    
1458    =over 4
1459    
1460    =item contigID
1461    
1462    ID of the contig containing the region of interest.
1463    
1464    =item start
1465    
1466    Offset of the first residue in the region of interest.
1467    
1468    =item stop
1469    
1470    Offset of the last residue in the region of interest.
1471    
1472    =item RETURN
1473    
1474    Returns a list of B<ERDBObjects> for the desired features. Each object will
1475    contain a B<Feature> record.
1476    
1477    =back
1478    
1479    =cut
1480    
1481    sub GeneDataInRegion {
1482        # Get the parameters.
1483        my ($self, $contigID, $start, $stop) = @_;
1484        # Get the maximum segment length.
1485        my $maximumSegmentLength = $self->MaxSegment;
1486        # Create a hash to receive the feature list. We use a hash so that we can eliminate
1487        # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1488        # ERDBObject from the query.
1489        my %featuresFound = ();
1490        # Create a table of parameters for the queries. Each query looks for features travelling in
1491      # 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,
1492      # 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
1493      # 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 1059  Line 1496 
1496      # Loop through the query parameters.      # Loop through the query parameters.
1497      for my $parms (values %queryParms) {      for my $parms (values %queryParms) {
1498          # Create the query.          # Create the query.
1499          my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1500              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1501              $parms);              $parms);
1502          # Loop through the feature segments found.          # Loop through the feature segments found.
1503          while (my $segment = $query->Fetch) {          while (my $segment = $query->Fetch) {
1504              # Get the data about this segment.              # Get the data about this segment.
1505              my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1506                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1507              # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1508              # this will be the case if the segment is the maximum length, so to fine-tune              # this will be the case if the segment is the maximum length, so to fine-tune
1509              # the results we insure that the inequality from the query holds using the actual              # the results we insure that the inequality from the query holds using the actual
1510              # length.              # length.
1511              my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1512              if ($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.  
                     $found = 1;  
                 }  
             }  
1513              if ($found) {              if ($found) {
1514                  # Here we need to record the feature and update the minima and maxima. First,                  # Save this feature in the result list.
1515                  # get the current entry for the specified feature.                  $featuresFound{$featureID} = $segment;
                 my ($loc1, $loc2) = (exists $featuresFound{$featureID} ? @{$featuresFound{$featureID}} :  
                                      @initialMinMax);  
                 # Merge the current segment's begin and end into the feature begin and end and the  
                 # global min and max.  
                 if ($beg < $loc1) {  
                     $loc1 = $beg;  
                     $min = $beg if $beg < $min;  
                 }  
                 if ($end > $loc2) {  
                     $loc2 = $end;  
                     $max = $end if $end > $max;  
1516                  }                  }
                 # Store the entry back into the hash table.  
                 $featuresFound{$featureID} = [$loc1, $loc2];  
1517              }              }
1518          }          }
1519      }      # Return the ERDB objects for the features found.
1520      # Now we must compute the list of the IDs for the features found. We start with a list      return values %featuresFound;
     # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,  
     # but the result of the sort will be the same.)  
     my @list = map { [$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);  
1521  }  }
1522    
1523  =head3 FType  =head3 FType
1524    
1525  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1526    
1527  Return the type of a feature.  Return the type of a feature.
1528    
# Line 1149  Line 1552 
1552    
1553  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1554    
1555  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1556    
1557  Return the annotations of a feature.  Return the annotations of a feature.
1558    
# Line 1212  Line 1615 
1615    
1616  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1617    
1618  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1619    
1620  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
1621  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 1267  Line 1670 
1670    
1671  =head3 FunctionOf  =head3 FunctionOf
1672    
1673  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1674    
1675  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1676    
1677  The functional assignment is handled differently depending on the type of feature. If  The functional assignment is handled differently depending on the type of feature. If
1678  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional  the feature is identified by a FIG ID (begins with the string C<fig|>), then the functional
1679  assignment is a type of annotation. The format of an assignment is described in  assignment is taken from the B<Feature> or C<Annotation> table, depending.
 L</ParseAssignment>. Its worth noting that we cannot filter on the content of the  
 annotation itself because it's a text field; however, this is not a big problem because  
 most features only have a small number of annotations.  
1680    
1681  Each user has an associated list of trusted users. The assignment returned will be the most  Each user has an associated list of trusted users. The assignment returned will be the most
1682  recent one by at least one of the trusted users. If no trusted user list is available, then  recent one by at least one of the trusted users. If no trusted user list is available, then
1683  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
1684  is trusted.  is trusted.
1685    
1686  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.
1687  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.  
1688    
1689  =over 4  =over 4
1690    
# Line 1295  Line 1694 
1694    
1695  =item userID (optional)  =item userID (optional)
1696    
1697  ID of the user whose function determination is desired. If omitted, only the latest  ID of the user whose function determination is desired. If omitted, the primary
1698  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1699    
1700  =item RETURN  =item RETURN
1701    
# Line 1311  Line 1710 
1710      my ($self, $featureID, $userID) = @_;      my ($self, $featureID, $userID) = @_;
1711      # Declare the return value.      # Declare the return value.
1712      my $retVal;      my $retVal;
1713      # Determine the ID type.      # Find a FIG ID for this feature.
1714      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1715          # Here we have a FIG feature ID. We must build the list of trusted      # Only proceed if we have an ID.
1716          # users.      if ($fid) {
1717            # Here we have a FIG feature ID.
1718            if (!$userID) {
1719                # Use the primary assignment.
1720                ($retVal) = $self->GetEntityValues('Feature', $fid, ['Feature(assignment)']);
1721            } else {
1722                # We must build the list of trusted users.
1723          my %trusteeTable = ();          my %trusteeTable = ();
1724          # Check the user ID.          # Check the user ID.
1725          if (!$userID) {          if (!$userID) {
# Line 1338  Line 1743 
1743          # 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.
1744          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1745                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1746                                 [$featureID]);                                     [$fid]);
1747          my $timeSelected = 0;          my $timeSelected = 0;
1748          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1749          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
# Line 1357  Line 1762 
1762                  }                  }
1763              }              }
1764          }          }
1765      } else {          }
         # Here we have a non-FIG feature ID. In this case the user ID does not  
         # matter. We simply get the information from the External Alias Function  
         # table.  
         ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);  
1766      }      }
1767      # Return the assignment found.      # Return the assignment found.
1768      return $retVal;      return $retVal;
# Line 1369  Line 1770 
1770    
1771  =head3 FunctionsOf  =head3 FunctionsOf
1772    
1773  C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>      my @functionList = $sprout->FunctionOf($featureID, $userID);
1774    
1775  Return the functional assignments of a particular feature.  Return the functional assignments of a particular feature.
1776    
# Line 1380  Line 1781 
1781  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
1782  most features only have a small number of annotations.  most features only have a small number of annotations.
1783    
 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.  
   
