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

Diff of /Sprout/Sprout.pm

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

revision 1.77, Sun Jul 23 16:44:10 2006 UTC revision 1.113, Tue Aug 12 06:01:49 2008 UTC
# Line 1  Line 1 
1  package Sprout;  package Sprout;
2    
     require Exporter;  
     use ERDB;  
     @ISA = qw(Exporter ERDB);  
3      use Data::Dumper;      use Data::Dumper;
4      use strict;      use strict;
     use Carp;  
5      use DBKernel;      use DBKernel;
6      use XML::Simple;      use XML::Simple;
7      use DBQuery;      use DBQuery;
8      use DBObject;      use ERDBObject;
9      use Tracer;      use Tracer;
10      use FIGRules;      use FIGRules;
11      use FidCheck;      use FidCheck;
12      use Stats;      use Stats;
13      use POSIX qw(strftime);      use POSIX qw(strftime);
14      use BasicLocation;      use BasicLocation;
15        use CustomAttributes;
16        use RemoteCustomAttributes;
17        use CGI;
18        use WikiTools;
19        use base qw(ERDB);
20    
21  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
22    
# Line 28  Line 29 
29  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>
30  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>.
31    
32  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' });
33    
34  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
35  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
36  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
37  L</dna_seq> returns the DNA sequence for a specified genome location.  L</DNASeq> returns the DNA sequence for a specified genome location.
38    
39  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.
40    
# Line 45  Line 46 
46    
47  =head3 new  =head3 new
48    
49  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
50    
51  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
52  database definition into memory. The positional first parameter specifies the name of the  database definition into memory. The positional first parameter specifies the name of the
# Line 79  Line 80 
80    
81  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
82    
83    * B<host> name of the database host
84    
85  =back  =back
86    
87  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
88  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
89  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
90    
91  C<< my $sprout = Sprout->new('Sprout', { userData =>; 'fig/admin', dataDir => '/usr/fig/SproutData' }); >>      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });
92    
93  =cut  =cut
94    
95  sub new {  sub new {
96      # Get the parameters.      # Get the parameters.
97      my ($class, $dbName, $options) = @_;      my ($class, $dbName, $options) = @_;
98        # Compute the DBD directory.
99        my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
100                                                      $FIG_Config::fig );
101      # 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
102      # the incoming data.      # the incoming data.
103      my $optionTable = Tracer::GetOptions({      my $optionTable = Tracer::GetOptions({
# Line 99  Line 105 
105                                                          # database type                                                          # database type
106                         dataDir      => $FIG_Config::sproutData,                         dataDir      => $FIG_Config::sproutData,
107                                                          # data file directory                                                          # data file directory
108                         xmlFileName  => "$FIG_Config::fig/SproutDBD.xml",                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
109                                                          # database definition file name                                                          # database definition file name
110                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
111                                                          # user name and password                                                          # user name and password
112                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::dbport,
113                                                          # database connection port                                                          # database connection port
114                         sock         => $FIG_Config::dbsock,                         sock         => $FIG_Config::dbsock,
115                           host         => $FIG_Config::sprout_host,
116                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
117                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
118                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
# Line 118  Line 125 
125      # Connect to the database.      # Connect to the database.
126      my $dbh;      my $dbh;
127      if (! $optionTable->{noDBOpen}) {      if (! $optionTable->{noDBOpen}) {
128            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
129          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
130                                  $password, $optionTable->{port}, undef, $optionTable->{sock});                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
131      }      }
132      # Create the ERDB object.      # Create the ERDB object.
133      my $xmlFileName = "$optionTable->{xmlFileName}";      my $xmlFileName = "$optionTable->{xmlFileName}";
# Line 127  Line 135 
135      # Add the option table and XML file name.      # Add the option table and XML file name.
136      $retVal->{_options} = $optionTable;      $retVal->{_options} = $optionTable;
137      $retVal->{_xmlName} = $xmlFileName;      $retVal->{_xmlName} = $xmlFileName;
138        # Set up space for the group file data.
139        $retVal->{groupHash} = undef;
140        # Set up space for the genome hash. We use this to identify NMPDR genomes.
141        $retVal->{genomeHash} = undef;
142        # Connect to the attributes.
143        if ($FIG_Config::attrURL) {
144            Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
145            $retVal->{_ca} = RemoteCustomAttributes->new($FIG_Config::attrURL);
146        } elsif ($FIG_Config::attrDbName) {
147            Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
148            my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
149            $retVal->{_ca} = CustomAttributes->new(user => $user);
150        }
151        # Insure we have access to the stem module.
152        WikiUse('Lingua::Stem');
153        $retVal->{stemmer} = Lingua::Stem->new();
154        $retVal->{stemmer}->stem_caching({ -level => 2 });
155      # Return it.      # Return it.
156      return $retVal;      return $retVal;
157  }  }
158    
159    =head3 CoreGenomes
160    
161        my @genomes = $sprout->CoreGenomes($scope);
162    
163    Return the IDs of NMPDR genomes in the specified scope.
164    
165    =over 4
166    
167    =item scope
168    
169    Scope of the desired genomes. C<core> covers the original core genomes,
170    C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
171    genomes in the system.
172    
173    =item RETURN
174    
175    Returns a list of the IDs for the genomes in the specified scope.
176    
177    =back
178    
179    =cut
180    
181    sub CoreGenomes {
182        # Get the parameters.
183        my ($self, $scope) = @_;
184        # Declare the return variable.
185        my @retVal = ();
186        # If we want all genomes, then this is easy.
187        if ($scope eq 'all') {
188            @retVal = $self->Genomes();
189        } else {
190            # Here we're dealing with groups. Get the hash of all the
191            # genome groups.
192            my %groups = $self->GetGroups();
193            # Loop through the groups, keeping the ones that we want.
194            for my $group (keys %groups) {
195                # Decide if we want to keep this group.
196                my $keepGroup = 0;
197                if ($scope eq 'nmpdr') {
198                    # NMPDR mode: keep all groups.
199                    $keepGroup = 1;
200                } elsif ($scope eq 'core') {
201                    # CORE mode. Only keep real core groups.
202                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
203                        $keepGroup = 1;
204                    }
205                }
206                # Add this group if we're keeping it.
207                if ($keepGroup) {
208                    push @retVal, @{$groups{$group}};
209                }
210            }
211        }
212        # Return the result.
213        return @retVal;
214    }
215    
216    =head3 SuperGroup
217    
218        my $superGroup = $sprout->SuperGroup($groupName);
219    
220    Return the name of the super-group containing the specified NMPDR genome
221    group. If no appropriate super-group can be found, an error will be
222    thrown.
223    
224    =over 4
225    
226    =item groupName
227    
228    Name of the group whose super-group is desired.
229    
230    =item RETURN
231    
232    Returns the name of the super-group containing the incoming group.
233    
234    =back
235    
236    =cut
237    
238    sub SuperGroup {
239        # Get the parameters.
240        my ($self, $groupName) = @_;
241        # Declare the return variable.
242        my $retVal;
243        # Get the group hash.
244        my %groupHash = $self->CheckGroupFile();
245        # Find the super-group genus.
246        $groupName =~ /([A-Z]\w+)/;
247        my $nameThing = $1;
248        # See if it's directly in the group hash.
249        if (exists $groupHash{$nameThing}) {
250            # Yes, then it's our result.
251            $retVal = $nameThing;
252        } else {
253            # No, so we have to search.
254            for my $superGroup (keys %groupHash) {
255                # Get this super-group's item list.
256                my $list = $groupHash{$superGroup}->{contents};
257                # Search it.
258                if (grep { $_->[0] eq $nameThing } @{$list}) {
259                    $retVal = $superGroup;
260                }
261            }
262            # Make sure we found something.
263            if (! $retVal) {
264                Confess("No super-group found for \"$groupName\".");
265            }
266        }
267        # Return the result.
268        return $retVal;
269    }
270    
271  =head3 MaxSegment  =head3 MaxSegment
272    
273  C<< my $length = $sprout->MaxSegment(); >>      my $length = $sprout->MaxSegment();
274    
275  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
276  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 287 
287    
288  =head3 MaxSequence  =head3 MaxSequence
289    
290  C<< my $length = $sprout->MaxSequence(); >>      my $length = $sprout->MaxSequence();
291    
292  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
293  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 302 
302    
303  =head3 Load  =head3 Load
304    
305  C<< $sprout->Load($rebuild); >>;      $sprout->Load($rebuild);;
306    
307  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.
308    
# Line 205  Line 342 
342    
343  =head3 LoadUpdate  =head3 LoadUpdate
344    
345  C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
346    
347  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
348  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 388 
388              Trace("No load file found for $tableName in $dataDir.") if T(0);              Trace("No load file found for $tableName in $dataDir.") if T(0);
389          } else {          } else {
390              # Attempt to load this table.              # Attempt to load this table.
391              my $result = $self->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
392              # Accumulate the resulting statistics.              # Accumulate the resulting statistics.
393              $retVal->Accumulate($result);              $retVal->Accumulate($result);
394          }          }
# Line 262  Line 399 
399    
400  =head3 GenomeCounts  =head3 GenomeCounts
401    
402  C<< my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete); >>      my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
403    
404  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
405  genomes will be included in the counts.  genomes will be included in the counts.
# Line 307  Line 444 
444    
445  =head3 ContigCount  =head3 ContigCount
446    
447  C<< my $count = $sprout->ContigCount($genomeID); >>      my $count = $sprout->ContigCount($genomeID);
448    
449  Return the number of contigs for the specified genome ID.  Return the number of contigs for the specified genome ID.
450    
# Line 334  Line 471 
471      return $retVal;      return $retVal;
472  }  }
473    
474  =head3 GeneMenu  =head3 GenomeMenu
475    
476  C<< my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params); >>      my $html = $sprout->GenomeMenu(%options);
477    
478  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.
479  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
480  value will be the genome ID. The genomes will be sorted by genus/species name.  B<SearchHelper> class. Eventually, the two will be combined.
481    
482  =over 4  =over 4
483    
484  =item attributes  =item options
485    
486    Optional parameters for the control (see below).
487    
488    =item RETURN
489    
490  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).
491    
492  =item filterString  =back
493    
494  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.  
495    
496  =item params  =over 4
497    
498  Reference to a list of values to be substituted in for the parameter marks in  =item name
 the filter string.  
499    
500  =item RETURN  Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
501    Terrible things will happen if you have two controls with the same name on the same page.
502    
503    =item filter
504    
505    If specified, a filter for the list of genomes to display. The filter should be in the form of a
506    list reference. The first element of the list should be the filter string, and the remaining elements
507    the filter parameters.
508    
509    =item multiSelect
510    
511    If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
512    
513  Returns an HTML select menu with the specified genomes as selectable options.  =item size
514    
515    Number of rows to display in the control. The default is C<10>
516    
517    =item id
518    
519    ID to give this control. The default is the value of the C<name> option. Nothing will work correctly
520    unless this ID is unique.
521    
522    =item selected
523    
524    A comma-delimited list of selected genomes, or a reference to a list of selected genomes. The
525    default is none.
526    
527    =item class
528    
529    If specified, a style class to assign to the genome control.
530    
531  =back  =back
532    
533  =cut  =cut
534    
535  sub GeneMenu {  sub GenomeMenu {
536      # Get the parameters.      # Get the parameters.
537      my ($self, $attributes, $filterString, $params) = @_;      my ($self, %options) = @_;
538      # Start the menu.      # Get the control's name and ID.
539      my $retVal = "<select " .      my $menuName = $options{name} || 'myGenomeControl';
540          join(" ", map { "$_=\"$attributes->{$_}\"" } keys %{$attributes}) .      my $menuID = $options{id} || $menuName;
541          ">\n";      # Compute the IDs for the status display.
542      # Get the genomes.      my $divID = "${menuID}_status";
543      my @genomes = $self->GetAll(['Genome'], $filterString, $params, ['Genome(id)',      my $urlID = "${menuID}_url";