1784  =over 4  =over 4
1785    
1786  =item featureID  =item featureID
# Line 1404  Line 1801 
1801      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1802      # Declare the return value.      # Declare the return value.
1803      my @retVal = ();      my @retVal = ();
1804      # Determine the ID type.      # Convert to a FIG ID.
1805      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1806        # Only proceed if we found one.
1807        if ($fid) {
1808          # 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
1809          # users.          # users.
1810          my %trusteeTable = ();          my %trusteeTable = ();
1811          # 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.
1812          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1813                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1814                                 [$featureID]);                                 [$fid]);
1815          my $timeSelected = 0;          my $timeSelected = 0;
1816          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1817          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
# Line 1427  Line 1826 
1826                  push @retVal, [$actualUser, $function];                  push @retVal, [$actualUser, $function];
1827              }              }
1828          }          }
     } 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;  
1829      }      }
1830      # Return the assignments found.      # Return the assignments found.
1831      return @retVal;      return @retVal;
# Line 1441  Line 1833 
1833    
1834  =head3 BBHList  =head3 BBHList
1835    
1836  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1837    
1838  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
1839  on a specified target genome.  on a specified target genome.
# Line 1472  Line 1864 
1864      my %retVal = ();      my %retVal = ();
1865      # Loop through the incoming features.      # Loop through the incoming features.
1866      for my $featureID (@{$featureList}) {      for my $featureID (@{$featureList}) {
1867          # Create a query to get the feature's best hit.          # Ask the server for the feature's best hit.
1868          my $query = $self->Get(['IsBidirectionalBestHitOf'],          my $bbhData = FIGRules::BBHData($featureID);
                                "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",  
                                [$featureID, $genomeID]);  
1869          # Peel off the BBHs found.          # Peel off the BBHs found.
1870          my @found = ();          my @found = ();
1871          while (my $bbh = $query->Fetch) {          for my $bbh (@$bbhData) {
1872              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');              my $fid = $bbh->[0];
1873                my $bbGenome = $self->GenomeOf($fid);
1874                if ($bbGenome eq $genomeID) {
1875                    push @found, $fid;
1876                }
1877          }          }
1878          $retVal{$featureID} = \@found;          $retVal{$featureID} = \@found;
1879      }      }
# Line 1489  Line 1883 
1883    
1884  =head3 SimList  =head3 SimList
1885    
1886  C<< my %similarities = $sprout->SimList($featureID, $count); >>      my %similarities = $sprout->SimList($featureID, $count);
1887    
1888  Return a list of the similarities to the specified feature.  Return a list of the similarities to the specified feature.
1889    
1890  Sprout does not support real similarities, so this method just returns the bidirectional  This method just returns the bidirectional best hits for performance reasons.
 best hits.  
1891    
1892  =over 4  =over 4
1893    
# Line 1514  Line 1907 
1907      # Get the parameters.      # Get the parameters.
1908      my ($self, $featureID, $count) = @_;      my ($self, $featureID, $count) = @_;
1909      # Ask for the best hits.      # Ask for the best hits.
1910      my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],      my $lists = FIGRules::BBHData($featureID);
                               "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",  
                               [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],  
                               $count);  
1911      # Create the return value.      # Create the return value.
1912      my %retVal = ();      my %retVal = ();
1913      for my $tuple (@lists) {      for my $tuple (@$lists) {
1914          $retVal{$tuple->[0]} = $tuple->[1];          $retVal{$tuple->[0]} = $tuple->[1];
1915      }      }
1916      # Return the result.      # Return the result.
1917      return %retVal;      return %retVal;
1918  }  }
1919    
   
   
1920  =head3 IsComplete  =head3 IsComplete
1921    
1922  C<< my $flag = $sprout->IsComplete($genomeID); >>      my $flag = $sprout->IsComplete($genomeID);
1923    
1924  Return TRUE if the specified genome is complete, else FALSE.  Return TRUE if the specified genome is complete, else FALSE.
1925    
# Line 1556  Line 1944 
1944      # Declare the return variable.      # Declare the return variable.
1945      my $retVal;      my $retVal;
1946      # Get the genome's data.      # Get the genome's data.
1947      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->_GenomeData($genomeID);
1948      if ($genomeData) {      # Only proceed if it exists.
1949        if (defined $genomeData) {
1950          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1951          ($retVal) = $genomeData->Value('Genome(complete)');          $retVal = $genomeData->PrimaryValue('Genome(complete)');
1952      }      }
1953      # Return the result.      # Return the result.
1954      return $retVal;      return $retVal;
# Line 1567  Line 1956 
1956    
1957  =head3 FeatureAliases  =head3 FeatureAliases
1958    
1959  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1960    
1961  Return a list of the aliases for a specified feature.  Return a list of the aliases for a specified feature.
1962    
# Line 1590  Line 1979 
1979      # Get the parameters.      # Get the parameters.
1980      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1981      # Get the desired feature's aliases      # Get the desired feature's aliases
1982      my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
1983      # Return the result.      # Return the result.
1984      return @retVal;      return @retVal;
1985  }  }
1986    
1987  =head3 GenomeOf  =head3 GenomeOf
1988    
1989  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $genomeID = $sprout->GenomeOf($featureID);
1990    
1991  Return the genome that contains a specified feature or contig.  Return the genome that contains a specified feature or contig.
1992    
# Line 1619  Line 2008 
2008  sub GenomeOf {  sub GenomeOf {
2009      # Get the parameters.      # Get the parameters.
2010      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]);  
2011      # Declare the return value.      # Declare the return value.
2012      my $retVal;      my $retVal;
2013      # Get the genome ID.      # Parse the genome ID from the feature ID.
2014      if (my $relationship = $query->Fetch()) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
2015          ($retVal) = $relationship->Value('HasContig(from-link)');          $retVal = $1;
2016        } else {
2017            # Find the feature by alias.
2018            my ($realFeatureID) = $self->FeaturesByAlias($featureID);
2019            if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {
2020                $retVal = $1;
2021            }
2022      }      }
2023      # Return the value found.      # Return the value found.
2024      return $retVal;      return $retVal;
# Line 1634  Line 2026 
2026    
2027  =head3 CoupledFeatures  =head3 CoupledFeatures
2028    
2029  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
2030    
2031  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
2032  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 1656  Line 2048 
2048  sub CoupledFeatures {  sub CoupledFeatures {
2049      # Get the parameters.      # Get the parameters.
2050      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2051      # Create a query to retrieve the functionally-coupled features.      # Ask the coupling server for the data.
2052      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
2053                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
2054      # This value will be set to TRUE if we find at least one coupled feature.      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
2055      my $found = 0;      # Form them into a hash.
     # Create the return hash.  
2056      my %retVal = ();      my %retVal = ();
2057      # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
2058      while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
2059          # Get the ID and score of the coupling.          my ($featureID2, $score) = @{$pair};
2060          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',          # Only proceed if the feature is in NMPDR.
2061                                                          'Coupling(score)']);          if ($self->_CheckFeature($featureID2)) {
2062          # Get the other feature that participates in the coupling.              $retVal{$featureID2} = $score;
         my ($otherFeatureID) = $self->GetFlat(['ParticipatesInCoupling'],  
                                            "ParticipatesInCoupling(to-link) = ? AND ParticipatesInCoupling(from-link) <> ?",  
                                            [$couplingID, $featureID], 'ParticipatesInCoupling(from-link)');  
         # Attach the other feature's score to its ID.  
         $retVal{$otherFeatureID} = $score;  
         $found = 1;  
2063      }      }
     # Functional coupling is reflexive. If we found at least one coupled feature, we must add  
     # the incoming feature as well.  
     if ($found) {  
         $retVal{$featureID} = 9999;  
2064      }      }
2065      # Return the hash.      # Return the hash.
2066      return %retVal;      return %retVal;
# Line 1687  Line 2068 
2068    
2069  =head3 CouplingEvidence  =head3 CouplingEvidence
2070    
2071  C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>      my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
2072    
2073  Return the evidence for a functional coupling.  Return the evidence for a functional coupling.
2074    
# Line 1735  Line 2116 
2116      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
2117      # Declare the return variable.      # Declare the return variable.
2118      my @retVal = ();      my @retVal = ();
2119      # Our first task is to find out the nature of the coupling: whether or not      # Get the coupling and evidence data.
2120      # it exists, its score, and whether the features are stored in the same      my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
2121      # order as the ones coming in.      # Loop through the raw data, saving the ones that are in NMPDR genomes.
2122      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);      for my $rawTuple (@rawData) {
2123      # Only proceed if a coupling exists.          if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
2124      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);  
2125      }      }
     # Return the result.  
     return @retVal;  
 }  
   
 =head3 GetCoupling  
   
 C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>  
   
 Return the coupling (if any) for the specified pair of PEGs. If a coupling  
 exists, we return the coupling ID along with an indicator of whether the  
 coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.  
 In the second case, we say the coupling is I<inverted>. The importance of an  
 inverted coupling is that the PEGs in the evidence will appear in reverse order.  
   
 =over 4  
   
 =item peg1  
   
 ID of the feature of interest.  
   
 =item peg2  
   
 ID of the potentially coupled feature.  
   
 =item RETURN  
   
 Returns a three-element list. The first element contains the database ID of  
 the coupling. The second element is FALSE if the coupling is stored in the  
 database in the caller specified order and TRUE if it is stored in the  
 inverted order. The third element is the coupling's score. If the coupling  
 does not exist, all three list elements will be C<undef>.  
   
 =back  
   
 =cut  
 #: Return Type $%@;  
 sub GetCoupling {  
     # Get the parameters.  
     my ($self, $peg1, $peg2) = @_;  
     # Declare the return values. We'll start with the coupling ID and undefine the  
     # flag and score until we have more information.  
     my ($retVal, $inverted, $score) = ($self->CouplingID($peg1, $peg2), undef, undef);  
     # Find the coupling data.  
     my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],  
                                  "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",  
                                  [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);  
     # Check to see if we found anything.  
     if (!@pegs) {  
         Trace("No coupling found.") if T(Coupling => 4);  
         # No coupling, so undefine the return value.  
         $retVal = undef;  
     } else {  
         # We have a coupling! Get the score and check for inversion.  
         $score = $pegs[0]->[1];  
         my $firstFound = $pegs[0]->[0];  
         $inverted = ($firstFound ne $peg1);  
         Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);  
2126      }      }
2127      # Return the result.      # Return the result.
2128      return ($retVal, $inverted, $score);      return @retVal;
2129  }  }
2130    
2131  =head3 GetSynonymGroup  =head3 GetSynonymGroup
2132    
2133  C<< my $id = $sprout->GetSynonymGroup($fid); >>      my $id = $sprout->GetSynonymGroup($fid);
2134    
2135  Return the synonym group name for the specified feature.  Return the synonym group name for the specified feature.
2136    
# Line 1866  Line 2169 
2169    
2170  =head3 GetBoundaries  =head3 GetBoundaries
2171    
2172  C<< my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList); >>      my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2173    
2174  Determine the begin and end boundaries for the locations in a list. All of the  Determine the begin and end boundaries for the locations in a list. All of the
2175  locations must belong to the same contig and have mostly the same direction in  locations must belong to the same contig and have mostly the same direction in
# Line 1928  Line 2231 
2231      return ($contig, $beg, $end);      return ($contig, $beg, $end);
2232  }  }
2233    
2234  =head3 CouplingID  =head3 ReadFasta
2235    
2236  C<< my $couplingID = $sprout->CouplingID($peg1, $peg2); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2237    
2238  Return the coupling ID for a pair of feature IDs.  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
2239    one or more lines of data. The first line begins with a > character and contains an ID.
2240  The coupling ID is currently computed by joining the feature IDs in  The remaining lines contain the sequence data in order.
 sorted order with a space. Client modules (that is, modules which  
 use Sprout) should not, however, count on this always being the  
 case. This method provides a way for abstracting the concept of a  
 coupling ID. All that we know for sure about it is that it can be  
 generated easily from the feature IDs and the order of the IDs  
 in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>  
 will have the same value as C<CouplingID("b1", "a1")>.  
   
 =over 4  
   
 =item peg1  
   
 First feature of interest.  
   
 =item peg2  
   
 Second feature of interest.  
   
 =item RETURN  
   
 Returns the ID that would be used to represent a functional coupling of  
 the two specified PEGs.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub CouplingID {  
     my ($self, @pegs) = @_;  
     return $self->DigestKey(join " ", sort @pegs);  
 }  
   
 =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.  
2241    
2242  =over 4  =over 4
2243    
# Line 2035  Line 2299 
2299    
2300  =head3 FormatLocations  =head3 FormatLocations
2301    
2302  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2303    
2304  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
2305  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 2100  Line 2364 
2364    
2365  =head3 DumpData  =head3 DumpData
2366    
2367  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2368    
2369  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.
2370    
# Line 2117  Line 2381 
2381    
2382  =head3 XMLFileName  =head3 XMLFileName
2383    
2384  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2385    
2386  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2387    
# Line 2128  Line 2392 
2392      return $self->{_xmlName};      return $self->{_xmlName};
2393  }  }
2394    
2395    =head3 GetGenomeNameData
2396    
2397        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2398    
2399    Return the genus, species, and unique characterization for a genome. This
2400    is similar to L</GenusSpecies>, with the exception that it returns the
2401    values in three seperate fields.
2402    
2403    =over 4
2404    
2405    =item genomeID
2406    
2407    ID of the genome whose name data is desired.
2408    
2409    =item RETURN
2410    
2411    Returns a three-element list, consisting of the genus, species, and strain
2412    of the specified genome. If the genome is not found, an error occurs.
2413    
2414    =back
2415    
2416    =cut
2417    
2418    sub GetGenomeNameData {
2419        # Get the parameters.
2420        my ($self, $genomeID) = @_;
2421        # Declare the return variables.
2422        my ($genus, $species, $strain);
2423        # Get the genome's data.
2424        my $genomeData = $self->_GenomeData($genomeID);
2425        # Only proceed if the genome exists.
2426        if (defined $genomeData) {
2427            # Get the desired values.
2428            ($genus, $species, $strain) = $genomeData->Values(['Genome(genus)',
2429                                                               'Genome(species)',
2430                                                               'Genome(unique-characterization)']);
2431        } else {
2432            # Throw an error because they were not found.
2433            Confess("Genome $genomeID not found in database.");
2434        }
2435        # Return the results.
2436        return ($genus, $species, $strain);
2437    }
2438    
2439    =head3 GetGenomeByNameData
2440    
2441        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2442    
2443    Return a list of the IDs of the genomes with the specified genus,
2444    species, and strain. In almost every case, there will be either zero or
2445    one IDs returned; however, two or more IDs could be returned if there are
2446    multiple versions of the genome in the database.
2447    
2448    =over 4
2449    
2450    =item genus
2451    
2452    Genus of the desired genome.
2453    
2454    =item species
2455    
2456    Species of the desired genome.
2457    
2458    =item strain
2459    
2460    Strain (unique characterization) of the desired genome. This may be an empty
2461    string, in which case it is presumed that the desired genome has no strain
2462    specified.
2463    
2464    =item RETURN
2465    
2466    Returns a list of the IDs of the genomes having the specified genus, species, and
2467    strain.
2468    
2469    =back
2470    
2471    =cut
2472    
2473    sub GetGenomeByNameData {
2474        # Get the parameters.
2475        my ($self, $genus, $species, $strain) = @_;
2476        # Try to find the genomes.
2477        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2478                                    [$genus, $species, $strain], 'Genome(id)');
2479        # Return the result.
2480        return @retVal;
2481    }
2482    
2483  =head3 Insert  =head3 Insert
2484    
2485  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2486    
2487  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
2488  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 2139  Line 2491 
2491  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
2492  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>.
2493    
2494  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']});
2495    
2496  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
2497  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>.
2498    
2499  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'});
2500    
2501  =over 4  =over 4
2502    
# Line 2169  Line 2521 
2521    
2522  =head3 Annotate  =head3 Annotate
2523    
2524  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2525    
2526  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
2527  specified feature and user.  specified feature and user.
# Line 2223  Line 2575 
2575    
2576  =head3 AssignFunction  =head3 AssignFunction
2577    
2578  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2579    
2580  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
2581  format is described in L</ParseAssignment>.  format is described in L</ParseAssignment>.
# Line 2283  Line 2635 
2635    
2636  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2637    
2638  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2639    
2640  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
2641  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 2317  Line 2669 
2669          push @retVal, $mappedAlias;          push @retVal, $mappedAlias;
2670      } else {      } else {
2671          # 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.
2672          @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2673      }      }
2674      # Return the result.      # Return the result.
2675      return @retVal;      return @retVal;
# Line 2325  Line 2677 
2677    
2678  =head3 FeatureTranslation  =head3 FeatureTranslation
2679    
2680  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2681    
2682  Return the translation of a feature.  Return the translation of a feature.
2683    
# Line 2353  Line 2705 
2705    
2706  =head3 Taxonomy  =head3 Taxonomy
2707    
2708  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2709    
2710  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
2711  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>,
2712  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2713    
2714  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2715    
2716  =over 4  =over 4
2717    
# Line 2378  Line 2730 
2730  sub Taxonomy {  sub Taxonomy {
2731      # Get the parameters.      # Get the parameters.
2732      my ($self, $genome) = @_;      my ($self, $genome) = @_;
     # Find the specified genome's taxonomy string.  
     my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);  
2733      # Declare the return variable.      # Declare the return variable.
2734      my @retVal = ();      my @retVal = ();
2735      # If we found the genome, return its taxonomy string.      # Get the genome data.
2736      if ($list) {      my $genomeData = $self->_GenomeData($genome);
2737          @retVal = split /\s*;\s*/, $list;      # Only proceed if it exists.
2738        if (defined $genomeData) {
2739            # Create the taxonomy from the taxonomy string.
2740            @retVal = split /\s*;\s*/, $genomeData->PrimaryValue('Genome(taxonomy)');
2741      } else {      } else {
2742            # Genome doesn't exist, so emit a warning.
2743          Trace("Genome \"$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);
2744      }      }
2745      # Return the value found.      # Return the value found.
# Line 2394  Line 2748 
2748    
2749  =head3 CrudeDistance  =head3 CrudeDistance
2750    
2751  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2752    
2753  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
2754  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 2430  Line 2784 
2784      }      }
2785      my @taxA = $self->Taxonomy($genomeA);      my @taxA = $self->Taxonomy($genomeA);
2786      my @taxB = $self->Taxonomy($genomeB);      my @taxB = $self->Taxonomy($genomeB);
2787      # Initialize the distance to 1. We'll reduce it each time we find a match between the      # Compute the distance.
2788      # 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;  
     }  
2789      return $retVal;      return $retVal;
2790  }  }
2791    
2792  =head3 RoleName  =head3 RoleName
2793    
2794  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2795    
2796  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
2797  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 2480  Line 2825 
2825    
2826  =head3 RoleDiagrams  =head3 RoleDiagrams
2827    
2828  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2829    
2830  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2831    
# Line 2508  Line 2853 
2853      return @retVal;      return @retVal;
2854  }  }
2855    
 =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;  
 }  
   