544                                                                       'Genome(genus)',      # Compute the code to show selected genomes in the status area.
545                                                                       'Genome(species)',      my $showSelect = "showSelected('$menuID', '$divID', '$urlID', 1000)";
546                                                                       'Genome(unique-characterization)']);      # Check for single-select or multi-select.
547      # Sort them by name.      my $multiSelect = $options{multiSelect} || 0;
548      my @sorted = sort { lc("$a->[1] $a->[2]") cmp lc("$b->[1] $b->[2]") } @genomes;      # Get the style data.
549      # Loop through the genomes, creating the option tags.      my $class = $options{class} || '';
550      for my $genomeData (@sorted) {      # Get the list of pre-selected items.
551          # Get the data for this genome.      my $selections = $options{selected} || [];
552          my ($genomeID, $genus, $species, $strain) = @{$genomeData};      if (ref $selections ne 'ARRAY') {
553          # Get the contig count.          $selections = [ split /\s*,\s*/, $selections ];
554          my $count = $self->ContigCount($genomeID);      }
555          my $counting = ($count == 1 ? "contig" : "contigs");      my %selected = map { $_ => 1 } @{$selections};
556          # Build the option tag.      # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
557          $retVal .= "<option value=\"$genomeID\">$genus $species $strain ($genomeID) [$count $counting]</option>\n";      # string or a list reference.
558          Trace("Option tag built for $genomeID: $genus $species $strain.") if T(3);      my $filterParms = $options{filter} || "";
559        if (! ref $filterParms) {
560            $filterParms = [split /\t|\\t/, $filterParms];
561        }
562        my $filterString = shift @{$filterParms};
563        # Get a list of all the genomes in group order. In fact, we only need them ordered
564        # by name (genus,species,strain), but putting primary-group in front enables us to
565        # take advantage of an existing index.
566        my @genomeList = $self->GetAll(['Genome'], "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
567                                       $filterParms,
568                                       [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
569        # Create a hash to organize the genomes by group. Each group will contain a list of
570        # 2-tuples, the first element being the genome ID and the second being the genome
571        # name.
572        my %gHash = ();
573        for my $genome (@genomeList) {
574            # Get the genome data.
575            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
576            # Compute its name. This is the genus, species, strain (if any), and the contig count.
577            my $name = "$genus $species ";
578            $name .= "$strain " if $strain;
579            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
580            # Now we get the domain. The domain tells us the display style of the organism.
581            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
582            # Now compute the display group. This is normally the primary group, but if the
583            # organism is supporting, we blank it out.
584            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
585            # Push the genome into the group's list. Note that we use the real group
586            # name for the hash key here, not the display group name.
587            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
588        }
589        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
590        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
591        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
592        # that aren't "other". At some point, we will want to make this less complicated.
593        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
594                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
595        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
596        # Remember the number of NMPDR groups.
597        my $nmpdrGroupCount = scalar @groups;
598        # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
599        # of the domains found.
600        my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
601        my @domains = ();
602        for my $genomeData (@otherGenomes) {
603            my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
604            if (exists $gHash{$domain}) {
605                push @{$gHash{$domain}}, $genomeData;
606            } else {
607                $gHash{$domain} = [$genomeData];
608                push @domains, $domain;
609            }
610        }
611        # Add the domain groups at the end of the main group list. The main group list will now
612        # contain all the categories we need to display the genomes.
613        push @groups, sort @domains;
614        # Delete the supporting group.
615        delete $gHash{$FIG_Config::otherGroup};
616        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
617        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
618        # and use that to make the selections.
619        my $nmpdrCount = 0;
620        # Create the type counters.
621        my $groupCount = 1;
622        # Get the number of rows to display.
623        my $rows = $options{size} || 10;
624        # If we're multi-row, create an onChange event.
625        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
626        # Set up the multiple-select flag.
627        my $multipleTag = ($multiSelect ? " multiple" : "" );
628        # Set up the style class.
629        my $classTag = ($class ? " class=\"$class\"" : "" );
630        # Create the SELECT tag and stuff it into the output array.
631        my @lines = ("<SELECT name=\"$menuID\" id=\"$menuID\" $onChangeTag$multipleTag$classTag size=\"$rows\">");
632        # Loop through the groups.
633        for my $group (@groups) {
634            # Get the genomes in the group.
635            for my $genome (@{$gHash{$group}}) {
636                # If this is an NMPDR organism, we add an extra style and count it.
637                my $nmpdrStyle = "";
638                if ($nmpdrGroupCount > 0) {
639                    $nmpdrCount++;
640                    $nmpdrStyle = " Core";
641                }
642                # Get the organism ID, name, contig count, and domain.
643                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
644                # See if we're pre-selected.
645                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
646                # Compute the display name.
647                my $nameString = "$name ($genomeID$contigCount)";
648                # Generate the option tag.
649                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
650                push @lines, "    $optionTag";
651            }
652            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
653            # groups.
654            $nmpdrGroupCount--;
655      }      }
656      # Close the SELECT tag.      # Close the SELECT tag.
657      $retVal .= "</select>\n";      push @lines, "</SELECT>";
658        if ($rows > 1) {
659            # We're in a non-compact mode, so we need to add some selection helpers. First is
660            # the search box. This allows the user to type text and change which genomes are
661            # displayed. For multiple-select mode, we include a button that selects the displayed
662            # genes. For single-select mode, we use a plain label instead.
663            my $searchThingName = "${menuID}_SearchThing";
664            my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"
665                                                 : "Show genomes containing");
666            push @lines, "<br />$searchThingLabel&nbsp;" .
667                         "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />";
668            # For multi-select mode, we also have buttons to set and clear selections.
669            if ($multiSelect) {
670                push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll('$menuID'); $showSelect\" />";
671                push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll('$menuID'); $showSelect\" />";
672                push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome('$menuID', $nmpdrCount, true); $showSelect;\" />";
673            }
674            # Add a hidden field we can use to generate organism page hyperlinks.
675            push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/seedviewer.cgi?page=Organism;organism=\" />";
676            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
677            push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";
678        }
679        # Assemble all the lines into a string.
680        my $retVal = join("\n", @lines, "");
681        # Return the result.
682        return $retVal;
683    }
684    
685    
686    =head3 Stem
687    
688        my $stem = $sprout->Stem($word);
689    
690    Return the stem of the specified word, or C<undef> if the word is not
691    stemmable. Note that even if the word is stemmable, the stem may be
692    the same as the original word.
693    
694    =over 4
695    
696    =item word
697    
698    Word to convert into a stem.
699    
700    =item RETURN
701    
702    Returns a stem of the word (which may be the word itself), or C<undef> if
703    the word is not stemmable.
704    
705    =back
706    
707    =cut
708    
709    sub Stem {
710        # Get the parameters.
711        my ($self, $word) = @_;
712        # Declare the return variable.
713        my $retVal;
714        # See if it's stemmable.
715        if ($word =~ /^[A-Za-z]+$/) {
716            # Compute the stem.
717            my $stemList = $self->{stemmer}->stem($word);
718            my $stem = $stemList->[0];
719            # Check to see if it's long enough.
720            if (length $stem >= 3) {
721                # Yes, keep it.
722                $retVal = $stem;
723            } else {
724                # No, use the original word.
725                $retVal = $word;
726            }
727        }
728      # Return the result.      # Return the result.
729      return $retVal;      return $retVal;
730  }  }
731    
732    
733  =head3 Build  =head3 Build
734    
735  C<< $sprout->Build(); >>      $sprout->Build();
736    
737  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.
738  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 749 
749    
750  =head3 Genomes  =head3 Genomes
751    
752  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
753    
754  Return a list of all the genome IDs.  Return a list of all the genome IDs.
755    
# Line 432  Line 766 
766    
767  =head3 GenusSpecies  =head3 GenusSpecies
768    
769  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
770    
771  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
772    
# Line 464  Line 798 
798    
799  =head3 FeaturesOf  =head3 FeaturesOf
800    
801  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
802    
803  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
804    
# Line 509  Line 843 
843    
844  =head3 FeatureLocation  =head3 FeatureLocation
845    
846  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
847    
848  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
849  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 867 
867  =item RETURN  =item RETURN
868    
869  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
870  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
871    wasn't found.
872    
873  =back  =back
874    
875  =cut  =cut
876  #: Return Type @;  
 #: Return Type $;  
877  sub FeatureLocation {  sub FeatureLocation {
878      # Get the parameters.      # Get the parameters.
879      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
880      # 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.  
881      my @retVal = ();      my @retVal = ();
882      # Set up the variables used to determine if we have adjacent segments. This initial setup will      # Get the feature record.
883      # not match anything.      my $object = $self->GetEntity('Feature', $featureID);
884      my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);      # Only proceed if we found it.
885      # Loop through the query results, creating location specifiers.      if (defined $object) {
886      while (my $location = $query->Fetch()) {          # Get the location string.
887          # Get the location parameters.          my $locString = $object->PrimaryValue('Feature(location-string)');
888          my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',          # Create the return list.
889              '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$len";  
890      }      }
891      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
892      return (wantarray ? @retVal : join(',', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
# Line 588  Line 894 
894    
895  =head3 ParseLocation  =head3 ParseLocation
896    
897  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
898    
899  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
900  length.  length.
# Line 607  Line 913 
913  =back  =back
914    
915  =cut  =cut
916  #: Return Type @;  
917  sub ParseLocation {  sub ParseLocation {
918      # 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
919      # the first parameter.      # the first parameter.
# Line 630  Line 936 
936      return ($contigID, $start, $dir, $len);      return ($contigID, $start, $dir, $len);
937  }  }
938    
939    
940    
941  =head3 PointLocation  =head3 PointLocation
942    
943  C<< my $found = Sprout::PointLocation($location, $point); >>      my $found = Sprout::PointLocation($location, $point);
944    
945  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
946  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 969 
969  =back  =back
970    
971  =cut  =cut
972  #: Return Type $;  
973  sub PointLocation {  sub PointLocation {
974      # 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
975      # the first parameter.      # the first parameter.
# Line 684  Line 992 
992    
993  =head3 DNASeq  =head3 DNASeq
994    
995  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
996    
997  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
998  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 1076 
1076    
1077  =head3 AllContigs  =head3 AllContigs
1078    
1079  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1080    
1081  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1082    
# Line 798  Line 1106 
1106    
1107  =head3 GenomeLength  =head3 GenomeLength
1108    
1109  C<< my $length = $sprout->GenomeLength($genomeID); >>      my $length = $sprout->GenomeLength($genomeID);
1110    
1111  Return the length of the specified genome in base pairs.  Return the length of the specified genome in base pairs.
1112    
# Line 833  Line 1141 
1141    
1142  =head3 FeatureCount  =head3 FeatureCount
1143    
1144  C<< my $count = $sprout->FeatureCount($genomeID, $type); >>      my $count = $sprout->FeatureCount($genomeID, $type);
1145    
1146  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.
1147    
# Line 868  Line 1176 
1176    
1177  =head3 GenomeAssignments  =head3 GenomeAssignments
1178    
1179  C<< my $fidHash = $sprout->GenomeAssignments($genomeID); >>      my $fidHash = $sprout->GenomeAssignments($genomeID);
1180    
1181  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
1182  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 1202 
1202      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
1203      # Declare the return variable.      # Declare the return variable.
1204      my $retVal = {};      my $retVal = {};
1205      # Query the genome's features and annotations. We'll put the oldest annotations      # Query the genome's features.
1206      # 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 = $self->Get(['HasFeature', 'IsTargetOfAnnotation', 'Annotation'],  
                            "HasFeature(from-link) = ? ORDER BY Annotation(time)",  
1207                             [$genomeID]);                             [$genomeID]);
1208      # Loop through the annotations.      # Loop through the features.
1209      while (my $data = $query->Fetch) {      while (my $data = $query->Fetch) {
1210          # Get the feature ID and annotation text.          # Get the feature ID and assignment.
1211          my ($fid, $annotation) = $data->Values(['HasFeature(to-link)',          my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
1212                                                  'Annotation(annotation)']);          if ($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.  
1213              $retVal->{$fid} = $assignment;              $retVal->{$fid} = $assignment;
1214          }          }
1215      }      }
# Line 920  Line 1219 
1219    
1220  =head3 ContigLength  =head3 ContigLength
1221    
1222  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->ContigLength($contigID);
1223    
1224  Compute the length of a contig.  Compute the length of a contig.
1225    
# Line 959  Line 1258 
1258    
1259  =head3 ClusterPEGs  =head3 ClusterPEGs
1260    
1261  C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>      my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1262    
1263  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
1264  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
1265  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
1266  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
1267  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
1268  sequence.  appear in the output sequence.
1269    
1270  =over 4  =over 4
1271    
# Line 1007  Line 1306 
1306    
1307  =head3 GenesInRegion  =head3 GenesInRegion
1308    
1309  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1310    
1311  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1312    
# Line 1036  Line 1335 
1335  =back  =back
1336    
1337  =cut  =cut
1338  #: Return Type @@;  
1339  sub GenesInRegion {  sub GenesInRegion {
1340      # Get the parameters.      # Get the parameters.
1341      my ($self, $contigID, $start, $stop) = @_;      my ($self, $contigID, $start, $stop) = @_;
1342      # Get the maximum segment length.      # Get the maximum segment length.
1343      my $maximumSegmentLength = $self->MaxSegment;      my $maximumSegmentLength = $self->MaxSegment;
     # Create a hash to receive the feature list. We use a hash so that we can eliminate  
     # duplicates easily. The hash key will be the feature ID. The value will be a two-element  
     # containing the minimum and maximum offsets. We will use the offsets to sort the results  
     # when we're building the result set.  
     my %featuresFound = ();  
1344      # Prime the values we'll use for the returned beginning and end.      # Prime the values we'll use for the returned beginning and end.
1345      my @initialMinMax = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
1346      my ($min, $max) = @initialMinMax;      my ($min, $max) = @initialMinMax;
1347      # Create a table of parameters for each query. Each query looks for features travelling in      # Get the overlapping features.
1348        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1349        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1350        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1351        # of the feature's locations.
1352        my %featureMap = ();
1353        # Loop through them to do the begin/end analysis.
1354        for my $featureObject (@featureObjects) {
1355            # Get the feature's location string. This may contain multiple actual locations.
1356            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1357            my @locationSegments = split /\s*,\s*/, $locations;
1358            # Loop through the locations.
1359            for my $locationSegment (@locationSegments) {
1360                # Construct an object for the location.
1361                my $locationObject = BasicLocation->new($locationSegment);
1362                # Merge the current segment's begin and end into the min and max.
1363                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1364                my ($beg, $end);
1365                if (exists $featureMap{$fid}) {
1366                    ($beg, $end) = @{$featureMap{$fid}};
1367                    $beg = $left if $left < $beg;
1368                    $end = $right if $right > $end;
1369                } else {
1370                    ($beg, $end) = ($left, $right);
1371                }
1372                $min = $beg if $beg < $min;
1373                $max = $end if $end > $max;
1374                # Store the feature's new extent back into the hash table.
1375                $featureMap{$fid} = [$beg, $end];
1376            }
1377        }
1378        # Now we must compute the list of the IDs for the features found. We start with a list
1379        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1380        # but the result of the sort will be the same.)
1381        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1382        # Now we sort by midpoint and yank out the feature IDs.
1383        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1384        # Return it along with the min and max.
1385        return (\@retVal, $min, $max);
1386    }
1387    
1388    =head3 GeneDataInRegion
1389    
1390        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1391    
1392    List the features which overlap a specified region in a contig.
1393    
1394    =over 4
1395    
1396    =item contigID
1397    
1398    ID of the contig containing the region of interest.
1399    
1400    =item start
1401    
1402    Offset of the first residue in the region of interest.
1403    
1404    =item stop
1405    
1406    Offset of the last residue in the region of interest.
1407    
1408    =item RETURN
1409    
1410    Returns a list of B<ERDBObjects> for the desired features. Each object will
1411    contain a B<Feature> record.
1412    
1413    =back
1414    
1415    =cut
1416    
1417    sub GeneDataInRegion {
1418        # Get the parameters.
1419        my ($self, $contigID, $start, $stop) = @_;
1420        # Get the maximum segment length.
1421        my $maximumSegmentLength = $self->MaxSegment;
1422        # Create a hash to receive the feature list. We use a hash so that we can eliminate
1423        # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1424        # ERDBObject from the query.
1425        my %featuresFound = ();
1426        # Create a table of parameters for the queries. Each query looks for features travelling in
1427      # 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,
1428      # 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
1429      # 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 1432 
1432      # Loop through the query parameters.      # Loop through the query parameters.
1433      for my $parms (values %queryParms) {      for my $parms (values %queryParms) {
1434          # Create the query.          # Create the query.
1435          my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1436              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1437              $parms);              $parms);
1438          # Loop through the feature segments found.          # Loop through the feature segments found.
1439          while (my $segment = $query->Fetch) {          while (my $segment = $query->Fetch) {
1440              # Get the data about this segment.              # Get the data about this segment.
1441              my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1442                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1443              # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1444              # this will be the case if the segment is the maximum length, so to fine-tune              # this will be the case if the segment is the maximum length, so to fine-tune
1445              # the results we insure that the inequality from the query holds using the actual              # the results we insure that the inequality from the query holds using the actual
1446              # length.              # length.
1447              my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1448              if ($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.  
                     $found = 1;  
                 }  
             }  
1449              if ($found) {              if ($found) {
1450                  # Here we need to record the feature and update the minima and maxima. First,                  # Save this feature in the result list.
1451                  # 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;  
                 }  
                 # Store the entry back into the hash table.  
                 $featuresFound{$featureID} = [$loc1, $loc2];  
1452              }              }
1453          }          }
1454      }      }
1455      # Now we must compute the list of the IDs for the features found. We start with a list      # Return the ERDB objects for the features found.
1456      # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,      return values %featuresFound;
     # but the result of the sort will be the same.)  
     my @list = map { [$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);  
1457  }  }
1458    
1459  =head3 FType  =head3 FType
1460    
1461  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1462    
1463  Return the type of a feature.  Return the type of a feature.
1464    
# Line 1149  Line 1488 
1488    
1489  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1490    
1491  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1492    
1493  Return the annotations of a feature.  Return the annotations of a feature.
1494    
# Line 1212  Line 1551 
1551    
1552  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1553    
1554  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1555    
1556  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
1557  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 1606 
1606    
1607  =head3 FunctionOf  =head3 FunctionOf
1608    
1609  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1610    
1611  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1612    
1613  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
1614  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
1615  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.  
1616    
1617  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
1618  recent one by at least one of the trusted users. If no trusted user list is available, then  recent one by at least one of the trusted users. If no trusted user list is available, then
# Line 1295  Line 1631 
1631    
1632  =item userID (optional)  =item userID (optional)
1633    
1634  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
1635  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1636    
1637  =item RETURN  =item RETURN
1638    
# Line 1313  Line 1649 
1649      my $retVal;      my $retVal;
1650      # Determine the ID type.      # Determine the ID type.
1651      if ($featureID =~ m/^fig\|/) {      if ($featureID =~ m/^fig\|/) {
1652          # Here we have a FIG feature ID. We must build the list of trusted          # Here we have a FIG feature ID.
1653          # users.          if (!$userID) {
1654                # Use the primary assignment.
1655                ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);
1656            } else {
1657                # We must build the list of trusted users.
1658          my %trusteeTable = ();          my %trusteeTable = ();
1659          # Check the user ID.          # Check the user ID.
1660          if (!$userID) {          if (!$userID) {
# Line 1357  Line 1697 
1697                  }                  }
1698              }              }
1699          }          }
1700            }
1701      } else {      } else {
1702          # Here we have a non-FIG feature ID. In this case the user ID does not          # Here we have a non-FIG feature ID. In this case the user ID does not
1703          # matter. We simply get the information from the External Alias Function          # matter. We simply get the information from the External Alias Function
# Line 1369  Line 1710 
1710    
1711  =head3 FunctionsOf  =head3 FunctionsOf
1712    
1713  C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>      my @functionList = $sprout->FunctionOf($featureID, $userID);
1714    
1715  Return the functional assignments of a particular feature.  Return the functional assignments of a particular feature.
1716    
# Line 1441  Line 1782 
1782    
1783  =head3 BBHList  =head3 BBHList
1784    
1785  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1786    
1787  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
1788  on a specified target genome.  on a specified target genome.
# Line 1472  Line 1813 
1813      my %retVal = ();      my %retVal = ();
1814      # Loop through the incoming features.      # Loop through the incoming features.
1815      for my $featureID (@{$featureList}) {      for my $featureID (@{$featureList}) {
1816          # Create a query to get the feature's best hit.          # Ask the server for the feature's best hit.
1817          my $query = $self->Get(['IsBidirectionalBestHitOf'],          my @bbhData = FIGRules::BBHData($featureID);
                                "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",  
                                [$featureID, $genomeID]);  
1818          # Peel off the BBHs found.          # Peel off the BBHs found.
1819          my @found = ();          my @found = ();
1820          while (my $bbh = $query->Fetch) {          for my $bbh (@bbhData) {
1821              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');              my $fid = $bbh->[0];
1822                my $bbGenome = $self->GenomeOf($fid);
1823                if ($bbGenome eq $genomeID) {
1824                    push @found, $fid;
1825                }
1826          }          }
1827          $retVal{$featureID} = \@found;          $retVal{$featureID} = \@found;
1828      }      }
# Line 1489  Line 1832 
1832    
1833  =head3 SimList  =head3 SimList
1834    
1835  C<< my %similarities = $sprout->SimList($featureID, $count); >>      my %similarities = $sprout->SimList($featureID, $count);
1836    
1837  Return a list of the similarities to the specified feature.  Return a list of the similarities to the specified feature.
1838    
1839  Sprout does not support real similarities, so this method just returns the bidirectional  This method just returns the bidirectional best hits for performance reasons.
 best hits.  
1840    
1841  =over 4  =over 4
1842    
# Line 1514  Line 1856 
1856      # Get the parameters.      # Get the parameters.
1857      my ($self, $featureID, $count) = @_;      my ($self, $featureID, $count) = @_;
1858      # Ask for the best hits.      # Ask for the best hits.
1859      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);  
1860      # Create the return value.      # Create the return value.
1861      my %retVal = ();      my %retVal = ();
1862      for my $tuple (@lists) {      for my $tuple (@lists) {
# Line 1527  Line 1866 
1866      return %retVal;      return %retVal;
1867  }  }
1868    
   