2856  =head3 FeatureProperties  =head3 FeatureProperties
2857    
2858  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2859    
2860  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
2861  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
2862  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
2863  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
2864  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.  
2865    
2866  =over 4  =over 4
2867    
# Line 2611  Line 2871 
2871    
2872  =item RETURN  =item RETURN
2873    
2874  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.  
2875    
2876  =back  =back
2877    
# Line 2622  Line 2881 
2881      # Get the parameters.      # Get the parameters.
2882      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2883      # Get the properties.      # Get the properties.
2884      my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->ca->GetAttributes($featureID);
2885                              ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2886                               'HasProperty(evidence)']);      my @retVal = ();
2887        for my $attributeRow (@attributes) {
2888            shift @{$attributeRow};
2889            push @retVal, $attributeRow;
2890        }
2891      # Return the resulting list.      # Return the resulting list.
2892      return @retVal;      return @retVal;
2893  }  }
2894    
2895  =head3 DiagramName  =head3 DiagramName
2896    
2897  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2898    
2899  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2900    
# Line 2657  Line 2920 
2920      return $retVal;      return $retVal;
2921  }  }
2922    
2923    =head3 PropertyID
2924    
2925        my $id = $sprout->PropertyID($propName, $propValue);
2926    
2927    Return the ID of the specified property name and value pair, if the
2928    pair exists. Only a small subset of the FIG attributes are stored as
2929    Sprout properties, mostly for use in search optimization.
2930    
2931    =over 4
2932    
2933    =item propName
2934    
2935    Name of the desired property.
2936    
2937    =item propValue
2938    
2939    Value expected for the desired property.
2940    
2941    =item RETURN
2942    
2943    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2944    
2945    =back
2946    
2947    =cut
2948    
2949    sub PropertyID {
2950        # Get the parameters.
2951        my ($self, $propName, $propValue) = @_;
2952        # Try to find the ID.
2953        my ($retVal) = $self->GetFlat(['Property'],
2954                                      "Property(property-name) = ? AND Property(property-value) = ?",
2955                                      [$propName, $propValue], 'Property(id)');
2956        # Return the result.
2957        return $retVal;
2958    }
2959    
2960  =head3 MergedAnnotations  =head3 MergedAnnotations
2961    
2962  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2963    
2964  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2965  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2708  Line 3008 
3008    
3009  =head3 RoleNeighbors  =head3 RoleNeighbors
3010    
3011  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
3012    
3013  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
3014  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 2751  Line 3051 
3051    
3052  =head3 FeatureLinks  =head3 FeatureLinks
3053    
3054  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
3055    
3056  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
3057  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 2782  Line 3082 
3082    
3083  =head3 SubsystemsOf  =head3 SubsystemsOf
3084    
3085  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3086    
3087  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
3088  to the roles the feature performs.  to the roles the feature performs.
# Line 2830  Line 3130 
3130    
3131  =head3 SubsystemList  =head3 SubsystemList
3132    
3133  C<< my @subsystems = $sprout->SubsystemList($featureID); >>      my @subsystems = $sprout->SubsystemList($featureID);
3134    
3135  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
3136  feature participates. Unlike L</SubsystemsOf>, this method only returns the  feature participates. Unlike L</SubsystemsOf>, this method only returns the
# Line 2853  Line 3153 
3153  sub SubsystemList {  sub SubsystemList {
3154      # Get the parameters.      # Get the parameters.
3155      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
3156      # Get the list of names.      # Get the list of names. We do a join to the Subsystem table because we have missing subsystems in
3157      my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",      # the Sprout database!
3158                                  [$featureID], 'HasSSCell(from-link)');      my @retVal = $self->GetFlat(['HasRoleInSubsystem', 'Subsystem'], "HasRoleInSubsystem(from-link) = ?",
3159                                    [$featureID], 'HasRoleInSubsystem(to-link)');
3160        # Return the result, sorted.
3161        return sort @retVal;
3162    }
3163    
3164    =head3 GenomeSubsystemData
3165    
3166        my %featureData = $sprout->GenomeSubsystemData($genomeID);
3167    
3168    Return a hash mapping genome features to their subsystem roles.
3169    
3170    =over 4
3171    
3172    =item genomeID
3173    
3174    ID of the genome whose subsystem feature map is desired.
3175    
3176    =item RETURN
3177    
3178    Returns a hash mapping each feature of the genome to a list of 2-tuples. Eacb
3179    2-tuple contains a subsystem name followed by a role ID.
3180    
3181    =back
3182    
3183    =cut
3184    
3185    sub GenomeSubsystemData {
3186        # Get the parameters.
3187        my ($self, $genomeID) = @_;
3188        # Declare the return variable.
3189        my %retVal = ();
3190        # Get a list of the genome features that participate in subsystems. For each
3191        # feature we get its subsystem ID and the corresponding roles.
3192        my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf', 'HasSSCell'],
3193                                     "HasFeature(from-link) = ?", [$genomeID],
3194                                     ['HasFeature(to-link)', 'IsRoleOf(from-link)',  'HasSSCell(from-link)']);
3195        # Now we get a list of valid subsystems. These are the subsystems connected to the genome with
3196        # a non-negative variant code.
3197        my %subs = map { $_ => 1 } $self->GetFlat(['ParticipatesIn'],
3198                                                    "ParticipatesIn(from-link) = ? AND ParticipatesIn(variant-code) >= 0",
3199                                                    [$genomeID], 'ParticipatesIn(to-link)');
3200        # We loop through @roleData to build the hash.
3201        for my $roleEntry (@roleData) {
3202            # Get the data for this feature and cell.
3203            my ($fid, $role, $subsys) = @{$roleEntry};
3204            Trace("Subsystem for $fid is $subsys.") if T(4);
3205            # Check the subsystem;
3206            if ($subs{$subsys}) {
3207                Trace("Subsystem found.") if T(4);
3208                # Insure this feature has an entry in the return hash.
3209                if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3210                # Merge in this new data.
3211                push @{$retVal{$fid}}, [$subsys, $role];
3212            }
3213        }
3214      # Return the result.      # Return the result.
3215      return @retVal;      return %retVal;
3216  }  }
3217    
3218  =head3 RelatedFeatures  =head3 RelatedFeatures
3219    
3220  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
3221    
3222  Return a list of the features which are bi-directional best hits of the specified feature and  Return a list of the features which are bi-directional best hits of the specified feature and
3223  have been assigned the specified function by the specified user. If no such features exists,  have been assigned the specified function by the specified user. If no such features exists,
# Line 2895  Line 3250 
3250      # Get the parameters.      # Get the parameters.
3251      my ($self, $featureID, $function, $userID) = @_;      my ($self, $featureID, $function, $userID) = @_;
3252      # 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.
3253      my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],      my $bbhData = FIGRules::BBHData($featureID);
3254                                       "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],      my @bbhFeatures = map { $_->[0] } @$bbhData;
                                      'IsBidirectionalBestHitOf(to-link)');  
3255      # 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
3256      # functional assignment.      # functional assignment.
3257      my @retVal = ();      my @retVal = ();
# Line 2915  Line 3269 
3269    
3270  =head3 TaxonomySort  =head3 TaxonomySort
3271    