   
1869  =head3 IsComplete  =head3 IsComplete
1870    
1871  C<< my $flag = $sprout->IsComplete($genomeID); >>      my $flag = $sprout->IsComplete($genomeID);
1872    
1873  Return TRUE if the specified genome is complete, else FALSE.  Return TRUE if the specified genome is complete, else FALSE.
1874    
# Line 1559  Line 1896 
1896      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->GetEntity('Genome', $genomeID);
1897      if ($genomeData) {      if ($genomeData) {
1898          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1899          ($retVal) = $genomeData->Value('Genome(complete)');          $retVal = $genomeData->PrimaryValue('Genome(complete)');
1900      }      }
1901      # Return the result.      # Return the result.
1902      return $retVal;      return $retVal;
# Line 1567  Line 1904 
1904    
1905  =head3 FeatureAliases  =head3 FeatureAliases
1906    
1907  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1908    
1909  Return a list of the aliases for a specified feature.  Return a list of the aliases for a specified feature.
1910    
# Line 1590  Line 1927 
1927      # Get the parameters.      # Get the parameters.
1928      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1929      # Get the desired feature's aliases      # Get the desired feature's aliases
1930      my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
1931      # Return the result.      # Return the result.
1932      return @retVal;      return @retVal;
1933  }  }
1934    
1935  =head3 GenomeOf  =head3 GenomeOf
1936    
1937  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $genomeID = $sprout->GenomeOf($featureID);
1938    
1939  Return the genome that contains a specified feature or contig.  Return the genome that contains a specified feature or contig.
1940    
# Line 1619  Line 1956 
1956  sub GenomeOf {  sub GenomeOf {
1957      # Get the parameters.      # Get the parameters.
1958      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]);  
1959      # Declare the return value.      # Declare the return value.
1960      my $retVal;      my $retVal;
1961      # Get the genome ID.      # Parse the genome ID from the feature ID.
1962      if (my $relationship = $query->Fetch()) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
1963          ($retVal) = $relationship->Value('HasContig(from-link)');          $retVal = $1;
1964        } else {
1965            # Find the feature by alias.
1966            my ($realFeatureID) = $self->FeaturesByAlias($featureID);
1967            if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {
1968                $retVal = $1;
1969            } else {
1970                # Use the external table.
1971                my ($org) = $self->GetFlat(['ExternalAliasOrg'], "ExternalAliasOrg(id) = ?",
1972                                           [$featureID], "ExternalAliasOrg(org)");
1973                if ($org) {
1974                    $retVal = $org;
1975                } else {
1976                    Confess("Invalid feature ID $featureID.");
1977                }
1978            }
1979      }      }
1980      # Return the value found.      # Return the value found.
1981      return $retVal;      return $retVal;
# Line 1634  Line 1983 
1983    
1984  =head3 CoupledFeatures  =head3 CoupledFeatures
1985    
1986  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
1987    
1988  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
1989  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 2005 
2005  sub CoupledFeatures {  sub CoupledFeatures {
2006      # Get the parameters.      # Get the parameters.
2007      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2008        # Ask the coupling server for the data.
2009      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
2010      # Create a query to retrieve the functionally-coupled features.      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
2011      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
2012                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);      # Form them into a hash.
     # This value will be set to TRUE if we find at least one coupled feature.  
     my $found = 0;  
     # Create the return hash.  
2013      my %retVal = ();      my %retVal = ();
2014      # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
2015      while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
2016          # Get the ID and score of the coupling.          my ($featureID2, $score) = @{$pair};
2017          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',          # Only proceed if the feature is in NMPDR.
2018                                                          'Coupling(score)']);          if ($self->_CheckFeature($featureID2)) {
2019          Trace("$featureID coupled with score $score to ID $couplingID.") if T(coupling => 4);              $retVal{$featureID2} = $score;
2020          # Get the other feature that participates in the coupling.          }
         my ($otherFeatureID) = $self->GetFlat(['ParticipatesInCoupling'],  
                                            "ParticipatesInCoupling(to-link) = ? AND ParticipatesInCoupling(from-link) <> ?",  
                                            [$couplingID, $featureID], 'ParticipatesInCoupling(from-link)');  
         Trace("$couplingID target feature is $otherFeatureID.") if T(coupling => 4);  
         # Attach the other feature's score to its ID.  
         $retVal{$otherFeatureID} = $score;  
         $found = 1;  
2021      }      }
2022      # Functional coupling is reflexive. If we found at least one coupled feature, we must add      # Functional coupling is reflexive. If we found at least one coupled feature, we must add
2023      # the incoming feature as well.      # the incoming feature as well.
2024      if ($found) {      if (keys %retVal) {
2025          $retVal{$featureID} = 9999;          $retVal{$featureID} = 9999;
2026      }      }
2027      # Return the hash.      # Return the hash.
# Line 1690  Line 2030 
2030    
2031  =head3 CouplingEvidence  =head3 CouplingEvidence
2032    
2033  C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>      my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
2034    
2035  Return the evidence for a functional coupling.  Return the evidence for a functional coupling.
2036    
# Line 1738  Line 2078 
2078      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
2079      # Declare the return variable.      # Declare the return variable.
2080      my @retVal = ();      my @retVal = ();
2081      # Our first task is to find out the nature of the coupling: whether or not      # Get the coupling and evidence data.
2082      # it exists, its score, and whether the features are stored in the same      my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
2083      # order as the ones coming in.      # Loop through the raw data, saving the ones that are in NMPDR genomes.
2084      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);      for my $rawTuple (@rawData) {
2085      # Only proceed if a coupling exists.          if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
2086      if ($couplingID) {              push @retVal, $rawTuple;
         # Determine the ordering to place on the evidence items. If we're  
         # inverted, we want to see feature 2 before feature 1 (descending); otherwise,  
         # we want feature 1 before feature 2 (normal).  
         Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);  
         my $ordering = ($inverted ? "DESC" : "");  
         # Get the coupling evidence.  
         my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],  
                                           "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",  
                                           [$couplingID],  
                                           ['PCH(used)', 'UsesAsEvidence(to-link)']);  
         # Loop through the evidence items. Each piece of evidence is represented by two  
         # positions in the evidence list, one for each feature on the other side of the  
         # evidence link. If at some point we want to generalize to couplings with  
         # more than two positions, this section of code will need to be re-done.  
         while (@evidenceList > 0) {  
             my $peg1Data = shift @evidenceList;  
             my $peg2Data = shift @evidenceList;  
             Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);  
             push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];  
         }  
         Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);  
     }  
     # Return the result.  
     return @retVal;  
2087  }  }
   
 =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 $peg1.") if T(Coupling => 4);  
2088      }      }
2089      # Return the result.      # Return the result.
2090      return ($retVal, $inverted, $score);      return @retVal;
2091  }  }
2092    
2093  =head3 GetSynonymGroup  =head3 GetSynonymGroup
2094    
2095  C<< my $id = $sprout->GetSynonymGroup($fid); >>      my $id = $sprout->GetSynonymGroup($fid);
2096    
2097  Return the synonym group name for the specified feature.  Return the synonym group name for the specified feature.
2098    
# Line 1869  Line 2131 
2131    
2132  =head3 GetBoundaries  =head3 GetBoundaries
2133    
2134  C<< my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList); >>      my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2135    
2136  Determine the begin and end boundaries for the locations in a list. All of the  Determine the begin and end boundaries for the locations in a list. All of the
2137  locations must belong to the same contig and have mostly the same direction in  locations must belong to the same contig and have mostly the same direction in
# Line 1931  Line 2193 
2193      return ($contig, $beg, $end);      return ($contig, $beg, $end);
2194  }  }
2195    
 =head3 CouplingID  
   
 C<< my $couplingID = $sprout->CouplingID($peg1, $peg2); >>  
   
 Return the coupling ID for a pair of feature IDs.  
   
 The coupling ID is currently computed by joining the feature IDs in  
 sorted order with a space. Client modules (that is, modules which  
 use Sprout) should not, however, count on this always being the  
 case. This method provides a way for abstracting the concept of a  
 coupling ID. All that we know for sure about it is that it can be  
 generated easily from the feature IDs and the order of the IDs  
 in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>  
 will have the same value as C<CouplingID("b1", "a1")>.  
   
 =over 4  
   
 =item peg1  
   
 First feature of interest.  
   
 =item peg2  
   
 Second feature of interest.  
   
 =item RETURN  
   
 Returns the ID that would be used to represent a functional coupling of  
 the two specified PEGs.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub CouplingID {  
     my ($self, @pegs) = @_;  
     return $self->DigestKey(join " ", sort @pegs);  
 }  
   