3272  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3273    
3274  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a list formed by sorting the specified features by the taxonomy of the containing
3275  genome. This will cause genomes from similar organisms to float close to each other.  genome. This will cause genomes from similar organisms to float close to each other.
# Line 2950  Line 3304 
3304          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3305                                          [$fid], 'Genome(taxonomy)');                                          [$fid], 'Genome(taxonomy)');
3306          # Add this feature to the hash buffer.          # Add this feature to the hash buffer.
3307          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);          push @{$hashBuffer{$taxonomy}}, $fid;
3308      }      }
3309      # Sort the keys and get the elements.      # Sort the keys and get the elements.
3310      my @retVal = ();      my @retVal = ();
# Line 2963  Line 3317 
3317    
3318  =head3 Protein  =head3 Protein
3319    
3320  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3321    
3322  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3323    
# Line 3033  Line 3387 
3387      # Loop through the input triples.      # Loop through the input triples.
3388      my $n = length $sequence;      my $n = length $sequence;
3389      for (my $i = 0; $i < $n; $i += 3) {      for (my $i = 0; $i < $n; $i += 3) {
3390          # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3391          my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3392            my $triple = uc substr($sequence, $i, 3);
3393          # Translate it using the table.          # Translate it using the table.
3394          my $protein = "X";          my $protein = "X";
3395          if (exists $table->{$triple}) { $protein = $table->{$triple}; }          if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 3048  Line 3403 
3403    
3404  =head3 LoadInfo  =head3 LoadInfo
3405    
3406  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3407    
3408  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
3409  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 3067  Line 3422 
3422      return @retVal;      return @retVal;
3423  }  }
3424    
3425    =head3 BBHMatrix
3426    
3427        my $bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3428    
3429    Find all the bidirectional best hits for the features of a genome in a
3430    specified list of target genomes. The return value will be a hash mapping
3431    features in the original genome to their bidirectional best hits in the
3432    target genomes.
3433    
3434    =over 4
3435    
3436    =item genomeID
3437    
3438    ID of the genome whose features are to be examined for bidirectional best hits.
3439    
3440    =item cutoff
3441    
3442    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3443    
3444    =item targets
3445    
3446    List of target genomes. Only pairs originating in the original
3447    genome and landing in one of the target genomes will be returned.
3448    
3449    =item RETURN
3450    
3451    Returns a reference to a hash mapping each feature in the original genome
3452    to a sub-hash mapping its BBH pegs in the target genomes to their scores.
3453    
3454    =back
3455    
3456    =cut
3457    
3458    sub BBHMatrix {
3459        # Get the parameters.
3460        my ($self, $genomeID, $cutoff, @targets) = @_;
3461        # Declare the return variable.
3462        my %retVal = ();
3463        # Ask for the BBHs.
3464        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3465        Trace("Retrieved " . scalar(@bbhList) . " BBH results.") if T(3);
3466        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3467        for my $bbhData (@bbhList) {
3468            my ($peg1, $peg2, $score) = @{$bbhData};
3469            if (! exists $retVal{$peg1}) {
3470                $retVal{$peg1} = { $peg2 => $score };
3471            } else {
3472                $retVal{$peg1}->{$peg2} = $score;
3473            }
3474        }
3475        # Return the result.
3476        return \%retVal;
3477    }
3478    
3479    
3480    =head3 SimMatrix
3481    
3482        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3483    
3484    Find all the similarities for the features of a genome in a
3485    specified list of target genomes. The return value will be a hash mapping
3486    features in the original genome to their similarites in the
3487    target genomes.
3488    
3489    =over 4
3490    
3491    =item genomeID
3492    
3493    ID of the genome whose features are to be examined for similarities.
3494    
3495    =item cutoff
3496    
3497    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3498    
3499    =item targets
3500    
3501    List of target genomes. Only pairs originating in the original
3502    genome and landing in one of the target genomes will be returned.
3503    
3504    =item RETURN
3505    
3506    Returns a hash mapping each feature in the original genome to a hash mapping its
3507    similar pegs in the target genomes to their scores.
3508    
3509    =back
3510    
3511    =cut
3512    
3513    sub SimMatrix {
3514        # Get the parameters.
3515        my ($self, $genomeID, $cutoff, @targets) = @_;
3516        # Declare the return variable.
3517        my %retVal = ();
3518        # Get the list of features in the source organism.
3519        my @fids = $self->FeaturesOf($genomeID);
3520        # Ask for the sims. We only want similarities to fig features.
3521        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3522        if (! defined $simList) {
3523            Confess("Unable to retrieve similarities from server.");
3524        } else {
3525            Trace("Processing sims.") if T(3);
3526            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3527            # Create a hash for the target genomes.
3528            my %targetHash = map { $_ => 1 } @targets;
3529            for my $simData (@{$simList}) {
3530                # Get the PEGs and the score.
3531                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3532                # Insure the second ID is in the target list.
3533                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3534                if (exists $targetHash{$genome2}) {
3535                    # Here it is. Now we need to add it to the return hash. How we do that depends
3536                    # on whether or not $peg1 is new to us.
3537                    if (! exists $retVal{$peg1}) {
3538                        $retVal{$peg1} = { $peg2 => $score };
3539                    } else {
3540                        $retVal{$peg1}->{$peg2} = $score;
3541                    }
3542                }
3543            }
3544        }
3545        # Return the result.
3546        return %retVal;
3547    }
3548    
3549    
3550  =head3 LowBBHs  =head3 LowBBHs
3551    
3552  C<< my %bbhMap = $sprout->LowBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3553    
3554  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3555  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 3098  Line 3578 
3578      my ($self, $featureID, $cutoff) = @_;      my ($self, $featureID, $cutoff) = @_;
3579      # Create the return hash.      # Create the return hash.
3580      my %retVal = ();      my %retVal = ();
3581      # Create a query to get the desired BBHs.      # Query for the desired BBHs.
3582      my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],      my $bbhList = FIGRules::BBHData($featureID, $cutoff);
                                 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',  
                                 [$cutoff, $featureID],  
                                 ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);  
3583      # Form the results into the return hash.      # Form the results into the return hash.
3584      for my $pair (@bbhList) {      for my $pair (@$bbhList) {
3585          $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3586            if ($self->Exists('Feature', $fid)) {
3587                $retVal{$fid} = $pair->[1];
3588            }
3589      }      }
3590      # Return the result.      # Return the result.
3591      return %retVal;      return %retVal;
# Line 3113  Line 3593 
3593    
3594  =head3 Sims  =head3 Sims
3595    
3596  C<< my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters); >>      my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3597    
3598  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
3599  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 3123  Line 3603 
3603  Similarities can be either raw or expanded. The raw similarities are basic  Similarities can be either raw or expanded. The raw similarities are basic
3604  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
3605  features considered substantially identical. So, for example, if features B<A1>,  features considered substantially identical. So, for example, if features B<A1>,
3606  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
3607  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]>.
3608    
3609  =over 4  =over 4
3610    
3611  =item fid  =item fid
3612    
3613  ID of the feature whose similarities are desired.  ID of the feature whose similarities are desired, or reference to a list of IDs
3614    of features whose similarities are desired.
3615    
3616  =item maxN  =item maxN
3617    
# Line 3176  Line 3657 
3657      return $retVal;      return $retVal;
3658  }  }
3659    
3660    =head3 IsAllGenomes
3661    
3662        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3663    
3664    Return TRUE if all genomes in the second list are represented in the first list at
3665    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3666    compared to a list of all the genomes.
3667    
3668    =over 4
3669    
3670    =item list
3671    
3672    Reference to the list to be compared to the second list.
3673    
3674    =item checkList (optional)
3675    
3676    Reference to the comparison target list. Every genome ID in this list must occur at
3677    least once in the first list. If this parameter is omitted, a list of all the genomes
3678    is used.
3679    
3680    =item RETURN
3681    
3682    Returns TRUE if every item in the second list appears at least once in the
3683    first list, else FALSE.
3684    
3685    =back
3686    
3687    =cut
3688    
3689    sub IsAllGenomes {
3690        # Get the parameters.
3691        my ($self, $list, $checkList) = @_;
3692        # Supply the checklist if it was omitted.
3693        $checkList = [$self->Genomes()] if ! defined($checkList);
3694        # Create a hash of the original list.
3695        my %testList = map { $_ => 1 } @{$list};
3696        # Declare the return variable. We assume that the representation
3697        # is complete and stop at the first failure.
3698        my $retVal = 1;
3699        my $n = scalar @{$checkList};
3700        for (my $i = 0; $retVal && $i < $n; $i++) {
3701            if (! $testList{$checkList->[$i]}) {
3702                $retVal = 0;
3703            }
3704        }
3705        # Return the result.
3706        return $retVal;
3707    }
3708    
3709  =head3 GetGroups  =head3 GetGroups
3710    
3711  C<< my %groups = $sprout->GetGroups(\@groupList); >>      my %groups = $sprout->GetGroups(\@groupList);
3712    
3713  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.
3714  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 3197  Line 3727 
3727          # Here we have a group list. Loop through them individually,          # Here we have a group list. Loop through them individually,
3728          # getting a list of the relevant genomes.          # getting a list of the relevant genomes.
3729          for my $group (@{$groupList}) {          for my $group (@{$groupList}) {
3730              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3731                  [$group], "Genome(id)");                  [$group], "Genome(id)");
3732              $retVal{$group} = \@genomeIDs;              $retVal{$group} = \@genomeIDs;
3733          }          }
# Line 3205  Line 3735 
3735          # Here we need all of the groups. In this case, we run through all          # Here we need all of the groups. In this case, we run through all
3736          # of the genome records, putting each one found into the appropriate          # of the genome records, putting each one found into the appropriate
3737          # group. Note that we use a filter clause to insure that only genomes          # group. Note that we use a filter clause to insure that only genomes
3738          # in groups are included in the return set.          # in real NMPDR groups are included in the return set.
3739          my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],          my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3740                                      ['Genome(id)', 'Genome(group-name)']);                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3741          # Loop through the genomes found.          # Loop through the genomes found.
3742          for my $genome (@genomes) {          for my $genome (@genomes) {
3743              # Pop this genome's ID off the current list.              # Get the genome ID and group, and add this genome to the group's list.
3744              my @groups = @{$genome};              my ($genomeID, $group) = @{$genome};
3745              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, $genomeID);  
             }  
3746          }          }
3747      }      }
3748      # Return the hash we just built.      # Return the hash we just built.
# Line 3226  Line 3751 
3751    
3752  =head3 MyGenomes  =head3 MyGenomes
3753    
3754  C<< my @genomes = Sprout::MyGenomes($dataDir); >>      my @genomes = Sprout::MyGenomes($dataDir);
3755    
3756  Return a list of the genomes to be included in the Sprout.  Return a list of the genomes to be included in the Sprout.
3757    
# Line 3258  Line 3783 
3783    
3784  =head3 LoadFileName  =head3 LoadFileName
3785    
3786  C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>      my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3787    
3788  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
3789  directory.  directory.
# Line 3299  Line 3824 
3824    
3825  =head3 DeleteGenome  =head3 DeleteGenome
3826    
3827  C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>      my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3828    
3829  Delete a genome from the database.  Delete a genome from the database.
3830    
# Line 3325  Line 3850 
3850      # Get the parameters.      # Get the parameters.
3851      my ($self, $genomeID, $testFlag) = @_;      my ($self, $genomeID, $testFlag) = @_;
3852      # Perform the delete for the genome's features.      # Perform the delete for the genome's features.
3853      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", $testFlag);      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3854      # Perform the delete for the primary genome data.      # Perform the delete for the primary genome data.
3855      my $stats = $self->Delete('Genome', $genomeID, $testFlag);      my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3856      $retVal->Accumulate($stats);      $retVal->Accumulate($stats);
3857      # Return the result.      # Return the result.
3858      return $retVal;      return $retVal;
3859  }  }
3860    
3861    =head3 Fix
3862    
3863        my %fixedHash = $sprout->Fix(%groupHash);
3864    
3865    Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3866    The groups will be combined into the appropriate super-groups.
3867    
3868    =over 4
3869    
3870    =item groupHash
3871    
3872    Hash to be fixed up.
3873    
3874    =item RETURN
3875    
3876    Returns a fixed-up version of the hash.
3877    
3878    =back
3879    
3880    =cut
3881    
3882    sub Fix {
3883        # Get the parameters.
3884        my ($self, %groupHash) = @_;
3885        # Create the result hash.
3886        my %retVal = ();
3887        # Copy over the genomes.
3888        for my $groupID (keys %groupHash) {
3889            # Get the super-group name.
3890            my $realGroupID = $self->SuperGroup($groupID);
3891            # Append this group's genomes into the result hash
3892            # using the super-group name.
3893            push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3894        }
3895        # Return the result hash.
3896        return %retVal;
3897    }
3898    
3899    =head3 GroupPageName
3900    
3901        my $name = $sprout->GroupPageName($group);
3902    
3903    Return the name of the page for the specified NMPDR group.
3904    
3905    =over 4
3906    
3907    =item group
3908    
3909    Name of the relevant group.
3910    
3911    =item RETURN
3912    
3913    Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3914    memory it will be read in.
3915    
3916    =back
3917    
3918    =cut
3919    
3920    sub GroupPageName {
3921        # Get the parameters.
3922        my ($self, $group) = @_;
3923        # Check for the group file data.
3924        my %superTable = $self->CheckGroupFile();
3925        # Compute the real group name.
3926        my $realGroup = $self->SuperGroup($group);
3927        # Get the associated page name.
3928        my $retVal = "../content/$superTable{$realGroup}->{page}";
3929        # Return the result.
3930        return $retVal;
3931    }
3932    
3933    
3934    =head3 AddProperty
3935    
3936        $sprout->AddProperty($featureID, $key, @values);
3937    
3938    Add a new attribute value (Property) to a feature.
3939    
3940    =over 4
3941    
3942    =item peg
3943    
3944    ID of the feature to which the attribute is to be added.
3945    
3946    =item key
3947    
3948    Name of the attribute (key).
3949    
3950    =item values
3951    
3952    Values of the attribute.