2196  =head3 ReadFasta  =head3 ReadFasta
2197    
2198  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2199    
2200  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
2201  one or more lines of data. The first line begins with a > character and contains an ID.  one or more lines of data. The first line begins with a > character and contains an ID.
# Line 2038  Line 2261 
2261    
2262  =head3 FormatLocations  =head3 FormatLocations
2263    
2264  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2265    
2266  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
2267  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 2103  Line 2326 
2326    
2327  =head3 DumpData  =head3 DumpData
2328    
2329  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2330    
2331  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.
2332    
# Line 2120  Line 2343 
2343    
2344  =head3 XMLFileName  =head3 XMLFileName
2345    
2346  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2347    
2348  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2349    
# Line 2131  Line 2354 
2354      return $self->{_xmlName};      return $self->{_xmlName};
2355  }  }
2356    
2357  =head3 Insert  =head3 GetGenomeNameData
2358    
2359  C<< $sprout->Insert($objectType, \%fieldHash); >>      my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2360    
2361    Return the genus, species, and unique characterization for a genome. This
2362    is similar to L</GenusSpecies>, with the exception that it returns the
2363    values in three seperate fields.
2364    
2365    =over 4
2366    
2367    =item genomeID
2368    
2369    ID of the genome whose name data is desired.
2370    
2371    =item RETURN
2372    
2373    Returns a three-element list, consisting of the genus, species, and strain
2374    of the specified genome. If the genome is not found, an error occurs.
2375    
2376    =back
2377    
2378    =cut
2379    
2380    sub GetGenomeNameData {
2381        # Get the parameters.
2382        my ($self, $genomeID) = @_;
2383        # Get the desired values.
2384        my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>
2385                                                                [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);
2386        # Throw an error if they were not found.
2387        if (! defined $genus) {
2388            Confess("Genome $genomeID not found in database.");
2389        }
2390        # Return the results.
2391        return ($genus, $species, $strain);
2392    }
2393    
2394    =head3 GetGenomeByNameData
2395    
2396        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2397    
2398    Return a list of the IDs of the genomes with the specified genus,
2399    species, and strain. In almost every case, there will be either zero or
2400    one IDs returned; however, two or more IDs could be returned if there are
2401    multiple versions of the genome in the database.
2402    
2403    =over 4
2404    
2405    =item genus
2406    
2407    Genus of the desired genome.
2408    
2409    =item species
2410    
2411    Species of the desired genome.
2412    
2413    =item strain
2414    
2415    Strain (unique characterization) of the desired genome. This may be an empty
2416    string, in which case it is presumed that the desired genome has no strain
2417    specified.
2418    
2419    =item RETURN
2420    
2421    Returns a list of the IDs of the genomes having the specified genus, species, and
2422    strain.
2423    
2424    =back
2425    
2426    =cut
2427    
2428    sub GetGenomeByNameData {
2429        # Get the parameters.
2430        my ($self, $genus, $species, $strain) = @_;
2431        # Try to find the genomes.
2432        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2433                                    [$genus, $species, $strain], 'Genome(id)');
2434        # Return the result.
2435        return @retVal;
2436    }
2437    
2438    =head3 Insert
2439    
2440        $sprout->Insert($objectType, \%fieldHash);
2441    
2442  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
2443  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 2142  Line 2446 
2446  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
2447  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>.
2448    
2449  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']});
2450    
2451  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
2452  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>.
2453    
2454  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'});
2455    
2456  =over 4  =over 4
2457    
# Line 2172  Line 2476 
2476    
2477  =head3 Annotate  =head3 Annotate
2478    
2479  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2480    
2481  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
2482  specified feature and user.  specified feature and user.
# Line 2226  Line 2530 
2530    
2531  =head3 AssignFunction  =head3 AssignFunction
2532    
2533  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2534    
2535  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
2536  format is described in L</ParseAssignment>.  format is described in L</ParseAssignment>.
# Line 2286  Line 2590 
2590    
2591  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2592    
2593  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2594    
2595  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
2596  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 2320  Line 2624 
2624          push @retVal, $mappedAlias;          push @retVal, $mappedAlias;
2625      } else {      } else {
2626          # 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.
2627          @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2628      }      }
2629      # Return the result.      # Return the result.
2630      return @retVal;      return @retVal;
# Line 2328  Line 2632 
2632    
2633  =head3 FeatureTranslation  =head3 FeatureTranslation
2634    
2635  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2636    
2637  Return the translation of a feature.  Return the translation of a feature.
2638    
# Line 2356  Line 2660 
2660    
2661  =head3 Taxonomy  =head3 Taxonomy
2662    
2663  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2664    
2665  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
2666  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>,
2667  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2668    
2669  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2670    
2671  =over 4  =over 4
2672    
# Line 2397  Line 2701 
2701    
2702  =head3 CrudeDistance  =head3 CrudeDistance
2703    
2704  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2705    
2706  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
2707  that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.  that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.
# Line 2449  Line 2753 
2753    
2754  =head3 RoleName  =head3 RoleName
2755    
2756  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2757    
2758  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
2759  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 2483  Line 2787 
2787    
2788  =head3 RoleDiagrams  =head3 RoleDiagrams
2789    
2790  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2791    
2792  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2793    
# Line 2513  Line 2817 
2817    
2818  =head3 GetProperties  =head3 GetProperties
2819    
2820  C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>      my @list = $sprout->GetProperties($fid, $key, $value, $url);
2821    
2822  Return a list of the properties with the specified characteristics.  Return a list of the properties with the specified characteristics.
2823    
2824  Properties are arbitrary key-value pairs associated with a feature. (At some point they  Properties are the Sprout analog of the FIG attributes. The call is
2825  will also be associated with genomes.) A property value is represented by a 4-tuple of  passed directly to the CustomAttributes or RemoteCustomAttributes object
2826  the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter  contained in this object.
2827    
2828  =over 4  This method returns a series of tuples that match the specified criteria. Each tuple
2829    will contain an object ID, a key, and one or more values. The parameters to this
2830    method therefore correspond structurally to the values expected in each tuple. In
2831    addition, you can ask for a generic search by suffixing a percent sign (C<%>) to any
2832    of the parameters. So, for example,
2833    
2834  =item fid      my @attributeList = $sprout->GetProperties('fig|100226.1.peg.1004', 'structure%', 1, 2);
2835    
2836  ID of the feature possessing the property.  would return something like
2837    
2838  =item key      ['fig}100226.1.peg.1004', 'structure', 1, 2]
2839        ['fig}100226.1.peg.1004', 'structure1', 1, 2]
2840        ['fig}100226.1.peg.1004', 'structure2', 1, 2]
2841        ['fig}100226.1.peg.1004', 'structureA', 1, 2]
2842    
2843  Name or key of the property.  Use of C<undef> in any position acts as a wild card (all values). You can also specify
2844    a list reference in the ID column. Thus,
2845    
2846  =item value      my @attributeList = $sprout->GetProperties(['100226.1', 'fig|100226.1.%'], 'PUBMED');
2847    
2848  Value of the property.  would get the PUBMED attribute data for Streptomyces coelicolor A3(2) and all its
2849    features.
2850    
2851  =item url  In addition to values in multiple sections, a single attribute key can have multiple
2852    values, so even
2853    
2854  URL of the document that indicated the property should have this particular value, or an      my @attributeList = $sprout->GetProperties($peg, 'virulent');
 empty string if no such document exists.  
2855    
2856  =back  which has no wildcard in the key or the object ID, may return multiple tuples.
2857    
2858  The parameters act as a filter for the desired data. Any non-null parameter will  =over 4
 automatically match all the tuples returned. So, specifying just the I<$fid> will  
 return all the properties of the specified feature; similarly, specifying the I<$key>  
 and I<$value> parameters will return all the features having the specified property  
 value.  
2859    
2860  A single property key can have many values, representing different ideas about the  =item objectID
 feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is  
 virulent, and another may declare that it is not virulent. A query about the virulence of  
 C<fig|83333.1.peg.10> would be coded as  
2861    
2862      my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');  ID of object whose attributes are desired. If the attributes are desired for multiple
2863    objects, this parameter can be specified as a list reference. If the attributes are
2864    desired for all objects, specify C<undef> or an empty string. Finally, you can specify
2865    attributes for a range of object IDs by putting a percent sign (C<%>) at the end.
2866    
2867  Here the I<$value> and I<$url> fields are left blank, indicating that those fields are  =item key
 not to be filtered. The tuples returned would be  
2868    
2869      ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')  Attribute key name. A value of C<undef> or an empty string will match all
2870      ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')  attribute keys. If the values are desired for multiple keys, this parameter can be
2871    specified as a list reference. Finally, you can specify attributes for a range of
2872    keys by putting a percent sign (C<%>) at the end.
2873    
2874    =item values
2875    
2876    List of the desired attribute values, section by section. If C<undef>
2877    or an empty string is specified, all values in that section will match. A
2878    generic match can be requested by placing a percent sign (C<%>) at the end.
2879    In that case, all values that match up to and not including the percent sign
2880    will match. You may also specify a regular expression enclosed
2881    in slashes. All values that match the regular expression will be returned. For
2882    performance reasons, only values have this extra capability.
2883    
2884    =item RETURN
2885    
2886    Returns a list of tuples. The first element in the tuple is an object ID, the
2887    second is an attribute key, and the remaining elements are the sections of
2888    the attribute value. All of the tuples will match the criteria set forth in
2889    the parameter list.
2890    
2891    =back
2892    
2893  =cut  =cut
2894  #: Return Type @@;  
2895  sub GetProperties {  sub GetProperties {
2896      # Get the parameters.      # Get the parameters.
2897      my ($self, @parms) = @_;      my ($self, @parms) = @_;
2898      # Declare the return variable.      # Declare the return variable.
2899      my @retVal = ();      my @retVal = $self->{_ca}->GetAttributes(@parms);
     # Now we need to create a WHERE clause that will get us the data we want. First,  
     # we create a list of the columns containing the data for each parameter.  
     my @colNames = ('HasProperty(from-link)', 'Property(property-name)',  
                     'Property(property-value)', 'HasProperty(evidence)');  
     # Now we build the WHERE clause and the list of parameter values.  
     my @where = ();  
     my @values = ();  
     for (my $i = 0; $i <= $#colNames; $i++) {  
         my $parm = $parms[$i];  
         if (defined $parm && ($parm ne '')) {  
             push @where, "$colNames[$i] = ?";  
             push @values, $parm;  
         }  
     }  
     # Format the WHERE clause.  
     my $filter = (@values > 0 ? (join " AND ", @where) : undef);  
     # Ask for all the propertie values with the desired characteristics.  
     my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);  
     while (my $valueObject = $query->Fetch()) {  
         my @tuple = $valueObject->Values(\@colNames);  
         push @retVal, \@tuple;  
     }  
2900      # Return the result.      # Return the result.
2901      return @retVal;      return @retVal;
2902  }  }
2903    
2904  =head3 FeatureProperties  =head3 FeatureProperties
2905    
2906  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2907    
2908  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
2909  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
2910  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
2911  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
2912  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.  
2913    
2914  =over 4  =over 4
2915    
# Line 2614  Line 2919 
2919    
2920  =item RETURN  =item RETURN
2921    
2922  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.  
2923    
2924  =back  =back
2925    
# Line 2625  Line 2929 
2929      # Get the parameters.      # Get the parameters.
2930      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2931      # Get the properties.      # Get the properties.
2932      my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->{_ca}->GetAttributes($featureID);
2933                              ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2934                               'HasProperty(evidence)']);      my @retVal = ();
2935        for my $attributeRow (@attributes) {
2936            shift @{$attributeRow};
2937            push @retVal, $attributeRow;
2938        }
2939      # Return the resulting list.      # Return the resulting list.
2940      return @retVal;      return @retVal;
2941  }  }
2942    
2943  =head3 DiagramName  =head3 DiagramName
2944    
2945  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2946    
2947  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2948    
# Line 2660  Line 2968 
2968      return $retVal;      return $retVal;
2969  }  }
2970    
2971    =head3 PropertyID
2972    
2973        my $id = $sprout->PropertyID($propName, $propValue);
2974    
2975    Return the ID of the specified property name and value pair, if the
2976    pair exists. Only a small subset of the FIG attributes are stored as
2977    Sprout properties, mostly for use in search optimization.
2978    
2979    =over 4
2980    
2981    =item propName
2982    
2983    Name of the desired property.
2984    
2985    =item propValue
2986    
2987    Value expected for the desired property.
2988    
2989    =item RETURN
2990    
2991    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2992    
2993    =back
2994    
2995    =cut
2996    
2997    sub PropertyID {
2998        # Get the parameters.
2999        my ($self, $propName, $propValue) = @_;
3000        # Try to find the ID.
3001        my ($retVal) = $self->GetFlat(['Property'],