3953    
3954    =back
3955    
3956    =cut
3957    #: Return Type ;
3958    sub AddProperty {
3959        # Get the parameters.
3960        my ($self, $featureID, $key, @values) = @_;
3961        # Add the property using the attached attributes object.
3962        $self->ca->AddAttribute($featureID, $key, @values);
3963    }
3964    
3965    =head3 CheckGroupFile
3966    
3967        my %groupData = $sprout->CheckGroupFile();
3968    
3969    Get the group file hash. The group file hash describes the relationship
3970    between a group and the super-group to which it belongs for purposes of
3971    display. The super-group name is computed from the first capitalized word
3972    in the actual group name. For each super-group, the group file contains
3973    the page name and a list of the species expected to be in the group.
3974    Each species is specified by a genus and a species name. A species name
3975    of C<0> implies an entire genus.
3976    
3977    This method returns a hash from super-group names to a hash reference. Each
3978    resulting hash reference contains the following fields.
3979    
3980    =over 4
3981    
3982    =item specials
3983    
3984    Reference to a hash whose keys are the names of special species.
3985    
3986    =item contents
3987    
3988    A list of 2-tuples, each containing a genus name followed by a species name
3989    (or 0, indicating all species). This list indicates which organisms belong
3990    in the super-group.
3991    
3992    =back
3993    
3994    =cut
3995    
3996    sub CheckGroupFile {
3997        # Get the parameters.
3998        my ($self) = @_;
3999        # Check to see if we already have this hash.
4000        if (! defined $self->{groupHash}) {
4001            # We don't, so we need to read it in.
4002            my %groupHash;
4003            # Read the group file.
4004            my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
4005            # Loop through the list of sort-of groups.
4006            for my $groupLine (@groupLines) {
4007                my ($name, $specials, @contents) = split /\t/, $groupLine;
4008                $groupHash{$name} = { specials => { map { $_ => 1 } split /\s*,\s*/, $specials },
4009                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
4010                                    };
4011            }
4012            # Save the hash.
4013            $self->{groupHash} = \%groupHash;
4014        }
4015        # Return the result.
4016        return %{$self->{groupHash}};
4017    }
4018    
4019    =head2 Virtual Methods
4020    
4021    =head3 CleanKeywords
4022    
4023        my $cleanedString = $sprout->CleanKeywords($searchExpression);
4024    
4025    Clean up a search expression or keyword list. This involves converting the periods
4026    in EC numbers to underscores, converting non-leading minus signs to underscores,
4027    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
4028    characters. In addition, any extra spaces are removed.
4029    
4030    =over 4
4031    
4032    =item searchExpression
4033    
4034    Search expression or keyword list to clean. Note that a search expression may
4035    contain boolean operators which need to be preserved. This includes leading
4036    minus signs.
4037    
4038    =item RETURN
4039    
4040    Cleaned expression or keyword list.
4041    
4042    =back
4043    
4044    =cut
4045    
4046    sub CleanKeywords {
4047        # Get the parameters.
4048        my ($self, $searchExpression) = @_;
4049        # Get the stemmer.
4050        my $stemmer = $self->GetStemmer();
4051        # Convert the search expression using the stemmer.
4052        my $retVal = $stemmer->PrepareSearchExpression($searchExpression);
4053        Trace("Cleaned keyword list for \"$searchExpression\" is \"$retVal\".") if T(3);
4054        # Return the result.
4055        return $retVal;
4056    }
4057    
4058    =head3 GetSourceObject
4059    
4060        my $source = $erdb->GetSourceObject();
4061    
4062    Return the object to be used in creating load files for this database.
4063    
4064    =cut
4065    
4066    sub GetSourceObject {
4067        # Get the parameters.
4068        my ($self) = @_;
4069        # Check to see if we already have a source object.
4070        my $retVal = $self->{_fig};
4071        if (! defined $retVal) {
4072            # No, so create one.
4073            require FIG;
4074            $retVal = FIG->new();
4075        }
4076        # Return the object.
4077        return $retVal;
4078    }
4079    
4080    =head3 SectionList
4081    
4082        my @sections = $erdb->SectionList();
4083    
4084    Return a list of the names for the different data sections used when loading this database.
4085    The default is a single string, in which case there is only one section representing the
4086    entire database.
4087    
4088    =cut
4089    
4090    sub SectionList {
4091        # Get the parameters.
4092        my ($self, $source) = @_;
4093        # Ask the BaseSproutLoader for a section list.
4094        require BaseSproutLoader;
4095        my @retVal = BaseSproutLoader::GetSectionList($self);
4096        # Return the list.
4097        return @retVal;
4098    }
4099    
4100    =head3 Loader
4101    
4102        my $groupLoader = $erdb->Loader($groupName, $options);
4103    
4104    Return an [[ERDBLoadGroupPm]] object for the specified load group. This method is used
4105    by [[ERDBGeneratorPl]] to create the load group objects. If you are not using
4106    [[ERDBGeneratorPl]], you don't need to override this method.
4107    
4108    =over 4
4109    
4110    =item groupName
4111    
4112    Name of the load group whose object is to be returned. The group name is
4113    guaranteed to be a single word with only the first letter capitalized.
4114    
4115    =item options
4116    
4117    Reference to a hash of command-line options.
4118    
4119    =item RETURN
4120    
4121    Returns an [[ERDBLoadGroupPm]] object that can be used to process the specified load group
4122    for this database.
4123    
4124    =back
4125    
4126    =cut
4127    
4128    sub Loader {
4129        # Get the parameters.
4130        my ($self, $groupName, $options) = @_;
4131        # Compute the loader name.
4132        my $loaderClass = "${groupName}SproutLoader";
4133        # Pull in its definition.
4134        require "$loaderClass.pm";
4135        # Create an object for it.
4136        my $retVal = eval("$loaderClass->new(\$self, \$options)");
4137        # Insure it worked.
4138        Confess("Could not create $loaderClass object: $@") if $@;
4139        # Return it to the caller.
4140        return $retVal;
4141    }
4142    
4143    
4144    =head3 LoadGroupList
4145    
4146        my @groups = $erdb->LoadGroupList();
4147    
4148    Returns a list of the names for this database's load groups. This method is used
4149    by [[ERDBGeneratorPl]] when the user wishes to load all table groups. The default
4150    is a single group called 'All' that loads everything.
4151    
4152    =cut
4153    
4154    sub LoadGroupList {
4155        # Return the list.
4156        return qw(Genome Subsystem Annotation Property Source Reaction Synonym Feature Drug);
4157    }
4158    
4159    =head3 LoadDirectory
4160    
4161        my $dirName = $erdb->LoadDirectory();
4162    
4163    Return the name of the directory in which load files are kept. The default is
4164    the FIG temporary directory, which is a really bad choice, but it's always there.
4165    
4166    =cut
4167    
4168    sub LoadDirectory {
4169        # Get the parameters.
4170        my ($self) = @_;
4171        # Return the directory name.
4172        return $self->{dataDir};
4173    }
4174    
4175  =head2 Internal Utility Methods  =head2 Internal Utility Methods
4176    
4177    =head3 GetStemmer
4178    
4179        my $stermmer = $sprout->GetStemmer();
4180    
4181    Return the stemmer object for this database.
4182    
4183    =cut
4184    
4185    sub GetStemmer {
4186        # Get the parameters.
4187        my ($self) = @_;
4188        # Declare the return variable.
4189        my $retVal = $self->{stemmer};
4190        if (! defined $retVal) {
4191            # We don't have one pre-built, so we build and save it now.
4192            $retVal = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
4193                                     stops => "$FIG_Config::sproutData/StopWords.txt",
4194                                     cache => 0);
4195            $self->{stemmer} = $retVal;
4196        }
4197        # Return the result.
4198        return $retVal;
4199    }
4200    
4201  =head3 ParseAssignment  =head3 ParseAssignment
4202    
4203  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 3343  Line 4206 
4206    
4207  A functional assignment is always of the form  A functional assignment is always of the form
4208    
4209      C<set >I<YYYY>C< function to\n>I<ZZZZZ>      set YYYY function to
4210        ZZZZ
4211    