3002                                      "Property(property-name) = ? AND Property(property-value) = ?",
3003                                      [$propName, $propValue], 'Property(id)');
3004        # Return the result.
3005        return $retVal;
3006    }
3007    
3008  =head3 MergedAnnotations  =head3 MergedAnnotations
3009    
3010  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
3011    
3012  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
3013  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2711  Line 3056 
3056    
3057  =head3 RoleNeighbors  =head3 RoleNeighbors
3058    
3059  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
3060    
3061  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
3062  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 2754  Line 3099 
3099    
3100  =head3 FeatureLinks  =head3 FeatureLinks
3101    
3102  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
3103    
3104  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
3105  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 2785  Line 3130 
3130    
3131  =head3 SubsystemsOf  =head3 SubsystemsOf
3132    
3133  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3134    
3135  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
3136  to the roles the feature performs.  to the roles the feature performs.
# Line 2833  Line 3178 
3178    
3179  =head3 SubsystemList  =head3 SubsystemList
3180    
3181  C<< my @subsystems = $sprout->SubsystemList($featureID); >>      my @subsystems = $sprout->SubsystemList($featureID);
3182    
3183  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
3184  feature participates. Unlike L</SubsystemsOf>, this method only returns the  feature participates. Unlike L</SubsystemsOf>, this method only returns the
# Line 2857  Line 3202 
3202      # Get the parameters.      # Get the parameters.
3203      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
3204      # Get the list of names.      # Get the list of names.
3205      my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",      my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?",
3206                                  [$featureID], 'HasSSCell(from-link)');                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3207        # Return the result, sorted.
3208        return sort @retVal;
3209    }
3210    
3211    =head3 GenomeSubsystemData
3212    
3213        my %featureData = $sprout->GenomeSubsystemData($genomeID);
3214    
3215    Return a hash mapping genome features to their subsystem roles.
3216    
3217    =over 4
3218    
3219    =item genomeID
3220    
3221    ID of the genome whose subsystem feature map is desired.
3222    
3223    =item RETURN
3224    
3225    Returns a hash mapping each feature of the genome to a list of 2-tuples. Eacb
3226    2-tuple contains a subsystem name followed by a role ID.
3227    
3228    =back
3229    
3230    =cut
3231    
3232    sub GenomeSubsystemData {
3233        # Get the parameters.
3234        my ($self, $genomeID) = @_;
3235        # Declare the return variable.
3236        my %retVal = ();
3237        # Get a list of the genome features that participate in subsystems. For each
3238        # feature we get its spreadsheet cells and the corresponding roles.
3239        my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'],
3240                                 "HasFeature(from-link) = ?", [$genomeID],
3241                                 ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']);
3242        # Now we get a list of the spreadsheet cells and their associated subsystems. Subsystems
3243        # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the
3244        # list. We use it at the beginning to get all the spreadsheet cells for the genome and
3245        # again at the end to filter out participation in subsystems with a negative variant code.
3246        my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'],
3247                                     "IsGenomeOf(from-link) = ? AND ParticipatesIn(variant-code) >= 0 AND ParticipatesIn(from-link) = ?",
3248                                     [$genomeID, $genomeID], ['HasSSCell(to-link)', 'HasSSCell(from-link)']);
3249        # Now "@roleData" lists the spreadsheet cell and role for each of the genome's features.
3250        # "@cellData" lists the subsystem name for each of the genome's spreadsheet cells. We
3251        # link these two lists together to create the result. First, we want a hash mapping
3252        # spreadsheet cells to subsystem names.
3253        my %subHash = map { $_->[0] => $_->[1] } @cellData;
3254        # We loop through @cellData to build the hash.
3255        for my $roleEntry (@roleData) {
3256            # Get the data for this feature and cell.
3257            my ($fid, $cellID, $role) = @{$roleEntry};
3258            # Check for a subsystem name.
3259            my $subsys = $subHash{$cellID};
3260            if ($subsys) {
3261                # Insure this feature has an entry in the return hash.
3262                if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3263                # Merge in this new data.
3264                push @{$retVal{$fid}}, [$subsys, $role];
3265            }
3266        }
3267      # Return the result.      # Return the result.
3268      return @retVal;      return %retVal;
3269  }  }
3270    
3271  =head3 RelatedFeatures  =head3 RelatedFeatures
3272    
3273  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
3274    
3275  Return a list of the features which are bi-directional best hits of the specified feature and  Return a list of the features which are bi-directional best hits of the specified feature and
3276  have been assigned the specified function by the specified user. If no such features exists,  have been assigned the specified function by the specified user. If no such features exists,
# Line 2898  Line 3303 
3303      # Get the parameters.      # Get the parameters.
3304      my ($self, $featureID, $function, $userID) = @_;      my ($self, $featureID, $function, $userID) = @_;
3305      # 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.
3306      my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);
                                      "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],  
                                      'IsBidirectionalBestHitOf(to-link)');  
3307      # 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
3308      # functional assignment.      # functional assignment.
3309      my @retVal = ();      my @retVal = ();
# Line 2918  Line 3321 
3321    
3322  =head3 TaxonomySort  =head3 TaxonomySort
3323    
3324  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3325    
3326  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a list formed by sorting the specified features by the taxonomy of the containing
3327  genome. This will cause genomes from similar organisms to float close to each other.  genome. This will cause genomes from similar organisms to float close to each other.
# Line 2953  Line 3356 
3356          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3357                                          [$fid], 'Genome(taxonomy)');                                          [$fid], 'Genome(taxonomy)');
3358          # Add this feature to the hash buffer.          # Add this feature to the hash buffer.
3359          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);          push @{$hashBuffer{$taxonomy}}, $fid;
3360      }      }
3361      # Sort the keys and get the elements.      # Sort the keys and get the elements.
3362      my @retVal = ();      my @retVal = ();
# Line 2966  Line 3369 
3369    
3370  =head3 Protein  =head3 Protein
3371    
3372  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3373    
3374  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3375    
# Line 3036  Line 3439 
3439      # Loop through the input triples.      # Loop through the input triples.
3440      my $n = length $sequence;      my $n = length $sequence;
3441      for (my $i = 0; $i < $n; $i += 3) {      for (my $i = 0; $i < $n; $i += 3) {
3442          # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3443          my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3444            my $triple = uc substr($sequence, $i, 3);
3445          # Translate it using the table.          # Translate it using the table.
3446          my $protein = "X";          my $protein = "X";
3447          if (exists $table->{$triple}) { $protein = $table->{$triple}; }          if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 3051  Line 3455 
3455    
3456  =head3 LoadInfo  =head3 LoadInfo
3457    
3458  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3459    
3460  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
3461  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 3070  Line 3474 
3474      return @retVal;      return @retVal;
3475  }  }
3476    
3477    =head3 BBHMatrix
3478    
3479        my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3480    
3481    Find all the bidirectional best hits for the features of a genome in a
3482    specified list of target genomes. The return value will be a hash mapping
3483    features in the original genome to their bidirectional best hits in the
3484    target genomes.
3485    
3486    =over 4
3487    
3488    =item genomeID
3489    
3490    ID of the genome whose features are to be examined for bidirectional best hits.
3491    
3492    =item cutoff
3493    
3494    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3495    
3496    =item targets
3497    
3498    List of target genomes. Only pairs originating in the original
3499    genome and landing in one of the target genomes will be returned.
3500    
3501    =item RETURN
3502    
3503    Returns a hash mapping each feature in the original genome to a hash mapping its
3504    BBH pegs in the target genomes to their scores.
3505    
3506    =back
3507    
3508    =cut
3509    
3510    sub BBHMatrix {
3511        # Get the parameters.
3512        my ($self, $genomeID, $cutoff, @targets) = @_;
3513        # Declare the return variable.
3514        my %retVal = ();
3515        # Ask for the BBHs.
3516        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3517        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3518        for my $bbhData (@bbhList) {
3519            my ($peg1, $peg2, $score) = @{$bbhData};
3520            if (! exists $retVal{$peg1}) {
3521                $retVal{$peg1} = { $peg2 => $score };
3522            } else {
3523                $retVal{$peg1}->{$peg2} = $score;
3524            }
3525        }
3526        # Return the result.
3527        return %retVal;
3528    }
3529    
3530    
3531    =head3 SimMatrix
3532    
3533        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3534    
3535    Find all the similarities for the features of a genome in a
3536    specified list of target genomes. The return value will be a hash mapping
3537    features in the original genome to their similarites in the
3538    target genomes.
3539    
3540    =over 4
3541    
3542    =item genomeID
3543    
3544    ID of the genome whose features are to be examined for similarities.
3545    
3546    =item cutoff
3547    
3548    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3549    
3550    =item targets
3551    
3552    List of target genomes. Only pairs originating in the original
3553    genome and landing in one of the target genomes will be returned.
3554    
3555    =item RETURN
3556    
3557    Returns a hash mapping each feature in the original genome to a hash mapping its
3558    similar pegs in the target genomes to their scores.
3559    
3560    =back
3561    
3562    =cut
3563    
3564    sub SimMatrix {
3565        # Get the parameters.
3566        my ($self, $genomeID, $cutoff, @targets) = @_;
3567        # Declare the return variable.
3568        my %retVal = ();
3569        # Get the list of features in the source organism.
3570        my @fids = $self->FeaturesOf($genomeID);
3571        # Ask for the sims. We only want similarities to fig features.
3572        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3573        if (! defined $simList) {
3574            Confess("Unable to retrieve similarities from server.");
3575        } else {
3576            Trace("Processing sims.") if T(3);
3577            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3578            # Create a hash for the target genomes.
3579            my %targetHash = map { $_ => 1 } @targets;
3580            for my $simData (@{$simList}) {
3581                # Get the PEGs and the score.
3582                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3583                # Insure the second ID is in the target list.
3584                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3585                if (exists $targetHash{$genome2}) {
3586                    # Here it is. Now we need to add it to the return hash. How we do that depends
3587                    # on whether or not $peg1 is new to us.
3588                    if (! exists $retVal{$peg1}) {
3589                        $retVal{$peg1} = { $peg2 => $score };
3590                    } else {
3591                        $retVal{$peg1}->{$peg2} = $score;
3592                    }
3593                }
3594            }
3595        }
3596        # Return the result.
3597        return %retVal;
3598    }
3599    
3600    
3601  =head3 LowBBHs  =head3 LowBBHs
3602    
3603  C<< my %bbhMap = $sprout->LowBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3604    
3605  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3606  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 3101  Line 3629 
3629      my ($self, $featureID, $cutoff) = @_;      my ($self, $featureID, $cutoff) = @_;
3630      # Create the return hash.      # Create the return hash.
3631      my %retVal = ();      my %retVal = ();
3632      # Create a query to get the desired BBHs.      # Query for the desired BBHs.
3633      my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],      my @bbhList = FIGRules::BBHData($featureID, $cutoff);
                                 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',  
                                 [$cutoff, $featureID],  
                                 ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);  
3634      # Form the results into the return hash.      # Form the results into the return hash.
3635      for my $pair (@bbhList) {      for my $pair (@bbhList) {
3636          $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3637            if ($self->Exists('Feature', $fid)) {
3638                $retVal{$fid} = $pair->[1];
3639            }
3640      }      }
3641      # Return the result.      # Return the result.
3642      return %retVal;      return %retVal;
# Line 3116  Line 3644 
3644    
3645  =head3 Sims  =head3 Sims
3646    
3647  C<< my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters); >>      my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3648    
3649  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
3650  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 3126  Line 3654 
3654  Similarities can be either raw or expanded. The raw similarities are basic  Similarities can be either raw or expanded. The raw similarities are basic
3655  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
3656  features considered substantially identical. So, for example, if features B<A1>,  features considered substantially identical. So, for example, if features B<A1>,
3657  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
3658  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]>.
3659    
3660  =over 4  =over 4
3661    
3662  =item fid  =item fid
3663    
3664  ID of the feature whose similarities are desired.  ID of the feature whose similarities are desired, or reference to a list of IDs
3665    of features whose similarities are desired.
3666    
3667  =item maxN  =item maxN
3668    
# Line 3179  Line 3708 
3708      return $retVal;      return $retVal;
3709  }  }
3710    
3711    =head3 IsAllGenomes
3712    
3713        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3714    
3715    Return TRUE if all genomes in the second list are represented in the first list at
3716    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3717    compared to a list of all the genomes.
3718    
3719    =over 4
3720    
3721    =item list
3722    
3723    Reference to the list to be compared to the second list.
3724    
3725    =item checkList (optional)
3726    
3727    Reference to the comparison target list. Every genome ID in this list must occur at
3728    least once in the first list. If this parameter is omitted, a list of all the genomes
3729    is used.
3730    
3731    =item RETURN
3732    
3733    Returns TRUE if every item in the second list appears at least once in the
3734    first list, else FALSE.
3735    
3736    =back
3737    
3738    =cut
3739    
3740    sub IsAllGenomes {
3741        # Get the parameters.
3742        my ($self, $list, $checkList) = @_;
3743        # Supply the checklist if it was omitted.
3744        $checkList = [$self->Genomes()] if ! defined($checkList);
3745        # Create a hash of the original list.
3746        my %testList = map { $_ => 1 } @{$list};
3747        # Declare the return variable. We assume that the representation
3748        # is complete and stop at the first failure.
3749        my $retVal = 1;
3750        my $n = scalar @{$checkList};
3751        for (my $i = 0; $retVal && $i < $n; $i++) {
3752            if (! $testList{$checkList->[$i]}) {
3753                $retVal = 0;
3754            }
3755        }
3756        # Return the result.
3757        return $retVal;
3758    }
3759    
3760  =head3 GetGroups  =head3 GetGroups
3761    
3762  C<< my %groups = $sprout->GetGroups(\@groupList); >>      my %groups = $sprout->GetGroups(\@groupList);
3763    
3764  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.
3765  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 3200  Line 3778 
3778          # Here we have a group list. Loop through them individually,          # Here we have a group list. Loop through them individually,
3779          # getting a list of the relevant genomes.          # getting a list of the relevant genomes.
3780          for my $group (@{$groupList}) {          for my $group (@{$groupList}) {
3781              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3782                  [$group], "Genome(id)");                  [$group], "Genome(id)");
3783              $retVal{$group} = \@genomeIDs;              $retVal{$group} = \@genomeIDs;
3784          }          }
# Line 3208  Line 3786 
3786          # 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
3787          # of the genome records, putting each one found into the appropriate          # of the genome records, putting each one found into the appropriate
3788          # 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
3789          # in groups are included in the return set.          # in real NMPDR groups are included in the return set.
3790          my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],          my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3791                                      ['Genome(id)', 'Genome(group-name)']);                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3792          # Loop through the genomes found.          # Loop through the genomes found.
3793          for my $genome (@genomes) {          for my $genome (@genomes) {
3794              # Pop this genome's ID off the current list.              # Get the genome ID and group, and add this genome to the group's list.
3795              my @groups = @{$genome};              my ($genomeID, $group) = @{$genome};
3796              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, $genomeID);  
             }  
3797          }          }
3798      }      }
3799      # Return the hash we just built.      # Return the hash we just built.
# Line 3229  Line 3802 
3802    
3803  =head3 MyGenomes  =head3 MyGenomes
3804    
3805  C<< my @genomes = Sprout::MyGenomes($dataDir); >>      my @genomes = Sprout::MyGenomes($dataDir);
3806    
3807  Return a list of the genomes to be included in the Sprout.  Return a list of the genomes to be included in the Sprout.
3808    
# Line 3261  Line 3834 
3834    
3835  =head3 LoadFileName  =head3 LoadFileName
3836    
3837  C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>      my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3838    
3839  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
3840  directory.  directory.
# Line 3302  Line 3875 
3875    
3876  =head3 DeleteGenome  =head3 DeleteGenome
3877    
3878  C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>      my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3879    
3880  Delete a genome from the database.  Delete a genome from the database.
3881    
# Line 3328  Line 3901 
3901      # Get the parameters.      # Get the parameters.
3902      my ($self, $genomeID, $testFlag) = @_;      my ($self, $genomeID, $testFlag) = @_;
3903      # Perform the delete for the genome's features.      # Perform the delete for the genome's features.
3904      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", $testFlag);      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3905      # Perform the delete for the primary genome data.      # Perform the delete for the primary genome data.
3906      my $stats = $self->Delete('Genome', $genomeID, $testFlag);      my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3907      $retVal->Accumulate($stats);      $retVal->Accumulate($stats);
3908      # Return the result.      # Return the result.
3909      return $retVal;      return $retVal;
3910  }  }
3911    
3912    =head3 Fix
3913    
3914        my %fixedHash = $sprout->Fix(%groupHash);
3915    
3916    Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3917    The groups will be combined into the appropriate super-groups.
3918    
3919    =over 4
3920    
3921    =item groupHash
3922    
3923    Hash to be fixed up.
3924    
3925    =item RETURN
3926    
3927    Returns a fixed-up version of the hash.
3928    
3929    =back
3930    
3931    =cut
3932    
3933    sub Fix {
3934        # Get the parameters.
3935        my ($self, %groupHash) = @_;
3936        # Create the result hash.
3937        my %retVal = ();
3938        # Copy over the genomes.
3939        for my $groupID (keys %groupHash) {
3940            # Get the super-group name.
3941            my $realGroupID = $self->SuperGroup($groupID);
3942            # Append this group's genomes into the result hash
3943            # using the super-group name.
3944            push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3945        }
3946        # Return the result hash.
3947        return %retVal;
3948    }
3949    
3950    =head3 GroupPageName
3951    
3952        my $name = $sprout->GroupPageName($group);
3953    
3954    Return the name of the page for the specified NMPDR group.
3955    
3956    =over 4
3957    
3958    =item group
3959    
3960    Name of the relevant group.
3961    
3962    =item RETURN
3963    
3964    Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3965    memory it will be read in.
3966    
3967    =back
3968    
3969    =cut
3970    
3971    sub GroupPageName {
3972        # Get the parameters.
3973        my ($self, $group) = @_;
3974        # Check for the group file data.
3975        my %superTable = $self->CheckGroupFile();
3976        # Compute the real group name.
3977        my $realGroup = $self->SuperGroup($group);
3978        # Get the associated page name.
3979        my $retVal = "../content/$superTable{$realGroup}->{page}";
3980        # Return the result.
3981        return $retVal;
3982    }
3983    
3984    
3985    =head3 AddProperty
3986    
3987        $sprout->AddProperty($featureID, $key, @values);
3988    
3989    Add a new attribute value (Property) to a feature.
3990    
3991    =over 4
3992    
3993    =item peg
3994    
3995    ID of the feature to which the attribute is to be added.
3996    
3997    =item key
3998    
3999    Name of the attribute (key).
4000    
4001    =item values
4002    
4003    Values of the attribute.
4004    
4005    =back
4006    
4007    =cut
4008    #: Return Type ;
4009    sub AddProperty {
4010        # Get the parameters.
4011        my ($self, $featureID, $key, @values) = @_;
4012        # Add the property using the attached attributes object.
4013        $self->{_ca}->AddAttribute($featureID, $key, @values);
4014    }
4015    
4016    =head3 CheckGroupFile
4017    
4018        my %groupData = $sprout->CheckGroupFile();
4019    
4020    Get the group file hash. The group file hash describes the relationship
4021    between a group and the super-group to which it belongs for purposes of
4022    display. The super-group name is computed from the first capitalized word
4023    in the actual group name. For each super-group, the group file contains
4024    the page name and a list of the species expected to be in the group.
4025    Each species is specified by a genus and a species name. A species name
4026    of C<0> implies an entire genus.
4027    
4028    This method returns a hash from super-group names to a hash reference. Each
4029    resulting hash reference contains the following fields.
4030    
4031    =over 4
4032    
4033    =item page
4034    
4035    The super-group's web page in the NMPDR.
4036    
4037    =item contents
4038    
4039    A list of 2-tuples, each containing a genus name followed by a species name
4040    (or 0, indicating all species). This list indicates which organisms belong
4041    in the super-group.
4042    
4043    =back
4044    
4045    =cut
4046    
4047    sub CheckGroupFile {
4048        # Get the parameters.
4049        my ($self) = @_;
4050        # Check to see if we already have this hash.
4051        if (! defined $self->{groupHash}) {
4052            # We don't, so we need to read it in.
4053            my %groupHash;
4054            # Read the group file.
4055            my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
4056            # Loop through the list of sort-of groups.
4057            for my $groupLine (@groupLines) {
4058                my ($name, $page, @contents) = split /\t/, $groupLine;
4059                $groupHash{$name} = { page => $page,
4060                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
4061                                    };
4062            }
4063            # Save the hash.
4064            $self->{groupHash} = \%groupHash;
4065        }
4066        # Return the result.
4067        return %{$self->{groupHash}};
4068    }
4069    
4070    =head2 Virtual Methods
4071    
4072    =head3 CleanKeywords
4073    
4074        my $cleanedString = $sprout->CleanKeywords($searchExpression);
4075    
4076    Clean up a search expression or keyword list. This involves converting the periods
4077    in EC numbers to underscores, converting non-leading minus signs to underscores,
4078    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
4079    characters. In addition, any extra spaces are removed.
4080    
4081    =over 4
4082    
4083    =item searchExpression
4084    
4085    Search expression or keyword list to clean. Note that a search expression may
4086    contain boolean operators which need to be preserved. This includes leading
4087    minus signs.
4088    
4089    =item RETURN
4090    
4091    Cleaned expression or keyword list.
4092    
4093    =back
4094    
4095    =cut
4096    
4097    sub CleanKeywords {
4098        # Get the parameters.
4099        my ($self, $searchExpression) = @_;
4100        # Perform the standard cleanup.
4101        my $words = $self->ERDB::CleanKeywords($searchExpression);
4102        # Fix the periods in EC and TC numbers.
4103        $words =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;
4104        # Fix non-trailing periods.
4105        $words =~ s/\.(\w)/_$1/g;
4106        # Fix non-leading minus signs.
4107        $words =~ s/(\w)[\-]/$1_/g;
4108        # Fix the vertical bars and colons
4109        $words =~ s/(\w)[|:](\w)/$1'$2/g;
4110        # Now split up the list so that each keyword is in its own string. We keep the delimiters
4111        # because they may contain boolean expression data.
4112        my @words = split /([^A-Za-z'0-9_]+)/, $words;
4113        # We'll convert the stemmable words into stems and re-assemble the result.
4114        my $retVal = "";
4115        for my $word (@words) {
4116            my $stem = $self->Stem($word);
4117            if (defined $stem) {
4118                $retVal .= $stem;
4119            } else {
4120                $retVal .= $word;
4121            }
4122        }
4123        Trace("Cleaned keyword list for \"$searchExpression\" is \"$retVal\".") if T(3);
4124        # Return the result.
4125        return $retVal;
4126    }
4127    
4128  =head2 Internal Utility Methods  =head2 Internal Utility Methods
4129    
4130  =head3 ParseAssignment  =head3 ParseAssignment
# Line 3346  Line 4135 
4135    
4136  A functional assignment is always of the form  A functional assignment is always of the form
4137    
4138      C<set >I<YYYY>C< function to\n>I<ZZZZZ>      set YYYY function to
4139        ZZZZ
4140    
4141  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,
4142  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 3392  Line 4182 
4182      }      }
4183      # 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
4184      # extra junk at the end added as a note from the user.      # extra junk at the end added as a note from the user.
4185      if (@retVal) {      if (defined( $retVal[1] )) {
4186          $retVal[1] =~ s/(\t\S)?\s*$//;          $retVal[1] =~ s/(\t\S)?\s*$//;
4187      }      }
4188      # Return the result list.      # Return the result list.
4189      return @retVal;      return @retVal;
4190  }  }
4191    
4192  =head3 FriendlyTimestamp  =head3 _CheckFeature
4193    
4194  Convert a time number to a user-friendly time stamp for display.      my $flag = $sprout->_CheckFeature($fid);
4195    
4196  This is a static method.  Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
4197    
4198  =over 4  =over 4
4199    
4200  =item timeValue  =item fid
4201    
4202  Numeric time value.  Feature ID to check.
4203    
4204  =item RETURN  =item RETURN
4205    
4206  Returns a string containing the same time in user-readable format.  Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE.
4207    
4208  =back  =back
4209    
4210  =cut  =cut
4211    
4212  sub FriendlyTimestamp {  sub _CheckFeature {
4213      my ($timeValue) = @_;      # Get the parameters.
4214      my $retVal = localtime($timeValue);      my ($self, $fid) = @_;
4215      return $retVal;      # Insure we have a genome hash.
4216        if (! defined $self->{genomeHash}) {
4217            my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');
4218            $self->{genomeHash} = \%genomeHash;
4219        }
4220        # Get the feature's genome ID.
4221        my ($genomeID) = FIGRules::ParseFeatureID($fid);
4222        # Return an indicator of whether or not the genome ID is in the hash.
4223        return ($self->{genomeHash}->{$genomeID} ? 1 : 0);
4224  }  }
4225    
4226  =head3 AddProperty  =head3 FriendlyTimestamp
4227    
4228  C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>  Convert a time number to a user-friendly time stamp for display.
4229    
4230  Add a new attribute value (Property) to a feature. In the SEED system, attributes can  This is a static method.
 be added to almost any object. In Sprout, they can only be added to features. In  
 Sprout, attributes are implemented using I<properties>. A property represents a key/value  
 pair. If the particular key/value pair coming in is not already in the database, a new  
 B<Property> record is created to hold it.  
4231    
4232  =over 4  =over 4
4233    
4234  =item peg  =item timeValue
   
 ID of the feature to which the attribute is to be replied.  
   
 =item key  
   
 Name of the attribute (key).  
   
 =item value  
4235    
4236  Value of the attribute.  Numeric time value.
4237    
4238  =item url  =item RETURN
4239    
4240  URL or text citation from which the property was obtained.  Returns a string containing the same time in user-readable format.
4241    
4242  =back  =back
4243    
4244  =cut  =cut
4245  #: Return Type ;  
4246  sub AddProperty {  sub FriendlyTimestamp {
4247      # Get the parameters.      my ($timeValue) = @_;
4248      my ($self, $featureID, $key, $value, $url) = @_;      my $retVal = localtime($timeValue);
4249      # Declare the variable to hold the desired property ID.      return $retVal;
     my $propID;  
     # Attempt to find a property record for this key/value pair.  
     my @properties = $self->GetFlat(['Property'],  
                                    "Property(property-name) = ? AND Property(property-value) = ?",  
                                    [$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 });  
     }  
     # Now we connect the incoming feature to the property.  
     $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });  
4250  }  }
4251    
4252    

Legend:
Removed from v.1.77  
changed lines
  Added in v.1.113

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3