4212  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,
4213  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 3389  Line 4253 
4253      }      }
4254      # If we have an assignment, we need to clean the function text. There may be      # If we have an assignment, we need to clean the function text. There may be
4255      # extra junk at the end added as a note from the user.      # extra junk at the end added as a note from the user.
4256      if (@retVal) {      if (defined( $retVal[1] )) {
4257          $retVal[1] =~ s/(\t\S)?\s*$//;          $retVal[1] =~ s/(\t\S)?\s*$//;
4258      }      }
4259      # Return the result list.      # Return the result list.
4260      return @retVal;      return @retVal;
4261  }  }
4262    
4263    =head3 _CheckFeature
4264    
4265        my $flag = $sprout->_CheckFeature($fid);
4266    
4267    Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
4268    
4269    =over 4
4270    
4271    =item fid
4272    
4273    Feature ID to check.
4274    
4275    =item RETURN
4276    
4277    Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE.
4278    
4279    =back
4280    
4281    =cut
4282    
4283    sub _CheckFeature {
4284        # Get the parameters.
4285        my ($self, $fid) = @_;
4286        # Insure we have a genome hash.
4287        my $genomes = $self->_GenomeHash();
4288        # Get the feature's genome ID.
4289        my ($genomeID) = FIGRules::ParseFeatureID($fid);
4290        # Return an indicator of whether or not the genome ID is in the hash.
4291        return ($self->{genomeHash}->{$genomeID} ? 1 : 0);
4292    }
4293    
4294  =head3 FriendlyTimestamp  =head3 FriendlyTimestamp
4295    
4296  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 3422  Line 4317 
4317      return $retVal;      return $retVal;
4318  }  }
4319    
 =head3 AddProperty  
4320    
4321  C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>  =head3 Hint
4322    
4323        my $htmlText = Sprout::Hint($wikiPage, $hintID);
4324    
4325  Add a new attribute value (Property) to a feature. In the SEED system, attributes can  Return the HTML for a help link that displays the specified hint text when it is clicked.
4326  be added to almost any object. In Sprout, they can only be added to features. In  This HTML can be put in forms to provide a useful hinting mechanism.
 Sprout, attributes are implemented using I<properties>. A property represents a key/value  
 pair. If the particular key/value pair coming in is not already in the database, a new  
 B<Property> record is created to hold it.  
4327    
4328  =over 4  =over 4
4329    
4330  =item peg  =item wikiPage
4331    
4332  ID of the feature to which the attribute is to be replied.  Name of the wiki page to be popped up when the hint mark is clicked.
4333    
4334  =item key  =item hintID
4335    
4336  Name of the attribute (key).  ID of the text to display for the hint. This should correspond to a tip number
4337    in the Wiki.
4338    
4339    =item RETURN
4340    
4341    Returns the html for the hint facility. The resulting html shows the word "help" and
4342    uses the standard FIG popup technology.
4343    
4344    =back
4345    
4346    =cut
4347    
4348    sub Hint {
4349        # Get the parameters.
4350        my ($wikiPage, $hintID) = @_;
4351        # Declare the return variable.
4352        my $retVal;
4353        # Convert the wiki page name to a URL.
4354        my $wikiURL;
4355        if ($wikiPage =~ m#/#) {
4356            # Here it's a URL of some sort.
4357            $wikiURL = $wikiPage;
4358        } else {
4359            # Here it's a wiki page.
4360            my $page = join("", map { ucfirst $_ } split /\s+/, $wikiPage);
4361            if ($page =~ /^(.+?)\.(.+)$/) {
4362                $page = "$1/$2";
4363            } else {
4364                $page = "FIG/$page";
4365            }
4366            $wikiURL = "$FIG_Config::cgi_url/wiki/view.cgi/$page";
4367        }
4368        # Is there hint text?
4369        if (! $hintID) {
4370            # No. Create a new-page hint.
4371            $retVal = qq(&nbsp;<a class="hint" onclick="doPagePopup(this, '$wikiURL')">(help)</a>);
4372        } else {
4373            # With hint text, we create a popup window hint. We need to compute the hint URL.
4374            my $tipURL = "$FIG_Config::cgi_url/wiki/view.cgi/FIG/TWikiCustomTip" .
4375                Tracer::Pad($hintID, 3, 1, "0");
4376            # Create a hint pop-up link.
4377            $retVal = qq(&nbsp;<a class="hint" onclick="doHintPopup(this, '$wikiURL', '$tipURL')">(help)</a>);
4378        }
4379        # Return the HTML.
4380        return $retVal;
4381    }
4382    
4383    =head3 _GenomeHash
4384    
4385        my $gHash = $sprout->_GenomeHash();
4386    
4387  =item value  Return a hash mapping all NMPDR genome IDs to [[ERDBObjectPm]] genome objects.
4388    
4389    =cut
4390    
4391    sub _GenomeHash {
4392        # Get the parameters.
4393        my ($self) = @_;
4394        # Do we already have a filled hash?
4395        if (! $self->{genomeHashFilled}) {
4396            # No, create it.
4397            my %gHash = map { $_->PrimaryValue('id') => $_ } $self->GetList("Genome", "", []);
4398            $self->{genomeHash} = \%gHash;
4399            # Denote we have it.
4400            $self->{genomeHashFilled} = 1;
4401        }
4402        # Return the hash.
4403        return $self->{genomeHash};
4404    }
4405    
4406  Value of the attribute.  =head3 _GenomeData
4407    
4408  =item url      my $genomeData = $sprout->_GenomeData($genomeID);
4409    
4410  URL or text citation from which the property was obtained.  Return an [[ERDBObjectPm]] object for the specified genome, or an undefined
4411    value if the genome does not exist.
4412    
4413    =over 4
4414    
4415    =item genomeID
4416    
4417    ID of the desired genome.
4418    
4419    =item RETURN
4420    
4421    Returns either an [[ERDBObjectPm]] containing the genome, or an undefined value.
4422    If the genome exists, it will have been read into the genome cache.
4423    
4424  =back  =back
4425    
4426  =cut  =cut
4427  #: Return Type ;  
4428  sub AddProperty {  sub _GenomeData {
4429      # Get the parameters.      # Get the parameters.
4430      my ($self, $featureID, $key, $value, $url) = @_;      my ($self, $genomeID) = @_;
4431      # Declare the variable to hold the desired property ID.      # Are we in the genome hash?
4432      my $propID;      if (! exists $self->{genomeHash}->{$genomeID} && ! $self->{genomeHashFilled}) {
4433      # Attempt to find a property record for this key/value pair.          # The genome isn't in the hash, and the hash is not complete, so we try to
4434      my @properties = $self->GetFlat(['Property'],          # read it.
4435                                     "Property(property-name) = ? AND Property(property-value) = ?",          $self->{genomeHash}->{$genomeID} = $self->GetEntity(Genome => $genomeID);
                                    [$key, $value], 'Property(id)');  
     if (@properties) {  
         # Here the property is already in the database. We save its ID.  
         $propID = $properties[0];  
         # Here the property value does not exist. We need to generate an ID. It will be set  
         # to a number one greater than the maximum value in the database. This call to  
         # GetAll will stop after one record.  
         my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],  
                                         1);  
         $propID = $maxProperty[0]->[0] + 1;  
         # Insert the new property value.  
         $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });  
4436      }      }
4437      # Now we connect the incoming feature to the property.      # Return the result.
4438      $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });      return $self->{genomeHash}->{$genomeID};
4439  }  }
4440    
4441    =head3 _CacheGenome
4442    
4443        $sprout->_CacheGenome($genomeID, $genomeData);
4444    
4445    Store the specified genome object in the genome cache if it is already there.
4446    
4447    =over 4
4448    
4449    =item genomeID
4450    
4451    ID of the genome to store in the cache.
4452    
4453    =item genomeData
4454    
4455    An [[ERDBObjectPm]] containing at least the data for the specified genome.
4456    Note that the Genome may not be the primary object in it, so a fully-qualified
4457    field name has to be used to retrieve data from it.
4458    
4459    =back
4460    
4461    =cut
4462    
4463    sub _CacheGenome {
4464        # Get the parameters.
4465        my ($self, $genomeID, $genomeData) = @_;
4466        # Only proceed if we don't already have the genome.
4467        if (! exists $self->{genomeHash}->{$genomeID}) {
4468            $self->{genomeHash}->{$genomeID} = $genomeData;
4469        }
4470    }
4471    
4472  1;  1;

Legend:
Removed from v.1.75  
changed lines
  Added in v.1.125

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3